1
|
Zhang H, Lu KH, Ebbini M, Huang P, Lu H, Li L. Mass spectrometry imaging for spatially resolved multi-omics molecular mapping. NPJ IMAGING 2024; 2:20. [PMID: 39036554 PMCID: PMC11254763 DOI: 10.1038/s44303-024-00025-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/07/2024] [Accepted: 06/21/2024] [Indexed: 07/23/2024]
Abstract
The recent upswing in the integration of spatial multi-omics for conducting multidimensional information measurements is opening a new chapter in biological research. Mapping the landscape of various biomolecules including metabolites, proteins, nucleic acids, etc., and even deciphering their functional interactions and pathways is believed to provide a more holistic and nuanced exploration of the molecular intricacies within living systems. Mass spectrometry imaging (MSI) stands as a forefront technique for spatially mapping the metabolome, lipidome, and proteome within diverse tissue and cell samples. In this review, we offer a systematic survey delineating different MSI techniques for spatially resolved multi-omics analysis, elucidating their principles, capabilities, and limitations. Particularly, we focus on the advancements in methodologies aimed at augmenting the molecular sensitivity and specificity of MSI; and depict the burgeoning integration of MSI-based spatial metabolomics, lipidomics, and proteomics, encompassing the synergy with other imaging modalities. Furthermore, we offer speculative insights into the potential trajectory of MSI technology in the future.
Collapse
Affiliation(s)
- Hua Zhang
- School of Pharmacy, University of Wisconsin-Madison, Madison, WI 53705 USA
| | - Kelly H. Lu
- Department of Chemistry, University of Wisconsin-Madison, Madison, WI 53706 USA
| | - Malik Ebbini
- School of Pharmacy, University of Wisconsin-Madison, Madison, WI 53705 USA
| | - Penghsuan Huang
- Department of Chemistry, University of Wisconsin-Madison, Madison, WI 53706 USA
| | - Haiyan Lu
- School of Pharmacy, University of Wisconsin-Madison, Madison, WI 53705 USA
| | - Lingjun Li
- School of Pharmacy, University of Wisconsin-Madison, Madison, WI 53705 USA
- Department of Chemistry, University of Wisconsin-Madison, Madison, WI 53706 USA
- Lachman Institute for Pharmaceutical Development, School of Pharmacy, University of Wisconsin-Madison, Madison, WI 53705 USA
- Wisconsin Center for NanoBioSystems, School of Pharmacy, University of Wisconsin-Madison, Madison, WI 53705 USA
| |
Collapse
|
2
|
Gardner W, Winkler DA, Bamford SE, Muir BW, Pigram PJ. Markedly Enhanced Analysis of Mass Spectrometry Images Using Weakly Supervised Machine Learning. SMALL METHODS 2024; 8:e2301230. [PMID: 38204217 DOI: 10.1002/smtd.202301230] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/12/2023] [Revised: 11/03/2023] [Indexed: 01/12/2024]
Abstract
Supervised and unsupervised machine learning algorithms are routinely applied to time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging data and, more broadly, to mass spectrometry imaging (MSI). These algorithms have accelerated large-scale, single-pixel analysis, classification, and regression. However, there is relatively little research on methods suited for so-called weakly supervised problems, where ground-truth class labels exist at the image level, but not at the individual pixel level. Unsupervised learning methods are usually applied to these problems. However, these methods cannot make use of available labels. Here a novel method specifically designed for weakly supervised MSI data is presented. A dual-stream multiple instance learning (MIL) approach is adapted from computational pathology that reveals the spatial-spectral characteristics distinguishing different classes of MSI images. The method uses an information entropy-regularized attention mechanism to identify characteristic class pixels that are then used to extract characteristic mass spectra. This work provides a proof-of-concept exemplification using printed ink samples imaged by ToF-SIMS. A second application-oriented study is also presented, focusing on the analysis of a mixed powder sample type. Results demonstrate the potential of the MIL method for broader application in MSI, with implications for understanding subtle spatial-spectral characteristics in various applications and contexts.
Collapse
Affiliation(s)
- Wil Gardner
- Centre for Materials and Surface Science and Department of Mathematical and Physical Sciences, La Trobe University, Bundoora, Victoria, 3086, Australia
| | - David A Winkler
- Department of Biochemistry and Chemistry, La Trobe Institute for Molecular Sciences, La Trobe University, Melbourne, Victoria, 3086, Australia
- Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, Victoria, 3052, Australia
- Advanced Materials and Healthcare Technologies, School of Pharmacy, University of Nottingham, Nottingham, NG7 2RD, UK
| | - Sarah E Bamford
- Centre for Materials and Surface Science and Department of Mathematical and Physical Sciences, La Trobe University, Bundoora, Victoria, 3086, Australia
| | | | - Paul J Pigram
- Centre for Materials and Surface Science and Department of Mathematical and Physical Sciences, La Trobe University, Bundoora, Victoria, 3086, Australia
| |
Collapse
|
3
|
Lu Y, Cao Y, Tang X, Hu N, Wang Z, Xu P, Hua Z, Wang Y, Su Y, Guo Y. Deep learning-assisted mass spectrometry imaging for preliminary screening and pre-classification of psychoactive substances. Talanta 2024; 272:125757. [PMID: 38368831 DOI: 10.1016/j.talanta.2024.125757] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2023] [Revised: 01/28/2024] [Accepted: 02/05/2024] [Indexed: 02/20/2024]
Abstract
Currently, it is of great urgency to develop a rapid pre-classification and screening method for suspected drugs as the constantly springing up of new psychoactive substances. In most researches, psychoactive substances classification approaches depended on the similar chemical structures and pharmacological action with known drugs. Such approaches could not face the complicated circumstance of emerging new psychoactive substances. Herein, mass spectrometry imaging and convolutional neural networks (CNN) were used for preliminary screening and pre-classification of suspected psychoactive substances. Mass spectrometry imaging was performed simultaneously on two brain slices as one was from blank group and another one was from psychoactive substance-induced group. Then, fused neurotransmitter variation mass spectrometry images (Nv-MSIs) reflecting the difference of neurotransmitters between two slices were achieved through two homemade programs. A CNN model was developed to classify the Nv-MSIs. Compared with traditional classification methods, CNN achieved better estimation accuracy and required minimal data preprocessing. Also, the specific region on Nv-MSIs and weight of each neurotransmitter that affected the classification most could be unraveled by CNN. Finally, the method was successfully applied to assist the identification of a new psychoactive substance seized recently. This sample was identified as cannabinoids, which greatly promoted the screening process.
Collapse
Affiliation(s)
- Yingjie Lu
- Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, 1200 Cailun Road, Shanghai, 201203, China; Department of Pharmacognosy, School of Pharmacy, Naval Medical University, Shanghai, 200433, China
| | - Yuqi Cao
- Technical Centre, Shanghai Tobacco (Group) Corp., Shanghai, 200082, China
| | - Xiaohang Tang
- Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, 1200 Cailun Road, Shanghai, 201203, China
| | - Na Hu
- Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, 1200 Cailun Road, Shanghai, 201203, China
| | - Zhengyong Wang
- Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, 1200 Cailun Road, Shanghai, 201203, China
| | - Peng Xu
- Key Laboratory of Drug Monitoring and Control, Drug Intelligence and Forensic Center, Ministry of Public Security, Beijing, 100193, China
| | - Zhendong Hua
- Key Laboratory of Drug Monitoring and Control, Drug Intelligence and Forensic Center, Ministry of Public Security, Beijing, 100193, China
| | - Youmei Wang
- Key Laboratory of Drug Monitoring and Control, Drug Intelligence and Forensic Center, Ministry of Public Security, Beijing, 100193, China.
| | - Yue Su
- Institute of Interdisciplinary Integrative Medicine Research, Shanghai University of Traditional Chinese Medicine, 1200 Cailun Road, Shanghai, 201203, China.
| | - Yinlong Guo
- State Key Laboratory of Organometallic Chemistry and National Center for Organic Mass Spectrometry in Shanghai, Center for Excellence in Molecular Synthesis, Shanghai Institute of Organic Chemistry, University of Chinese Academy of Sciences, Chinese Academy of Sciences, 345 Lingling Road, Shanghai, 200032, China.
| |
Collapse
|
4
|
Danaeifar M, Najafi A. Artificial Intelligence and Computational Biology in Gene Therapy: A Review. Biochem Genet 2024:10.1007/s10528-024-10799-1. [PMID: 38635012 DOI: 10.1007/s10528-024-10799-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/16/2023] [Accepted: 04/02/2024] [Indexed: 04/19/2024]
Abstract
One of the trending fields in almost all areas of science and technology is artificial intelligence. Computational biology and artificial intelligence can help gene therapy in many steps including: gene identification, gene editing, vector design, development of new macromolecules and modeling of gene delivery. There are various tools used by computational biology and artificial intelligence in this field, such as genomics, transcriptomic and proteomics data analysis, machine learning algorithms and molecular interaction studies. These tools can introduce new gene targets, novel vectors, optimized experiment conditions, predict the outcomes and suggest the best solutions to avoid undesired immune responses following gene therapy treatment.
Collapse
Affiliation(s)
- Mohsen Danaeifar
- Molecular Biology Research Center, Systems Biology and Poisonings Institute, Baqiyatallah University of Medical Science, P.O. Box 19395-5487, Tehran, Iran
| | - Ali Najafi
- Molecular Biology Research Center, Systems Biology and Poisonings Institute, Baqiyatallah University of Medical Science, P.O. Box 19395-5487, Tehran, Iran.
| |
Collapse
|
5
|
Duncan KD, Pětrošová H, Lum JJ, Goodlett DR. Mass spectrometry imaging methods for visualizing tumor heterogeneity. Curr Opin Biotechnol 2024; 86:103068. [PMID: 38310648 DOI: 10.1016/j.copbio.2024.103068] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2023] [Revised: 01/09/2024] [Accepted: 01/09/2024] [Indexed: 02/06/2024]
Abstract
Profiling spatial distributions of lipids, metabolites, and proteins in tumors can reveal unique cellular microenvironments and provide molecular evidence for cancer cell dysfunction and proliferation. Mass spectrometry imaging (MSI) is a label-free technique that can be used to map biomolecules in tumors in situ. Here, we discuss current progress in applying MSI to uncover molecular heterogeneity in tumors. First, the analytical strategies to profile small molecules and proteins are outlined, and current methods for multimodal imaging to maximize biological information are highlighted. Second, we present and summarize biological insights obtained by MSI of tumor tissue. Finally, we discuss important considerations for designing MSI experiments and several current analytical challenges.
Collapse
Affiliation(s)
- Kyle D Duncan
- Department of Chemistry, Vancouver Island University, Nanaimo, British Columbia, Canada; Department of Chemistry, University of Victoria, Victoria, British Columbia, Canada.
| | - Helena Pětrošová
- University of Victoria Genome British Columbia Proteomics Center, University of Victoria, Victoria, British Columbia, Canada; Department of Biochemistry and Microbiology, University of Victoria, Victoria, British Columbia, Canada.
| | - Julian J Lum
- Department of Biochemistry and Microbiology, University of Victoria, Victoria, British Columbia, Canada; Trev and Joyce Deeley Research Centre, BC Cancer, Victoria, British Columbia, Canada
| | - David R Goodlett
- University of Victoria Genome British Columbia Proteomics Center, University of Victoria, Victoria, British Columbia, Canada; Department of Biochemistry and Microbiology, University of Victoria, Victoria, British Columbia, Canada
| |
Collapse
|
6
|
Sarretto T, Gardner W, Brungs D, Napaki S, Pigram PJ, Ellis SR. A Machine Learning-Driven Comparison of Ion Images Obtained by MALDI and MALDI-2 Mass Spectrometry Imaging. JOURNAL OF THE AMERICAN SOCIETY FOR MASS SPECTROMETRY 2024; 35:466-475. [PMID: 38407924 DOI: 10.1021/jasms.3c00357] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/27/2024]
Abstract
Matrix-assisted laser desorption ionization mass spectrometry imaging (MALDI-MSI) enables label-free imaging of biomolecules in biological tissues. However, many species remain undetected due to their poor ionization efficiencies. MALDI-2 (laser-induced post-ionization) is the most widely used post-ionization method for improving analyte ionization efficiencies. Mass spectra acquired using MALDI-2 constitute a combination of ions generated by both MALDI and MALDI-2 processes. Until now, no studies have focused on a detailed comparison between the ion images (as opposed to the generated m/z values) produced by MALDI and MALDI-2 for mass spectrometry imaging (MSI) experiments. Herein, we investigated the ion images produced by both MALDI and MALDI-2 on the same tissue section using correlation analysis (to explore similarities in ion images for ions common to both MALDI and MALDI-2) and a deep learning approach. For the latter, we used an analytical workflow based on the Xception convolutional neural network, which was originally trained for human-like natural image classification but which we adapted to elucidate similarities and differences in ion images obtained using the two MSI techniques. Correlation analysis demonstrated that common ions yielded similar spatial distributions with low-correlation species explained by either poor signal intensity in MALDI or the generation of additional unresolved signals using MALDI-2. Using the Xception-based method, we identified many regions in the t-SNE space of spatially similar ion images containing MALDI and MALDI-2-related signals. More notably, the method revealed distinct regions containing only MALDI-2 ion images with unique spatial distributions that were not observed using MALDI. These data explicitly demonstrate the ability of MALDI-2 to reveal molecular features and patterns as well as histological regions of interest that are not visible when using conventional MALDI.
Collapse
Affiliation(s)
- Tassiani Sarretto
- Molecular Horizons and School of Chemistry and Molecular Bioscience, University of Wollongong, Wollongong, Australia, 2522
| | - Wil Gardner
- Centre for Materials and Surface Science and Department of Mathematical and Physical Sciences, La Trobe University, Bundoora, Australia, 3086
| | - Daniel Brungs
- Graduate School of Medicine, University of Wollongong, Wollongong, Australia, 2522
| | - Sarbar Napaki
- Graduate School of Medicine, University of Wollongong, Wollongong, Australia, 2522
| | - Paul J Pigram
- Centre for Materials and Surface Science and Department of Mathematical and Physical Sciences, La Trobe University, Bundoora, Australia, 3086
| | - Shane R Ellis
- Molecular Horizons and School of Chemistry and Molecular Bioscience, University of Wollongong, Wollongong, Australia, 2522
| |
Collapse
|
7
|
Ma X, Fernández FM. Advances in mass spectrometry imaging for spatial cancer metabolomics. MASS SPECTROMETRY REVIEWS 2024; 43:235-268. [PMID: 36065601 PMCID: PMC9986357 DOI: 10.1002/mas.21804] [Citation(s) in RCA: 29] [Impact Index Per Article: 29.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/12/2022] [Revised: 08/02/2022] [Accepted: 08/02/2022] [Indexed: 05/09/2023]
Abstract
Mass spectrometry (MS) has become a central technique in cancer research. The ability to analyze various types of biomolecules in complex biological matrices makes it well suited for understanding biochemical alterations associated with disease progression. Different biological samples, including serum, urine, saliva, and tissues have been successfully analyzed using mass spectrometry. In particular, spatial metabolomics using MS imaging (MSI) allows the direct visualization of metabolite distributions in tissues, thus enabling in-depth understanding of cancer-associated biochemical changes within specific structures. In recent years, MSI studies have been increasingly used to uncover metabolic reprogramming associated with cancer development, enabling the discovery of key biomarkers with potential for cancer diagnostics. In this review, we aim to cover the basic principles of MSI experiments for the nonspecialists, including fundamentals, the sample preparation process, the evolution of the mass spectrometry techniques used, and data analysis strategies. We also review MSI advances associated with cancer research in the last 5 years, including spatial lipidomics and glycomics, the adoption of three-dimensional and multimodal imaging MSI approaches, and the implementation of artificial intelligence/machine learning in MSI-based cancer studies. The adoption of MSI in clinical research and for single-cell metabolomics is also discussed. Spatially resolved studies on other small molecule metabolites such as amino acids, polyamines, and nucleotides/nucleosides will not be discussed in the context.
