Biology subjects

Nayar, G.

Publications and source records attributed to Nayar, G..

11 recordsLinked to original sources

bioRxiv2026

Homology-Based Variant-Effect Predictors Break Down on Cytochrome P450 Pharmacogenes

Cytochrome P450 (CYP) enzymes metabolize roughly three-quarters of clinically used drugs; genetic variation in these enzymes is a leading source of interindividual differences in drug response. Predicting a variants functional effect is therefore critical, yet the consequences of most CYP variants remain unknown. Many state-of-the-art variant-effect predictors rest on a homology-based paradigm that scores variants by evolutionary conservation -- an assumption that pharmacogenes including CYPs violate. Indeed, focusing on human CYPs, we show that homology-based models fail systematically. AlphaMissense (AM) assigns variants to its "ambiguous" class at nearly twice the proteome-wide rate across six CYPs, and within that class the scores are essentially uncorrelated with CYP2C9 DMS activity (Spearmans{rho} = 0.069); Evolutionary Scale Modeling 2 (ESM-2) shows the same pattern. We further hypothesized that non-homology-based features (sequence position, substitution chemistry, binding-site distance, and secondary structure) might help resolve the ambiguous calls, but their explanatory power is weak. Using CYP2C9 DMS activity as ground truth, we built a k-nearest-neighbors model over ESM-2 embeddings and ensembled it with AM and ESM-2 masked marginal probability, improving the ambiguous-class correlation roughly ten-fold, from{rho} = 0.069 to 0.715 (overall{rho} from 0.638 to 0.825). However, this markedly improved accuracy does not translate into agreement with clinical annotations. Drawing on evidence that a variants effect can depend on the drug, we hypothesize that substrate identity is the key missing feature in current models, and that predicting function for these multi-substrate enzymes may require redefining function as substrate-conditioned.

bioinformatics↗

bioRxiv2026

Interpreting Protein Language Models: high attention sites predict functional regions

Computational proteomics has revolutionized biomedical research, guiding targeted experimental exploration to accelerate protein-based mechanistic discovery. Protein Language Models (PLMs) enable scalable, resource-efficient study; through large-scale training on only primary protein sequences, PLMs generate vector representations of protein structure that have been shown to capture biochemical, evolutionary, and structural properties. A core component of PLMs is the attention mechanism, which specifically captures long-range interactions across a protein sequence in attention matrices. Using the Evolutionary Scale Modelling 2 (ESM-2) PLM, we previously developed a novel method to identify "High Attention" (HA) sites. HA sites are specific residues that ESM-2 assigns the most attention to early during encoding. Here, we further characterize these HA sites across structural and functional metrics. Using unsupervised clustering, we find HA sites can be categorized as "structural core", "structural pathogenic", "core pathogenic", or "low-confidence". We further use AlphaMissense pathogenicity predictions and the pan-cancer analysis of whole genomes (PCAWG)-labeled pathogenic variant positions to show that HA sites predict protein regions with high pathogenic risk. Finally, we explore the utility of HA sites for suggesting candidate binding sites, identifying multiple cancer protein examples where HA sites identified regions with previously undiscovered high interaction likelihood and thus potential therapeutic utility. Our work demonstrates the biological interpretability of PLM representations and offers a valuable method to prioritize functionally relevant protein residues for targeted biomedical research.

bioinformatics↗

bioRxiv2026

GATSBI: Improving context-aware protein embeddingsthrough biologically motivated data splits

MotivationUnderstanding protein function requires integrating diverse biological evidence while accounting for strong contextual dependence. Recent protein embedding methods increasingly leverage heterogeneous biological networks, yet their evaluation protocols often fail to reflect the specific biological tasks for which the embeddings are intended. Prediction of missing interactions, annotation of new proteins, and discovery of functional modules require fundamentally different data partitions, such as edge-masked versus node-held-out splits. Moreover, most approaches report performance primarily on well-studied proteins, where computational predictions are least needed, risking substantial overestimation of real-world utility. ResultsWe introduce a graph attention-based framework (Gatsbi) to construct context-aware protein embeddings from integrated protein-protein interactions, co-expression, sequence representations, and tissue-specific associations. Using task-aligned evaluation protocols, we show that models trained with biologically appropriate partitions achieve markedly better generalization. Across interaction, function, and functional set prediction, Gatsbi consistently outperforms existing pretrained embeddings for both well-studied and understudied proteins, with the largest gains observed for the understudied regime and under inductive node-held-out evaluation. To enable broad reuse, we provide the learned embeddings for download for application to other protein prediction tasks. Availability and Implementationhttps://github.com/Helix-Research-Lab/GATSBI-embedding

