Prosit Transformer: A transformer for Prediction of MS2 Spectrum Intensities

DeepMS: super-fast peptide identification using end-to-end deep learning method

Mass spectrometry (MS) has emerged as a powerful omics analysis technique, particularly in proteomics, where the initial step involves identifying MS spectra as peptide sequences. However, this process often requires substantial computational resources and expertise, taking hours or even days to complete, thereby limiting the widespread adoption of MS-based omics technologies. To overcome this challenge, we have developed DeepMS, a deep learning-based spectra identification algorithm that overcomes the speed limitations of traditional spectra identification methods. We conducted comprehensive benchmark tests, comparing six deep learning algorithms. Based on the results, we selected the VGG16 algorithm as the core model for DeepMS. This algorithm enables super-fast, end-to-end identification of peptide sequences from MS spectra with high accuracy. DeepMS is adaptable to post-translational modifications, enhancing its versatility. In fact, its identification speed surpasses the generation rate of MS spectra, enabling super-fast identification. Furthermore, we demonstrate the practical application of DeepMS in microorganism detection, highlighting its utility in clinical testing. Through the implementation of DeepMS, our aim is to revolutionize the field of MS-based proteomics and facilitate the broader application of omics technologies, opening new avenues for rapid and efficient analysis in various research and clinical domains.

Self-supervised learning of molecular representations from millions of tandem mass spectra using DreaMS

Characterizing biological and environmental samples at a molecular level primarily uses tandem mass spectroscopy (MS/MS), yet the interpretation of tandem mass spectra from untargeted metabolomics experiments remains a challenge. Existing computational methods for predictions from mass spectra rely on limited spectral libraries and on hard-coded human expertise. Here we introduce a transformer-based neural network pre-trained in a self-supervised way on millions of unannotated tandem mass spectra from our GNPS Experimental Mass Spectra (GeMS) dataset mined from the MassIVE GNPS repository. We show that pre-training our model to predict masked spectral peaks and chromatographic retention orders leads to the emergence of rich representations of molecular structures, which we named Deep Representations Empowering the Annotation of Mass Spectra (DreaMS). Further fine-tuning the neural network yields state-of-the-art performance across a variety of tasks. We make our new dataset and model available to the community and release the DreaMS Atlas-a molecular network of 201 million MS/MS spectra constructed using DreaMS annotations.

Peptide Property Prediction for Mass Spectrometry Using AI: An Introduction to State of the Art Models

This review explores state of the art machine learning and deep learning models for peptide property prediction in mass spectrometry-based proteomics, including, but not limited to, models for predicting digestibility, retention time, charge state distribution, collisional cross section, fragmentation ion intensities, and detectability. The combination of these models enables not only the in silico generation of spectral libraries but also finds many additional use cases in the design of targeted assays or data-driven rescoring. This review serves as both an introduction for newcomers and an update for experienced researchers aiming to develop accessible and reproducible models for peptide property predictions. Key limitations of the current models, including difficulties in handling diverse post-translational modifications and instrument variability, highlight the need for large-scale, harmonized datasets, and standardized evaluation metrics for benchmarking.

Enhanced Sample Multiplexing-Based Targeted Proteomics with Intelligent Data Acquisition

Targeted proteomics has been playing an increasingly important role in hypothesis-driven protein research and clinical biomarker discovery. We previously created a workflow, Tomahto, to enable real-time targeted pathway proteomics assays using two-dimensional multiplexing technology. Coupled with the TMT 11-plex reagent, hundreds of proteins of interest from up to 11 samples can be targeted and accurately quantified in a single-shot experiment with remarkable sensitivity. However, room remains to further improve the sensitivity, accuracy, and throughput, especially for targeted studies demanding a high peptide-level success rate. Here, bearing in mind the goal to improve peptide-level targeting, we introduce several new functionalities in Tomahto, featuring the integration of gas-phase fractionation using the FAIMS device, an accompanying software program (TomahtoPrimer) to customize fragmentation for each peptide target, and support for higher multiplexing capacity with the latest TMTpro reagent. We demonstrate that adding these features to the Tomahto platform significantly improves overall success rate from 89% to 98% in a single 60 min targeted assay of 290 peptides across human cell lines, while boosting quantitative accuracy via reducing TMT reporter ion interference.

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.

