Machine learning applications in proteomics research: how the past can boost the future

Machine learning for the advancement of genome-scale metabolic modeling

Constraint-based modeling (CBM) has evolved as the core systems biology tool to map the interrelations between genotype, phenotype, and external environment. The recent advancement of high-throughput experimental approaches and multi-omics strategies has generated a plethora of new and precise information from wide-ranging biological domains. On the other hand, the continuously growing field of machine learning (ML) and its specialized branch of deep learning (DL) provide essential computational architectures for decoding complex and heterogeneous biological data. In recent years, both multi-omics and ML have assisted in the escalation of CBM. Condition-specific omics data, such as transcriptomics and proteomics, helped contextualize the model prediction while analyzing a particular phenotypic signature. At the same time, the advanced ML tools have eased the model reconstruction and analysis to increase the accuracy and prediction power. However, the development of these multi-disciplinary methodological frameworks mainly occurs independently, which limits the concatenation of biological knowledge from different domains. Hence, we have reviewed the potential of integrating multi-disciplinary tools and strategies from various fields, such as synthetic biology, CBM, omics, and ML, to explore the biochemical phenomenon beyond the conventional biological dogma. How the integrative knowledge of these intersected domains has improved bioengineering and biomedical applications has also been highlighted. We categorically explained the conventional genome-scale metabolic model (GEM) reconstruction tools and their improvement strategies through ML paradigms. Further, the crucial role of ML and DL in omics data restructuring for GEM development has also been briefly discussed. Finally, the case-study-based assessment of the state-of-the-art method for improving biomedical and metabolic engineering strategies has been elaborated. Therefore, this review demonstrates how integrating experimental and in silico strategies can help map the ever-expanding knowledge of biological systems driven by condition-specific cellular information. This multiview approach will elevate the application of ML-based CBM in the biomedical and bioengineering fields for the betterment of society and the environment.

Machine Learning Strategies to Tackle Data Challenges in Mass Spectrometry-Based Proteomics

In computational proteomics, machine learning (ML) has emerged as a vital tool for enhancing data analysis. Despite significant advancements, the diversity of ML model architectures and the complexity of proteomics data present substantial challenges in the effective development and evaluation of these tools. Here, we highlight the necessity for high-quality, comprehensive data sets to train ML models and advocate for the standardization of data to support robust model development. We emphasize the instrumental role of key data sets like ProteomeTools and MassIVE-KB in advancing ML applications in proteomics and discuss the implications of data set size on model performance, highlighting that larger data sets typically yield more accurate models. To address data scarcity, we explore algorithmic strategies such as self-supervised pretraining and multitask learning. Ultimately, we hope that this discussion can serve as a call to action for the proteomics community to collaborate on data standardization and collection efforts, which are crucial for the sustainable advancement and refinement of ML methodologies in the field.

AI-organoid integrated systems for biomedical studies and applications

In this review, we explore the growing role of artificial intelligence (AI) in advancing the biomedical applications of human pluripotent stem cell (hPSC)-derived organoids. Stem cell-derived organoids, these miniature organ replicas, have become essential tools for disease modeling, drug discovery, and regenerative medicine. However, analyzing the vast and intricate datasets generated from these organoids can be inefficient and error-prone. AI techniques offer a promising solution to efficiently extract insights and make predictions from diverse data types generated from microscopy images, transcriptomics, metabolomics, and proteomics. This review offers a brief overview of organoid characterization and fundamental concepts in AI while focusing on a comprehensive exploration of AI applications in organoid-based disease modeling and drug evaluation. It provides insights into the future possibilities of AI in enhancing the quality control of organoid fabrication, label-free organoid recognition, and three-dimensional image reconstruction of complex organoid structures. This review presents the challenges and potential solutions in AI-organoid integration, focusing on the establishment of reliable AI model decision-making processes and the standardization of organoid research.

DeepDN_iGlu: prediction of lysine glutarylation sites based on attention residual learning method and DenseNet

As a key issue in orchestrating various biological processes and functions, protein post-translational modification (PTM) occurs widely in the mechanism of protein's function of animals and plants. Glutarylation is a type of protein-translational modification that occurs at active ε-amino groups of specific lysine residues in proteins, which is associated with various human diseases, including diabetes, cancer, and glutaric aciduria type I. Therefore, the issue of prediction for glutarylation sites is particularly important. This study developed a brand-new deep learning-based prediction model for glutarylation sites named DeepDN_iGlu via adopting attention residual learning method and DenseNet. The focal loss function is utilized in this study in place of the traditional cross-entropy loss function to address the issue of a substantial imbalance in the number of positive and negative samples. It can be noted that DeepDN_iGlu based on the deep learning model offers a greater potential for the glutarylation site prediction after employing the straightforward one hot encoding method, with Sensitivity (Sn), Specificity (Sp), Accuracy (ACC), Mathews Correlation Coefficient (MCC), and Area Under Curve (AUC) of 89.29%, 61.97%, 65.15%, 0.33 and 0.80 accordingly on the independent test set. To the best of the authors' knowledge, this is the first time that DenseNet has been used for the prediction of glutarylation sites. DeepDN_iGlu has been deployed as a web server (https://bioinfo.wugenqiang.top/~smw/DeepDN_iGlu/) that is available to make glutarylation site prediction data more accessible.

