FAVA: high-quality functional association networks inferred from scRNA-seq and proteomics data.

MOTIVATION: Protein networks are commonly used for understanding how proteins interact. However, they are typically biased by data availability, favoring well-studied proteins with more interactions. To uncover functions of understudied proteins, we must use data that are not affected by this literature bias, such as single-cell RNA-seq and proteomics. Due to data sparseness and redundancy, functional association analysis becomes complex. RESULTS: To address this, we have developed FAVA (Functional Associations using Variational Autoencoders), which compresses high-dimensional data into a low-dimensional space. FAVA infers networks from high-dimensional omics data with much higher accuracy than existing methods, across a diverse collection of real as well as simulated datasets. FAVA can process large datasets with over 0.5 million conditions and has predicted 4210 interactions between 1039 understudied proteins. Our findings showcase FAVA's capability to offer novel perspectives on protein interactions. FAVA functions within the scverse ecosystem, employing AnnData as its input source. AVAILABILITY AND IMPLEMENTATION: Source code, documentation, and tutorials for FAVA are accessible on GitHub at https://github.com/mikelkou/fava. FAVA can also be installed and used via pip/PyPI as well as via the scverse ecosystem https://github.com/scverse/ecosystem-packages/tree/main/packages/favapy.

Updated MS²PIP web server supports cutting-edge proteomics applications.

Interest in the use of machine learning for peptide fragmentation spectrum prediction has been strongly on the rise over the past years, especially for applications in challenging proteomics identification workflows such as immunopeptidomics and the full-proteome identification of data independent acquisition spectra. Since its inception, the MS²PIP peptide spectrum predictor has been widely used for various downstream applications, mostly thanks to its accuracy, ease-of-use, and broad applicability. We here present a thoroughly updated version of the MS²PIP web server, which includes new and more performant prediction models for both tryptic- and non-tryptic peptides, for immunopeptides, and for CID-fragmented TMT-labeled peptides. Additionally, we have also added new functionality to greatly facilitate the generation of proteome-wide predicted spectral libraries, requiring only a FASTA protein file as input. These libraries also include retention time predictions from DeepLC. Moreover, we now provide pre-built and ready-to-download spectral libraries for various model organisms in multiple DIA-compatible spectral library formats. Besides upgrading the back-end models, the user experience on the MS²PIP web server is thus also greatly enhanced, extending its applicability to new domains, including immunopeptidomics and MS3-based TMT quantification experiments. MS²PIP is freely available at https://iomics.ugent.be/ms2pip/.

Intensity and retention time prediction improves the rescoring of protein-nucleic acid cross-links.

In protein-RNA cross-linking mass spectrometry, UV or chemical cross-linking introduces stable bonds between amino acids and nucleic acids in protein-RNA complexes that are then analyzed and detected in mass spectra. This analytical tool delivers valuable information about RNA-protein interactions and RNA docking sites in proteins, both in vitro and in vivo. The identification of cross-linked peptides with oligonucleotides of different length leads to a combinatorial increase in search space. We demonstrate that the peptide retention time prediction tasks can be transferred to the task of cross-linked peptide retention time prediction using a simple amino acid composition encoding, yielding improved identification rates when the prediction error is included in rescoring. For the more challenging task of including fragment intensity prediction of cross-linked peptides in the rescoring, we obtain, on average, a similar improvement. Further improvement in the encoding and fine-tuning of retention time and intensity prediction models might lead to further gains, and merit further research.

MS2Rescore 3.0 Is a Modular, Flexible, and User-Friendly Platform to Boost Peptide Identifications, as Showcased with MS Amanda 3.0.