bioinformatics↗

bioRxiv2025

Exposing the Molecular Reaction Blind Spots of LLMs with PathwayQA

Proteins mediate a large portion of cellular activity, and understanding protein pathways can yield novel biological insights. Large language models (LLMs) have become increasingly adept at performing inference tasks across different fields of science and engineering. These models could facilitate the analysis of protein networks and help generate hypotheses about protein interactions in a scalable and accessible manner. However, the performance of LLMs in inferring protein-mediated biochemical reactions remains understudied. Here, we evaluate nine LLMs in reasoning over protein pathways included in the curated Reactome database. We find that all nine models struggle to infer products of a reaction when given reactants and enzymes. GPT-4o mini performed the best with a median recovery score of 0.6667, but no model surpassed the baseline strategy of parroting reactants back as predicted products. Most LLMs also performed poorly when inferring whether a protein pathway is associated with a human disease, with an average accuracy of 0.5980. DeepSeek 7B Chat performed the best with an accuracy of 0.9100. This study highlights an area where LLMs still struggle to make correct inferences and provides an opportunity for further work in developing biological LLMs. We also provide a novel question-answer dataset, PathwayQA, which is based on the Reactome database. PathwayQA can be used to benchmark and improve model performance on reasoning over protein-interaction networks. PathwayQA is available at https://github.com/Helix-Research-Lab/PathwayQA.

bioinformatics↗

bioRxiv2024

Paying Attention to Attention: High Attention Sites as Indicators of Protein Family and Function in Language Models

Protein Language Models (PLMs) use transformer architectures to capture patterns within protein sequences, providing a powerful computational representation of the protein sequence [1]. Through large-scale training on protein sequence data, PLMs generate vector representations that encapsulate the biochemical and structural properties of proteins [2]. At the core of PLMs is the attention mechanism, which facilitates the capture of long-range dependencies by computing pairwise importance scores across residues, thereby highlighting regions of biological interaction within the sequence [3]. The attention matrices offer an untapped opportunity to uncover specific biological properties of proteins, particularly their functions. In this work, we introduce a novel approach, using the Evolutionary Scale Model (ESM) [4], for identifying High Attention (HA) sites within protein sequences, corresponding to key residues that define protein families. By examining attention patterns across multiple layers, we pinpoint residues that contribute most to family classification and function prediction. Our contributions are as follows: (1) we propose a method for identifying HA sites at critical residues from the middle layers of the PLM; (2) we demonstrate that these HA sites provide interpretable links to biological functions; and (3) we show that HA sites improve active site predictions for functions of unannotated proteins. We make available the HA sites for the human proteome. This work offers a broadly applicable approach to protein classification and functional annotation and provides a biological interpretation of the PLMs representation. 1 Author SummaryUnderstanding how proteins work is critical to advancements in biology and medicine, and protein language models (PLMs) facilitate studying protein sequences at scale. These models identify patterns within protein sequences by focusing on key regions of the sequence that are important to distinguish the protein. Our work focuses on the Evolutionary Scale Model (ESM), a state-of-the-art PLM, and we analyze the models internal attention mechanism to identify the significant residues. We developed a new method to identify "High Attention (HA)" sites--specific parts of a protein sequence that are essential for classifying proteins into families and predicting their functions. By analyzing how the model prioritizes certain regions of protein sequences, we discovered that these HA sites often correspond to residues critical for biological activity, such as active sites where chemical reactions occur. Our approach helps interpret how PLMs understand protein data and enhances predictions for proteins whose functions are still unknown. As part of this work, we provide HA-site information for the entire human proteome, offering researchers a resource to further study the potential functional relevance of these residues.

bioinformatics↗

bioRxiv2024

Pool PaRTI: A PageRank-based Pooling Method for Robust Protein Sequence Representation in Deep Learning