The critical role that spectral libraries play in capturing the metabolomics community knowledge

BACKGROUND

Spectral library searching is currently the most common approach for compound annotation in untargeted metabolomics. Spectral libraries applicable to liquid chromatography mass spectrometry have grown in size over the past decade to include hundreds of thousands to millions of mass spectra and tens of thousands of compounds, forming an essential knowledge base for the interpretation of metabolomics experiments.

AIM OF REVIEW

We describe existing spectral library resources, highlight different strategies for compiling spectral libraries, and discuss quality considerations that should be taken into account when interpreting spectral library searching results. Finally, we describe how spectral libraries are empowering the next generation of machine learning tools in computational metabolomics, and discuss several opportunities for using increasingly accessible large spectral libraries.

KEY SCIENTIFIC CONCEPTS OF REVIEW

This review focuses on the current state of spectral libraries for untargeted LC-MS/MS based metabolomics. We show how the number of entries in publicly accessible spectral libraries has increased more than 60-fold in the past eight years to aid molecular interpretation and we discuss how the role of spectral libraries in untargeted metabolomics will evolve in the near future.

Multichannel CNN Model for Biomedical Entity Reorganization

Biomedical researchers and biologists often search a large amount of literature to find the relationship between biological entities, such as drug-drug and compound-protein. With the proliferation of medical literature and the development of deep learning, the automatic extraction of biological entity interaction relationships from literature has shown great potential. The fundamental scope of this research is that the approach described in this research uses technologies like dynamic word vectors and multichannel convolution to learn a larger variety of relational expression semantics, allowing it to detect more entity connections. The extraction of biological entity relationships is the foundation for achieving intelligent medical care, which may increase the effectiveness of intelligent medical question answering and enhance the development of precision healthcare. In the past, deep learning methods have achieved specific results, but there are the following problems: the model uses static word vectors, which cannot distinguish polysemy; the weight of words is not considered, and the extraction effect of long sentences is poor; the integration of various models can improve the sample imbalance problem, the model is more complex. The purpose of this work is to create a global approach for eliminating different physical entity links, such that the model can effectively extract the interpretation of the expression relationship without having to develop characteristics manually. To this end, a deep multichannel CNN model (MC-CNN) based on the residual structure is proposed, generating dynamic word vectors through BERT (Bidirectional Encoder Representation from Transformers) to improve the accuracy of lexical semantic representation and uses multihead attention to capture the dependencies of long sentences and by designing the Ranking loss function to replace the multimodel ensemble to reduce the impact of sample imbalance. Tested on multiple datasets, the results show that the proposed method has good performance.

Exposing the Brain Proteomic Signatures of Alzheimer's Disease in Diverse Racial Groups: Leveraging Multiple Data Sets and Machine Learning

Recent studies have highlighted that the proteome can be used to identify potential biomarker candidates for Alzheimer's disease (AD) in diverse cohorts. Furthermore, the racial and ethnic background of participants is an important factor to consider to ensure the effectiveness of potential biomarkers for representative populations. A promising approach to survey potential biomarker candidates for diagnosing AD in diverse cohorts is the application of machine learning to proteomics data sets. Herein, we leveraged six existing bottom-up proteomics data sets, which included non-Hispanic White, African American/Black, and Hispanic participants, to study protein changes in AD and cognitively unimpaired participants. Machine learning models were applied to these data sets and resulted in the identification of amyloid-β precursor protein (APP) and heat shock protein β-1 (HSPB1) as two proteins that have high ability to distinguish AD; however, each protein's performance varied based upon the racial and ethnic background of the participants. HSPB1 particularly was helpful for generating high areas under the curve (AUCs) for African American/Black participants. Overall, HSPB1 improved the performance of the machine learning models when combined with APP and/or participant age and is a potential candidate that should be further explored in AD biomarker discovery efforts.

Machine Learning in Epigenomics: Insights into Cancer Biology and Medicine

The recent deluge of genome-wide technologies for the mapping of the epigenome and resulting data in cancer samples has provided the opportunity for gaining insights into and understanding the roles of epigenetic processes in cancer. However, the complexity, high-dimensionality, sparsity, and noise associated with these data pose challenges for extensive integrative analyses. Machine Learning (ML) algorithms are particularly suited for epigenomic data analyses due to their flexibility and ability to learn underlying hidden structures. We will discuss four overlapping but distinct major categories under ML: dimensionality reduction, unsupervised methods, supervised methods, and deep learning (DL). We review the preferred use cases of these algorithms in analyses of cancer epigenomics data with the hope to provide an overview of how ML approaches can be used to explore fundamental questions on the roles of epigenome in cancer biology and medicine.

