Search for: All records

Tandem mass spectrometry (MS/MS) is crucial for small-molecule analysis; however, traditional computational methods are limited by incomplete reference libraries and complex data processing. Machine learning (ML) is transforming small-molecule mass spectrometry in three key directions: (a) predicting MS/MS spectra and related physicochemical properties to expand reference libraries, (b) improving spectral matching through automated pattern extraction, and (c) predicting molecular structures of compounds directly from their MS/MS spectra. We review ML approaches for molecular representations [descriptors, simplified molecular-input line-entry (SMILE) strings, and graphs] and MS/MS spectra representations (using binned vectors and peak lists) along with recent advances in spectra prediction, retention time, collision cross sections, and spectral matching. Finally, we discuss ML-integrated workflows for chemical formula identification. By addressing the limitations of current methods for compound identification, these ML approaches can greatly enhance the understanding of biological processes and the development of diagnostic and therapeutic tools. 

Recently developed protein language models have enabled a variety of applications with the protein contextual embeddings they produce. Per-protein representations (each protein is represented as a vector of fixed dimension) can be derived via averaging the embeddings of individual residues, or applying matrix transformation techniques such as the discrete cosine transformation (DCT) to matrices of residue embeddings. Such protein-level embeddings have been applied to enable fast searches of similar proteins; however, limitations have been found; for example, PROST is good at detecting global homologs but not local homologs, and knnProtT5 excels for proteins with single domains but not multidomain proteins. Here, we propose a novel approach that first segments proteins into domains (or subdomains) and then applies the DCT to the vectorized embeddings of residues in each domain to infer domain-level contextual vectors. Our approach, called DCTdomain, uses predicted contact maps from ESM-2 for domain segmentation, which is formulated as adomain segmentationproblem and can be solved using arecursive cutalgorithm (RecCut in short) in quadratic time to the protein length; for comparison, an existing approach for domain segmentation uses a cubic-time algorithm. We show such domain-level contextual vectors (termed asDCT fingerprints) enable fast and accurate detection of similarity between proteins that share global similarities but with undefined extended regions between shared domains, and those that only share local similarities. In addition, tests on a database search benchmark show that the DCTdomain is able to detect distant homologs by leveraging the structural information in the contextual embeddings. 

Abstract MotivationTandem mass spectrometry (MS/MS) is a crucial technology for large-scale proteomic analysis. The protein database search or the spectral library search are commonly used for peptide identification from MS/MS spectra, which, however, may face challenges due to experimental variations between replicated spectra and similar fragmentation patterns among distinct peptides. To address this challenge, we present SpecEncoder, a deep metric learning approach to address these challenges by transforming MS/MS spectra into robust and sensitive embedding vectors in a latent space. The SpecEncoder model can also embed predicted MS/MS spectra of peptides, enabling a hybrid search approach that combines spectral library and protein database searches for peptide identification. ResultsWe evaluated SpecEncoder on three large human proteomics datasets, and the results showed a consistent improvement in peptide identification. For spectral library search, SpecEncoder identifies 1%–2% more unique peptides (and PSMs) than SpectraST. For protein database search, it identifies 6%–15% more unique peptides than MSGF+ enhanced by Percolator, Furthermore, SpecEncoder identified 6%–12% additional unique peptides when utilizing a combined library of experimental and predicted spectra. SpecEncoder can also identify more peptides when compared to deep-learning enhanced methods (MSFragger boosted by MSBooster). These results demonstrate SpecEncoder’s potential to enhance peptide identification for proteomic data analyses. Availability and ImplementationThe source code and scripts for SpecEncoder and peptide identification are available on GitHub at https://github.com/lkytal/SpecEncoder. Contact: hatang@iu.edu. 

Abstract De novo peptide sequencing, which does not rely on a comprehensive target sequence database, provides us with a way to identify novel peptides from tandem mass spectra. However, current de novo sequencing algorithms suffer from low accuracy and coverage, which hinders their application in proteomics. In this paper, we presentPepNet, a fully convolutional neural network for high accuracy de novo peptide sequencing. PepNet takes an MS/MS spectrum (represented as a high-dimensional vector) as input, and outputs the optimal peptide sequence along with its confidence score. The PepNet model is trained using a total of 3 million high-energy collisional dissociation MS/MS spectra from multiple human peptide spectral libraries. Evaluation results show that PepNet significantly outperforms current best-performing de novo sequencing algorithms (e.g. PointNovo and DeepNovo) in both peptide-level accuracy and positional-level accuracy. PepNet can sequence a large fraction of spectra that were not identified by database search engines, and thus could be used as a complementary tool to database search engines for peptide identification in proteomics. In addition, PepNet runs around 3x and 7x faster than PointNovo and DeepNovo on GPUs, respectively, thus being more suitable for the analysis of large-scale proteomics data. 