MotivationProtein language models produce token-level embeddings for each residue, resulting in an output matrix with dimensions that vary based on sequence length. However, downstream machine learning models typically require fixed-length input vectors, necessitating a pooling method to compress the output matrix into a single vector representation of the entire protein. Traditional pooling methods often result in substantial information loss, impacting downstream task performance. We aim to develop a pooling method that produces more expressive general-purpose protein embedding vectors while offering biological interpretability. ResultsWe introduce Pool PaRTI, a novel pooling method that leverages internal transformer attention matrices and PageRank to assign token importance weights. Our unsupervised and parameter-free approach consistently prioritizes residues experimentally annotated as critical for function, assigning them higher importance scores. Across four diverse protein machine learning tasks, Pool PaRTI enables significant performance gains in predictive performance. Additionally, it enhances interpretability by identifying biologically relevant regions without relying on explicit structural data or annotated training. To assess generalizability, we evaluated Pool PaRTI with two encoder-only protein language models, confirming its robustness across different models. Availability and ImplementationPool PaRTI is implemented in Python with PyTorch and is available at https://github.com/Helix-Research-Lab/Pool_PaRTI.git. The Pool PaRTI sequence embeddings and residue importance values for all human proteins on UniProt are available at https://zenodo.org/records/15036725 for ESM2 and protBERT.

bioinformatics↗

bioRxiv2022

Predicting Epitope Candidates for SARS-CoV-2

Epitopes are short amino acid sequences that define the antigen signature to which an antibody binds. In light of the current pandemic, epitope analysis and prediction is paramount to improving serological testing and developing vaccines. In this paper, we leverage known epitope sequences from SARS-CoV, SARS-CoV-2 and other Coronaviridae and use those known epitopes to identify additional antigen regions in 62k SARS-CoV-2 genomes. Additionally, we present epitope distribution across SARS-CoV-2 genomes, locate the most commonly found epitopes, discuss where epitopes are located on proteins, and how epitopes can be grouped into classes. We also discuss the mutation density of different regions on proteins using a big data approach. We find that there are many conserved epitopes between SARS-CoV-2 and SARS-CoV, with more diverse sequences found in Nucleoprotein and Spike Glycoprotein.

bioinformatics↗

bioRxiv2021

Semi-supervised identification of SARS-CoV-2 molecular targets

SARS-CoV-2 genomic sequencing efforts have scaled dramatically to address the current global pandemic and aid public health. In this work, we analyzed a corpus of 66,000 SARS-CoV-2 genome sequences. We developed a novel semi-supervised pipeline for automated gene, protein, and functional domain annotation of SARS-CoV-2 genomes that differentiates itself by not relying on use of a single reference genome and by overcoming atypical genome traits. Using this method, we identified the comprehensive set of known proteins with 98.5% set membership accuracy and 99.1% accuracy in length prediction compared to proteome references including Replicase polyprotein 1ab (with its transcriptional slippage site). Compared to other published tools such as Prokka (base) and VAPiD, we yielded an 6.4- and 1.8-fold increase in protein annotations. Our method generated 13,000,000 molecular target sequences-- some conserved across time and geography while others represent emerging variants. We observed 3,362 non-redundant sequences per protein on average within this corpus and describe key D614G and N501Y variants spatiotemporally. For spike glycoprotein domains, we achieved greater than 97.9% sequence identity to references and characterized Receptor Binding Domain variants. Here, we comprehensively present the molecular targets to refine biomedical interventions for SARS-CoV-2 with a scalable high-accuracy method to analyze newly sequenced infections.

bioinformatics↗

bioRxiv2020

Analysis and Forecasting of Global of RT-PCR Primers for SARS-CoV-2

Rapid tests for active SARS-CoV-2 infections rely on reverse transcription polymerase chain reaction (RT-PCR). RT-PCR uses reverse transcription of RNA into complementary DNA (cDNA) and amplification of specific DNA (primer and probe) targets using polymerase chain reaction (PCR). The technology makes rapid and specific identification of the virus possible based on sequence homology of nucleic acid sequence and is much faster than tissue culture or animal cell models. However the technique can lose sensitivity over time as the virus evolves and the target sequences diverge from the selective primer sequences. Different primer sequences have been adopted in different geographic regions. As we rely on these existing RT-PCR primers to track and manage the spread of the Coronavirus, it is imperative to understand how SARS-CoV-2 mutations, over time and geographically, diverge from existing primers used today. In this study, we analyze the performance of the SARS-CoV-2 primers in use today by measuring the number of mismatches between primer sequence and genome targets over time and spatially. We find that there is a growing number of mismatches, an increase by 2% per month, as well as a high specificity of virus based on geographic location.