Collapse
Affiliation(s)
- Xin Ma
- School of Chemistry and Biochemistry and Petit Institute for Bioengineering and Bioscience, Georgia Institute of Technology, Atlanta, Georgia, USA
| | - Facundo M Fernández
- School of Chemistry and Biochemistry and Petit Institute for Bioengineering and Bioscience, Georgia Institute of Technology, Atlanta, Georgia, USA
| |
Collapse
|
8
|
Piga I, Magni F, Smith A. The journey towards clinical adoption of MALDI-MS-based imaging proteomics: from current challenges to future expectations. FEBS Lett 2024; 598:621-634. [PMID: 38140823 DOI: 10.1002/1873-3468.14795] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/03/2023] [Revised: 12/06/2023] [Accepted: 12/09/2023] [Indexed: 12/24/2023]
Abstract
Among the spatial omics techniques available, mass spectrometry imaging (MSI) represents one of the most promising owing to its capability to map the distribution of hundreds of peptides and proteins, as well as other classes of biomolecules, within a complex sample background in a multiplexed and relatively high-throughput manner. In particular, matrix-assisted laser desorption/ionisation (MALDI-MSI) has come to the fore and established itself as the most widely used technique in clinical research. However, the march of this technique towards clinical utility has been hindered by issues related to method reproducibility, appropriate biocomputational tools, and data storage. Notwithstanding these challenges, significant progress has been achieved in recent years regarding multiple facets of the technology and has rendered it more suitable for a possible clinical role. As such, there is now more robust and extensive evidence to suggest that the technology has the potential to support clinical decision-making processes under appropriate circumstances. In this review, we will discuss some of the recent developments that have facilitated this progress and outline some of the more promising clinical proteomics applications which have been developed with a clear goal towards implementation in mind.
Collapse
Affiliation(s)
- Isabella Piga
- Department of Medicine and Surgery, Proteomics and Metabolomics Unit, University of Milano-Bicocca, Vedano al Lambro, Italy
| | - Fulvio Magni
- Department of Medicine and Surgery, Proteomics and Metabolomics Unit, University of Milano-Bicocca, Vedano al Lambro, Italy
| | - Andrew Smith
- Department of Medicine and Surgery, Proteomics and Metabolomics Unit, University of Milano-Bicocca, Vedano al Lambro, Italy
| |
Collapse
|
9
|
Baquer G, Sementé L, Ràfols P, Martín-Saiz L, Bookmeyer C, Fernández JA, Correig X, García-Altares M. rMSIfragment: improving MALDI-MSI lipidomics through automated in-source fragment annotation. J Cheminform 2023; 15:80. [PMID: 37715285 PMCID: PMC10504721 DOI: 10.1186/s13321-023-00756-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Accepted: 08/29/2023] [Indexed: 09/17/2023] Open
Abstract
Matrix-Assisted Laser Desorption Ionization Mass Spectrometry Imaging (MALDI-MSI) spatially resolves the chemical composition of tissues. Lipids are of particular interest, as they influence important biological processes in health and disease. However, the identification of lipids in MALDI-MSI remains a challenge due to the lack of chromatographic separation or untargeted tandem mass spectrometry. Recent studies have proposed the use of MALDI in-source fragmentation to infer structural information and aid identification. Here we present rMSIfragment, an open-source R package that exploits known adducts and fragmentation pathways to confidently annotate lipids in MALDI-MSI. The annotations are ranked using a novel score that demonstrates an area under the curve of 0.7 in ROC analyses using HPLC-MS and Target-Decoy validations. rMSIfragment applies to multiple MALDI-MSI sample types and experimental setups. Finally, we demonstrate that overlooking in-source fragments increases the number of incorrect annotations. Annotation workflows should consider in-source fragmentation tools such as rMSIfragment to increase annotation confidence and reduce the number of false positives.
Collapse
Affiliation(s)
- Gerard Baquer
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain.
| | - Lluc Sementé
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
| | - Pere Ràfols
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain.
- Spanish Biomedical Research Center in Diabetes and Associated Metabolic Disorders (CIBERDEM), Madrid, Spain.
- Institut D'Investigacio Sanitaria Pere Virgili, Tarragona, Spain.
| | - Lucía Martín-Saiz
- Department of Physical Chemistry, Faculty of Science and Technology, University of the Basque Country (UPV/EHU), Leioa, Spain
| | - Christoph Bookmeyer
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
- Institute of Hygiene, University of Münster, Münster, Germany
| | - José A Fernández
- Department of Physical Chemistry, Faculty of Science and Technology, University of the Basque Country (UPV/EHU), Leioa, Spain
| | - Xavier Correig
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
- Spanish Biomedical Research Center in Diabetes and Associated Metabolic Disorders (CIBERDEM), Madrid, Spain
- Institut D'Investigacio Sanitaria Pere Virgili, Tarragona, Spain
| | - María García-Altares
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
- Spanish Biomedical Research Center in Diabetes and Associated Metabolic Disorders (CIBERDEM), Madrid, Spain
| |
Collapse
|
10
|
Klaila G, Vutov V, Stefanou A. Supervised topological data analysis for MALDI mass spectrometry imaging applications. BMC Bioinformatics 2023; 24:279. [PMID: 37430224 DOI: 10.1186/s12859-023-05402-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2023] [Accepted: 06/26/2023] [Indexed: 07/12/2023] Open
Abstract
BACKGROUND Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) displays significant potential for applications in cancer research, especially in tumor typing and subtyping. Lung cancer is the primary cause of tumor-related deaths, where the most lethal entities are adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). Distinguishing between these two common subtypes is crucial for therapy decisions and successful patient management. RESULTS We propose a new algebraic topological framework, which obtains intrinsic information from MALDI data and transforms it to reflect topological persistence. Our framework offers two main advantages. Firstly, topological persistence aids in distinguishing the signal from noise. Secondly, it compresses the MALDI data, saving storage space and optimizes computational time for subsequent classification tasks. We present an algorithm that efficiently implements our topological framework, relying on a single tuning parameter. Afterwards, logistic regression and random forest classifiers are employed on the extracted persistence features, thereby accomplishing an automated tumor (sub-)typing process. To demonstrate the competitiveness of our proposed framework, we conduct experiments on a real-world MALDI dataset using cross-validation. Furthermore, we showcase the effectiveness of the single denoising parameter by evaluating its performance on synthetic MALDI images with varying levels of noise. CONCLUSION Our empirical experiments demonstrate that the proposed algebraic topological framework successfully captures and leverages the intrinsic spectral information from MALDI data, leading to competitive results in classifying lung cancer subtypes. Moreover, the framework's ability to be fine-tuned for denoising highlights its versatility and potential for enhancing data analysis in MALDI applications.
Collapse
Affiliation(s)
- Gideon Klaila
- Institute for Algebra, Geometry, Topology and their Applications (ALTA), University of Bremen, 28359, Bremen, Germany.
| | - Vladimir Vutov
- Institute for Statistics, University of Bremen, 28359, Bremen, Germany
| | - Anastasios Stefanou
- Institute for Algebra, Geometry, Topology and their Applications (ALTA), University of Bremen, 28359, Bremen, Germany
| |
Collapse
|
11
|
Vutov V, Dickhaus T. Multiple multi-sample testing under arbitrary covariance dependency. Stat Med 2023. [PMID: 37173292 DOI: 10.1002/sim.9761] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/24/2022] [Revised: 03/23/2023] [Accepted: 04/25/2023] [Indexed: 05/15/2023]
Abstract
Modern high-throughput biomedical devices routinely produce data on a large scale, and the analysis of high-dimensional datasets has become commonplace in biomedical studies. However, given thousands or tens of thousands of measured variables in these datasets, extracting meaningful features poses a challenge. In this article, we propose a procedure to evaluate the strength of the associations between a nominal (categorical) response variable and multiple features simultaneously. Specifically, we propose a framework of large-scale multiple testing under arbitrary correlation dependency among test statistics. First, marginal multinomial regressions are performed for each feature individually. Second, we use an approach of multiple marginal models for each baseline-category pair to establish asymptotic joint normality of the stacked vector of the marginal multinomial regression coefficients. Third, we estimate the (limiting) covariance matrix between the estimated coefficients from all marginal models. Finally, our approach approximates the realized false discovery proportion of a thresholding procedure for the marginal p-values for each baseline-category logit pair. The proposed approach offers a sensible trade-off between the expected numbers of true and false findings. Furthermore, we demonstrate a practical application of the method on hyperspectral imaging data. This dataset is obtained by a matrix-assisted laser desorption/ionization (MALDI) instrument. MALDI demonstrates tremendous potential for clinical diagnosis, particularly for cancer research. In our application, the nominal response categories represent cancer (sub-)types.
Collapse
Affiliation(s)
- Vladimir Vutov
- Institute for Statistics, University of Bremen, Bremen, Germany
| | | |
Collapse
|
12
|
Ma W, Luo L, Liang K, Liu T, Su J, Wang Y, Li J, Zhou SK, Shyh-Chang N. XAI-enabled neural network analysis of metabolite spatial distributions. Anal Bioanal Chem 2023; 415:2819-2830. [PMID: 37083759 DOI: 10.1007/s00216-023-04694-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2023] [Revised: 04/03/2023] [Accepted: 04/06/2023] [Indexed: 04/22/2023]
Abstract
We used deep neural networks to process the mass spectrometry imaging (MSI) data of mouse muscle (young vs aged) and human cancer (tumor vs normal adjacent) tissues, with the aim of using explainable artificial intelligence (XAI) methods to rapidly identify biomarkers that can distinguish different classes of tissues, from several thousands of metabolite features. We also modified classic neural network architectures to construct a deep convolutional neural network that is more suitable for processing high-dimensional MSI data directly, instead of using dimension reduction techniques, and compared it to seven other machine learning analysis methods' performance in classification accuracy. After ascertaining the superiority of Channel-ResNet10, we used a novel channel selection-based XAI method to identify the key metabolite features that were responsible for its learning accuracy. These key metabolite biomarkers were then processed using MetaboAnalyst for pathway enrichment mapping. We found that Channel-ResNet10 was superior to seven other machine learning methods for MSI analysis, reaching > 98% accuracy in muscle aging and colorectal cancer datasets. We also used a novel channel selection-based XAI method to find that in young and aged muscle tissues, the differentially distributed metabolite biomarkers were especially enriched in the propanoate metabolism pathway, suggesting it as a novel target pathway for anti-aging therapy.
Collapse
Affiliation(s)
- Wenwu Ma
- Department of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China
- State Key Laboratory of Stem Cell and Reproductive Biology, Chinese Academy of Sciences, Beijing, China
- Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
- Beijing Institute for Stem Cell and Regenerative Medicine, Beijing, China
| | - Lanfang Luo
- State Key Laboratory of Stem Cell and Reproductive Biology, Chinese Academy of Sciences, Beijing, China
- Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
- Beijing Institute for Stem Cell and Regenerative Medicine, Beijing, China
| | - Kun Liang
- State Key Laboratory of Stem Cell and Reproductive Biology, Chinese Academy of Sciences, Beijing, China
- Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
- Beijing Institute for Stem Cell and Regenerative Medicine, Beijing, China
| | - Taoyan Liu
- State Key Laboratory of Stem Cell and Reproductive Biology, Chinese Academy of Sciences, Beijing, China
- Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
- Beijing Institute for Stem Cell and Regenerative Medicine, Beijing, China
| | - Jiali Su
- State Key Laboratory of Stem Cell and Reproductive Biology, Chinese Academy of Sciences, Beijing, China
- Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
- Beijing Institute for Stem Cell and Regenerative Medicine, Beijing, China
| | - Yuefan Wang
- State Key Laboratory of Stem Cell and Reproductive Biology, Chinese Academy of Sciences, Beijing, China
- Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, China
- University of Chinese Academy of Sciences, Beijing, China
- Beijing Institute for Stem Cell and Regenerative Medicine, Beijing, China
| | - Jun Li
- Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China
- Center for Medical Imaging Robotics, Analytic Computing & Learning (MIRACLE), School of Biomedical Engineering &, Suzhou Institute for Advance Research, University of Science and Technology of China, Suzhou, China
| | - S Kevin Zhou
- Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS), Institute of Computing Technology, CAS, Beijing, China
- Center for Medical Imaging Robotics, Analytic Computing & Learning (MIRACLE), School of Biomedical Engineering &, Suzhou Institute for Advance Research, University of Science and Technology of China, Suzhou, China
| | - Ng Shyh-Chang
- State Key Laboratory of Stem Cell and Reproductive Biology, Chinese Academy of Sciences, Beijing, China.
- Institute for Stem Cell and Regeneration, Chinese Academy of Sciences, Beijing, China.
- University of Chinese Academy of Sciences, Beijing, China.