Alternative proteoforms and proteoform-dependent assemblies in humans and plants

The variability of proteins at the sequence level creates an enormous potential for proteome complexity. Exploring the depths and limits of this complexity is an ongoing goal in biology. Here, we systematically survey human and plant high-throughput bottom-up native proteomics data for protein truncation variants, where substantial regions of the full-length protein are missing from an observed protein product. In humans, Arabidopsis, and the green alga Chlamydomonas, approximately one percent of observed proteins show a short form, which we can assign by comparison to RNA isoforms as either likely deriving from transcript-directed processes or limited proteolysis. While some detected protein fragments align with known splice forms and protein cleavage events, multiple examples are previously undescribed, such as our observation of fibrocystin proteolysis and nuclear translocation in a green alga. We find that truncations occur almost entirely between structured protein domains, even when short forms are derived from transcript variants. Intriguingly, multiple endogenous protein truncations of phase-separating translational proteins resemble cleaved proteoforms produced by enteroviruses during infection. Some truncated proteins are also observed in both humans and plants, suggesting that they date to the last eukaryotic common ancestor. Finally, we describe novel proteoform-specific protein complexes, where the loss of a domain may accompany complex formation.

Recent Developments in Machine Learning for Mass Spectrometry

Statistical analysis and modeling of mass spectrometry (MS) data have a long and rich history with several modern MS-based applications using statistical and chemometric methods. Recently, machine learning (ML) has experienced a renaissance due to advents in computational hardware and the development of new algorithms for artificial neural networks (ANN) and deep learning architectures. Moreover, recent successes of new ANN and deep learning architectures in several areas of science, engineering, and society have further strengthened the ML field. Importantly, modern ML methods and architectures have enabled new approaches for tasks related to MS that are now widely adopted in several popular MS-based subdisciplines, such as mass spectrometry imaging and proteomics. Herein, we aim to provide an introductory summary of the practical aspects of ML methodology relevant to MS. Additionally, we seek to provide an up-to-date review of the most recent developments in ML integration with MS-based techniques while also providing critical insights into the future direction of the field.

Systematic Assessment of Deep Learning-Based Predictors of Fragmentation Intensity Profiles

In recent years, several deep learning-based methods have been proposed for predicting peptide fragment intensities. This study aims to provide a comprehensive assessment of six such methods, namely Prosit, DeepMass:Prism, pDeep3, AlphaPeptDeep, Prosit Transformer, and the method proposed by Guan et al. To this end, we evaluated the accuracy of the predicted intensity profiles for close to 1.7 million precursors (including both tryptic and HLA peptides) corresponding to more than 18 million experimental spectra procured from 40 independent submissions to the PRIDE repository that were acquired for different species using a variety of instruments and different dissociation types/energies. Specifically, for each method, distributions of similarity (measured by Pearson's correlation and normalized angle) between the predicted and the corresponding experimental b and y fragment intensities were generated. These distributions were used to ascertain the prediction accuracy and rank the prediction methods for particular types of experimental conditions. The effect of variables like precursor charge, length, and collision energy on the prediction accuracy was also investigated. In addition to prediction accuracy, the methods were evaluated in terms of prediction speed. The systematic assessment of these six methods may help in choosing the right method for MS/MS spectra prediction for particular needs.

Machine learning-based peptide-spectrum match rescoring opens up the immunopeptidome

Immunopeptidomics is a key technology in the discovery of targets for immunotherapy and vaccine development. However, identifying immunopeptides remains challenging due to their non-tryptic nature, which results in distinct spectral characteristics. Moreover, the absence of strict digestion rules leads to extensive search spaces, further amplified by the incorporation of somatic mutations, pathogen genomes, unannotated open reading frames, and post-translational modifications. This inflation in search space leads to an increase in random high-scoring matches, resulting in fewer identifications at a given false discovery rate. Peptide-spectrum match rescoring has emerged as a machine learning-based solution to address challenges in mass spectrometry-based immunopeptidomics data analysis. It involves post-processing unfiltered spectrum annotations to better distinguish between correct and incorrect peptide-spectrum matches. Recently, features based on predicted peptidoform properties, including fragment ion intensities, retention time, and collisional cross section, have been used to improve the accuracy and sensitivity of immunopeptide identification. In this review, we describe the diverse bioinformatics pipelines that are currently available for peptide-spectrum match rescoring and discuss how they can be used for the analysis of immunopeptidomics data. Finally, we provide insights into current and future machine learning solutions to boost immunopeptide identification.