AI applications in functional genomics

We review the current applications of artificial intelligence (AI) in functional genomics. The recent explosion of AI follows the remarkable achievements made possible by "deep learning", along with a burst of "big data" that can meet its hunger. Biology is about to overthrow astronomy as the paradigmatic representative of big data producer. This has been made possible by huge advancements in the field of high throughput technologies, applied to determine how the individual components of a biological system work together to accomplish different processes. The disciplines contributing to this bulk of data are collectively known as functional genomics. They consist in studies of: i) the information contained in the DNA (genomics); ii) the modifications that DNA can reversibly undergo (epigenomics); iii) the RNA transcripts originated by a genome (transcriptomics); iv) the ensemble of chemical modifications decorating different types of RNA transcripts (epitranscriptomics); v) the products of protein-coding transcripts (proteomics); and vi) the small molecules produced from cell metabolism (metabolomics) present in an organism or system at a given time, in physiological or pathological conditions. After reviewing main applications of AI in functional genomics, we discuss important accompanying issues, including ethical, legal and economic issues and the importance of explainability.

Rise of Clinical Studies in the Field of Machine Learning: A Review of Data Registered in ClinicalTrials.gov

Although advances in machine-learning healthcare applications promise great potential for innovative medical care, few data are available on the translational status of these new technologies. We aimed to provide a comprehensive characterization of the development and status quo of clinical studies in the field of machine learning. For this purpose, we performed a registry-based analysis of machine-learning-related studies that were published and first available in the ClinicalTrials.gov database until 2020, using the database's study classification. In total, n = 358 eligible studies could be included in the analysis. Of these, 82% were initiated by academic institutions/university (hospitals) and 18% by industry sponsors. A total of 96% were national and 4% international. About half of the studies (47%) had at least one recruiting location in a country in North America, followed by Europe (37%) and Asia (15%). Most of the studies reported were initiated in the medical field of imaging (12%), followed by cardiology, psychiatry, anesthesia/intensive care medicine (all 11%) and neurology (10%). Although the majority of the clinical studies were still initiated in an academic research context, the first industry-financed projects on machine-learning-based algorithms are becoming visible. The number of clinical studies with machine-learning-related applications and the variety of medical challenges addressed serve to indicate their increasing importance in future clinical care. Finally, they also set a time frame for the adjustment of medical device-related regulation and governance.

Machine learning reveals hidden stability code in protein native fluorescence

Conformational stability of a protein is usually obtained by spectroscopically measuring the unfolding melting temperature. However, optical spectra under native conditions are considered to contain too little resolution to probe protein stability. Here, we have built and trained a neural network model to take the temperature-dependence of intrinsic fluorescence emission under native-only conditions as inputs, and then predict the spectra at the unfolding transition and denatured state. Application to a therapeutic antibody fragment demonstrates that thermal transitions obtained from the predicted spectra correlate highly with those measured experimentally. Crucially, this work reveals that the temperature-dependence of native fluorescence spectra contains a high-degree of previously hidden information relating native ensemble features to stability. This could lead to rapid screening of therapeutic protein variants and formulations based on spectroscopic measurements under non-denaturing temperatures only.

Size Dependent Fragmentation Chemistry of Short Doubly Protonated Tryptic Peptides

Tandem mass spectrometry of electrospray ionized multiply charged peptide ions is commonly used to identify the sequence of peptide(s) and infer the identity of source protein(s). Doubly protonated peptide ions are consistently the most efficiently sequenced ions following collision-induced dissociation of peptides generated by tryptic digestion. While the broad characteristics of longer (N ≥ 8 residue) doubly protonated peptides have been investigated, there is comparatively little data on shorter systems where charge repulsion should exhibit the greatest influence on the dissociation chemistry. To address this gap and further understand the chemistry underlying collisional-dissociation of doubly charged tryptic peptides, two series of analytes ([G_xR+2H]²⁺ and [A_xR+2H]²⁺, x = 2-5) were investigated experimentally and with theory. We find distinct differences in the preference of bond cleavage sites for these peptides as a function of size and to a lesser extent composition. Density functional calculations at two levels of theory predict that the threshold relative energies required for bond cleavages at the same site for peptides of different size are quite similar (for example, b₂-y_N-2). In isolation, this finding is inconsistent with experiment. However, the predicted extent of entropy change of these reactions is size dependent. Subsequent RRKM rate constant calculations provide a far clearer picture of the kinetics of the competing bond cleavage reactions enabling rationalization of experimental findings. The M06-2X data were substantially more consistent with experiment than were the B3LYP data.

LIQUID CHROMATOGRAPHY-MASS SPECTROMETRY BOTTOM-UP PROTEOMIC METHODS IN ANIMAL SPECIES ANALYSIS OF PROCESSED MEAT FOR FOOD AUTHENTICATION AND THE DETECTION OF ADULTERATIONS

This review offers an overview of the current status and the most recent advances in liquid chromatography-mass spectrometry (LC-MS) techniques with both high-resolution and low-resolution tandem mass analyzers applied to the identification and detection of heat-stable species-specific peptide markers of meat in highly processed food products. We present sets of myofibrillar and sarcoplasmic proteins, which turned out to be the source of 105 heat-stable peptides, detectable in processed meat using LC-MS/MS. A list of heat-stable species-specific peptides was compiled for eleven types of white and red meat including chicken, duck, goose, turkey, pork, beef, lamb, rabbit, buffalo, deer, and horse meat, which can be used as markers for meat authentication. Among the 105 peptides, 57 were verified by multiple reaction monitoring, enabling identification of each species with high specificity and selectivity. The most described and monitored species by LC-MS/MS so far are chicken and pork with 26 confirmed heat-stable peptide markers for each meat. In thermally processed samples, myosin, myoglobin, hemoglobin, l-lactase dehydrogenase A and β-enolase are the main protein sources of heat-stable markers. © 2019 John Wiley & Sons Ltd. Mass Spec Rev.