bioinformatics↗

bioRxiv2020

Integrative and Conjugative Elements (ICE) and Associated Cargo Genes within and across Hundreds of Bacterial Genera

Horizontal gene transfer mediated by integrative and conjugative elements (ICE) is considered an important evolutionary mechanism of bacteria. It allows organisms to quickly evolve new phenotypic properties including antimicrobial resistance (AMR) and virulence. The rate of ICE-mediated cargo gene exchange has not yet been comprehensively studied within and between bacterial taxa. In this paper we report a big data analysis of ICE and associated cargo genes across over 200,000 bacterial genomes representing 1,345 genera. Our results reveal that half of bacterial genomes contain one or more known ICE features ("ICE genomes"), and that the associated genetic cargo may play an important role in the spread of AMR genes within and between bacterial genera. We identify 43 AMR genes that appear only in ICE genomes and never in non-ICE genomes. A further set of 95 AMR genes are found >5x more often in ICE versus non-ICE genomes. In contrast, only 29 AMR genes are observed more frequently (at least 5:1) in non-ICE genomes compared to ICE genomes. Analysis of NCBI antibiotic susceptibility assay data reveals that ICE genomes are also over-represented amongst phenotypically resistant isolates, suggesting that ICE processes are critical for both genotypic and phenotypic AMR. These results, as well as the underlying big data resource, are important foundational tools for understanding bacterial evolution, particularly in relation to important bacterial phenotypes such as AMR.

microbiology↗

bioRxiv2019

Survey of Public Assay Data: Opportunities and Challenges to Understanding Antimicrobial Resistance

ABSTRACTComputational learning methods allow researchers to make predictions, draw inferences, and automate generation of mathematical models. These models are crucial to solving real world problems, such as antimicrobial resistance, pathogen detection, and protein evolution. Machine learning methods depend upon ground truth data to achieve specificity and sensitivity. Since the data is limited in this case, as we will show during the course of this paper, and as the size of available data increases super-linearly, it is of paramount importance to understand the distribution of ground truth data and the analyses it is suited and where it may have limitations that bias downstream learning methods. In this paper, we focus on training data required to model antimicrobial resistance (AR). We report an analysis of bacterial biochemical assay data associated with whole genome sequencing (WGS) from the National Center for Biotechnology Information (NCBI), and discuss important implications when making use of assay data, utilizing genetic features as training data for machine learning models. Complete discussion of machine learning model implementation is outside the scope of this paper and the subject to a later publication. The antimicrobial assay data was obtained from NCBI BioSample, which contains descriptive information about the physical biological specimen from which experimental data is obtained and the results of those experiments themselves.[1] Assay data includes minimum inhibitory concentrations (MIC) of antibiotics, links to associated microbial WGS data, and treatment of a particular microorganism with antibiotics. We observe that there is minimal microbial data available for many antibiotics and for targeted taxonomic groups. The antibiotics with the highest number of assays have less than 1500 measurements each. Corresponding bias in available assays makes machine learning problematic for some important microbes and for building more advanced models that can work across microbial genera. In this study we focus, therefore, on the antibiotic with most assay data (tetracycline) and the corresponding genus with the most available sequence (Acinetobacter with 14000 measurements across 49 antibiotic compounds). Using this data for training and testing, we observed contradictions in the distribution of assay outcomes and report methods to identify and resolve such conflicts. Per antibiotic, we find that there can be up to 30% of (resolvable) conflicting measurements. As more data becomes available, automated training data curation will be an important part of creating useful machine learning models to predict antibiotic resistance. CCS CONCEPTS* Applied computing [->] Computational biology; Computational genomics; Bioinformatics;

bioinformatics↗