- Beijing Institute for Stem Cell and Regenerative Medicine, Beijing, China.
| |
Collapse
|
13
|
Vutov V, Dickhaus T. Multiple two-sample testing under arbitrary covariance dependency with an application in imaging mass spectrometry. Biom J 2023; 65:e2100328. [PMID: 36029271 DOI: 10.1002/bimj.202100328] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2021] [Revised: 05/12/2022] [Accepted: 07/04/2022] [Indexed: 11/12/2022]
Abstract
Large-scale hypothesis testing has become a ubiquitous problem in high-dimensional statistical inference, with broad applications in various scientific disciplines. One relevant application is constituted by imaging mass spectrometry (IMS) association studies, where a large number of tests are performed simultaneously in order to identify molecular masses that are associated with a particular phenotype, for example, a cancer subtype. Mass spectra obtained from matrix-assisted laser desorption/ionization (MALDI) experiments are dependent, when considered as statistical quantities. False discovery proportion (FDP) estimation and control under arbitrary dependency structure among test statistics is an active topic in modern multiple testing research. In this context, we are concerned with the evaluation of associations between the binary outcome variable (describing the phenotype) and multiple predictors derived from MALDI measurements. We propose an inference procedure in which the correlation matrix of the test statistics is utilized. The approach is based on multiple marginal models. Specifically, we fit a marginal logistic regression model for each predictor individually. Asymptotic joint normality of the stacked vector of the marginal regression coefficients is established under standard regularity assumptions, and their (limiting) correlation matrix is estimated. The proposed method extracts common factors from the resulting empirical correlation matrix. Finally, we estimate the realized FDP of a thresholding procedure for the marginal p-values. We demonstrate a practical application of the proposed workflow to MALDI IMS data in an oncological context.
Collapse
Affiliation(s)
- Vladimir Vutov
- Institute for Statistics, University of Bremen, Bremen, Germany
| | | |
Collapse
|
14
|
Kanter F, Lellmann J, Thiele H, Kalloger S, Schaeffer DF, Wellmann A, Klein O. Classification of Pancreatic Ductal Adenocarcinoma Using MALDI Mass Spectrometry Imaging Combined with Neural Networks. Cancers (Basel) 2023; 15:cancers15030686. [PMID: 36765644 PMCID: PMC9913229 DOI: 10.3390/cancers15030686] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2022] [Revised: 01/17/2023] [Accepted: 01/20/2023] [Indexed: 01/25/2023] Open
Abstract
Despite numerous diagnostic and therapeutic advances, pancreatic ductal adenocarcinoma (PDAC) has a high mortality rate, and is the fourth leading cause of cancer death in developing countries. Besides its increasing prevalence, pancreatic malignancies are characterized by poor prognosis. Omics technologies have potential relevance for PDAC assessment but are time-intensive and relatively cost-intensive and limited by tissue heterogeneity. Matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI) can obtain spatially distinct peptide-signatures and enables tumor classification within a feasible time with relatively low cost. While MALDI-MSI data sets are inherently large, machine learning methods have the potential to greatly decrease processing time. We present a pilot study investigating the potential of MALDI-MSI in combination with neural networks, for classification of pancreatic ductal adenocarcinoma. Neural-network models were trained to distinguish between pancreatic ductal adenocarcinoma and other pancreatic cancer types. The proposed methods are able to correctly classify the PDAC types with an accuracy of up to 86% and a sensitivity of 82%. This study demonstrates that machine learning tools are able to identify different pancreatic carcinoma from complex MALDI data, enabling fast prediction of large data sets. Our results encourage a more frequent use of MALDI-MSI and machine learning in histopathological studies in the future.
Collapse
Affiliation(s)
- Frederic Kanter
- Institute of Mathematics and Image Computing, Universität zu Lübeck, 23562 Luebeck, Germany
| | - Jan Lellmann
- Institute of Mathematics and Image Computing, Universität zu Lübeck, 23562 Luebeck, Germany
- Correspondence: (J.L.); (O.K.)
| | - Herbert Thiele
- Fraunhofer Institute for Digital Medicine MEVIS, 23562 Luebeck, Germany
| | - Steve Kalloger
- Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC V6T 1Z4, Canada
| | - David F. Schaeffer
- Department of Pathology and Laboratory Medicine, University of British Columbia, Vancouver, BC V6T 1Z4, Canada
- Pancreas Centre BC, Vancouver, BC V5Z 1G1, Canada
- Division of Anatomic Pathology, Vancouver General Hospital, Vancouver, BC V5Z 1M9, Canada
| | - Axel Wellmann
- Institute of Pathology, Wittinger Strasse 14, 29223 Celle, Germany
| | - Oliver Klein
- BIH Center for Regenerative Therapies, Berlin Institute of Health at Charité-Universitätsmedizin Berlin, 13353 Berlin, Germany
- Correspondence: (J.L.); (O.K.)
| |
Collapse
|
15
|
Guo L, Dong J, Xu X, Wu Z, Zhang Y, Wang Y, Li P, Tang Z, Zhao C, Cai Z. Divide and Conquer: A Flexible Deep Learning Strategy for Exploring Metabolic Heterogeneity from Mass Spectrometry Imaging Data. Anal Chem 2023; 95:1924-1932. [PMID: 36633187 PMCID: PMC9878502 DOI: 10.1021/acs.analchem.2c04045] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2022] [Accepted: 12/29/2022] [Indexed: 01/13/2023]
Abstract
Research on metabolic heterogeneity provides an important basis for the study of the molecular mechanism of a disease and personalized treatment. The screening of metabolism-related sub-regions that affect disease development is essential for the more focused exploration on disease progress aberrant phenotypes, even carcinogenesis and metastasis. The mass spectrometry imaging (MSI) technique has distinct advantages to reveal the heterogeneity of an organism based on in situ molecular profiles. The challenge of heterogeneous analysis has been to perform an objective identification among biological tissues with different characteristics. By introducing the divide-and-conquer strategy to architecture design and application, we establish here a flexible unsupervised deep learning model, called divide-and-conquer (dc)-DeepMSI, for metabolic heterogeneity analysis from MSI data without prior knowledge of histology. dc-DeepMSI can be used to identify either spatially contiguous regions of interest (ROIs) or spatially sporadic ROIs by designing two specific modes, spat-contig and spat-spor. Comparison results on fetus mouse data demonstrate that the dc-DeepMSI outperforms state-of-the-art MSI segmentation methods. We demonstrate that the novel learning strategy successfully obtained sub-regions that are statistically linked to the invasion status and molecular phenotypes of breast cancer as well as organizing principles during developmental phase.
Collapse
Affiliation(s)
- Lei Guo
- Department
of Electronic Science, National Institute
for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361005, China
| | - Jiyang Dong
- Department
of Electronic Science, National Institute
for Data Science in Health and Medicine, Xiamen University, Xiamen, Fujian 361005, China
| | - Xiangnan Xu
- School
of Mathematics and Statistics, The University
of Sydney, Sydney, NSW 2006, Australia
| | - Zhichao Wu
- School
of Artificial Intelligence, Beijing Normal
University, Beijing 100875, China
| | - Yinbin Zhang
- Department
of Oncology, The Second Affiliated Hospital
of Medical College, Xi’an Jiaotong University, Xi’an, Shaanxi 710004, China
| | - Yongwei Wang
- Bruker
Scientific Technology Co., Ltd., Beijing 100086, China
| | - Pengfei Li
- Bruker
Scientific Technology Co., Ltd., Beijing 100086, China
| | - Zhi Tang
- School
of Public Health, Dongguan Key Laboratory of Environmental Medicine, Institute of Environmental Health, Guangdong Medical
University, Dongguan, Guangdong 523808, China
| | - Chao Zhao
- Bionic
Sensing and Intelligence Center, Institute of Biomedical and Health
Engineering, Shenzhen Institute of Advanced
Technology, Chinese Academy of Sciences, Shenzhen, Guangdong 518055, China
- State
Key Laboratory of Environmental and Biological Analysis, Department
of Chemistry, Hong Kong Baptist University, Hong Kong SAR 999077, China
| | - Zongwei Cai
- State
Key Laboratory of Environmental and Biological Analysis, Department
of Chemistry, Hong Kong Baptist University, Hong Kong SAR 999077, China
| |
Collapse
|
16
|
Qin L, Han J, Wang C, Xu B, Tan D, He S, Guo L, Bo X, Xie J. Key defatting tissue pretreatment protocol for enhanced MALDI MS Imaging of peptide biomarkers visualization in the castor beans and their attribution applications. FRONTIERS IN PLANT SCIENCE 2022; 13:1083901. [PMID: 36589060 PMCID: PMC9800866 DOI: 10.3389/fpls.2022.1083901] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Accepted: 11/29/2022] [Indexed: 06/17/2023]
Abstract
INTRODUCTION Castor bean or ricin-induced intoxication or terror events have threatened public security and social safety. Potential resources or materials include beans, raw extraction products, crude toxins, and purified ricin. The traceability of the origins of castor beans is thus essential for forensic and anti-terror investigations. As a new imaging technique with label-free, rapid, and high throughput features, matrix-assisted laser desorption ionization mass spectrometry imaging (MALDI-MSI) has been gradually stressed in plant research. However, sample preparation approaches for plant tissues still face severe challenges, especially for some lipid-rich, water-rich, or fragile tissues. Proper tissue washing procedures would be pivotal, but little information is known until now. METHODS For castor beans containing plenty of lipids that were fragile when handled, we developed a comprehensive tissue pretreatment protocol. Eight washing procedures aimed at removing lipids were discussed in detail. We then constructed a robust MALDI-MSI method to enhance the detection sensitivity of RCBs in castor beans. RESULTS AND DISCUSSION A modified six-step washing procedure was chosen as the most critical parameter regarding the MSI visualization of peptides. The method was further applied to visualize and quantify the defense peptides, Ricinus communis biomarkers (RCBs) in castor bean tissue sections from nine different geographic sources from China, Pakistan, and Ethiopia. Multivariate statistical models, including deep learning network, revealed a valuable classification clue concerning nationality and altitude.
Collapse
Affiliation(s)
- Luyuan Qin
- State Key Laboratory of Toxicology and Medical Countermeasures, Institute of Pharmacology and Toxicology, Academy of Military Medical Sciences, Beijing, China
| | - Junshan Han
- Department of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing, China
| | - Chuang Wang
- State Key Laboratory of Toxicology and Medical Countermeasures, Institute of Pharmacology and Toxicology, Academy of Military Medical Sciences, Beijing, China
- Ministry of Education Key Laboratory of Ethnic Medicine, College of Pharmacy, Minzu University of China, Beijing, China
| | - Bin Xu
- State Key Laboratory of Toxicology and Medical Countermeasures, Institute of Pharmacology and Toxicology, Academy of Military Medical Sciences, Beijing, China
| | - Deyun Tan
- Institute of Cash Crop Research, Zibo Academy of Agricultural Sciences, Zibo, China
| | - Song He
- Department of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing, China
| | - Lei Guo
- State Key Laboratory of Toxicology and Medical Countermeasures, Institute of Pharmacology and Toxicology, Academy of Military Medical Sciences, Beijing, China
| | - Xiaochen Bo
- Department of Bioinformatics, Institute of Health Service and Transfusion Medicine, Beijing, China
| | - Jianwei Xie
- State Key Laboratory of Toxicology and Medical Countermeasures, Institute of Pharmacology and Toxicology, Academy of Military Medical Sciences, Beijing, China
| |
Collapse
|
17
|
Janßen C, Boskamp T, Le’Clerc Arrastia J, Otero Baguer D, Hauberg-Lotte L, Kriegsmann M, Kriegsmann K, Steinbuß G, Casadonte R, Kriegsmann J, Maaß P. Multimodal Lung Cancer Subtyping Using Deep Learning Neural Networks on Whole Slide Tissue Images and MALDI MSI. Cancers (Basel) 2022; 14:cancers14246181. [PMID: 36551667 PMCID: PMC9776684 DOI: 10.3390/cancers14246181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/15/2022] [Revised: 12/12/2022] [Accepted: 12/12/2022] [Indexed: 12/23/2022] Open
Abstract
Artificial intelligence (AI) has shown potential for facilitating the detection and classification of tumors. In patients with non-small cell lung cancer, distinguishing between the most common subtypes, adenocarcinoma (ADC) and squamous cell carcinoma (SqCC), is crucial for the development of an effective treatment plan. This task, however, may still present challenges in clinical routine. We propose a two-modality, AI-based classification algorithm to detect and subtype tumor areas, which combines information from matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) data and digital microscopy whole slide images (WSIs) of lung tissue sections. The method consists of first detecting areas with high tumor cell content by performing a segmentation of the hematoxylin and eosin-stained (H&E-stained) WSIs, and subsequently classifying the tumor areas based on the corresponding MALDI MSI data. We trained the algorithm on six tissue microarrays (TMAs) with tumor samples from N = 232 patients and used 14 additional whole sections for validation and model selection. Classification accuracy was evaluated on a test dataset with another 16 whole sections. The algorithm accurately detected and classified tumor areas, yielding a test accuracy of 94.7% on spectrum level, and correctly classified 15 of 16 test sections. When an additional quality control criterion was introduced, a 100% test accuracy was achieved on sections that passed the quality control (14 of 16). The presented method provides a step further towards the inclusion of AI and MALDI MSI data into clinical routine and has the potential to reduce the pathologist's work load. A careful analysis of the results revealed specific challenges to be considered when training neural networks on data from lung cancer tissue.
Collapse
Affiliation(s)
- Charlotte Janßen
- Center for Industrial Mathematics (ZeTeM), University of Bremen, 28359 Bremen, Germany
- Correspondence:
| | - Tobias Boskamp
- Center for Industrial Mathematics (ZeTeM), University of Bremen, 28359 Bremen, Germany
- Bruker Daltonics, 28359 Bremen, Germany
| | | | - Daniel Otero Baguer
- Center for Industrial Mathematics (ZeTeM), University of Bremen, 28359 Bremen, Germany
| | - Lena Hauberg-Lotte
- Center for Industrial Mathematics (ZeTeM), University of Bremen, 28359 Bremen, Germany
| | - Mark Kriegsmann
- Institute of Pathology, University Hospital Heidelberg, 69120 Heidelberg, Germany
- Translational Lung Research Center Heidelberg (TLRC), Member of the German Center for Lung Research (DZL), 69120 Heidelberg, Germany
- Institute of Pathology Wiesbaden, 65199 Wiesbaden, Germany
| | - Katharina Kriegsmann
- Department of Hematology, Oncology and Rheumatology, University Hospital Heidelberg, 69120 Heidelberg, Germany
| | - Georg Steinbuß
- Department of Hematology, Oncology and Rheumatology, University Hospital Heidelberg, 69120 Heidelberg, Germany
| | | | - Jörg Kriegsmann
- Proteopath, 54926 Trier, Germany
- Center for Histology, Cytology and Molecular Diagnostic, 54296 Trier, Germany
- Faculty of Medicine and Dentistry, Danube Private University, 3500 Krems, Austria
| | - Peter Maaß
- Center for Industrial Mathematics (ZeTeM), University of Bremen, 28359 Bremen, Germany
| |
Collapse
|
18
|
Hu H, Laskin J. Emerging Computational Methods in Mass Spectrometry Imaging. ADVANCED SCIENCE (WEINHEIM, BADEN-WURTTEMBERG, GERMANY) 2022; 9:e2203339. [PMID: 36253139 PMCID: PMC9731724 DOI: 10.1002/advs.202203339] [Citation(s) in RCA: 20] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Revised: 09/17/2022] [Indexed: 05/10/2023]
Abstract
Mass spectrometry imaging (MSI) is a powerful analytical technique that generates maps of hundreds of molecules in biological samples with high sensitivity and molecular specificity. Advanced MSI platforms with capability of high-spatial resolution and high-throughput acquisition generate vast amount of data, which necessitates the development of computational tools for MSI data analysis. In addition, computation-driven MSI experiments have recently emerged as enabling technologies for further improving the MSI capabilities with little or no hardware modification. This review provides a critical summary of computational methods and resources developed for MSI data analysis and interpretation along with computational approaches for improving throughput and molecular coverage in MSI experiments. This review is focused on the recently developed artificial intelligence methods and provides an outlook for a future paradigm shift in MSI with transformative computational methods.