Two-dimensional gel electrophoresis (2D-GE) image analysis based on CellProfiler: Pseudomonas aeruginosa AG1 as model

Two-dimensional gel electrophoresis (2D-GE) is an indispensable technique for the study of proteomes of biological systems, providing an assessment of changes in protein abundance under various experimental conditions. However, due to the complexity of 2D-GE gels, there is no systematic, automatic, and reproducible protocol for image analysis and specific implementations are required for each context. In addition, practically all available solutions are commercial, which implies high cost and little flexibility to modulate the parameters of the algorithms. Using the bacterial strain, Pseudomonas aeruginosaAG1 as a model, we obtained images from 2D-GE of periplasmic protein profiles when the strain was exposed to multiple conditions, including antibiotics. Then, we proceeded to implement and evaluate an image analysis protocol with open-source software, CellProfiler. First, a preprocessing step included a bUnwarpJ-Image pipeline for aligning 2D-GE images. Then, using CellProfiler, we standardized two pipelines for spots identification. Total spots recognition was achieved using segmentation by intensity, whose performance was evaluated when compared with a reference protocol. In a second pipeline with the same program, differential identification of spots was addressed when comparing pairs of protein profiles. Due to the characteristics of the programs used, our workflow can automatically analyze a large number of images and it is parallelizable, which is an advantage with respect to other implementations. Finally, we compared six experimental conditions of bacterial strain in the presence or absence of antibiotics, determining protein profiles relationships by applying clustering algorithms PCA (Principal Components Analysis) and HC (Hierarchical Clustering).

Deep Learning in Proteomics

Proteomics, the study of all the proteins in biological systems, is becoming a data-rich science. Protein sequences and structures are comprehensively catalogued in online databases. With recent advancements in tandem mass spectrometry (MS) technology, protein expression and post-translational modifications (PTMs) can be studied in a variety of biological systems at the global scale. Sophisticated computational algorithms are needed to translate the vast amount of data into novel biological insights. Deep learning automatically extracts data representations at high levels of abstraction from data, and it thrives in data-rich scientific research domains. Here, a comprehensive overview of deep learning applications in proteomics, including retention time prediction, MS/MS spectrum prediction, de novo peptide sequencing, PTM prediction, major histocompatibility complex-peptide binding prediction, and protein structure prediction, is provided. Limitations and the future directions of deep learning in proteomics are also discussed. This review will provide readers an overview of deep learning and how it can be used to analyze proteomics data.

Proteomics and Metabolomics for Cystic Fibrosis Research

The aim of this review article is to introduce the reader to the state-of-the-art of the contribution that proteomics and metabolomics sciences are currently providing for cystic fibrosis (CF) research: from the understanding of cystic fibrosis transmembrane conductance regulator (CFTR) biology to biomarker discovery for CF diagnosis. Our work particularly focuses on CFTR post-translational modifications and their role in cellular trafficking as well as on studies that allowed the identification of CFTR molecular interactors. We also show how metabolomics is currently helping biomarker discovery in CF. The most recent advances in these fields are covered by this review, as well as some considerations on possible future scenarios for new applications.

The Age of Data-Driven Proteomics: How Machine Learning Enables Novel Workflows

A lot of energy in the field of proteomics is dedicated to the application of challenging experimental workflows, which include metaproteomics, proteogenomics, data independent acquisition (DIA), non-specific proteolysis, immunopeptidomics, and open modification searches. These workflows are all challenging because of ambiguity in the identification stage; they either expand the search space and thus increase the ambiguity of identifications, or, in the case of DIA, they generate data that is inherently more ambiguous. In this context, machine learning-based predictive models are now generating considerable excitement in the field of proteomics because these predictive models hold great potential to drastically reduce the ambiguity in the identification process of the above-mentioned workflows. Indeed, the field has already produced classical machine learning and deep learning models to predict almost every aspect of a liquid chromatography-mass spectrometry (LC-MS) experiment. Yet despite all the excitement, thorough integration of predictive models in these challenging LC-MS workflows is still limited, and further improvements to the modeling and validation procedures can still be made. Therefore, highly promising recent machine learning developments in proteomics are pointed out in this viewpoint, alongside some of the remaining challenges.

Anatomy and evolution of database search engines-a central component of mass spectrometry based proteomic workflows

Sequence database search engines are bioinformatics algorithms that identify peptides from tandem mass spectra using a reference protein sequence database. Two decades of development, notably driven by advances in mass spectrometry, have provided scientists with more than 30 published search engines, each with its own properties. In this review, we present the common paradigm behind the different implementations, and its limitations for modern mass spectrometry datasets. We also detail how the search engines attempt to alleviate these limitations, and provide an overview of the different software frameworks available to the researcher. Finally, we highlight alternative approaches for the identification of proteomic mass spectrometry datasets, either as a replacement for, or as a complement to, sequence database search engines.

