Biology subjects

Venkat, A.

Publications and source records attributed to Venkat, A..

At least 19 recordsLinked to original sources

bioRxiv2026

Glydentify: An explainable deep learning platform for glycosyltransferase donor substrate prediction

Glycosyltransferases (GTs) are a large family of enzymes that catalyze glycosidic linkages formation between chemically diverse donor and acceptor molecules to regulate diverse cellular processes across all domains of life. Despite their importance, the activated sugar donors (donor substrates) used by most GTs remain unidentified, limiting our understanding of GT functions. To address this challenge, we developed Glydentify, a deep learning framework that predicts donor usage across GT-A and GT-B fold glycosyltransferases. Trained on large-scale UniProt annotations, Glydentify integrates protein sequence embeddings learned from protein language models with chemical features derived from molecular encoders trained on extensive chemical datasets. The resulting models achieve high predictive performance, with precision-recall AUCs (PR-AUC) of 0.86 for GT-A and 0.91 for GT-B, surpassing general enzyme-substrate predictors while requiring minimal manual curation. We employed Glydentify to predict the donor specificity of uncharacterized plant GTs and experimentally tested the predictions using in vitro biochemical assays. Furthermore, we demonstrate that the model utilizes a combination of evolutionary, structural, and biochemical features to predict donor specificity through residue attention score analysis. Together, these results establish Glydentify as a robust, explainable framework for decoding donor-glycosyltransferase relationships and highlight its potential as a broadly applicable framework for modeling enzyme classes that act on chemically diverse substrates.

bioinformatics↗

bioRxiv2025

Query Augmented Generation (QAG) from the Genomic DataCommons for Accurate Variant Statistics

In precision oncology, researchers often use public knowledgebases to check somatic variant frequencies against their cohort data. Large language models (LLMs) can quickly answer questions on somatic variant frequencies, but often hallucinate and give inaccurate results for factual data. Using synthetic queries, we show that somatic variant frequencies in baseline LLM responses are underestimated compared to the Genomic Data Commons (GDC), the worlds largest data commons for cancer research. We present a modular architecture called Query Augmented Generation (QAG) for integrating LLMs with high-quality data from a third party data source such as a data commons, knowledgebase or database. We apply QAG to the GDC to help researchers obtain accurate frequencies for somatic variants, copy number variants, and MSI status--even for complex queries requiring multiple steps in the GDC portal and API. Our software is deployed as a model context protocol (MCP) server on Hugging Face and available on GitHub.

bioinformatics↗

bioRxiv2025

ICEPIC: A Toolkit to Discover Ice Binding Proteins from Sequence

Ice binding proteins, such as antifreeze proteins (AFPs) and ice nucleation proteins (INPs), are critical for survival in subzero environments and have wide-ranging applications in biotechnology, agriculture, and materials science. Current discovery methods for these proteins are constrained by low throughput and limited datasets that are not conducive for engineering. Here, we present a high-throughput, sequence-based model that leverages contextual embeddings from protein language models to predict ice binding potential, as well as the expression and activity potential of candidate proteins. Using a curated data corpus of over 18,000 ice binding proteins -- far larger than previous datasets -- we fine-tuned a ProtBERT-based model, achieving 99% accuracy for prediction of ice binding potential. Sensitivity analyses through targeted mutagenesis (alanine and threonine substitutions) confirmed the models biological significance, revealing functionally important residues and sequence patterns. Additionally, we developed an expression prediction model that achieved an R2 score of 0.64 and low false-negative rates in identifying highly expressible candidates in Pichia pastoris. An additional regression model trained to predict ice activity as measured by thermal hysteresis achieved an R2 score of at least 0.79 with a clear difference in prediction between ice binding and non-ice binding proteins. Our toolkit advances the predictive accuracy, interpretability, and scalability of ice binding protein discovery, offering a powerful tool for protein engineering in cold-environment applications. Significance StatementIce binding proteins enable organisms to survive freezing temperatures and are essential for applications in cryopreservation, agriculture, and materials science. However, discovering and engineering these proteins has been limited by small datasets and inadequate predictive tools. We developed a machine learning model trained on over 18,000 ice binding protein sequences to predict not only ice binding potential but also protein activity and expression in engineered hosts. This approach integrates advanced protein language models with biological context, enabling faster, more reliable discovery of ice binding proteins. Our platform advances rational protein design for real-world applications in climate resilience, biotechnology, and beyond.