Rescoring of peptide-spectrum matches (PSMs) has emerged as a standard procedure for the analysis of tandem mass spectrometry data. This emphasizes the need for software maintenance and continuous improvement for such algorithms. We introduce MS2Rescore 3.0, a versatile, modular, and user-friendly platform designed to increase peptide identifications. Researchers can install MS2Rescore across various platforms with minimal effort and benefit from a graphical user interface, a modular Python API, and extensive documentation. To showcase this new version, we connected MS2Rescore 3.0 with MS Amanda 3.0, a new release of the well-established search engine, addressing previous limitations on automatic rescoring. Among new features, MS Amanda now contains additional output columns that can be used for rescoring. The full potential of rescoring is best revealed when applied on challenging data sets. We therefore evaluated the performance of these two tools on publicly available single-cell data sets, where the number of PSMs was substantially increased, thereby demonstrating that MS2Rescore offers a powerful solution to boost peptide identifications. MS2Rescore's modular design and user-friendly interface make data-driven rescoring easily accessible, even for inexperienced users. We therefore expect the MS2Rescore to be a valuable tool for the wider proteomics community. MS2Rescore is available at https://github.com/compomics/ms2rescore.

Benefit of In Silico Predicted Spectral Libraries in Data-Independent Acquisition Data Analysis Workflows.

Data-independent acquisition (DIA) has become a well-established method for MS-based proteomics. However, the list of options to analyze this type of data is quite extensive, and the use of spectral libraries has become an important factor in DIA data analysis. More specifically the use of in silico predicted libraries is gaining more interest. By working with a differential spike-in of human standard proteins (UPS2) in a constant yeast tryptic digest background, we evaluated the sensitivity, precision, and accuracy of the use of in silico predicted libraries in data DIA data analysis workflows compared to more established workflows. Three commonly used DIA software tools, DIA-NN, EncyclopeDIA, and Spectronaut, were each tested in spectral library mode and spectral library-free mode. In spectral library mode, we used independent spectral library prediction tools PROSIT and MS2PIP together with DeepLC, next to classical data-dependent acquisition (DDA)-based spectral libraries. In total, we benchmarked 12 computational workflows for DIA. Our comparison showed that DIA-NN reached the highest sensitivity while maintaining a good compromise on the reproducibility and accuracy levels in either library-free mode or using in silico predicted libraries pointing to a general benefit in using in silico predicted libraries.

DeepLC can predict retention times for peptides that carry as-yet unseen modifications.

The inclusion of peptide retention time prediction promises to remove peptide identification ambiguity in complex liquid chromatography-mass spectrometry identification workflows. However, due to the way peptides are encoded in current prediction models, accurate retention times cannot be predicted for modified peptides. This is especially problematic for fledgling open searches, which will benefit from accurate retention time prediction for modified peptides to reduce identification ambiguity. We present DeepLC, a deep learning peptide retention time predictor using peptide encoding based on atomic composition that allows the retention time of (previously unseen) modified peptides to be predicted accurately. We show that DeepLC performs similarly to current state-of-the-art approaches for unmodified peptides and, more importantly, accurately predicts retention times for modifications not seen during training. Moreover, we show that DeepLC's ability to predict retention times for any modification enables potentially incorrect identifications to be flagged in an open search of a wide variety of proteome data.

MS2Rescore: Data-Driven Rescoring Dramatically Boosts Immunopeptide Identification Rates.

Immunopeptidomics aims to identify major histocompatibility complex (MHC)-presented peptides on almost all cells that can be used in anti-cancer vaccine development. However, existing immunopeptidomics data analysis pipelines suffer from the nontryptic nature of immunopeptides, complicating their identification. Previously, peak intensity predictions by MS2PIP and retention time predictions by DeepLC have been shown to improve tryptic peptide identifications when rescoring peptide-spectrum matches with Percolator. However, as MS2PIP was tailored toward tryptic peptides, we have here retrained MS2PIP to include nontryptic peptides. Interestingly, the new models not only greatly improve predictions for immunopeptides but also yield further improvements for tryptic peptides. We show that the integration of new MS2PIP models, DeepLC, and Percolator in one software package, MS2Rescore, increases spectrum identification rate and unique identified peptides with 46% and 36% compared to standard Percolator rescoring at 1% FDR. Moreover, MS2Rescore also outperforms the current state-of-the-art in immunopeptide-specific identification approaches. Altogether, MS2Rescore thus allows substantially improved identification of novel epitopes from existing immunopeptidomics workflows.

psm_utils: A High-Level Python API for Parsing and Handling Peptide-Spectrum Matches and Proteomics Search Results.

