1
|
Bitto V, Hönscheid P, Besso MJ, Sperling C, Kurth I, Baumann M, Brors B. Enhancing mass spectrometry imaging accessibility using convolutional autoencoders for deriving hypoxia-associated peptides from tumors. NPJ Syst Biol Appl 2024; 10:57. [PMID: 38802379 PMCID: PMC11130291 DOI: 10.1038/s41540-024-00385-x] [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: 01/12/2024] [Accepted: 05/13/2024] [Indexed: 05/29/2024] Open
Abstract
Mass spectrometry imaging (MSI) allows to study cancer's intratumoral heterogeneity through spatially-resolved peptides, metabolites and lipids. Yet, in biomedical research MSI is rarely used for biomarker discovery. Besides its high dimensionality and multicollinearity, mass spectrometry (MS) technologies typically output mass-to-charge ratio values but not the biochemical compounds of interest. Our framework makes particularly low-abundant signals in MSI more accessible. We utilized convolutional autoencoders to aggregate features associated with tumor hypoxia, a parameter with significant spatial heterogeneity, in cancer xenograft models. We highlight that MSI captures these low-abundant signals and that autoencoders can preserve them in their latent space. The relevance of individual hyperparameters is demonstrated through ablation experiments, and the contribution from original features to latent features is unraveled. Complementing MSI with tandem MS from the same tumor model, multiple hypoxia-associated peptide candidates were derived. Compared to random forests alone, our autoencoder approach yielded more biologically relevant insights for biomarker discovery.
Collapse
Affiliation(s)
- Verena Bitto
- Division of Applied Bioinformatics, German Cancer Research Center (DKFZ), Heidelberg, Germany.
- Division of Radiooncology/Radiobiology, German Cancer Research Center (DKFZ), Heidelberg, Germany.
- HIDSS4Health - Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Heidelberg, Germany.
- Faculty for Mathematics and Computer Science, Heidelberg University, Heidelberg, Germany.
| | - Pia Hönscheid
- National Center for Tumor Diseases (NCT), Partner Site Dresden, German Cancer Research Center (DKFZ), Heidelberg, Germany
- University Hospital Carl Gustav Carus (UKD), Technische Universität Dresden, Institute of Pathology, Dresden, Germany
- Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
| | - María José Besso
- Division of Radiooncology/Radiobiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
| | - Christian Sperling
- National Center for Tumor Diseases (NCT), Partner Site Dresden, German Cancer Research Center (DKFZ), Heidelberg, Germany
- University Hospital Carl Gustav Carus (UKD), Technische Universität Dresden, Institute of Pathology, Dresden, Germany
- Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Dresden, Germany
| | - Ina Kurth
- Division of Radiooncology/Radiobiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Consortium (DKTK), Core Center Heidelberg, Heidelberg, Germany
| | - Michael Baumann
- Division of Radiooncology/Radiobiology, German Cancer Research Center (DKFZ), Heidelberg, Germany
- OncoRay - National Center for Radiation Research in Oncology, Faculty of Medicine and University Hospital Carl Gustav Carus, Technische Universität Dresden, Helmholtz-Zentrum Dresden - Rossendorf, Dresden, Germany
- German Cancer Consortium (DKTK), Core Center Heidelberg, Heidelberg, Germany
| | - Benedikt Brors
- Division of Applied Bioinformatics, German Cancer Research Center (DKFZ), Heidelberg, Germany
- German Cancer Consortium (DKTK), Core Center Heidelberg, Heidelberg, Germany
- National Center for Tumor Diseases (NCT), Heidelberg, Germany
- Medical Faculty Heidelberg and Faculty of Biosciences, Heidelberg University, Heidelberg, Germany
| |
Collapse
|
2
|
Aoyagi S, Cant DJH, Dürr M, Eyres A, Fearn S, Gilmore IS, Iida SI, Ikeda R, Ishikawa K, Lagator M, Lockyer N, Keller P, Matsuda K, Murayama Y, Okamoto M, Reed BP, Shard AG, Takano A, Trindade GF, Vorng JL. Quantitative and Qualitative Analyses of Mass Spectra of OEL Materials by Artificial Neural Network and Interface Evaluation: Results from a VAMAS Interlaboratory Study. Anal Chem 2023; 95:15078-15085. [PMID: 37715701 PMCID: PMC10569169 DOI: 10.1021/acs.analchem.3c03173] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/19/2023] [Accepted: 09/05/2023] [Indexed: 09/18/2023]