Proteomic investigations into resistance in colorectal cancer

Introduction: Despite advances in screening and treatment options, colorectal cancer (CRC) remains one of the most prevalent and lethal cancer subtypes. Resistance to cytotoxic or targeted therapy has remained a constant challenge to the treatment and long-term management of patients, attracting intense worldwide investigation since the 1950s. Through extensive investigations into the proteomic mechanisms and functions that convey resistance to therapy/s, researchers have become able to implicate alterations in several signaling pathways that provide and sustain resistance to treatment.Areas covered: In this review, we summarize how protein alterations are associated with resistance to therapy, with particular emphasis on CRC. An overview of the mechanisms of therapeutic resistance is described, highlighting recent studies which endeavor to elucidate the proteomic changes that are associated with the acquisition and promulgation of therapeutic resistance.Expert opinion: While cancers such as CRC have been intensively studied for decades, unresponsiveness and the resistance to therapy remain critical obstacles in the treatment of patients. Due to the inherent biological and clinical heterogeneity of individual CRCs, proteomic methods stand to become powerful tools to provide biological insights that may guide therapeutic strategies with the ultimate goal of refining emergent immunotherapeutic treatments.

Extremely Fast and Accurate Open Modification Spectral Library Searching of High-Resolution Mass Spectra Using Feature Hashing and Graphics Processing Units

Open modification searching (OMS) is a powerful search strategy to identify peptides with any type of modification. OMS works by using a very wide precursor mass window to allow modified spectra to match against their unmodified variants, after which the modification types can be inferred from the corresponding precursor mass differences. A disadvantage of this strategy, however, is the large computational cost, because each query spectrum has to be compared against a multitude of candidate peptides. We have previously introduced the ANN-SoLo tool for fast and accurate open spectral library searching. ANN-SoLo uses approximate nearest neighbor indexing to speed up OMS by selecting only a limited number of the most relevant library spectra to compare to an unknown query spectrum. Here we demonstrate how this candidate selection procedure can be further optimized using graphics processing units. Additionally, we introduce a feature hashing scheme to convert high-resolution spectra to low-dimensional vectors. On the basis of these algorithmic advances, along with low-level code optimizations, the new version of ANN-SoLo is up to an order of magnitude faster than its initial version. This makes it possible to efficiently perform open searches on a large scale to gain a deeper understanding about the protein modification landscape. We demonstrate the computational efficiency and identification performance of ANN-SoLo based on a large data set of the draft human proteome. ANN-SoLo is implemented in Python and C++. It is freely available under the Apache 2.0 license at https://github.com/bittremieux/ANN-SoLo .

Potential early clinical stage colorectal cancer diagnosis using a proteomics blood test panel

BACKGROUND

One of the most significant challenges in colorectal cancer (CRC) management is the use of compliant early stage population-based diagnostic tests as adjuncts to confirmatory colonoscopy. Despite the near curative nature of early clinical stage surgical resection, mortality remains unacceptably high-as the majority of patients diagnosed by faecal haemoglobin followed by colonoscopy occur at latter stages. Additionally, current population-based screens reliant on fecal occult blood test (FOBT) have low compliance (~ 40%) and tests suffer low sensitivities. Therefore, blood-based diagnostic tests offer survival benefits from their higher compliance (≥ 97%), if they can at least match the sensitivity and specificity of FOBTs. However, discovery of low abundance plasma biomarkers is difficult due to occupancy of a high percentage of proteomic discovery space by many high abundance plasma proteins (e.g., human serum albumin).

METHODS

A combination of high abundance protein ultradepletion (e.g., MARS-14 and an in-house IgY depletion columns) strategies, extensive peptide fractionation methods (SCX, SAX, High pH and SEC) and SWATH-MS were utilized to uncover protein biomarkers from a cohort of 100 plasma samples (i.e., pools of 20 healthy and 20 stages I-IV CRC plasmas). The differentially expressed proteins were analyzed using ANOVA and pairwise t-tests (p < 0.05; fold-change > 1.5), and further examined with a neural network classification method using in silico augmented 5000 patient datasets.

RESULTS

Ultradepletion combined with peptide fractionation allowed for the identification of a total of 513 plasma proteins, 8 of which had not been previously reported in human plasma (based on PeptideAtlas database). SWATH-MS analysis revealed 37 protein biomarker candidates that exhibited differential expression across CRC stages compared to healthy controls. Of those, 7 candidates (CST3, GPX3, CFD, MRC1, COMP, PON1 and ADAMDEC1) were validated using Western blotting and/or ELISA. The neural network classification narrowed down candidate biomarkers to 5 proteins (SAA2, APCS, APOA4, F2 and AMBP) that had maintained accuracy which could discern early (I/II) from late (III/IV) stage CRC.

CONCLUSION

MS-based proteomics in combination with ultradepletion strategies have an immense potential of identifying diagnostic protein biosignature.

Predictive chromatography of peptides and proteins as a complementary tool for proteomics

In the last couple of decades, considerable effort has been focused on developing methods for quantitative and qualitative proteome characterization. The method of choice in this characterization is mass spectrometry used in combination with sample separation. One of the most widely used separation techniques at the front end of a mass spectrometer is high performance liquid chromatography (HPLC). A unique feature of HPLC is its specificity to the amino acid sequence of separated peptides and proteins. This specificity may provide additional information about the peptides or proteins under study which is complementary to the mass spectrometry data. The value of this information for proteomics has been recognized in the past few decades, which has stimulated significant effort in the development and implementation of computational and theoretical models for the prediction of peptide retention time for a given sequence. Here we review the advances in this area and the utility of predicted retention times for proteomic applications.