A plethora of proteomics search engine output file formats are in circulation. This lack of standardized output files greatly complicates generic downstream processing of peptide-spectrum matches (PSMs) and PSM files. While standards exist to solve this problem, these are far from universally supported by search engines. Moreover, software libraries are available to read a selection of PSM file formats, but a package to parse PSM files into a unified data structure has been missing. Here, we present psm_utils, a Python package to read and write various PSM file formats and to handle peptidoforms, PSMs, and PSM lists in a unified and user-friendly Python-, command line-, and web-interface. psm_utils was developed with pragmatism and maintainability in mind, adhering to community standards and relying on existing packages where possible. The Python API and command line interface greatly facilitate handling various PSM file formats. Moreover, a user-friendly web application was built using psm_utils that allows anyone to interconvert PSM files and retrieve basic PSM statistics. psm_utils is freely available under the permissive Apache2 license at https://github.com/compomics/psm_utils.

Machine Learning on Large-Scale Proteomics Data Identifies Tissue and Cell-Type Specific Proteins.

Using data from 183 public human data sets from PRIDE, a machine learning model was trained to identify tissue and cell-type specific protein patterns. PRIDE projects were searched with ionbot and tissue/cell type annotation was manually added. Data from physiological samples were used to train a Random Forest model on protein abundances to classify samples into tissues and cell types. Subsequently, a one-vs-all classification and feature importance were used to analyze the most discriminating protein abundances per class. Based on protein abundance alone, the model was able to predict tissues with 98% accuracy, and cell types with 99% accuracy. The F-scores describe a clear view on tissue-specific proteins and tissue-specific protein expression patterns. In-depth feature analysis shows slight confusion between physiologically similar tissues, demonstrating the capacity of the algorithm to detect biologically relevant patterns. These results can in turn inform downstream uses, from identification of the tissue of origin of proteins in complex samples such as liquid biopsies, to studying the proteome of tissue-like samples such as organoids and cell lines.

ProteomicsML: An Online Platform for Community-Curated Data sets and Tutorials for Machine Learning in Proteomics.

Data set acquisition and curation are often the most difficult and time-consuming parts of a machine learning endeavor. This is especially true for proteomics-based liquid chromatography (LC) coupled to mass spectrometry (MS) data sets, due to the high levels of data reduction that occur between raw data and machine learning-ready data. Since predictive proteomics is an emerging field, when predicting peptide behavior in LC-MS setups, each lab often uses unique and complex data processing pipelines in order to maximize performance, at the cost of accessibility and reproducibility. For this reason we introduce ProteomicsML, an online resource for proteomics-based data sets and tutorials across most of the currently explored physicochemical peptide properties. This community-driven resource makes it simple to access data in easy-to-process formats, and contains easy-to-follow tutorials that allow new users to interact with even the most advanced algorithms in the field. ProteomicsML provides data sets that are useful for comparing state-of-the-art machine learning algorithms, as well as providing introductory material for teachers and newcomers to the field alike. The platform is freely available at https://www.proteomicsml.org/, and we welcome the entire proteomics community to contribute to the project at https://github.com/ProteomicsML/ProteomicsML.

Toward an Integrated Machine Learning Model of a Proteomics Experiment.

In recent years machine learning has made extensive progress in modeling many aspects of mass spectrometry data. We brought together proteomics data generators, repository managers, and machine learning experts in a workshop with the goals to evaluate and explore machine learning applications for realistic modeling of data from multidimensional mass spectrometry-based proteomics analysis of any sample or organism. Following this sample-to-data roadmap helped identify knowledge gaps and define needs. Being able to generate bespoke and realistic synthetic data has legitimate and important uses in system suitability, method development, and algorithm benchmarking, while also posing critical ethical questions. The interdisciplinary nature of the workshop informed discussions of what is currently possible and future opportunities and challenges. In the following perspective we summarize these discussions in the hope of conveying our excitement about the potential of machine learning in proteomics and to inspire future research.

The nutritional composition and cell size of microbial biomass for food applications are defined by the growth conditions.