Abstract
Quantitative analysis of binary mixtures of tris(2-phenylpyridinato)iridium(III) (Ir(ppy)3) and tris(8-hydroxyquinolinato)aluminum (Alq3) by using an artificial neural network (ANN) system to mass spectra was attempted based on the results of a VAMAS (Versailles Project on Advanced Materials and Standards) interlaboratory study (TW2 A31) to evaluate matrix-effect correction and to investigate interface determination. Monolayers of binary mixtures having different Ir(ppy)3 ratios (0, 0.25, 0.50, 0.75, and 1.00), and the multilayers containing these mixtures and pure samples were measured using time-of-flight secondary ion mass spectrometry (ToF-SIMS) with different primary ion beams, OrbiSIMS (SIMS with both Orbitrap and ToF mass spectrometers), laser desorption ionization (LDI), desorption/ionization induced by neutral clusters (DINeC), and X-ray photoelectron spectroscopy (XPS). The mass spectra were analyzed using a simple ANN with one hidden layer. The Ir(ppy)3 ratios of the unknown samples and the interfaces of the multilayers were predicted using the simple ANN system, even though the mass spectra of binary mixtures exhibited matrix effects. The Ir(ppy)3 ratios at the interfaces indicated by the simple ANN were consistent with the XPS results and the ToF-SIMS depth profiles. The simple ANN system not only provided quantitative information on unknown samples, but also indicated important mass peaks related to each molecule in the samples without a priori information. The important mass peaks indicated by the simple ANN depended on the ionization process. The simple ANN results of the spectra sets obtained by a softer ionization method, such as LDI and DINeC, suggested large ions such as trimers. From the first step of the investigation to build an ANN model for evaluating mixture samples influenced by matrix effects, it was indicated that the simple ANN method is useful for obtaining candidate mass peaks for identification and for assuming mixture conditions that are helpful for further analysis.
Collapse
Affiliation(s)
- Satoka Aoyagi
- Faculty
of Science and Technology, Seikei University, Musashino, Tokyo 180-8633, Japan
| | - David J. H. Cant
- National
Physical Laboratory, Hampton Road, Teddington, Middlesex TW11 0LW, United Kingdom
| | - Michael Dürr
- Institute
of Applied Physics and Center for Materials Research, Justus Liebig University Giessen, 35394 Giessen, Germany
| | - Anya Eyres
- National
Physical Laboratory, Hampton Road, Teddington, Middlesex TW11 0LW, United Kingdom
| | - Sarah Fearn
- Department
of Materials, Imperial College London, London SW7 2AZ, United Kingdom
| | - Ian S. Gilmore
- National
Physical Laboratory, Hampton Road, Teddington, Middlesex TW11 0LW, United Kingdom
| | - Shin-ichi Iida
- ULVAC-PHI,
Inc., 2500 Hagisono, Chigasaki, Kanagawa 253-8522, Japan
| | - Reiko Ikeda
- Analytical
Science Research Laboratory, Kao Corp., Minato 1334, Wakayama-shi, Wakayama 640-8580, Japan
| | - Kazutaka Ishikawa
- Analytical
Science Research Laboratory, Kao Corp., Minato 1334, Wakayama-shi, Wakayama 640-8580, Japan
| | - Matija Lagator
- Photon
Science Institute, Department of Chemistry, University of Manchester, Manchester M13 9PL, United
Kingdom
| | - Nicholas Lockyer
- Photon
Science Institute, Department of Chemistry, University of Manchester, Manchester M13 9PL, United
Kingdom
| | - Philip Keller
- Institute
of Applied Physics and Center for Materials Research, Justus Liebig University Giessen, 35394 Giessen, Germany
| | - Kazuhiro Matsuda
- Surface
Science Laboratories, Toray Research Center, Inc., 3-3-7, Sonoyama, Otsu, Shiga 520-8567, Japan
| | - Yohei Murayama
- Specialty
Chemicals Development Center, Peripheral Products Operations, Canon Inc., 4202, Fukara, Susono, Shizuoka 410-1196, Japan
| | - Masayuki Okamoto
- Analytical