Collapse
Affiliation(s)
- Hang Hu
- Department of ChemistryPurdue University560 Oval DriveWest LafayetteIN47907USA
| | - Julia Laskin
- Department of ChemistryPurdue University560 Oval DriveWest LafayetteIN47907USA
| |
Collapse
|
19
|
Yamada H, Xu L, Eto F, Takeichi R, Islam A, Mamun MA, Zhang C, Yao I, Sakamoto T, Aramaki S, Kikushima K, Sato T, Takahashi Y, Machida M, Kahyo T, Setou M. Changes of Mass Spectra Patterns on a Brain Tissue Section Revealed by Deep Learning with Imaging Mass Spectrometry Data. JOURNAL OF THE AMERICAN SOCIETY FOR MASS SPECTROMETRY 2022; 33:1607-1614. [PMID: 35881989 DOI: 10.1021/jasms.2c00080] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
The characteristic patterns of mass spectra in imaging mass spectrometry (IMS) strongly reflect the tissue environment. However, the boundaries formed where different tissue environments collide have not been visually assessed. In this study, IMS and convolutional neural network (CNN), one of the deep learning methods, were applied to the extraction of characteristic mass spectra patterns from training brain regions on rodents' brain sections. CNN produced classification models with high accuracy and low loss rate in any test data sets of mouse coronal sections measured by desorption electrospray ionization (DESI)-IMS and of mouse and rat sagittal sections by matrix-assisted laser desorption (MALDI)-IMS. On the basis of the extracted mass spectra pattern features, the histologically plausible segmentation and classification score imaging of the brain sections were obtained. The boundary imaging generated from classification scores showed the extreme changes of mass spectra patterns between the tissue environments, with no significant buffer zones for the intermediate state. The CNN-based analysis of IMS data is a useful tool for visually assessing the changes of mass spectra patterns on a tissue section, and it will contribute to a comprehensive view of the tissue environment.
Collapse
Affiliation(s)
- Hidemoto Yamada
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Lili Xu
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Fumihiro Eto
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Rei Takeichi
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Ariful Islam
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Md Ai Mamun
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Chi Zhang
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Ikuko Yao
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- Department of Biomedical Sciences, School of Biological and Environmental Sciences, Kwansei Gakuin University, 2-1 Gakuen, Sanda, Hyogo 669-1337, Japan
| | - Takumi Sakamoto
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- International Mass Imaging Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Shuhei Aramaki
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- Department of Radiation Oncology, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Kenji Kikushima
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- International Mass Imaging Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Tomohito Sato
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- International Mass Imaging Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Yutaka Takahashi
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- International Mass Imaging Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Manabu Machida
- Department of Systems Molecular Anatomy, Institute for Medical Photonics Research, Preeminent Medical Photonics Education & Research Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Tomoaki Kahyo
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- International Mass Imaging Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| | - Mitsutoshi Setou
- Department of Cellular and Molecular Anatomy, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- International Mass Imaging Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
- Department of Systems Molecular Anatomy, Institute for Medical Photonics Research, Preeminent Medical Photonics Education & Research Center, Hamamatsu University School of Medicine, 1-20-1 Handayama, Higashi-ku, Hamamatsu, Shizuoka 431-3192, Japan
| |
Collapse
|
20
|
Pertzborn D, Arolt C, Ernst G, Lechtenfeld OJ, Kaesler J, Pelzel D, Guntinas-Lichius O, von Eggeling F, Hoffmann F. Multi-Class Cancer Subtyping in Salivary Gland Carcinomas with MALDI Imaging and Deep Learning. Cancers (Basel) 2022; 14:cancers14174342. [PMID: 36077876 PMCID: PMC9454426 DOI: 10.3390/cancers14174342] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/15/2022] [Revised: 08/18/2022] [Accepted: 09/03/2022] [Indexed: 11/16/2022] Open
Abstract
Salivary gland carcinomas (SGC) are a heterogeneous group of tumors. The prognosis varies strongly according to its type, and even the distinction between benign and malign tumor is challenging. Adenoid cystic carcinoma (AdCy) is one subgroup of SGCs that is prone to late metastasis. This makes accurate tumor subtyping an important task. Matrix-assisted laser desorption/ionization (MALDI) imaging is a label-free technique capable of providing spatially resolved information about the abundance of biomolecules according to their mass-to-charge ratio. We analyzed tissue micro arrays (TMAs) of 25 patients (including six different SGC subtypes and a healthy control group of six patients) with high mass resolution MALDI imaging using a 12-Tesla magnetic resonance mass spectrometer. The high mass resolution allowed us to accurately detect single masses, with strong contributions to each class prediction. To address the added complexity created by the high mass resolution and multiple classes, we propose a deep-learning model. We showed that our deep-learning model provides a per-class classification accuracy of greater than 80% with little preprocessing. Based on this classification, we employed methods of explainable artificial intelligence (AI) to gain further insights into the spectrometric features of AdCys.
Collapse
Affiliation(s)
- David Pertzborn
- Innovative Biophotonics & MALDI Imaging, ENT Department, Jena University Hospital, 07747 Jena, Germany
| | - Christoph Arolt
- Institute of Pathology, Medical Faculty, University of Cologne, 50937 Cologne, Germany
| | - Günther Ernst
- Innovative Biophotonics & MALDI Imaging, ENT Department, Jena University Hospital, 07747 Jena, Germany
| | - Oliver J. Lechtenfeld
- Department of Analytical Chemistry, Research Group BioGeoOmics, Helmholtz Centre for Environmental Research—UFZ, 04318 Leipzig, Germany
- ProVIS−Centre for Chemical Microscopy, Helmholtz Centre for Environmental Research—UFZ, 04318 Leipzig, Germany
| | - Jan Kaesler
- Department of Analytical Chemistry, Research Group BioGeoOmics, Helmholtz Centre for Environmental Research—UFZ, 04318 Leipzig, Germany
| | - Daniela Pelzel
- Innovative Biophotonics & MALDI Imaging, ENT Department, Jena University Hospital, 07747 Jena, Germany
| | - Orlando Guntinas-Lichius
- Innovative Biophotonics & MALDI Imaging, ENT Department, Jena University Hospital, 07747 Jena, Germany
| | - Ferdinand von Eggeling
- Innovative Biophotonics & MALDI Imaging, ENT Department, Jena University Hospital, 07747 Jena, Germany
| | - Franziska Hoffmann
- Innovative Biophotonics & MALDI Imaging, ENT Department, Jena University Hospital, 07747 Jena, Germany
- Correspondence:
| |
Collapse
|
21
|
Shen X, Shao W, Wang C, Liang L, Chen S, Zhang S, Rusu M, Snyder MP. Deep learning-based pseudo-mass spectrometry imaging analysis for precision medicine. Brief Bioinform 2022; 23:6659741. [PMID: 35947990 DOI: 10.1093/bib/bbac331] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2022] [Revised: 07/02/2022] [Accepted: 07/20/2022] [Indexed: 11/14/2022] Open
Abstract
Liquid chromatography-mass spectrometry (LC-MS)-based untargeted metabolomics provides systematic profiling of metabolic. Yet, its applications in precision medicine (disease diagnosis) have been limited by several challenges, including metabolite identification, information loss and low reproducibility. Here, we present the deep-learning-based Pseudo-Mass Spectrometry Imaging (deepPseudoMSI) project (https://www.deeppseudomsi.org/), which converts LC-MS raw data to pseudo-MS images and then processes them by deep learning for precision medicine, such as disease diagnosis. Extensive tests based on real data demonstrated the superiority of deepPseudoMSI over traditional approaches and the capacity of our method to achieve an accurate individualized diagnosis. Our framework lays the foundation for future metabolic-based precision medicine.
Collapse
Affiliation(s)
- Xiaotao Shen
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.,Stanford Center for Genomics and Personalized Medicine, Stanford, CA, USA
| | - Wei Shao
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA
| | - Chuchu Wang
- Howard Hughes Medical Institute, Stanford University, Stanford, CA 94305, USA
| | - Liang Liang
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.,Stanford Center for Genomics and Personalized Medicine, Stanford, CA, USA
| | - Songjie Chen
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.,Stanford Center for Genomics and Personalized Medicine, Stanford, CA, USA
| | - Sai Zhang
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.,Stanford Center for Genomics and Personalized Medicine, Stanford, CA, USA
| | - Mirabela Rusu
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA
| | - Michael P Snyder
- Department of Genetics, Stanford University School of Medicine, Stanford, CA, USA.,Stanford Center for Genomics and Personalized Medicine, Stanford, CA, USA
| |
Collapse
|
22
|
Boiko DA, Kozlov KS, Burykina JV, Ilyushenkova VV, Ananikov VP. Fully Automated Unconstrained Analysis of High-Resolution Mass Spectrometry Data with Machine Learning. J Am Chem Soc 2022; 144:14590-14606. [PMID: 35939718 DOI: 10.1021/jacs.2c03631] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
Mass spectrometry (MS) is a convenient, highly sensitive, and reliable method for the analysis of complex mixtures, which is vital for materials science, life sciences fields such as metabolomics and proteomics, and mechanistic research in chemistry. Although it is one of the most powerful methods for individual compound detection, complete signal assignment in complex mixtures is still a great challenge. The unconstrained formula-generating algorithm, covering the entire spectra and revealing components, is a "dream tool" for researchers. We present the framework for efficient MS data interpretation, describing a novel approach for detailed analysis based on deisotoping performed by gradient-boosted decision trees and a neural network that generates molecular formulas from the fine isotopic structure, approaching the long-standing inverse spectral problem. The methods were successfully tested on three examples: fragment ion analysis in protein sequencing for proteomics, analysis of the natural samples for life sciences, and study of the cross-coupling catalytic system for chemistry.
Collapse
Affiliation(s)
- Daniil A Boiko
- Zelinsky Institute of Organic Chemistry, Russian Academy of Sciences, Leninsky Prospekt 47, Moscow 119991, Russia
| | - Konstantin S Kozlov
- Zelinsky Institute of Organic Chemistry, Russian Academy of Sciences, Leninsky Prospekt 47, Moscow 119991, Russia
| | - Julia V Burykina
- Zelinsky Institute of Organic Chemistry, Russian Academy of Sciences, Leninsky Prospekt 47, Moscow 119991, Russia
| | - Valentina V Ilyushenkova
- Zelinsky Institute of Organic Chemistry, Russian Academy of Sciences, Leninsky Prospekt 47, Moscow 119991, Russia
| | - Valentine P Ananikov
- Zelinsky Institute of Organic Chemistry, Russian Academy of Sciences, Leninsky Prospekt 47, Moscow 119991, Russia
| |
Collapse
|
23
|
Towards In-Situ Geochemical Analysis of Planetary Rocks and Soils by Laser Ablation/Ionisation Time-of-Flight Mass Spectrometry. UNIVERSE 2022. [DOI: 10.3390/universe8080410] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Spectroscopic instruments were a part of payloads on orbiter and lander missions and delivered vast data sets to explore minerals, elements and molecules on air-less rocky planets, asteroids and comets on global and local scales. To answer current space science questions, the chemical composition of planetary rocks and soils at grain scale is required, as well as measurements of element (isotope) concentrations down to the part per million or lower. Only mass spectrometric methods equipped with laser sampling ion sources can deliver the necessary information. Laser sampling techniques can reduce the dimensions of the investigated sample material down to micrometre scale, allowing for the composition analysis of grain-sized objects or thin mineral layers with sufficiently high spatial resolution, such that important geological processes can be recognised and studied as they progressed in time. We describe the performance characteristics, when applied to meteorite and geological samples, of a miniaturised laser ablation/ionisation mass spectrometer (named LMS) system that has been developed in our group. The main advantages of the LMS instrument over competing techniques are illustrated by examples of high spatial (lateral and vertical) resolution studies in different meteorites, terrestrial minerals and fossil-like structures in ancient rocks for most elements of geochemical interest. Top-level parameters, such as dimension, weight, and power consumption of a possible flight design of the LMS system are presented as well.
Collapse
|
24
|
Petrick LM, Shomron N. AI/ML-driven advances in untargeted metabolomics and exposomics for biomedical applications. CELL REPORTS. PHYSICAL SCIENCE 2022; 3:100978. [PMID: 35936554 PMCID: PMC9354369 DOI: 10.1016/j.xcrp.2022.100978] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Metabolomics describes a high-throughput approach for measuring a repertoire of metabolites and small molecules in biological samples. One utility of untargeted metabolomics, unbiased global analysis of the metabolome, is to detect key metabolites as contributors to, or readouts of, human health and disease. In this perspective, we discuss how artificial intelligence (AI) and machine learning (ML) have promoted major advances in untargeted metabolomics workflows and facilitated pivotal findings in the areas of disease screening and diagnosis. We contextualize applications of AI and ML to the emerging field of high-resolution mass spectrometry (HRMS) exposomics, which unbiasedly detects endogenous metabolites and exogenous chemicals in human tissue to characterize exposure linked with disease outcomes. We discuss the state of the science and suggest potential opportunities for using AI and ML to improve data quality, rigor, detection, and chemical identification in untargeted metabolomics and exposomics studies.
Collapse
Affiliation(s)
- Lauren M. Petrick
- The Bert Strassburger Metabolic Center, Sheba Medical Center, Tel-Hashomer, Israel
- Department of Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Institute for Exposomics Research, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Noam Shomron
- Faculty of Medicine, Edmond J. Safra Center for Bioinformatics, Sagol School of Neuroscience, Center for Nanoscience and Nanotechnology, Center for Innovation Laboratories (TILabs), Tel Aviv University, Tel Aviv, Israel
| |
Collapse
|
25
|
Baquer G, Sementé L, Mahamdi T, Correig X, Ràfols P, García-Altares M. What are we imaging? Software tools and experimental strategies for annotation and identification of small molecules in mass spectrometry imaging. MASS SPECTROMETRY REVIEWS 2022:e21794. [PMID: 35822576 DOI: 10.1002/mas.21794] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2023]
Abstract
Mass spectrometry imaging (MSI) has become a widespread analytical technique to perform nonlabeled spatial molecular identification. The Achilles' heel of MSI is the annotation and identification of molecular species due to intrinsic limitations of the technique (lack of chromatographic separation and the difficulty to apply tandem MS). Successful strategies to perform annotation and identification combine extra analytical steps, like using orthogonal analytical techniques to identify compounds; with algorithms that integrate the spectral and spatial information. In this review, we discuss different experimental strategies and bioinformatics tools to annotate and identify compounds in MSI experiments. We target strategies and tools for small molecule applications, such as lipidomics and metabolomics. First, we explain how sample preparation and the acquisition process influences annotation and identification, from sample preservation to the use of orthogonal techniques. Then, we review twelve software tools for annotation and identification in MSI. Finally, we offer perspectives on two current needs of the MSI community: the adaptation of guidelines for communicating confidence levels in identifications; and the creation of a standard format to store and exchange annotations and identifications in MSI.