Leveraging transformers-based language models in proteome bioinformatics

In recent years, the rapid growth of biological data has increased interest in using bioinformatics to analyze and interpret this data. Proteomics, which studies the structure, function, and interactions of proteins, is a crucial area of bioinformatics. Using natural language processing (NLP) techniques in proteomics is an emerging field that combines machine learning and text mining to analyze biological data. Recently, transformer-based NLP models have gained significant attention for their ability to process variable-length input sequences in parallel, using self-attention mechanisms to capture long-range dependencies. In this review paper, we discuss the recent advancements in transformer-based NLP models in proteome bioinformatics and examine their advantages, limitations, and potential applications to improve the accuracy and efficiency of various tasks. Additionally, we highlight the challenges and future directions of using these models in proteome bioinformatics research. Overall, this review provides valuable insights into the potential of transformer-based NLP models to revolutionize proteome bioinformatics.

AIomics: Exploring More of the Proteome Using Mass Spectral Libraries Extended by Artificial Intelligence

The unbounded permutations of biological molecules, including proteins and their constituent peptides, present a dilemma in identifying the components of complex biosamples. Sequence search algorithms used to identify peptide spectra can be expanded to cover larger classes of molecules, including more modifications, isoforms, and atypical cleavage, but at the cost of false positives or false negatives due to the simplified spectra they compute from sequence records. Spectral library searching can help solve this issue by precisely matching experimental spectra to library spectra with excellent sensitivity and specificity. However, compiling spectral libraries that span entire proteomes is pragmatically difficult. Neural networks that predict complete spectra containing a full range of annotated and unannotated ions can be used to replace these simplified spectra with libraries of fully predicted spectra, including modified peptides. Using such a network, we created predicted spectral libraries that were used to rescore matches from a sequence search done over a large search space, including a large number of modifications. Rescoring improved the separation of true and false hits by 82%, yielding an 8% increase in peptide identifications, including a 21% increase in nonspecifically cleaved peptides and a 17% increase in phosphopeptides.

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.

Peptidomics Methods Applied to the Study of Flower Development

Understanding the global and dynamic nature of plant developmental processes requires not only the study of the transcriptome, but also of the proteome, including its largely uncharacterized peptidome fraction. Recent advances in proteomics and high-throughput analyses of translating RNAs (ribosome profiling) have begun to address this issue, evidencing the existence of novel, uncharacterized, and possibly functional peptides. To validate the accumulation in tissues of sORF-encoded polypeptides (SEPs), the basic setup of proteomic analyses (i.e., LC-MS/MS) can be followed. However, the detection of peptides that are small (up to ~100 aa, 6-7 kDa) and novel (i.e., not annotated in reference databases) presents specific challenges that need to be addressed both experimentally and with computational biology resources. Several methods have been developed in recent years to isolate and identify peptides from plant tissues. In this chapter, we outline two different peptide extraction protocols and the subsequent peptide identification by mass spectrometry using the database search or the de novo identification methods.

AlphaPeptDeep: a modular deep learning framework to predict peptide properties for proteomics

Machine learning and in particular deep learning (DL) are increasingly important in mass spectrometry (MS)-based proteomics. Recent DL models can predict the retention time, ion mobility and fragment intensities of a peptide just from the amino acid sequence with good accuracy. However, DL is a very rapidly developing field with new neural network architectures frequently appearing, which are challenging to incorporate for proteomics researchers. Here we introduce AlphaPeptDeep, a modular Python framework built on the PyTorch DL library that learns and predicts the properties of peptides ( https://github.com/MannLabs/alphapeptdeep ). It features a model shop that enables non-specialists to create models in just a few lines of code. AlphaPeptDeep represents post-translational modifications in a generic manner, even if only the chemical composition is known. Extensive use of transfer learning obviates the need for large data sets to refine models for particular experimental conditions. The AlphaPeptDeep models for predicting retention time, collisional cross sections and fragment intensities are at least on par with existing tools. Additional sequence-based properties can also be predicted by AlphaPeptDeep, as demonstrated with a HLA peptide prediction model to improve HLA peptide identification for data-independent acquisition ( https://github.com/MannLabs/PeptDeep-HLA ).