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

The PRIDE database at 20 years: 2025 update

The PRoteomics IDEntifications (PRIDE) database (https://www.ebi.ac.uk/pride/) is the world's leading mass spectrometry (MS)-based proteomics data repository and one of the founding members of the ProteomeXchange consortium. This manuscript summarizes the developments in PRIDE resources and related tools for the last three years. The number of submitted datasets to PRIDE Archive (the archival component of PRIDE) has reached on average around 534 datasets per month. This has been possible thanks to continuous improvements in infrastructure such as a new file transfer protocol for very large datasets (Globus), a new data resubmission pipeline and an automatic dataset validation process. Additionally, we will highlight novel activities such as the availability of the PRIDE chatbot (based on the use of open-source Large Language Models), and our work to improve support for MS crosslinking datasets. Furthermore, we will describe how we have increased our efforts to reuse, reanalyze and disseminate high-quality proteomics data into added-value resources such as UniProt, Ensembl and Expression Atlas.

Open-source large language models in action: A bioinformatics chatbot for PRIDE database

We here present a chatbot assistant infrastructure (https://www.ebi.ac.uk/pride/chatbot/) that simplifies user interactions with the PRIDE database's documentation and dataset search functionality. The framework utilizes multiple Large Language Models (LLM): llama2, chatglm, mixtral (mistral), and openhermes. It also includes a web service API (Application Programming Interface), web interface, and components for indexing and managing vector databases. An Elo-ranking system-based benchmark component is included in the framework as well, which allows for evaluating the performance of each LLM and for improving PRIDE documentation. The chatbot not only allows users to interact with PRIDE documentation but can also be used to search and find PRIDE datasets using an LLM-based recommendation system, enabling dataset discoverability. Importantly, while our infrastructure is exemplified through its application in the PRIDE database context, the modular and adaptable nature of our approach positions it as a valuable tool for improving user experiences across a spectrum of bioinformatics and proteomics tools and resources, among other domains. The integration of advanced LLMs, innovative vector-based construction, the benchmarking framework, and optimized documentation collectively form a robust and transferable chatbot assistant infrastructure. The framework is open-source (https://github.com/PRIDE-Archive/pride-chatbot).

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.

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.

Test-Time Training for Deep MS/MS Spectrum Prediction Improves Peptide Identification

In bottom-up proteomics, peptide-spectrum matching is critical for peptide and protein identification. Recently, deep learning models have been used to predict tandem mass spectra of peptides, enabling the calculation of similarity scores between the predicted and experimental spectra for peptide-spectrum matching. These models follow the supervised learning paradigm, which trains a general model using paired peptides and spectra from standard data sets and directly employs the model on experimental data. However, this approach can lead to inaccurate predictions due to differences between the training data and the experimental data, such as sample types, enzyme specificity, and instrument calibration. To tackle this problem, we developed a test-time training paradigm that adapts the pretrained model to generate experimental data-specific models, namely, PepT3. PepT3 yields a 10-40% increase in peptide identification depending on the variability in training and experimental data. Intriguingly, when applied to a patient-derived immunopeptidomic sample, PepT3 increases the identification of tumor-specific immunopeptide candidates by 60%. Two-thirds of the newly identified candidates are predicted to bind to the patient's human leukocyte antigen isoforms. To facilitate access of the model and all the results, we have archived all the intermediate files in Zenodo.org with identifier 8231084.

The role of clinical glyco(proteo)mics in precision medicine

Glycoproteomics reveals site-specific O- and N-glycosylation that may influence protein properties including binding, activity and half-life. The increasingly mature toolbox with glycomic- and glycoproteomic strategies is applied for the development of biopharmaceuticals and discovery and clinical evaluation of glycobiomarkers in various disease fields. Notwithstanding the contributions of glycoscience in identifying new drug targets, the current report is focused on the biomarker modality that is of interest for diagnostic and monitoring purposes. To this end it is noted that the identification of biomarkers has received more attention than corresponding quantification. Most analytical methods are very efficient in detecting large numbers of analytes but developments to accurately quantify these have so far been limited. In this perspective a parallel is made with earlier proposed tiers for protein quantification using mass spectrometry. Moreover, the foreseen reporting of multimarker readouts is discussed to describe an individual's health or disease state and their role in clinical decision-making. The potential of longitudinal sampling and monitoring of glycomic features for diagnosis and treatment monitoring is emphasized. Finally, different strategies that address quantification of a multimarker panel will be discussed.

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.

Variability analysis of LC-MS experimental factors and their impact on machine learning

BACKGROUND

Machine learning (ML) technologies, especially deep learning (DL), have gained increasing attention in predictive mass spectrometry (MS) for enhancing the data-processing pipeline from raw data analysis to end-user predictions and rescoring. ML models need large-scale datasets for training and repurposing, which can be obtained from a range of public data repositories. However, applying ML to public MS datasets on larger scales is challenging, as they vary widely in terms of data acquisition methods, biological systems, and experimental designs.

RESULTS

We aim to facilitate ML efforts in MS data by conducting a systematic analysis of the potential sources of variability in public MS repositories. We also examine how these factors affect ML performance and perform a comprehensive transfer learning to evaluate the benefits of current best practice methods in the field for transfer learning.

CONCLUSIONS

Our findings show significantly higher levels of homogeneity within a project than between projects, which indicates that it is important to construct datasets most closely resembling future test cases, as transferability is severely limited for unseen datasets. We also found that transfer learning, although it did increase model performance, did not increase model performance compared to a non-pretrained model.