synthetic biology↗

bioRxiv2024

Beta cells are essential drivers of pancreatic ductal adenocarcinoma development

Pancreatic endocrine-exocrine crosstalk plays a key role in normal physiology and disease. For instance, endocrine islet beta ({beta}) cell secretion of insulin or cholecystokinin (CCK) promotes progression of pancreatic adenocarcinoma (PDAC), an exocrine cell-derived tumor. However, the cellular and molecular mechanisms that govern endocrine-exocrine signaling in tumorigenesis remain incompletely understood. We find that {beta} cell ablation impedes PDAC development in mice, arguing that the endocrine pancreas is critical for exocrine tumorigenesis. Conversely, obesity induces {beta} cell hormone dysregulation, alters CCK-dependent peri-islet exocrine cell transcriptional states, and enhances islet proximal tumor formation. Single-cell RNA-sequencing, in silico latent-space archetypal and trajectory analysis, and genetic lineage tracing in vivo reveal that obesity stimulates postnatal immature {beta} cell expansion and adaptation towards a pro-tumorigenic CCK+ state via JNK/cJun stress-responsive signaling. These results define endocrine-exocrine signaling as a driver of PDAC development and uncover new avenues to target the endocrine pancreas to subvert exocrine tumorigenesis.

cancer biology↗

bioRxiv2024

AAnet resolves a continuum of spatially-localized cell states to unveil tumor complexity

Identifying functionally important cell states and structure within a heterogeneous tumor remains a significant biological and computational challenge. Moreover, current clustering or trajectory-based computational models are ill-equipped to address the notion that cancer cells reside along a phenotypic continuum. To address this, we present Archetypal Analysis network (AAnet), a neural network that learns key archetypal cell states within a phenotypic continuum of cell states in single-cell data. Applied to single-cell RNA sequencing data from pre-clinical models and a cohort of 34 clinical breast cancers, AAnet identifies archetypes that resolve distinct biological cell states and processes, including cell proliferation, hypoxia, metabolism and immune interactions. Notably, archetypes identified in primary tumors are recapitulated in matched liver, lung and lymph node metastases, demonstrating that a significant component of intratumoral heterogeneity is driven by cell intrinsic properties. Using spatial transcriptomics as orthogonal validation, AAnet-derived archetypes show discrete spatial organization within tumors, supporting their distinct archetypal biology. We further reveal that ligand:receptor cross-talk between cancer and adjacent stromal cells contributes to intra-archetypal biological mimicry. Finally, we use AAnet archetype identifiers to validate GLUT3 as a critical mediator of a hypoxic cell archetype harboring a cancer stem cell population, which we validate in human triple-negative breast cancer specimens. AAnet is a powerful tool to reveal functional cell states within complex samples from multimodal single-cell data.

bioinformatics↗

bioRxiv2023

Mapping the gene space at single-cell resolution with gene signal pattern analysis

In single-cell sequencing analysis, several computational methods have been developed to map the cellular state space, but little has been done to map or create embeddings of the gene space. Here, we formulate the gene embedding problem, design tasks with simulated single-cell data to evaluate representations, and establish ten relevant baselines. We then present a graph signal processing approach we call gene signal pattern analysis (GSPA) that learns rich gene representations from single-cell data using a dictionary of diffusion wavelets on the cell-cell graph. GSPA enables characterization of genes based on their patterning on the cellular manifold. It also captures how localized or diffuse the expression of a gene is, for which we present a score called the gene localization score. We motivate and demonstrate the efficacy of GSPA as a framework for a range of biological tasks, such as capturing gene coexpression modules, condition-specific enrichment, and perturbation-specific gene-gene interactions. Then, we showcase the broad utility of gene rep-resentations derived from GSPA, including for cell-cell communication (GSPA-LR), spatial transcriptomics (GSPA-multimodal), and patient response (GSPA-Pt) analysis.