Artificial intelligence, physiological genomics, and precision medicine

Big data are a major driver in the development of precision medicine. Efficient analysis methods are needed to transform big data into clinically-actionable knowledge. To accomplish this, many researchers are turning toward machine learning (ML), an approach of artificial intelligence (AI) that utilizes modern algorithms to give computers the ability to learn. Much of the effort to advance ML for precision medicine has been focused on the development and implementation of algorithms and the generation of ever larger quantities of genomic sequence data and electronic health records. However, relevance and accuracy of the data are as important as quantity of data in the advancement of ML for precision medicine. For common diseases, physiological genomic readouts in disease-applicable tissues may be an effective surrogate to measure the effect of genetic and environmental factors and their interactions that underlie disease development and progression. Disease-applicable tissue may be difficult to obtain, but there are important exceptions such as kidney needle biopsy specimens. As AI continues to advance, new analytical approaches, including those that go beyond data correlation, need to be developed and ethical issues of AI need to be addressed. Physiological genomic readouts in disease-relevant tissues, combined with advanced AI, can be a powerful approach for precision medicine for common diseases.

Protein Inference from the Integration of Tandem MS Data and Interactome Networks

Since proteins are digested into a mixture of peptides in the preprocessing step of tandem mass spectrometry (MS), it is difficult to determine which specific protein a shared peptide belongs to. In recent studies, besides tandem MS data and peptide identification information, some other information is exploited to infer proteins. Different from the methods which first use only tandem MS data to infer proteins and then use network information to refine them, this study proposes a protein inference method named TMSIN, which uses interactome networks directly. As two interacting proteins should co-exist, it is reasonable to assume that if one of the interacting proteins is confidently inferred in a sample, its interacting partners should have a high probability in the same sample, too. Therefore, we can use the neighborhood information of a protein in an interactome network to adjust the probability that the shared peptide belongs to the protein. In TMSIN, a multi-weighted graph is constructed by incorporating the bipartite graph with interactome network information, where the bipartite graph is built with the peptide identification information. Based on multi-weighted graphs, TMSIN adopts an iterative workflow to infer proteins. At each iterative step, the probability that a shared peptide belongs to a specific protein is calculated by using the Bayes' law based on the neighbor protein support scores of each protein which are mapped by the shared peptides. We carried out experiments on yeast data and human data to evaluate the performance of TMSIN in terms of ROC, q-value, and accuracy. The experimental results show that AUC scores yielded by TMSIN are 0.742 and 0.874 in yeast dataset and human dataset, respectively, and TMSIN yields the maximum number of true positives when q-value less than or equal to 0.05. The overlap analysis shows that TMSIN is an effective complementary approach for protein inference.

Synthetic biology approaches for the production of plant metabolites in unicellular organisms

Synthetic biology is the repurposing of biological systems for novel objectives and applications. Through the co-ordinated and balanced expression of genes, both native and those introduced from other organisms, resources within an industrial chassis can be siphoned for the commercial production of high-value commodities. This developing interdisciplinary field has the potential to revolutionize natural product discovery from higher plants, by providing a diverse array of tools, technologies, and strategies for exploring the large chemically complex space of plant natural products using unicellular organisms. In this review, we emphasize the key features that influence the generation of biorefineries and highlight technologies and strategic solutions that can be used to overcome engineering pitfalls with rational design. Also presented is a succinct guide to assist the selection of unicellular chassis most suited for the engineering and subsequent production of the desired natural product, in order to meet the global demand for plant natural products in a safe and sustainable manner.

Machine learning for epigenetics and future medical applications

Understanding epigenetic processes holds immense promise for medical applications. Advances in Machine Learning (ML) are critical to realize this promise. Previous studies used epigenetic data sets associated with the germline transmission of epigenetic transgenerational inheritance of disease and novel ML approaches to predict genome-wide locations of critical epimutations. A combination of Active Learning (ACL) and Imbalanced Class Learning (ICL) was used to address past problems with ML to develop a more efficient feature selection process and address the imbalance problem in all genomic data sets. The power of this novel ML approach and our ability to predict epigenetic phenomena and associated disease is suggested. The current approach requires extensive computation of features over the genome. A promising new approach is to introduce Deep Learning (DL) for the generation and simultaneous computation of novel genomic features tuned to the classification task. This approach can be used with any genomic or biological data set applied to medicine. The application of molecular epigenetic data in advanced machine learning analysis to medicine is the focus of this review.

Building ProteomeTools based on a complete synthetic human proteome

We describe ProteomeTools, a project building molecular and digital tools from the human proteome to facilitate biomedical research. Here we report the generation and multimodal liquid chromatography-tandem mass spectrometry analysis of >330,000 synthetic tryptic peptides representing essentially all canonical human gene products, and we exemplify the utility of these data in several applications. The resource (available at http://www.proteometools.org) will be extended to >1 million peptides, and all data will be shared with the community via ProteomicsDB and ProteomeXchange.