BACKGROUND: It is increasingly recognized that conventional food production systems are not able to meet the globally increasing protein needs, resulting in overexploitation and depletion of resources, and environmental degradation. In this context, microbial biomass has emerged as a promising sustainable protein alternative. Nevertheless, often no consideration is given on the fact that the cultivation conditions affect the composition of microbial cells, and hence their quality and nutritional value. Apart from the properties and nutritional quality of the produced microbial food (ingredient), this can also impact its sustainability. To qualitatively assess these aspects, here, we investigated the link between substrate availability, growth rate, cell composition and size of Cupriavidus necator and Komagataella phaffii. RESULTS: Biomass with decreased nucleic acid and increased protein content was produced at low growth rates. Conversely, high rates resulted in larger cells, which could enable more efficient biomass harvesting. The proteome allocation varied across the different growth rates, with more ribosomal proteins at higher rates, which could potentially affect the techno-functional properties of the biomass. Considering the distinct amino acid profiles established for the different cellular components, variations in their abundance impacts the product quality leading to higher cysteine and phenylalanine content at low growth rates. Therefore, we hint that costly external amino acid supplementations that are often required to meet the nutritional needs could be avoided by carefully applying conditions that enable targeted growth rates. CONCLUSION: In summary, we demonstrate tradeoffs between nutritional quality and production rate, and we discuss the microbial biomass properties that vary according to the growth conditions.

Sensitive and Specific Spectral Library Searching with CompOmics Spectral Library Searching Tool and Percolator.

Maintaining high sensitivity while limiting false positives is a key challenge in peptide identification from mass spectrometry data. Here, we investigate the effects of integrating the machine learning-based postprocessor Percolator into our spectral library searching tool COSS (CompOmics Spectral library Searching tool). To evaluate the effects of this postprocessing, we have used 40 data sets from 2 different projects and have searched these against the NIST and MassIVE spectral libraries. The searching is carried out using 2 spectral library search tools, COSS and MSPepSearch with and without Percolator postprocessing, and using sequence database search engine MS-GF+ as a baseline comparator. The addition of the Percolator rescoring step to COSS is effective and results in a substantial improvement in sensitivity and specificity of the identifications. COSS is freely available as open source under the permissive Apache2 license, and binaries and source code are found at https://github.com/compomics/COSS.

Personalized Proteome: Comparing Proteogenomics and Open Variant Search Approaches for Single Amino Acid Variant Detection.

Discovery of variant peptides such as a single amino acid variant (SAAV) in shotgun proteomics data is essential for personalized proteomics. Both the resolution of shotgun proteomics methods and the search engines have improved dramatically, allowing for confident identification of SAAV peptides. However, it is not yet known if these methods are truly successful in accurately identifying SAAV peptides without prior genomic information in the search database. We studied this in unprecedented detail by exploiting publicly available long-read RNA sequences and shotgun proteomics data from the gold standard reference cell line NA12878. Searching spectra from this cell line with the state-of-the-art open modification search engine ionbot against carefully curated search databases resulted in 96.7% false-positive SAAVs and an 85% lower true positive rate than searching with peptide search databases that incorporate prior genetic information. While adding genetic variants to the search database remains indispensable for correct peptide identification, inclusion of long-read RNA sequences in the search database contributes only 0.3% new peptide identifications. These findings reveal the differences in SAAV detection that result from various approaches, providing guidance to researchers studying SAAV peptides and developers of peptide spectrum identification tools.

Graph Convolutional Networks for Improved Prediction and Interpretability of Chromatographic Retention Data.

Machine learning is a popular technique to predict the retention times of molecules based on descriptors. Descriptors and associated labels (e.g., retention times) of a set of molecules can be used to train a machine learning algorithm. However, descriptors are fixed molecular features which are not necessarily optimized for the given machine learning problem (e.g., to predict retention times). Recent advances in molecular machine learning make use of so-called graph convolutional networks (GCNs) to learn molecular representations from atoms and their bonds to adjacent atoms to optimize the molecular representation for the given problem. In this study, two GCNs were implemented to predict the retention times of molecules for three different chromatographic data sets and compared to seven benchmarks (including two state-of-the art machine learning models). Additionally, saliency maps were computed from trained GCNs to better interpret the importance of certain molecular sub-structures in the data sets. Based on the overall observations of this study, the GCNs performed better than all benchmarks, either significantly outperforming them (5-25% lower mean absolute error) or performing similar to them (<5% difference). Saliency maps revealed a significant difference in molecular sub-structures that are important for predictions of different chromatographic data sets (reversed-phase liquid chromatography vs hydrophilic interaction liquid chromatography).