Science Research Laboratory, Kao Corp., Minato 1334, Wakayama-shi, Wakayama 640-8580, Japan
| | - Benjamen P. Reed
- National
Physical Laboratory, Hampton Road, Teddington, Middlesex TW11 0LW, United Kingdom
| | - Alexander G. Shard
- National
Physical Laboratory, Hampton Road, Teddington, Middlesex TW11 0LW, United Kingdom
| | - Akio Takano
- Toyama Co., Ltd., 3816-1 Kishi, Yamakita-machi, Ashigarakami-gun Kanagawa 258-0112, Japan
| | - Gustavo F. Trindade
- National
Physical Laboratory, Hampton Road, Teddington, Middlesex TW11 0LW, United Kingdom
| | - Jean-Luc Vorng
- National
Physical Laboratory, Hampton Road, Teddington, Middlesex TW11 0LW, United Kingdom
| |
Collapse
|
4
|
Gardner W, Winkler DA, Cutts SM, Torney SA, Pietersz GA, Muir BW, Pigram PJ. Two-Dimensional and Three-Dimensional Time-of-Flight Secondary Ion Mass Spectrometry Image Feature Extraction Using a Spatially Aware Convolutional Autoencoder. Anal Chem 2022; 94:7804-7813. [PMID: 35616489 DOI: 10.1021/acs.analchem.1c05453] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2022]
Abstract
Feature extraction algorithms are an important class of unsupervised methods used to reduce data dimensionality. They have been applied extensively for time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging─commonly, matrix factorization (MF) techniques such as principal component analysis have been used. A limitation of MF is the assumption of linearity, which is generally not accurate for ToF-SIMS data. Recently, nonlinear autoencoders have been shown to outperform MF techniques for ToF-SIMS image feature extraction. However, another limitation of most feature extraction methods (including autoencoders) that is particularly important for hyperspectral data is that they do not consider spatial information. To address this limitation, we describe the application of the convolutional autoencoder (CNNAE) to hyperspectral ToF-SIMS imaging data. The CNNAE is an artificial neural network developed specifically for hyperspectral data that uses convolutional layers for image encoding, thereby explicitly incorporating pixel neighborhood information. We compared the performance of the CNNAE with other common feature extraction algorithms for two biological ToF-SIMS imaging data sets. We investigated the extracted features and used the dimensionality-reduced data to train additional ML algorithms. By converting two-dimensional convolutional layers to three-dimensional (3D), we also showed how the CNNAE can be extended to 3D ToF-SIMS images. In general, the CNNAE produced features with significantly higher contrast and autocorrelation than other techniques. Furthermore, histologically recognizable features in the data were more accurately represented. The extension of the CNNAE to 3D data also provided an important proof of principle for the analysis of more complex 3D data sets.
Collapse
Affiliation(s)
- Wil Gardner
- Centre for Materials and Surface Science and Department of Chemistry and Physics, La Trobe University, Bundoora, Victoria 3086, Australia.,La Trobe Institute for Molecular Sciences, La Trobe University, Bundoora, Victoria 3086, Australia.,CSIRO Manufacturing, Clayton, Victoria 3168, Australia
| | - David A Winkler
- La Trobe Institute for Molecular Sciences, La Trobe University, Bundoora, Victoria 3086, Australia.,Monash Institute of Pharmaceutical Sciences, Monash University, Parkville, Victoria 3052, Australia.,School of Pharmacy, University of Nottingham, Nottingham NG7 2RD, U.K
| | - Suzanne M Cutts
- La Trobe Institute for Molecular Sciences, La Trobe University, Bundoora, Victoria 3086, Australia
| | - Steven A Torney
- La Trobe Institute for Molecular Sciences, La Trobe University, Bundoora, Victoria 3086, Australia
| | - Geoffrey A Pietersz
- Immune Therapies Laboratory, Burnet Institute, Melbourne, Victoria 3004, Australia.,Atherothrombosis and Vascular Biology Laboratory, Baker Heart and Diabetes Institute, Melbourne, Victoria 3004, Australia
| | | | - Paul J Pigram
- Centre for Materials and Surface Science and Department of Chemistry and Physics, La Trobe University, Bundoora, Victoria 3086, Australia
| |
Collapse
|