Abstract MotivationTandem mass spectrometry is an essential technology for characterizing chemical compounds at high sensitivity and throughput, and is commonly adopted in many fields. However, computational methods for automated compound identification from their MS/MS spectra are still limited, especially for novel compounds that have not been previously characterized. In recent years, in silico methods were proposed to predict the MS/MS spectra of compounds, which can then be used to expand the reference spectral libraries for compound identification. However, these methods did not consider the compounds’ 3D conformations, and thus neglected critical structural information. ResultsWe present the 3D Molecular Network for Mass Spectra Prediction (3DMolMS), a deep neural network model to predict the MS/MS spectra of compounds from their 3D conformations. We evaluated the model on the experimental spectra collected in several spectral libraries. The results showed that 3DMolMS predicted the spectra with the average cosine similarity of 0.691 and 0.478 with the experimental MS/MS spectra acquired in positive and negative ion modes, respectively. Furthermore, 3DMolMS model can be generalized to the prediction of MS/MS spectra acquired by different labs on different instruments through minor fine-tuning on a small set of spectra. Finally, we demonstrate that the molecular representation learned by 3DMolMS from MS/MS spectra prediction can be adapted to enhance the prediction of chemical properties such as the elution time in the liquid chromatography and the collisional cross section measured by ion mobility spectrometry, both of which are often used to improve compound identification. Availability and implementationThe codes of 3DMolMS are available at https://github.com/JosieHong/3DMolMS and the web service is at https://spectrumprediction.gnps2.org. 

Host-microbiome interactions and the microbial community have broad impact in human health and diseases. Most microbiome based studies are performed at the genome level based on next-generation sequencing techniques, but metaproteomics is emerging as a powerful technique to study microbiome functional activity by characterizing the complex and dynamic composition of microbial proteins. We conducted a large-scale survey of human gut microbiome metaproteomic data to identify generalist species that are ubiquitously expressed across all samples and specialists that are highly expressed in a small subset of samples associated with a certain phenotype. We were able to utilize the metaproteomic mass spectrometry data to reveal the protein landscapes of these species, which enables the characterization of the expression levels of proteins of different functions and underlying regulatory mechanisms, such as operons. Finally, we were able to recover a large number of open reading frames (ORFs) with spectral support, which were missed by de novo protein-coding gene predictors. We showed that a majority of the rescued ORFs overlapped with de novo predicted protein-coding genes, but on opposite strands or in different frames. Together, these demonstrate applications of metaproteomics for the characterization of important gut bacterial species. 

Abstract Background A few recent large efforts significantly expanded the collection of human-associated bacterial genomes, which now contains thousands of entities including reference complete/draft genomes and metagenome assembled genomes (MAGs). These genomes provide useful resource for studying the functionality of the human-associated microbiome and their relationship with human health and diseases. One application of these genomes is to provide a universal reference for database search in metaproteomic studies, when matched metagenomic/metatranscriptomic data are unavailable. However, a greater collection of reference genomes may not necessarily result in better peptide/protein identification because the increase of search space often leads to fewer spectrum-peptide matches, not to mention the drastic increase of computation time. Methods Here, we present a new approach that uses two steps to optimize the use of the reference genomes and MAGs as the universal reference for human gut metaproteomic MS/MS data analysis. The first step is to use only the high-abundance proteins (HAPs) (i.e., ribosomal proteins and elongation factors) for metaproteomic MS/MS database search and, based on the identification results, to derive the taxonomic composition of the underlying microbial community. The second step is to expand the search database by including all proteins from identified abundant species. We call our approach HAPiID (HAPs guided metaproteomics IDentification). Results We tested our approach using human gut metaproteomic datasets from a previous study and compared it to the state-of-the-art reference database search method MetaPro-IQ for metaproteomic identification in studying human gut microbiota. Our results show that our two-steps method not only performed significantly faster but also was able to identify more peptides. We further demonstrated the application of HAPiID to revealing protein profiles of individual human-associated bacterial species, one or a few species at a time, using metaproteomic data. Conclusions The HAP guided profiling approach presents a novel effective way for constructing target database for metaproteomic data analysis. The HAPiID pipeline built upon this approach provides a universal tool for analyzing human gut-associated metaproteomic data. 

Microbial community members exhibit various forms of interactions. Taking advantage of the increasing availability of microbiome data, many computational approaches have been developed to infer bacterial interactions from the co-occurrence of microbes across diverse microbial communities. Additionally, the introduction of genome-scale metabolic models have also enabled the inference of cooperative and competitive metabolic interactions between bacterial species. By nature, phylogenetically similar microbial species are more likely to share common functional profiles or biological pathways due to their genomic similarity. Without properly factoring out the phylogenetic relationship, any estimation of the competition and cooperation between species based on functional/pathway profiles may bias downstream applications. To address these challenges, we developed a novel approach for estimating the competition and complementarity indices for a pair of microbial species, adjusted by their phylogenetic distance. An automated pipeline, PhyloMint, was implemented to construct competition and complementarity indices from genome scale metabolic models derived from microbial genomes. Application of our pipeline to 2,815 human-gut associated bacteria showed high correlation between phylogenetic distance and metabolic competition/cooperation indices among bacteria. Using a discretization approach, we were able to detect pairs of bacterial species with cooperation scores significantly higher than the average pairs of bacterial species with similar phylogenetic distances. A network community analysis of high metabolic cooperation but low competition reveals distinct modules of bacterial interactions. Our results suggest that niche differentiation plays a dominant role in microbial interactions, while habitat filtering also plays a role among certain clades of bacterial species.