Collapse
Affiliation(s)
- Gerard Baquer
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
| | - Lluc Sementé
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
| | - Toufik Mahamdi
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
| | - Xavier Correig
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
- Spanish Biomedical Research Center in Diabetes and Associated Metabolic Disorders (CIBERDEM), Madrid, Spain
- Institut D'Investigacio Sanitaria Pere Virgili, Tarragona, Spain
| | - Pere Ràfols
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
- Spanish Biomedical Research Center in Diabetes and Associated Metabolic Disorders (CIBERDEM), Madrid, Spain
- Institut D'Investigacio Sanitaria Pere Virgili, Tarragona, Spain
| | - María García-Altares
- Department of Electronic Engineering, University Rovira I Virgili, Tarragona, Spain
- Spanish Biomedical Research Center in Diabetes and Associated Metabolic Disorders (CIBERDEM), Madrid, Spain
| |
Collapse
|
26
|
Janßen C, Boskamp T, Hauberg-Lotte L, Behrmann J, Deininger SO, Kriegsmann M, Kriegsmann K, Steinbuß G, Winter H, Muley T, Casadonte R, Kriegsmann J, Maaß P. Robust subtyping of non-small cell lung cancer whole sections through MALDI mass spectrometry imaging. Proteomics Clin Appl 2022; 16:e2100068. [PMID: 35238465 DOI: 10.1002/prca.202100068] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2021] [Revised: 01/24/2022] [Accepted: 02/28/2022] [Indexed: 12/30/2022]
Abstract
Subtyping of the most common non-small cell lung cancer (NSCLC) tumor types adenocarcinoma (ADC) and squamous cell carcinoma (SqCC) is still a challenge in the clinical routine and a correct diagnosis is crucial for an adequate therapy selection. Matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) has shown potential for NSCLC subtyping but is subject to strong technical variability and has only been applied to tissue samples assembled in tissue microarrays (TMAs). To our knowledge, a successful transfer of a classifier from TMAs to whole sections, which are generated in the standard clinical routine, has not been presented in the literature as of yet. We introduce a classification algorithm using extensive preprocessing and a classifier (either a neural network or a linear discriminant analysis (LDA)) to robustly classify whole sections of ADC and SqCC lung tissue. The classifiers were trained on TMAs and validated and tested on whole sections. Vital for a successful application on whole sections is the extensive preprocessing and the use of whole sections for hyperparameter selection. The classification system with the neural network/LDA results in 99.0%/98.3% test accuracy on spectra level and 100.0%/100.0% test accuracy on whole section level, respectively, and, therefore, provides a powerful tool to support the pathologist's decision making process. The presented method is a step further towards a clinical application of MALDI MSI and artificial intelligence for subtyping of NSCLC tissue sections.
Collapse
Affiliation(s)
- Charlotte Janßen
- Center for Industrial Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| | - Tobias Boskamp
- Center for Industrial Mathematics (ZeTeM), University of Bremen, Bremen, Germany.,Bruker Daltonics GmbH, Bremen, Germany
| | - Lena Hauberg-Lotte
- Center for Industrial Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| | - Jens Behrmann
- Center for Industrial Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| | | | - Mark Kriegsmann
- Institute of Pathology, University Hospital Heidelberg, Heidelberg, Germany.,Translational Lung Research Center Heidelberg (TLRC), Member of the German Center for Lung Research (DZL), Heidelberg, Germany
| | - Katharina Kriegsmann
- Department of Hematology, Oncology and Rheumatology, University Hospital Heidelberg, Heidelberg, Germany
| | - Georg Steinbuß
- Department of Hematology, Oncology and Rheumatology, University Hospital Heidelberg, Heidelberg, Germany
| | - Hauke Winter
- Translational Lung Research Center Heidelberg (TLRC), Member of the German Center for Lung Research (DZL), Heidelberg, Germany.,Department of Thoracic Surgery, Thoraxklinik, Heidelberg University Hospital, Heidelberg, Germany
| | - Thomas Muley
- Translational Lung Research Center Heidelberg (TLRC), Member of the German Center for Lung Research (DZL), Heidelberg, Germany.,Translational Research Unit, Thoraxklinik, Heidelberg University Hospital, Heidelberg, Germany
| | | | - Jörg Kriegsmann
- Proteopath, Trier, Germany.,Center for Histology, Cytology and Molecular Diagnostic, Trier, Germany
| | - Peter Maaß
- Center for Industrial Mathematics (ZeTeM), University of Bremen, Bremen, Germany
| |
Collapse
|
27
|
Abdelmoula WM, Stopka SA, Randall EC, Regan M, Agar JN, Sarkaria JN, Wells WM, Kapur T, Agar NYR. massNet: integrated processing and classification of spatially resolved mass spectrometry data using deep learning for rapid tumor delineation. Bioinformatics 2022; 38:2015-2021. [PMID: 35040929 PMCID: PMC8963284 DOI: 10.1093/bioinformatics/btac032] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/12/2021] [Revised: 01/04/2022] [Accepted: 01/13/2022] [Indexed: 01/21/2023] Open
Abstract
MOTIVATION Mass spectrometry imaging (MSI) provides rich biochemical information in a label-free manner and therefore holds promise to substantially impact current practice in disease diagnosis. However, the complex nature of MSI data poses computational challenges in its analysis. The complexity of the data arises from its large size, high-dimensionality and spectral nonlinearity. Preprocessing, including peak picking, has been used to reduce raw data complexity; however, peak picking is sensitive to parameter selection that, perhaps prematurely, shapes the downstream analysis for tissue classification and ensuing biological interpretation. RESULTS We propose a deep learning model, massNet, that provides the desired qualities of scalability, nonlinearity and speed in MSI data analysis. This deep learning model was used, without prior preprocessing and peak picking, to classify MSI data from a mouse brain harboring a patient-derived tumor. The massNet architecture established automatically learning of predictive features, and automated methods were incorporated to identify peaks with potential for tumor delineation. The model's performance was assessed using cross-validation, and the results demonstrate higher accuracy and a substantial gain in speed compared to the established classical machine learning method, support vector machine. AVAILABILITY AND IMPLEMENTATION https://github.com/wabdelmoula/massNet. The data underlying this article are available in the NIH Common Fund's National Metabolomics Data Repository (NMDR) Metabolomics Workbench under project id (PR001292) with http://dx.doi.org/10.21228/M8Q70T. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Walid M Abdelmoula
- Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA,Invicro LLC, Boston, MA 02210, USA
| | - Sylwia A Stopka
- Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA,Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Elizabeth C Randall
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Michael Regan
- Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Jeffrey N Agar
- Department of Chemistry and Chemical Biology, Northeastern University, Boston, MA 02111, USA
| | - Jann N Sarkaria
- Department of Radiation Oncology, Mayo Clinic, Rochester, MN 55902, USA
| | - William M Wells
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA,Computer Science and Artificial Intelligence Laboratory, MIT, Cambridge, MA 02139, USA
| | - Tina Kapur
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA
| | - Nathalie Y R Agar
- Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA,Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA 02115, USA,Department of Cancer Biology, Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA 02115, USA,To whom correspondence should be addressed.
| |
Collapse
|
28
|
Althobaiti MM, Almulihi A, Ashour AA, Mansour RF, Gupta D. Design of Optimal Deep Learning-Based Pancreatic Tumor and Nontumor Classification Model Using Computed Tomography Scans. JOURNAL OF HEALTHCARE ENGINEERING 2022; 2022:2872461. [PMID: 35070232 PMCID: PMC8769827 DOI: 10.1155/2022/2872461] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 10/29/2021] [Revised: 12/10/2021] [Accepted: 12/17/2021] [Indexed: 12/18/2022]
Abstract
Pancreatic tumor is a lethal kind of tumor and its prediction is really poor in the current scenario. Automated pancreatic tumor classification using computer-aided diagnosis (CAD) model is necessary to track, predict, and classify the existence of pancreatic tumors. Artificial intelligence (AI) can offer extensive diagnostic expertise and accurate interventional image interpretation. With this motivation, this study designs an optimal deep learning based pancreatic tumor and nontumor classification (ODL-PTNTC) model using CT images. The goal of the ODL-PTNTC technique is to detect and classify the existence of pancreatic tumors and nontumor. The proposed ODL-PTNTC technique includes adaptive window filtering (AWF) technique to remove noise existing in it. In addition, sailfish optimizer based Kapur's Thresholding (SFO-KT) technique is employed for image segmentation process. Moreover, feature extraction using Capsule Network (CapsNet) is derived to generate a set of feature vectors. Furthermore, Political Optimizer (PO) with Cascade Forward Neural Network (CFNN) is employed for classification purposes. In order to validate the enhanced performance of the ODL-PTNTC technique, a series of simulations take place and the results are investigated under several aspects. A comprehensive comparative results analysis stated the promising performance of the ODL-PTNTC technique over the recent approaches.
Collapse
Affiliation(s)
- Maha M. Althobaiti
- Department of Computer Science College of Computing and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia
| | - Ahmed Almulihi
- Department of Computer Science College of Computing and Information Technology, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia
| | - Amal Adnan Ashour
- Department of Oral & Maxillofacial Surgery and Diagnostic Sciences Faculty of Dentistry, Taif University, P.O. Box 11099, Taif 21944, Saudi Arabia
| | - Romany F. Mansour
- Department of Mathematics Faculty of Science, New Valley University, El-Kharga 72511, Egypt
| | - Deepak Gupta
- Department of Computer Science & Engineering, Maharaja Agrasen Institute of Technology, Delhi, India
| |
Collapse
|
29
|
Rehfeldt TG, Krawczyk K, Bøgebjerg M, Schwämmle V, Röttger R. MS2AI: automated repurposing of public peptide LC-MS data for machine learning applications. Bioinformatics 2022; 38:875-877. [PMID: 34636883 DOI: 10.1093/bioinformatics/btab701] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2021] [Revised: 09/09/2021] [Accepted: 10/11/2021] [Indexed: 02/03/2023] Open
Abstract
MOTIVATION Liquid-chromatography mass-spectrometry (LC-MS) is the established standard for analyzing the proteome in biological samples by identification and quantification of thousands of proteins. Machine learning (ML) promises to considerably improve the analysis of the resulting data, however, there is yet to be any tool that mediates the path from raw data to modern ML applications. More specifically, ML applications are currently hampered by three major limitations: (i) absence of balanced training data with large sample size; (ii) unclear definition of sufficiently information-rich data representations for e.g. peptide identification; (iii) lack of benchmarking of ML methods on specific LC-MS problems. RESULTS We created the MS2AI pipeline that automates the process of gathering vast quantities of MS data for large-scale ML applications. The software retrieves raw data from either in-house sources or from the proteomics identifications database, PRIDE. Subsequently, the raw data are stored in a standardized format amenable for ML, encompassing MS1/MS2 spectra and peptide identifications. This tool bridges the gap between MS and AI, and to this effect we also present an ML application in the form of a convolutional neural network for the identification of oxidized peptides. AVAILABILITY AND IMPLEMENTATION An open-source implementation of the software can be found at https://gitlab.com/roettgerlab/ms2ai. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
| | - Konrad Krawczyk
- Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark
| | - Mathias Bøgebjerg
- Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark
| | - Veit Schwämmle
- Department of Biochemistry and Molecular Biology, University of Southern Denmark, Odense, Denmark
| | - Richard Röttger
- Department of Mathematics and Computer Science, University of Southern Denmark, Odense, Denmark
| |
Collapse
|
30
|
Santilli AML, Ren K, Oleschuk R, Kaufmann M, Rudan J, Fichtinger G, Mousavi P. Application of Intraoperative Mass Spectrometry and Data Analytics for Oncological Margin Detection, A Review. IEEE Trans Biomed Eng 2022; 69:2220-2232. [PMID: 34982670 DOI: 10.1109/tbme.2021.3139992] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
OBJECTIVE A common phase of early-stage oncological treatment is the surgical resection of cancerous tissue. The presence of cancer cells on the resection margin, referred to as positive margin, is correlated with the recurrence of cancer and may require re-operation, negatively impacting many facets of patient outcomes. There exists a significant gap in the surgeons ability to intraoperatively delineate between tissues. Mass spectrometry methods have shown considerable promise as intraoperative tissue profiling tools that can assist with the complete resection of cancer. To do so, the vastness of the information collected through these modalities must be digested, relying on robust and efficient extraction of insights through data analysis pipelines. METHODS We review clinical mass spectrometry literature and prioritize intraoperatively applied modalities. We also survey the data analysis methods employed in these studies. RESULTS Our review outlines the advantages and shortcomings of mass spectrometry imaging and point-based tissue probing methods. For each modality, we identify statistical, linear transformation and machine learning techniques that demonstrate high performance in classifying cancerous tissues across several organ systems. A limited number of studies presented results captured intraoperatively. CONCLUSION Through continued research of data centric techniques, like mass spectrometry, and the development of robust analysis approaches, intraoperative margin assessment is becoming feasible. SIGNIFICANCE By establishing the relatively short history of mass spectrometry techniques applied to surgical studies, we hope to inform future applications and aid in the selection of suitable data analysis frameworks for the development of intraoperative margin detection technologies.