Analysis of Major Histocompatibility Complex (MHC) Immunopeptidomes Using Mass Spectrometry

The myriad of peptides presented at the cell surface by class I and class II major histocompatibility complex (MHC) molecules are referred to as the immunopeptidome and are of great importance for basic and translational science. For basic science, the immunopeptidome is a critical component for understanding the immune system; for translational science, exact knowledge of the immunopeptidome can directly fuel and guide the development of next-generation vaccines and immunotherapies against autoimmunity, infectious diseases, and cancers. In this mini-review, we summarize established isolation techniques as well as emerging mass spectrometry-based platforms (i.e. SWATH-MS) to identify and quantify MHC-associated peptides. We also highlight selected biological applications and discuss important current technical limitations that need to be solved to accelerate the development of this field.

A robust data scaling algorithm to improve classification accuracies in biomedical data

Background

Machine learning models have been adapted in biomedical research and practice for knowledge discovery and decision support. While mainstream biomedical informatics research focuses on developing more accurate models, the importance of data preprocessing draws less attention. We propose the Generalized Logistic (GL) algorithm that scales data uniformly to an appropriate interval by learning a generalized logistic function to fit the empirical cumulative distribution function of the data. The GL algorithm is simple yet effective; it is intrinsically robust to outliers, so it is particularly suitable for diagnostic/classification models in clinical/medical applications where the number of samples is usually small; it scales the data in a nonlinear fashion, which leads to potential improvement in accuracy.

Results

To evaluate the effectiveness of the proposed algorithm, we conducted experiments on 16 binary classification tasks with different variable types and cover a wide range of applications. The resultant performance in terms of area under the receiver operation characteristic curve (AUROC) and percentage of correct classification showed that models learned using data scaled by the GL algorithm outperform the ones using data scaled by the Min-max and the Z-score algorithm, which are the most commonly used data scaling algorithms.

Conclusion

The proposed GL algorithm is simple and effective. It is robust to outliers, so no additional denoising or outlier detection step is needed in data preprocessing. Empirical results also show models learned from data scaled by the GL algorithm have higher accuracy compared to the commonly used data scaling algorithms.

Machine learning approaches in MALDI-MSI: clinical applications

INTRODUCTION

Despite the unquestionable advantages of Matrix-Assisted Laser Desorption/Ionization Mass Spectrometry Imaging in visualizing the spatial distribution and the relative abundance of biomolecules directly on-tissue, the yielded data is complex and high dimensional. Therefore, analysis and interpretation of this huge amount of information is mathematically, statistically and computationally challenging.

AREAS COVERED

This article reviews some of the challenges in data elaboration with particular emphasis on machine learning techniques employed in clinical applications, and can be useful in general as an entry point for those who want to study the computational aspects. Several characteristics of data processing are described, enlightening advantages and disadvantages. Different approaches for data elaboration focused on clinical applications are also provided. Practical tutorial based upon Orange Canvas and Weka software is included, helping familiarization with the data processing. Expert commentary: Recently, MALDI-MSI has gained considerable attention and has been employed for research and diagnostic purposes, with successful results. Data dimensionality constitutes an important issue and statistical methods for information-preserving data reduction represent one of the most challenging aspects. The most common data reduction methods are characterized by collecting independent observations into a single table. However, the incorporation of relational information can improve the discriminatory capability of the data.

Designing biomedical proteomics experiments: state-of-the-art and future perspectives

With the current expanded technical capabilities to perform mass spectrometry-based biomedical proteomics experiments, an improved focus on the design of experiments is crucial. As it is clear that ignoring the importance of a good design leads to an unprecedented rate of false discoveries which would poison our results, more and more tools are developed to help researchers designing proteomic experiments. In this review, we apply statistical thinking to go through the entire proteomics workflow for biomarker discovery and validation and relate the considerations that should be made at the level of hypothesis building, technology selection, experimental design and the optimization of the experimental parameters.

Database Search Engines: Paradigms, Challenges and Solutions

The first step in identifying proteins from mass spectrometry based shotgun proteomics data is to infer peptides from tandem mass spectra, a task generally achieved using database search engines. In this chapter, the basic principles of database search engines are introduced with a focus on open source software, and the use of database search engines is demonstrated using the freely available SearchGUI interface. This chapter also discusses how to tackle general issues related to sequence database searching and shows how to minimize their impact.

Big Data in Plant Science: Resources and Data Mining Tools for Plant Genomics and Proteomics

In modern plant biology, progress is increasingly defined by the scientists' ability to gather and analyze data sets of high volume and complexity, otherwise known as "big data". Arguably, the largest increase in the volume of plant data sets over the last decade is a consequence of the application of the next-generation sequencing and mass-spectrometry technologies to the study of experimental model and crop plants. The increase in quantity and complexity of biological data brings challenges, mostly associated with data acquisition, processing, and sharing within the scientific community. Nonetheless, big data in plant science create unique opportunities in advancing our understanding of complex biological processes at a level of accuracy without precedence, and establish a base for the plant systems biology. In this chapter, we summarize the major drivers of big data in plant science and big data initiatives in life sciences with a focus on the scope and impact of iPlant, a representative cyberinfrastructure platform for plant science.