bioinformatics↗

bioRxiv2023

Redox Regulation of Brain Selective Kinases BRSK1/2: Implications for Dynamic Control of the Eukaryotic AMPK family through Cys-based mechanisms

In eukaryotes, protein kinase signaling is regulated by a diverse array of post-translational modifications (PTMs), including phosphorylation of Ser/Thr residues and oxidation of cysteine (Cys) residues. While regulation by activation segment phosphorylation of Ser/Thr residues is well understood, relatively little is known about how oxidation of cysteine residues modulate catalysis. In this study, we investigate redox regulation of the AMPK-related Brain-selective kinases (BRSK) 1 and 2, and detail how broad catalytic activity is directly regulated through reversible oxidation and reduction of evolutionarily conserved Cys residues within the catalytic domain. We show that redox-dependent control of BRSKs is a dynamic and multilayered process involving oxidative modifications of several Cys residues, including the formation of intra-molecular disulfide bonds involving a pair of Cys residues near the catalytic HRD motif and a highly conserved T-Loop Cys with a BRSK-specific Cys within an unusual CPE motif at the end of the activation segment. Consistently, mutation of the CPE-Cys increases catalytic activity in vitro and drives phosphorylation of the BRSK substrate Tau in cells. Molecular modeling and molecular dynamics simulations indicate that oxidation of the CPE-Cys destabilizes a conserved salt bridge network critical for allosteric activation. The occurrence of spatially proximal Cys amino acids in diverse Ser/Thr protein kinase families suggests that disulfide mediated control of catalytic activity may be a prevalent mechanism for regulation within the broader AMPK family.

biochemistry↗

bioRxiv2023

Learning transcriptional and regulatory dynamics driving cancer cell plasticity using neural ODE-based optimal transport

While single-cell technologies provide snapshots of tumor states, building continuous trajectories and uncovering causative gene regulatory networks remains a significant challenge. We present Cflows, an AI framework that combines neural ODE networks with Granger causality to infer continuous cell state transitions and gene regulatory interactions from static scRNA-seq data. In a new 5-time point dataset capturing tumorsphere development over 30 days, Cflows reconstructs two types of trajectories leading to tumorsphere formation or apoptosis. Trajectory-based cell-of-origin analysis delineated a novel cancer stem cell profile characterized by CD44hiEPCAM+CAV1+, and uncovered a cell cycle-dependent enrichment of tumorsphere-initiating potential in G2/M or S-phase cells. Cflows uncovers ESRRA as a crucial causal driver of the tumor-forming gene regulatory network. Indeed, ESRRA inhibition significantly reduces tumor growth and metastasis in vivo. Cflows offers a powerful framework for uncovering cellular transitions and dynamic regulatory networks from static single-cell data.

cancer biology↗

bioRxiv2023

Mechanistic and evolutionary insights into isoform-specific 'supercharging' in DCLK family kinases

Catalytic signaling outputs of protein kinases are dynamically regulated by an array of structural mechanisms, including allosteric interactions mediated by intrinsically disordered segments flanking the conserved catalytic domain. The Doublecortin Like Kinases (DCLKs) are a family of microtubule-associated proteins characterized by a flexible C-terminal autoregulatory tail segment that varies in length across the various human DCLK isoforms. However, the mechanism whereby these isoform-specific variations contribute to unique modes of autoregulation is not well understood. Here, we employ a combination of statistical sequence analysis, molecular dynamics simulations and in vitro mutational analysis to define hallmarks of DCLK family evolutionary divergence, including analysis of splice variants within the DCLK1 sub-family, which arise through alternative codon usage and serve to supercharge the inhibitory potential of the DCLK1 C-tail. We identify co-conserved motifs that readily distinguish DCLKs from all other Calcium Calmodulin Kinases (CAMKs), and a Swiss-army assembly of distinct motifs that tether the C-terminal tail to conserved ATP and substrate-binding regions of the catalytic domain to generate a scaffold for auto-regulation through C-tail dynamics. Consistently, deletions and mutations that alter C-terminal tail length or interfere with co-conserved interactions within the catalytic domain alter intrinsic protein stability, nucleotide/inhibitor-binding, and catalytic activity, suggesting isoform-specific regulation of activity through alternative splicing. Our studies provide a detailed framework for investigating kinome-wide regulation of catalytic output through cis-regulatory events mediated by intrinsically disordered segments, opening new avenues for the design of mechanistically-divergent DCLK1 modulators, stabilizers or degraders.