Collapse
|
31
|
Horgan C, Jensen M, Nagelkerke A, St-Pierre JP, Vercauteren T, Stevens MM, Bergholt MS. High-Throughput Molecular Imaging via Deep-Learning-Enabled Raman Spectroscopy. Anal Chem 2021; 93:15850-15860. [PMID: 34797972 PMCID: PMC9286315 DOI: 10.1021/acs.analchem.1c02178] [Citation(s) in RCA: 22] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/28/2022]
Abstract
Raman spectroscopy enables nondestructive, label-free imaging with unprecedented molecular contrast, but is limited by slow data acquisition, largely preventing high-throughput imaging applications. Here, we present a comprehensive framework for higher-throughput molecular imaging via deep-learning-enabled Raman spectroscopy, termed DeepeR, trained on a large data set of hyperspectral Raman images, with over 1.5 million spectra (400 h of acquisition) in total. We first perform denoising and reconstruction of low signal-to-noise ratio Raman molecular signatures via deep learning, with a 10× improvement in the mean-squared error over common Raman filtering methods. Next, we develop a neural network for robust 2-4× spatial super-resolution of hyperspectral Raman images that preserve molecular cellular information. Combining these approaches, we achieve Raman imaging speed-ups of up to 40-90×, enabling good-quality cellular imaging with a high-resolution, high signal-to-noise ratio in under 1 min. We further demonstrate Raman imaging speed-up of 160×, useful for lower resolution imaging applications such as the rapid screening of large areas or for spectral pathology. Finally, transfer learning is applied to extend DeepeR from cell to tissue-scale imaging. DeepeR provides a foundation that will enable a host of higher-throughput Raman spectroscopy and molecular imaging applications across biomedicine.
Collapse
Affiliation(s)
- Conor
C. Horgan
- Centre
for Craniofacial and Regenerative Biology, King’s College London, London SE1 9RT, U.K.
- Department
of Materials, Department of Bioengineering, and Institute of Biomedical
Engineering, Imperial College London, London SW7 2AZ, U.K.
| | - Magnus Jensen
- Centre
for Craniofacial and Regenerative Biology, King’s College London, London SE1 9RT, U.K.
| | - Anika Nagelkerke
- Groningen
Research Institute of Pharmacy, Pharmaceutical Analysis, University of Groningen, P.O. Box 196, XB20, Groningen 9700 AD, The Netherlands
- Department
of Materials, Department of Bioengineering, and Institute of Biomedical
Engineering, Imperial College London, London SW7 2AZ, U.K.
| | - Jean-Philippe St-Pierre
- Department
of Chemical and Biological Engineering, University of Ottawa, Ottawa, Ontario K1N 6N5, Canada
- Department
of Materials, Department of Bioengineering, and Institute of Biomedical
Engineering, Imperial College London, London SW7 2AZ, U.K.
| | - Tom Vercauteren
- School
of Biomedical Engineering and Imaging Sciences, King’s College London, London WC2R 2LS, U.K.
| | - Molly M. Stevens
- Department
of Materials, Department of Bioengineering, and Institute of Biomedical
Engineering, Imperial College London, London SW7 2AZ, U.K.
| | - Mads S. Bergholt
- Centre
for Craniofacial and Regenerative Biology, King’s College London, London SE1 9RT, U.K.
| |
Collapse
|
32
|
Mridha MF, Hamid MA, Monowar MM, Keya AJ, Ohi AQ, Islam MR, Kim JM. A Comprehensive Survey on Deep-Learning-Based Breast Cancer Diagnosis. Cancers (Basel) 2021; 13:6116. [PMID: 34885225 PMCID: PMC8656730 DOI: 10.3390/cancers13236116] [Citation(s) in RCA: 15] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2021] [Revised: 11/25/2021] [Accepted: 12/01/2021] [Indexed: 12/11/2022] Open
Abstract
Breast cancer is now the most frequently diagnosed cancer in women, and its percentage is gradually increasing. Optimistically, there is a good chance of recovery from breast cancer if identified and treated at an early stage. Therefore, several researchers have established deep-learning-based automated methods for their efficiency and accuracy in predicting the growth of cancer cells utilizing medical imaging modalities. As of yet, few review studies on breast cancer diagnosis are available that summarize some existing studies. However, these studies were unable to address emerging architectures and modalities in breast cancer diagnosis. This review focuses on the evolving architectures of deep learning for breast cancer detection. In what follows, this survey presents existing deep-learning-based architectures, analyzes the strengths and limitations of the existing studies, examines the used datasets, and reviews image pre-processing techniques. Furthermore, a concrete review of diverse imaging modalities, performance metrics and results, challenges, and research directions for future researchers is presented.
Collapse
Affiliation(s)
- Muhammad Firoz Mridha
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka 1216, Bangladesh; (M.F.M.); (A.J.K.); (A.Q.O.)
| | - Md. Abdul Hamid
- Department of Information Technology, Faculty of Computing & Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia; (M.A.H.); (M.M.M.)
| | - Muhammad Mostafa Monowar
- Department of Information Technology, Faculty of Computing & Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia; (M.A.H.); (M.M.M.)
| | - Ashfia Jannat Keya
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka 1216, Bangladesh; (M.F.M.); (A.J.K.); (A.Q.O.)
| | - Abu Quwsar Ohi
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka 1216, Bangladesh; (M.F.M.); (A.J.K.); (A.Q.O.)
| | - Md. Rashedul Islam
- Department of Computer Science and Engineering, University of Asia Pacific, Dhaka 1216, Bangladesh;
| | - Jong-Myon Kim
- Department of Electrical, Electronics, and Computer Engineering, University of Ulsan, Ulsan 680-749, Korea
| |
Collapse
|
33
|
Li R, Li L, Xu Y, Yang J. Machine learning meets omics: applications and perspectives. Brief Bioinform 2021; 23:6425809. [PMID: 34791021 DOI: 10.1093/bib/bbab460] [Citation(s) in RCA: 44] [Impact Index Per Article: 14.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2021] [Revised: 09/29/2021] [Accepted: 10/07/2021] [Indexed: 02/07/2023] Open
Abstract
The innovation of biotechnologies has allowed the accumulation of omics data at an alarming rate, thus introducing the era of 'big data'. Extracting inherent valuable knowledge from various omics data remains a daunting problem in bioinformatics. Better solutions often need some kind of more innovative methods for efficient handlings and effective results. Recent advancements in integrated analysis and computational modeling of multi-omics data helped address such needs in an increasingly harmonious manner. The development and application of machine learning have largely advanced our insights into biology and biomedicine and greatly promoted the development of therapeutic strategies, especially for precision medicine. Here, we propose a comprehensive survey and discussion on what happened, is happening and will happen when machine learning meets omics. Specifically, we describe how artificial intelligence can be applied to omics studies and review recent advancements at the interface between machine learning and the ever-widest range of omics including genomics, transcriptomics, proteomics, metabolomics, radiomics, as well as those at the single-cell resolution. We also discuss and provide a synthesis of ideas, new insights, current challenges and perspectives of machine learning in omics.
Collapse
Affiliation(s)
- Rufeng Li
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi'an Jiaotong University Health Science Center, Xi'an 710061, P. R. China
| | - Lixin Li
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi'an Jiaotong University Health Science Center, Xi'an 710061, P. R. China
| | - Yungang Xu
- School of Electronics and Information, Northwestern Polytechnical University, Xi'an, 710129, China
| | - Juan Yang
- Department of Cell Biology and Genetics, School of Basic Medical Sciences, Xi'an Jiaotong University Health Science Center, Xi'an 710061, P. R. China.,Key Laboratory of Environment and Genes Related to Diseases (Xi'an Jiaotong University), Ministry of Education of China, Xi'an 710061, P. R. China
| |
Collapse
|
34
|
Thomas SA. Combining Image Features and Patient Metadata to Enhance Transfer Learning. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2021; 2021:2660-2663. [PMID: 34891799 DOI: 10.1109/embc46164.2021.9630047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/17/2023]
Abstract
In this work, we compare the performance of six state-of-the-art deep neural networks in classification tasks when using only image features, to when these are combined with patient metadata. We utilise transfer learning from networks pretrained on ImageNet to extract image features from the ISIC HAM10000 dataset prior to classification. Using several classification performance metrics, we evaluate the effects of including metadata with the image features. Furthermore, we repeat our experiments with data augmentation. Our results show an overall enhancement in performance of each network as assessed by all metrics, only noting degradation in a vgg16 architecture. Our results indicate that this performance enhancement may be a general property of deep networks and should be explored in other areas. Moreover, these improvements come at a negligible additional cost in computation time, and therefore are a practical method for other applications.
Collapse
|
35
|
Cancer Tissue Classification Using Supervised Machine Learning Applied to MALDI Mass Spectrometry Imaging. Cancers (Basel) 2021; 13:cancers13215388. [PMID: 34771551 PMCID: PMC8582378 DOI: 10.3390/cancers13215388] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/25/2021] [Revised: 10/15/2021] [Accepted: 10/24/2021] [Indexed: 01/13/2023] Open
Abstract
Simple Summary Classic histopathological examination of tissues remains the mainstay for cancer diagnosis and staging. However, in some cases histopathologic analysis yields ambiguous results, leading to inconclusive disease classification. We set out to explore the diagnostic potential of mass spectrometry-based imaging for tumour classification based on proteomic fingerprints. Combining mass spectrometry with supervised machine learning, we were able to distinguish colorectal tumor from normal tissue with an overall accuracy of 98%. In addition, this approach was able to predict the presence of lymph node metastasis in primary tumour of endometrial cancer with an overall accuracy of 80%. These results highlight the potential of this technology to determine the optimal treatment for cancer patients to reduce morbidity and improve patients’ outcomes. Abstract Matrix assisted laser desorption/ionization mass spectrometry imaging (MALDI MSI) can determine the spatial distribution of analytes such as protein distributions in a tissue section according to their mass-to-charge ratio. Here, we explored the clinical potential of machine learning (ML) applied to MALDI MSI data for cancer diagnostic classification using tissue microarrays (TMAs) on 302 colorectal (CRC) and 257 endometrial cancer (EC)) patients. ML based on deep neural networks discriminated colorectal tumour from normal tissue with an overall accuracy of 98% in balanced cross-validation (98.2% sensitivity and 98.6% specificity). Moreover, our machine learning approach predicted the presence of lymph node metastasis (LNM) for primary tumours of EC with an accuracy of 80% (90% sensitivity and 69% specificity). Our results demonstrate the capability of MALDI MSI for complementing classic histopathological examination for cancer diagnostic applications.
Collapse
|
36
|
Loch FN, Klein O, Beyer K, Klauschen F, Schineis C, Lauscher JC, Margonis GA, Degro CE, Rayya W, Kamphues C. Peptide Signatures for Prognostic Markers of Pancreatic Cancer by MALDI Mass Spectrometry Imaging. BIOLOGY 2021; 10:1033. [PMID: 34681132 PMCID: PMC8533220 DOI: 10.3390/biology10101033] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 08/13/2021] [Revised: 10/07/2021] [Accepted: 10/08/2021] [Indexed: 12/23/2022]
Abstract
Despite the overall poor prognosis of pancreatic cancer there is heterogeneity in clinical courses of tumors not assessed by conventional risk stratification. This yields the need of additional markers for proper assessment of prognosis and multimodal clinical management. We provide a proof of concept study evaluating the feasibility of Matrix-assisted laser desorption/ionization (MALDI) mass spectrometry imaging (MSI) to identify specific peptide signatures linked to prognostic parameters of pancreatic cancer. On 18 patients with exocrine pancreatic cancer after tumor resection, MALDI imaging analysis was performed additional to histopathological assessment. Principal component analysis (PCA) was used to explore discrimination of peptide signatures of prognostic histopathological features and receiver operator characteristic (ROC) to identify which specific m/z values are the most discriminative between the prognostic subgroups of patients. Out of 557 aligned m/z values discriminate peptide signatures for the prognostic histopathological features lymphatic vessel invasion (pL, 16 m/z values, eight proteins), nodal metastasis (pN, two m/z values, one protein) and angioinvasion (pV, 4 m/z values, two proteins) were identified. These results yield proof of concept that MALDI-MSI of pancreatic cancer tissue is feasible to identify peptide signatures of prognostic relevance and can augment risk assessment.
Collapse
Affiliation(s)
- Florian N. Loch
- Department of Surgery, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; (K.B.); (C.S.); (J.C.L.); (C.E.D.); (W.R.); (C.K.)
| | - Oliver Klein
- Berlin Institute of Health, Charité—Universitätsmedizin Berlin, Center for Regenerative Therapies BCRT, Charitéplatz 1, 10117 Berlin, Germany;
| | - Katharina Beyer
- Department of Surgery, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; (K.B.); (C.S.); (J.C.L.); (C.E.D.); (W.R.); (C.K.)
| | - Frederick Klauschen
- Institute for Pathology, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 10117 Berlin, Germany;
- Institute for Pathology, Ludwig-Maximilians-Universität München, 80337 München, Germany
| | - Christian Schineis
- Department of Surgery, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; (K.B.); (C.S.); (J.C.L.); (C.E.D.); (W.R.); (C.K.)
| | - Johannes C. Lauscher
- Department of Surgery, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; (K.B.); (C.S.); (J.C.L.); (C.E.D.); (W.R.); (C.K.)
| | - Georgios A. Margonis
- Department of Surgery, Memorial Sloan Kettering Cancer Center, New York, NY 10065, USA;
| | - Claudius E. Degro
- Department of Surgery, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; (K.B.); (C.S.); (J.C.L.); (C.E.D.); (W.R.); (C.K.)
| | - Wael Rayya
- Department of Surgery, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; (K.B.); (C.S.); (J.C.L.); (C.E.D.); (W.R.); (C.K.)
| | - Carsten Kamphues
- Department of Surgery, Charité—Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Hindenburgdamm 30, 12203 Berlin, Germany; (K.B.); (C.S.); (J.C.L.); (C.E.D.); (W.R.); (C.K.)
| |
Collapse
|
37
|
Peak learning of mass spectrometry imaging data using artificial neural networks. Nat Commun 2021; 12:5544. [PMID: 34545087 PMCID: PMC8452737 DOI: 10.1038/s41467-021-25744-8] [Citation(s) in RCA: 40] [Impact Index Per Article: 13.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/10/2020] [Accepted: 08/18/2021] [Indexed: 02/07/2023] Open
Abstract
Mass spectrometry imaging (MSI) is an emerging technology that holds potential for improving, biomarker discovery, metabolomics research, pharmaceutical applications and clinical diagnosis. Despite many solutions being developed, the large data size and high dimensional nature of MSI, especially 3D datasets, still pose computational and memory complexities that hinder accurate identification of biologically relevant molecular patterns. Moreover, the subjectivity in the selection of parameters for conventional pre-processing approaches can lead to bias. Therefore, we assess if a probabilistic generative model based on a fully connected variational autoencoder can be used for unsupervised analysis and peak learning of MSI data to uncover hidden structures. The resulting msiPL method learns and visualizes the underlying non-linear spectral manifold, revealing biologically relevant clusters of tissue anatomy in a mouse kidney and tumor heterogeneity in human prostatectomy tissue, colorectal carcinoma, and glioblastoma mouse model, with identification of underlying m/z peaks. The method is applied for the analysis of MSI datasets ranging from 3.3 to 78.9 GB, without prior pre-processing and peak picking, and acquired using different mass spectrometers at different centers.