Using Peptide-Level Proteomics Data for Detecting Differentially Expressed Proteins

The expression of proteins can be quantified in high-throughput means using different types of mass spectrometers. In recent years, there have emerged label-free methods for determining protein abundance. Although the expression is initially measured at the peptide level, a common approach is to combine the peptide-level measurements into protein-level values before differential expression analysis. However, this simple combination is prone to inconsistencies between peptides and may lose valuable information. To this end, we introduce here a method for detecting differentially expressed proteins by combining peptide-level expression-change statistics. Using controlled spike-in experiments, we show that the approach of averaging peptide-level expression changes yields more accurate lists of differentially expressed proteins than does the conventional protein-level approach. This is particularly true when there are only few replicate samples or the differences between the sample groups are small. The proposed technique is implemented in the Bioconductor package PECA, and it can be downloaded from http://www.bioconductor.org.

Metaproteomics of complex microbial communities in biogas plants

Production of biogas from agricultural biomass or organic wastes is an important source of renewable energy. Although thousands of biogas plants (BGPs) are operating in Germany, there is still a significant potential to improve yields, e.g. from fibrous substrates. In addition, process stability should be optimized. Besides evaluating technical measures, improving our understanding of microbial communities involved into the biogas process is considered as key issue to achieve both goals. Microscopic and genetic approaches to analyse community composition provide valuable experimental data, but fail to detect presence of enzymes and overall metabolic activity of microbial communities. Therefore, metaproteomics can significantly contribute to elucidate critical steps in the conversion of biomass to methane as it delivers combined functional and phylogenetic data. Although metaproteomics analyses are challenged by sample impurities, sample complexity and redundant protein identification, and are still limited by the availability of genome sequences, recent studies have shown promising results. In the following, the workflow and potential pitfalls for metaproteomics of samples from full-scale BGP are discussed. In addition, the value of metaproteomics to contribute to the further advancement of microbial ecology is evaluated. Finally, synergistic effects expected when metaproteomics is combined with advanced imaging techniques, metagenomics, metatranscriptomics and metabolomics are addressed.

Bioinformatics approaches for the functional interpretation of protein lists: from ontology term enrichment to network analysis

The main result of a great deal of the published proteomics studies is a list of identified proteins, which then needs to be interpreted in relation to the research question and existing knowledge. In the early days of proteomics this interpretation was only based on expert insights, acquired by digesting a large amount of relevant literature. With the growing size and complexity of the experimental datasets, many computational techniques, databases, and tools have claimed a central role in this task. In this review we discuss commonly and less commonly used methods to functionally interpret experimental proteome lists and compare them with available knowledge. We first address several functional analysis and enrichment techniques based on ontologies and literature. Then we outline how various types of network and pathway information can be used. While the problem of functional interpretation of proteome data is to an extent equivalent to the interpretation of transcriptome or other ''omics'' data, this paper addresses some of the specific challenges and solutions of the proteomics field.

Viewing the proteome: how to visualize proteomics data?

Proteomics has become one of the main approaches for analyzing and understanding biological systems. Yet similar to other high-throughput analysis methods, the presentation of the large amounts of obtained data in easily interpretable ways remains challenging. In this review, we present an overview of the different ways in which proteomics software supports the visualization and interpretation of proteomics data. The unique challenges and current solutions for visualizing the different aspects of proteomics data, from acquired spectra via protein identification and quantification to pathway analysis, are discussed, and examples of the most useful visualization approaches are highlighted. Finally, we offer our ideas about future directions for proteomics data visualization.

Machine learning for Big Data analytics in plants

Rapid advances in high-throughput genomic technology have enabled biology to enter the era of 'Big Data' (large datasets). The plant science community not only needs to build its own Big-Data-compatible parallel computing and data management infrastructures, but also to seek novel analytical paradigms to extract information from the overwhelming amounts of data. Machine learning offers promising computational and analytical solutions for the integrative analysis of large, heterogeneous and unstructured datasets on the Big-Data scale, and is gradually gaining popularity in biology. This review introduces the basic concepts and procedures of machine-learning applications and envisages how machine learning could interface with Big Data technology to facilitate basic research and biotechnology in the plant sciences.

The probabilistic convolution tree: efficient exact Bayesian inference for faster LC-MS/MS protein inference

Exact Bayesian inference can sometimes be performed efficiently for special cases where a function has commutative and associative symmetry of its inputs (called “causal independence”). For this reason, it is desirable to exploit such symmetry on big data sets. Here we present a method to exploit a general form of this symmetry on probabilistic adder nodes by transforming those probabilistic adder nodes into a probabilistic convolution tree with which dynamic programming computes exact probabilities. A substantial speedup is demonstrated using an illustration example that can arise when identifying splice forms with bottom-up mass spectrometry-based proteomics. On this example, even state-of-the-art exact inference algorithms require a runtime more than exponential in the number of splice forms considered. By using the probabilistic convolution tree, we reduce the runtime to and the space to where is the number of variables joined by an additive or cardinal operator. This approach, which can also be used with junction tree inference, is applicable to graphs with arbitrary dependency on counting variables or cardinalities and can be used on diverse problems and fields like forward error correcting codes, elemental decomposition, and spectral demixing. The approach also trivially generalizes to multiple dimensions.