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.

Generalized Calibration Across Liquid Chromatography Setups for Generic Prediction of Small-Molecule Retention Times.

Accurate prediction of liquid chromatographic retention times from small-molecule structures is useful for reducing experimental measurements and for improved identification in targeted and untargeted MS. However, different experimental setups (e.g., differences in columns, gradients, solvents, or stationary phase) have given rise to a multitude of prediction models that only predict accurate retention times for a specific experimental setup. In practice this typically results in the fitting of a new predictive model for each specific type of setup, which is not only inefficient but also requires substantial prior data to be accumulated on each such setup. Here we introduce the concept of generalized calibration, which is capable of the straightforward mapping of retention time models between different experimental setups. This concept builds on the database-controlled calibration approach implemented in PredRet and fits calibration curves on predicted retention times instead of only on observed retention times. We show that this approach results in substantially higher accuracy of elution-peak prediction than is achieved by setup-specific models.

Accurate peptide fragmentation predictions allow data driven approaches to replace and improve upon proteomics search engine scoring functions.

MOTIVATION: The use of post-processing tools to maximize the information gained from a proteomics search engine is widely accepted and used by the community, with the most notable example being Percolator-a semi-supervised machine learning model which learns a new scoring function for a given dataset. The usage of such tools is however bound to the search engine's scoring scheme, which doesn't always make full use of the intensity information present in a spectrum. We aim to show how this tool can be applied in such a way that maximizes the use of spectrum intensity information by leveraging another machine learning-based tool, MS2PIP. MS2PIP predicts fragment ion peak intensities. RESULTS: We show how comparing predicted intensities to annotated experimental spectra by calculating direct similarity metrics provides enough information for a tool such as Percolator to accurately separate two classes of peptide-to-spectrum matches. This approach allows using more information out of the data (compared with simpler intensity based metrics, like peak counting or explained intensities summing) while maintaining control of statistics such as the false discovery rate. AVAILABILITY AND IMPLEMENTATION: All of the code is available online at https://github.com/compomics/ms2rescore. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Comprehensive and Empirical Evaluation of Machine Learning Algorithms for Small Molecule LC Retention Time Prediction.

Liquid chromatography is a core component of almost all mass spectrometric analyses of (bio)molecules. Because of the high-throughput nature of mass spectrometric analyses, the interpretation of these chromatographic data increasingly relies on informatics solutions that attempt to predict an analyte's retention time. The key components of such predictive algorithms are the features these are supplies with, and the actual machine learning algorithm used to fit the model parameters. Therefore, we have evaluated the performance of seven machine learning algorithms on 36 distinct metabolomics data sets, using two distinct feature sets. Interestingly, the results show that no single learning algorithm performs optimally for all data sets, with different types of algorithms achieving top performance for different types of analytes or different protocols. Our results thus show that an evaluation of machine learning algorithms for retention time prediction is needed to find a suitable algorithm for specific analytes or protocols. Importantly, however, our results also show that blending different types of models together decreases the error on outliers, indicating that the combination of several approaches holds substantial promise for the development of more generic, high-performing algorithms.

Bioinformatics Pipeline for Processing Single-Cell Data.

Single-cell proteomics can offer valuable insights into dynamic cellular interactions, but identifying proteins at this level is challenging due to their low abundance. In this chapter, we present a state-of-the-art bioinformatics pipeline for single-cell proteomics that combines the search engine Sage (via SearchGUI), identification rescoring with MS2Rescore, quantification through FlashLFQ, and differential expression analysis using MSqRob2. MS2Rescore leverages LC-MS/MS behavior predictors, such as MS2PIP and DeepLC, to recalibrate scores with Percolator or mokapot. Combining these tools into a unified pipeline, this approach improves the detection of low-abundance peptides, resulting in increased identifications while maintaining stringent FDR thresholds.