Collapse
|
38
|
Tideman LEM, Migas LG, Djambazova KV, Patterson NH, Caprioli RM, Spraggins JM, Van de Plas R. Automated biomarker candidate discovery in imaging mass spectrometry data through spatially localized Shapley additive explanations. Anal Chim Acta 2021; 1177:338522. [PMID: 34482894 PMCID: PMC10124144 DOI: 10.1016/j.aca.2021.338522] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/12/2021] [Revised: 04/04/2021] [Accepted: 04/11/2021] [Indexed: 01/09/2023]
Abstract
The search for molecular species that are differentially expressed between biological states is an important step towards discovering promising biomarker candidates. In imaging mass spectrometry (IMS), performing this search manually is often impractical due to the large size and high-dimensionality of IMS datasets. Instead, we propose an interpretable machine learning workflow that automatically identifies biomarker candidates by their mass-to-charge ratios, and that quantitatively estimates their relevance to recognizing a given biological class using Shapley additive explanations (SHAP). The task of biomarker candidate discovery is translated into a feature ranking problem: given a classification model that assigns pixels to different biological classes on the basis of their mass spectra, the molecular species that the model uses as features are ranked in descending order of relative predictive importance such that the top-ranking features have a higher likelihood of being useful biomarkers. Besides providing the user with an experiment-wide measure of a molecular species' biomarker potential, our workflow delivers spatially localized explanations of the classification model's decision-making process in the form of a novel representation called SHAP maps. SHAP maps deliver insight into the spatial specificity of biomarker candidates by highlighting in which regions of the tissue sample each feature provides discriminative information and in which regions it does not. SHAP maps also enable one to determine whether the relationship between a biomarker candidate and a biological state of interest is correlative or anticorrelative. Our automated approach to estimating a molecular species' potential for characterizing a user-provided biological class, combined with the untargeted and multiplexed nature of IMS, allows for the rapid screening of thousands of molecular species and the obtention of a broader biomarker candidate shortlist than would be possible through targeted manual assessment. Our biomarker candidate discovery workflow is demonstrated on mouse-pup and rat kidney case studies.
Collapse
Affiliation(s)
- Leonoor E M Tideman
- Delft Center for Systems and Control, Delft University of Technology, Delft, Netherlands
| | - Lukasz G Migas
- Delft Center for Systems and Control, Delft University of Technology, Delft, Netherlands
| | - Katerina V Djambazova
- Mass Spectrometry Research Center, Vanderbilt University, Nashville, TN, USA; Department of Chemistry, Vanderbilt University, Nashville, TN, USA
| | - Nathan Heath Patterson
- Mass Spectrometry Research Center, Vanderbilt University, Nashville, TN, USA; Department of Biochemistry, Vanderbilt University, Nashville, TN, USA
| | - Richard M Caprioli
- Mass Spectrometry Research Center, Vanderbilt University, Nashville, TN, USA; Department of Biochemistry, Vanderbilt University, Nashville, TN, USA; Department of Chemistry, Vanderbilt University, Nashville, TN, USA; Department of Pharmacology, Vanderbilt University, Nashville, TN, USA; Department of Medicine, Vanderbilt University, Nashville, TN, USA
| | - Jeffrey M Spraggins
- Mass Spectrometry Research Center, Vanderbilt University, Nashville, TN, USA; Department of Biochemistry, Vanderbilt University, Nashville, TN, USA; Department of Chemistry, Vanderbilt University, Nashville, TN, USA
| | - Raf Van de Plas
- Delft Center for Systems and Control, Delft University of Technology, Delft, Netherlands; Mass Spectrometry Research Center, Vanderbilt University, Nashville, TN, USA; Department of Biochemistry, Vanderbilt University, Nashville, TN, USA.
| |
Collapse
|
39
|
Morimoto Y, Oya T, Ichimura-Shimizu M, Matsumoto M, Ogawa H, Kobayashi T, Sumida S, Kakimoto T, Yamashita M, Cheng C, Tsuneyama K. Applying Probe Electrospray Ionization Mass Spectrometry to Cytological Diagnosis: A Preliminary Study by Using Cultured Lung Cancer Cells. Acta Cytol 2021; 65:430-439. [PMID: 34098551 DOI: 10.1159/000516639] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/27/2020] [Accepted: 04/18/2021] [Indexed: 11/19/2022]
Abstract
OBJECTIVES Cytology and histology are 2 indispensable diagnostic tools for cancer diagnosis, which are rapidly increasing in importance with aging populations. We applied mass spectrometry (MS) as a rapid approach for swiftly acquiring nonmorphological information of interested cells. Conventional MS, which primarily rely on promoting ionization by pre-applying a matrix to cells, has the drawback of time-consuming both on data acquisition and analysis. As an emerging method, probe electrospray ionization-MS (PESI-MS) with a dedicated probe is capable to pierce sample and measure specimen in small amounts, either liquid or solid, without the requirement for sample pretreatment. Furthermore, PESI-MS is timesaving compared to the conventional MS. Herein, we investigated the capability of PESI-MS to characterize the cell types derived from the respiratory tract of human tissues. STUDY DESIGN PESI-MS analyses with DPiMS-2020 were performed on various type of cultured cells including 5 lung squamous cell carcinomas, 5 lung adenocarcinomas, 5 small-cell carcinomas, 4 malignant mesotheliomas, and 2 normal controls. RESULTS Several characteristic peaks were detected at around m/z 200 and 800 that were common in all samples. As expected, partial least squares-discriminant analysis of PESI-MS data distinguished the cancer cell types from normal control cells. Moreover, distinct clusters divided squamous cell carcinoma from adenocarcinoma. CONCLUSION PESI-MS presented a promising potential as a novel diagnostic modality for swiftly acquiring specific cytological information.
Collapse
Affiliation(s)
- Yuki Morimoto
- Department of Pathology and Laboratory Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Takeshi Oya
- Department of Molecular Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Mayuko Ichimura-Shimizu
- Department of Pathology and Laboratory Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Minoru Matsumoto
- Department of Molecular Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Hirohisa Ogawa
- Department of Pathology and Laboratory Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Tomoko Kobayashi
- Department of Pathology and Laboratory Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Satoshi Sumida
- Department of Pathology and Laboratory Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Takumi Kakimoto
- Department of Pathology and Laboratory Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Michiko Yamashita
- Department of Morphological Laboratory Science, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan
| | - Chunmei Cheng
- Pharmacology and Histopathology, Novo Nordisk Research Centre China, Beijing, China
| | - Koichi Tsuneyama
- Department of Pathology and Laboratory Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan,
- Department of Molecular Medicine, Institute of Biomedical Sciences, Tokushima University Graduate School, Tokushima, Japan,
| |
Collapse
|
40
|
Angel PM, Rujchanarong D, Pippin S, Spruill L, Drake R. Mass Spectrometry Imaging of Fibroblasts: Promise and Challenge. Expert Rev Proteomics 2021; 18:423-436. [PMID: 34129411 PMCID: PMC8717608 DOI: 10.1080/14789450.2021.1941893] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/18/2021] [Accepted: 06/09/2021] [Indexed: 10/21/2022]
Abstract
INTRODUCTION Fibroblasts maintain tissue and organ homeostasis through output of extracellular matrix that affects nearby cell signaling within the stroma. Altered fibroblast signaling contributes to many disease states and extracellular matrix secreted by fibroblasts has been used to stratify patient by outcome, recurrence, and therapeutic resistance. Recent advances in imaging mass spectrometry allow access to single cell fibroblasts and their ECM niche within clinically relevant tissue samples. AREAS COVERED We review biological and technical challenges as well as new solutions to proteomic access of fibroblast expression within the complex tissue microenvironment. Review topics cover conventional proteomic methods for single fibroblast analysis and current approaches to accessing single fibroblast proteomes by imaging mass spectrometry approaches. Strategies to target and evaluate the single cell stroma proteome on the basis of cell signaling are presented. EXPERT OPINION The promise of defining proteomic signatures from fibroblasts and their extracellular matrix niches is the discovery of new disease markers and the ability to refine therapeutic treatments. Several imaging mass spectrometry approaches exist to define the fibroblast in the setting of pathological changes from clinically acquired samples. Continued technology advances are needed to access and understand the stromal proteome and apply testing to the clinic.
Collapse
Affiliation(s)
- Peggi M. Angel
- Department of Cell and Molecular Pharmacology & Experimental Therapeutics, Bruker-MUSC Center of Excellence, Clinical Glycomics, Medical University of South Carolina, Charleston SC USA
| | - Denys Rujchanarong
- Department of Cell and Molecular Pharmacology & Experimental Therapeutics, Bruker-MUSC Center of Excellence, Clinical Glycomics, Medical University of South Carolina, Charleston SC USA
| | - Sarah Pippin
- Department of Cell and Molecular Pharmacology & Experimental Therapeutics, Bruker-MUSC Center of Excellence, Clinical Glycomics, Medical University of South Carolina, Charleston SC USA
| | - Laura Spruill
- Department of Pathology and Laboratory Medicine, Medical University of South Carolina, Charleston, SC
| | - Richard Drake
- Department of Cell and Molecular Pharmacology & Experimental Therapeutics, Bruker-MUSC Center of Excellence, Clinical Glycomics, Medical University of South Carolina, Charleston SC USA
| |
Collapse
|
41
|
Le’Clerc Arrastia J, Heilenkötter N, Otero Baguer D, Hauberg-Lotte L, Boskamp T, Hetzer S, Duschner N, Schaller J, Maass P. Deeply Supervised UNet for Semantic Segmentation to Assist Dermatopathological Assessment of Basal Cell Carcinoma. J Imaging 2021; 7:71. [PMID: 34460521 PMCID: PMC8321345 DOI: 10.3390/jimaging7040071] [Citation(s) in RCA: 21] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/10/2021] [Revised: 03/29/2021] [Accepted: 04/06/2021] [Indexed: 11/19/2022] Open
Abstract
Accurate and fast assessment of resection margins is an essential part of a dermatopathologist's clinical routine. In this work, we successfully develop a deep learning method to assist the dermatopathologists by marking critical regions that have a high probability of exhibiting pathological features in whole slide images (WSI). We focus on detecting basal cell carcinoma (BCC) through semantic segmentation using several models based on the UNet architecture. The study includes 650 WSI with 3443 tissue sections in total. Two clinical dermatopathologists annotated the data, marking tumor tissues' exact location on 100 WSI. The rest of the data, with ground-truth sectionwise labels, are used to further validate and test the models. We analyze two different encoders for the first part of the UNet network and two additional training strategies: (a) deep supervision, (b) linear combination of decoder outputs, and obtain some interpretations about what the network's decoder does in each case. The best model achieves over 96%, accuracy, sensitivity, and specificity on the Test set.
Collapse
Affiliation(s)
- Jean Le’Clerc Arrastia
- Center for Industrial Mathematics, University of Bremen, 28359 Bremen, Germany; (N.H.); (D.O.B.); (L.H.-L.); (P.M.)
| | - Nick Heilenkötter
- Center for Industrial Mathematics, University of Bremen, 28359 Bremen, Germany; (N.H.); (D.O.B.); (L.H.-L.); (P.M.)
| | - Daniel Otero Baguer
- Center for Industrial Mathematics, University of Bremen, 28359 Bremen, Germany; (N.H.); (D.O.B.); (L.H.-L.); (P.M.)
| | - Lena Hauberg-Lotte
- Center for Industrial Mathematics, University of Bremen, 28359 Bremen, Germany; (N.H.); (D.O.B.); (L.H.-L.); (P.M.)
| | | | - Sonja Hetzer
- Dermatopathologie Duisburg Essen, 45329 Essen, Germany; (S.H.); (N.D.); (J.S.)
| | - Nicole Duschner
- Dermatopathologie Duisburg Essen, 45329 Essen, Germany; (S.H.); (N.D.); (J.S.)
| | - Jörg Schaller
- Dermatopathologie Duisburg Essen, 45329 Essen, Germany; (S.H.); (N.D.); (J.S.)
| | - Peter Maass
- Center for Industrial Mathematics, University of Bremen, 28359 Bremen, Germany; (N.H.); (D.O.B.); (L.H.-L.); (P.M.)
| |
Collapse
|
42
|
Zhang W, Claesen M, Moerman T, Groseclose MR, Waelkens E, De Moor B, Verbeeck N. Spatially aware clustering of ion images in mass spectrometry imaging data using deep learning. Anal Bioanal Chem 2021; 413:2803-2819. [PMID: 33646352 PMCID: PMC8007517 DOI: 10.1007/s00216-021-03179-w] [Citation(s) in RCA: 20] [Impact Index Per Article: 6.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/28/2020] [Revised: 11/25/2020] [Accepted: 01/15/2021] [Indexed: 11/12/2022]
Abstract
Computational analysis is crucial to capitalize on the wealth of spatio-molecular information generated by mass spectrometry imaging (MSI) experiments. Currently, the spatial information available in MSI data is often under-utilized, due to the challenges of in-depth spatial pattern extraction. The advent of deep learning has greatly facilitated such complex spatial analysis. In this work, we use a pre-trained neural network to extract high-level features from ion images in MSI data, and test whether this improves downstream data analysis. The resulting neural network interpretation of ion images, coined neural ion images, is used to cluster ion images based on spatial expressions. We evaluate the impact of neural ion images on two ion image clustering pipelines, namely DBSCAN clustering, combined with UMAP-based dimensionality reduction, and k-means clustering. In both pipelines, we compare regular and neural ion images from two different MSI datasets. All tested pipelines could extract underlying spatial patterns, but the neural network-based pipelines provided better assignment of ion images, with more fine-grained clusters, and greater consistency in the spatial structures assigned to individual clusters. Additionally, we introduce the relative isotope ratio metric to quantitatively evaluate clustering quality. The resulting scores show that isotopical m/z values are more often clustered together in the neural network-based pipeline, indicating improved clustering outcomes. The usefulness of neural ion images extends beyond clustering towards a generic framework to incorporate spatial information into any MSI-focused machine learning pipeline, both supervised and unsupervised.
Collapse
Affiliation(s)
- Wanqiu Zhang
- KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Kasteelpark Arenberg 10, 3001, Leuven, Belgium.
- Aspect Analytics NV, C-mine 12, 3600, Genk, Belgium.
| | - Marc Claesen
- Aspect Analytics NV, C-mine 12, 3600, Genk, Belgium
| | | | | | - Etienne Waelkens
- KU Leuven, Department of Cellular and Molecular Medicine, Campus Gasthuisberg O&N1, Herestraat 49, Box 901, 3000, Leuven, Belgium
| | - Bart De Moor
- KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Kasteelpark Arenberg 10, 3001, Leuven, Belgium
| | | |
Collapse
|
43
|
A versatile deep learning architecture for classification and label-free prediction of hyperspectral images. NAT MACH INTELL 2021; 3:306-315. [PMID: 34676358 PMCID: PMC8528004 DOI: 10.1038/s42256-021-00309-y] [Citation(s) in RCA: 36] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
Hyperspectral imaging is a technique that provides rich chemical or compositional information not regularly available to traditional imaging modalities such as intensity imaging or color imaging based on the reflection, transmission, or emission of light. Analysis of hyperspectral imaging often relies on machine learning methods to extract information. Here, we present a new flexible architecture, the U-within-U-Net, that can perform classification, segmentation, and prediction of orthogonal imaging modalities on a variety of hyperspectral imaging techniques. Specifically, we demonstrate feature segmentation and classification on the Indian Pines hyperspectral dataset and simultaneous location prediction of multiple drugs in mass spectrometry imaging of rat liver tissue. We further demonstrate label-free fluorescence image prediction from hyperspectral stimulated Raman scattering microscopy images. The applicability of the U-within-U-Net architecture on diverse datasets with widely varying input and output dimensions and data sources suggest that it has great potential in advancing the use of hyperspectral imaging across many different application areas ranging from remote sensing, to medical imaging, to microscopy.
Collapse
|
44
|
Guo D, Föll MC, Volkmann V, Enderle-Ammour K, Bronsert P, Schilling O, Vitek O. Deep multiple instance learning classifies subtissue locations in mass spectrometry images from tissue-level annotations. Bioinformatics 2021; 36:i300-i308. [PMID: 32657378 PMCID: PMC7355295 DOI: 10.1093/bioinformatics/btaa436] [Citation(s) in RCA: 16] [Impact Index Per Article: 5.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/27/2023] Open
Abstract
MOTIVATION Mass spectrometry imaging (MSI) characterizes the molecular composition of tissues at spatial resolution, and has a strong potential for distinguishing tissue types, or disease states. This can be achieved by supervised classification, which takes as input MSI spectra, and assigns class labels to subtissue locations. Unfortunately, developing such classifiers is hindered by the limited availability of training sets with subtissue labels as the ground truth. Subtissue labeling is prohibitively expensive, and only rough annotations of the entire tissues are typically available. Classifiers trained on data with approximate labels have sub-optimal performance. RESULTS To alleviate this challenge, we contribute a semi-supervised approach mi-CNN. mi-CNN implements multiple instance learning with a convolutional neural network (CNN). The multiple instance aspect enables weak supervision from tissue-level annotations when classifying subtissue locations. The convolutional architecture of the CNN captures contextual dependencies between the spectral features. Evaluations on simulated and experimental datasets demonstrated that mi-CNN improved the subtissue classification as compared to traditional classifiers. We propose mi-CNN as an important step toward accurate subtissue classification in MSI, enabling rapid distinction between tissue types and disease states. AVAILABILITY AND IMPLEMENTATION The data and code are available at https://github.com/Vitek-Lab/mi-CNN_MSI.
Collapse
Affiliation(s)
- Dan Guo
- Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, USA
| | - Melanie Christine Föll
- Institute for Surgical Pathology, Medical Center - University of Freiburg, 79106 Freiburg, Germany.,Faculty of Medicine, University of Freiburg, 79110 Freiburg, Germany
| | - Veronika Volkmann
- Institute for Surgical Pathology, Medical Center - University of Freiburg, 79106 Freiburg, Germany.,Faculty of Medicine, University of Freiburg, 79110 Freiburg, Germany
| | - Kathrin Enderle-Ammour
- Institute for Surgical Pathology, Medical Center - University of Freiburg, 79106 Freiburg, Germany.,Faculty of Medicine, University of Freiburg, 79110 Freiburg, Germany
| | - Peter Bronsert
- Institute for Surgical Pathology, Medical Center - University of Freiburg, 79106 Freiburg, Germany.,Faculty of Medicine, University of Freiburg, 79110 Freiburg, Germany.,Tumorbank Comprehensive Cancer Center Freiburg, Medical Center - University of Freiburg.,German Cancer Consortium (DKTK) and Cancer Research Center (DKFZ), 79106 Freiburg, Germany
| | - Oliver Schilling
- Institute for Surgical Pathology, Medical Center - University of Freiburg, 79106 Freiburg, Germany.,Faculty of Medicine, University of Freiburg, 79110 Freiburg, Germany
| | - Olga Vitek
- Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115, USA
| |
Collapse
|
45
|
Shi C, Zhou Z, Lin H, Gao J. Imaging Beyond Seeing: Early Prognosis of Cancer Treatment. SMALL METHODS 2021; 5:e2001025. [PMID: 34927817 DOI: 10.1002/smtd.202001025] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/27/2020] [Revised: 11/24/2020] [Indexed: 06/14/2023]
Abstract
Assessing cancer response to therapeutic interventions has been realized as an important course to early predict curative efficacy and treatment outcomes due to tumor heterogeneity. Compared to the traditional invasive tissue biopsy method, molecular imaging techniques have fundamentally revolutionized the ability to evaluate cancer response in a spatiotemporal manner. The past few years has witnessed a paradigm shift on the efforts from manufacturing functional molecular imaging probes for seeing a tumor to a vantage stage of interpreting the tumor response during different treatments. This review is to stand by the current development of advanced imaging technologies aiming to predict the treatment response in cancer therapy. Special interest is placed on the systems that are able to provide rapid and noninvasive assessment of pharmacokinetic drug fates (e.g., drug distribution, release, and activation) and tumor microenvironment heterogeneity (e.g., tumor cells, macrophages, dendritic cells (DCs), T cells, and inflammatory cells). The current status, practical significance, and future challenges of the emerging artificial intelligence (AI) technology and machine learning in the applications of medical imaging fields is overviewed. Ultimately, the authors hope that this review is timely to spur research interest in molecular imaging and precision medicine.
Collapse
Affiliation(s)
- Changrong Shi
- State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics and Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, 361102, China
| | - Zijian Zhou
- State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics and Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, 361102, China
| | - Hongyu Lin
- State Key Laboratory of Physical Chemistry of Solid Surfaces, The Key Laboratory for Chemical Biology of Fujian Province and Department of Chemical Biology, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen, 361005, China
| | - Jinhao Gao
- State Key Laboratory of Physical Chemistry of Solid Surfaces, The Key Laboratory for Chemical Biology of Fujian Province and Department of Chemical Biology, College of Chemistry and Chemical Engineering, Xiamen University, Xiamen, 361005, China
| |
Collapse
|
46
|
Xu W, Tian Y, Wang S, Cui Y. Feature selection and classification of noisy proteomics mass spectrometry data based on one-bit perturbed compressed sensing. Bioinformatics 2021; 36:4423-4431. [PMID: 32415972 DOI: 10.1093/bioinformatics/btaa516] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2019] [Revised: 02/28/2020] [Accepted: 05/12/2020] [Indexed: 11/12/2022] Open
Abstract
MOTIVATION The classification of high-throughput protein data based on mass spectrometry (MS) is of great practical significance in medical diagnosis. Generally, MS data are characterized by high dimension, which inevitably leads to prohibitive cost of computation. To solve this problem, one-bit compressed sensing (CS), which is an extreme case of quantized CS, has been employed on MS data to select important features with low dimension. Though enjoying remarkably reduction of computation complexity, the current one-bit CS method does not consider the unavoidable noise contained in MS dataset, and does not exploit the inherent structure of the underlying MS data. RESULTS We propose two feature selection (FS) methods based on one-bit CS to deal with the noise and the underlying block-sparsity features, respectively. In the first method, the FS problem is modeled as a perturbed one-bit CS problem, where the perturbation represents the noise in MS data. By iterating between perturbation refinement and FS, this method selects the significant features from noisy data. The second method formulates the problem as a perturbed one-bit block CS problem and selects the features block by block. Such block extraction is due to the fact that the significant features in the first method usually cluster in groups. Experiments show that, the two proposed methods have better classification performance for real MS data when compared with the existing method, and the second one outperforms the first one. AVAILABILITY AND IMPLEMENTATION The source code of our methods is available at: https://github.com/tianyan8023/OBCS. SUPPLEMENTARY INFORMATION Supplementary data are available at Bioinformatics online.
Collapse
Affiliation(s)
- Wenbo Xu
- Key Lab of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China
| | - Yan Tian
- Key Lab of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China
| | - Siye Wang
- Key Lab of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China
| | - Yupeng Cui
- Key Lab of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing 100876, China
| |
Collapse
|
47
|
Campi G, Nicora G, Fiorentino G, Smith A, Magni F, Garagna S, Zuccotti M, Bellazzi R. A Topological Data Analysis Mapper of the Ovarian Folliculogenesis Based on MALDI Mass Spectrometry Imaging Proteomics. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-77211-6_5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/21/2022]
|
48
|
McLaughlin N, Bielinski TM, Tressler CM, Barton E, Glunde K, Stumpo KA. Pneumatically Sprayed Gold Nanoparticles for Mass Spectrometry Imaging of Neurotransmitters. JOURNAL OF THE AMERICAN SOCIETY FOR MASS SPECTROMETRY 2020; 31:2452-2461. [PMID: 32841002 DOI: 10.1021/jasms.0c00156] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Using citrate-capped gold nanoparticles (AuNPs) for laser desorption ionization mass spectrometry (LDI-MS) is an approach that has demonstrated broad applicability to ionization of different classes of molecules. Here, we show a simple AuNP-based approach for the ionization of neurotransmitters. Specifically, the detection of acetylcholine, dopamine, epinephrine, glutamine, 4-aminobutyric acid, norepinephrine, octopamine, and serotonin was achieved at physiologically relevant concentrations in serum and homogenized tissue. Additionally, pneumatic spraying of AuNPs onto tissue sections facilitated mass spectrometry imaging (MSI) of rabbit brain tissue sections, zebrafish embryos, and neuroblastoma cells for several neurotransmitters simultaneously using this quick and simple sample preparation. AuNP LDI-MS achieved mapping of neurotransmitters in fine structures of zebrafish embryos and neuroblastoma cells at a lateral spatial resolution of 5 μm. The use of AuNPs to ionize small aminergic neurotransmitters in situ provides a fast, high-spatial resolution method for simultaneous detection of a class of molecules that typically evade comprehensive detection with traditional matrixes.
Collapse
Affiliation(s)
- Nolan McLaughlin
- Department of Chemistry, University of Scranton, Scranton, Pennsylvania 18510, United States
| | - Tyler M Bielinski
- Department of Chemistry, University of Scranton, Scranton, Pennsylvania 18510, United States
| | - Caitlin M Tressler
- The Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, Maryland 21205, United States
| | - Eric Barton
- The Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, Maryland 21205, United States
| | - Kristine Glunde
- The Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, Maryland 21205, United States
- The Sidney Kimmel Comprehensive Cancer Center, The Johns Hopkins School of Medicine, Baltimore, Maryland 21205, United States
| | - Katherine A Stumpo
- Department of Chemistry, University of Scranton, Scranton, Pennsylvania 18510, United States
| |
Collapse
|
49
|
Cumulative learning enables convolutional neural network representations for small mass spectrometry data classification. Nat Commun 2020; 11:5595. [PMID: 33154370 PMCID: PMC7644674 DOI: 10.1038/s41467-020-19354-z] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2020] [Accepted: 10/05/2020] [Indexed: 12/13/2022] Open
Abstract
Rapid and accurate clinical diagnosis remains challenging. A component of diagnosis tool development is the design of effective classification models with Mass spectrometry (MS) data. Some Machine Learning approaches have been investigated but these models require time-consuming preprocessing steps to remove artifacts, making them unsuitable for rapid analysis. Convolutional Neural Networks (CNNs) have been found to perform well under such circumstances since they can learn representations from raw data. However, their effectiveness decreases when the number of available training samples is small, which is a common situation in medicine. In this work, we investigate transfer learning on 1D-CNNs, then we develop a cumulative learning method when transfer learning is not powerful enough. We propose to train the same model through several classification tasks over various small datasets to accumulate knowledge in the resulting representation. By using rat brain as the initial training dataset, a cumulative learning approach can have a classification accuracy exceeding 98% for 1D clinical MS-data. We show the use of cumulative learning using datasets generated in different biological contexts, on different organisms, and acquired by different instruments. Here we show a promising strategy for improving MS data classification accuracy when only small numbers of samples are available. Convolutional Neural Networks are powerful tools for clinical diagnosis but their effectiveness decreases when the number of available samples is small. Here, the authors develop a cumulative learning method by training the same model through several classification tasks over various small Mass Spectrometry datasets.
Collapse
|
50
|
Möginger U, Marcussen N, Jensen ON. Histo-molecular differentiation of renal cancer subtypes by mass spectrometry imaging and rapid proteome profiling of formalin-fixed paraffin-embedded tumor tissue sections. Oncotarget 2020; 11:3998-4015. [PMID: 33216824 PMCID: PMC7646834 DOI: 10.18632/oncotarget.27787] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/09/2020] [Accepted: 10/10/2020] [Indexed: 12/24/2022] Open
Abstract
Pathology differentiation of renal cancer types is challenging due to tissue similarities or overlapping histological features of various tumor (sub) types. As assessment is often manually conducted outcomes can be prone to human error and therefore require high-level expertise and experience. Mass spectrometry can provide detailed histo-molecular information on tissue and is becoming increasingly popular in clinical settings. Spatially resolving technologies such as mass spectrometry imaging and quantitative microproteomics profiling in combination with machine learning approaches provide promising tools for automated tumor classification of clinical tissue sections. In this proof of concept study we used MALDI-MS imaging (MSI) and rapid LC-MS/MS-based microproteomics technologies (15 min/sample) to analyze formalin-fixed paraffin embedded (FFPE) tissue sections and classify renal oncocytoma (RO, n = 11), clear cell renal cell carcinoma (ccRCC, n = 12) and chromophobe renal cell carcinoma (ChRCC, n = 5). Both methods were able to distinguish ccRCC, RO and ChRCC in cross-validation experiments. MSI correctly classified 87% of the patients whereas the rapid LC-MS/MS-based microproteomics approach correctly classified 100% of the patients. This strategy involving MSI and rapid proteome profiling by LC-MS/MS reveals molecular features of tumor sections and enables cancer subtype classification. Mass spectrometry provides a promising complementary approach to current pathological technologies for precise digitized diagnosis of diseases.
Collapse
Affiliation(s)
- Uwe Möginger
- Department of Biochemistry & Molecular Biology and VILLUM Center for Bioanalytical Sciences, University of Southern Denmark, Odense, Denmark.,Present address: Global Research Technologies, Novo Nordisk A/S, Novo Nordisk Park, Bagsværd, Denmark
| | - Niels Marcussen
- Institute for Pathology, Odense University Hospital, Odense, Denmark
| | - Ole N Jensen
- Department of Biochemistry & Molecular Biology and VILLUM Center for Bioanalytical Sciences, University of Southern Denmark, Odense, Denmark
| |
Collapse
|