evolutionary biology↗

bioRxiv2022

A Deep-learning based RNA-seq Germline Variant Caller

RNA sequencing (RNA-seq) can be applied to diverse tasks including quantifying gene expression, discovering quantitative trait loci, and identifying gene fusion events. Although RNA-seq can detect germline variants, the complexities of variable transcript abundance, target capture, and amplification introduce challenging sources of error. Here, we extend DeepVariant, a deep-learning based variant caller, to learn and account for the unique challenges presented by RNA-seq data. Our DeepVariant RNA-seq model produces highly accurate variant calls from RNA-sequencing data, and outperforms existing approaches such as Platypus and GATK. We examine factors that influence accuracy, how our model addresses RNA editing events, and how additional thresholding can be used to facilitate our models use in a production pipeline.

bioinformatics↗

bioRxiv2022

Single-Cell Multi-Modal GAN (scMMGAN) reveals spatial patterns in single-cell data from triple negative breast cancer

Exciting advances in technologies to measure biological systems are currently at the forefront of research. The ability to gather data along an increasing number of omic dimensions has created a need for tools to analyze all of this information together, rather than siloing each technology into separate analysis pipelines. To advance this goal, we introduce a framework called the Single-Cell Multi-Modal GAN (scMMGAN) that integrates data from multiple modalities into a unified representation in the ambient data space for downstream analysis using a combination of adversarial learning and data geometry techniques. The frameworks key improvement is an additional diffusion geometry loss with a new kernel that constrains the otherwise over-parameterized GAN network. We demonstrate scMMGANs ability to produce more meaningful alignments than alternative methods on a wide variety of data modalities, and that its output can be used to draw conclusions from real-world biological experimental data. We highlight data from an experiment studying the development of triple negative breast cancer, where we show how scMMGAN can be used to identify novel gene associations and we demonstrate that cell clusters identified only on the scRNAseq data occur in localized spatial patterns that reveal insights on the spatial transcriptomic images.

bioinformatics↗

bioRxiv2022

An explainable unsupervised framework for alignment-free protein classification using sequence embeddings

Protein classification is a cornerstone of biology that relies heavily on alignment-based comparison of primary sequences. However, the systematic classification of large protein superfamilies is impeded by unique challenges in aligning divergent sequence datasets. We developed an alignment-free approach for sequence analysis and classification using embedding vectors generated from pre-trained protein language models that capture underlying protein structural-functional properties from unsupervised training on millions of biologically-observed sequences. We constructed embedding-based trees (with branch support) which depict hierarchical clustering of protein sequences and infer fast/slow evolving sites through interpretable sequence projections. Applied towards diverse protein superfamilies, embedding tree infers Casein Kinase 1 (CK1) as the basal protein kinase clade, identifies convergent functional motifs shared between divergent phosphatase folds, and infers evolutionary relationships between diverse radical S-Adenosyl-L-Methionine (SAM) enzyme families. Overall results indicate that embedding trees effectively capture global data structures, functioning as a general unsupervised approach for visualizing high-dimensional manifolds.

bioinformatics↗

bioRxiv2021

Evolution of functional diversity in the holozoan tyrosine kinome

The emergence of multicellularity is strongly correlated with the expansion of tyrosine kinases, a conserved family of signaling enzymes that regulates pathways essential for cell-to-cell communication. Although tyrosine kinases have been classified from several model organisms, a molecular-level understanding of tyrosine kinase evolution across all holozoans is currently lacking. Using a hierarchical sequence constraint-based classification of diverse holozoan tyrosine kinases, we construct a new phylogenetic tree that identifies two ancient clades of cytoplasmic and receptor tyrosine kinases separated by the presence of an extended insert segment in the kinase domain connecting the D and E helices. Present in nearly all receptor tyrosine kinases, this fast-evolving insertion imparts diverse functionalities such as post-translational modification sites and regulatory interactions. Eph and EGFR receptor tyrosine kinases are two exceptions which lack this insert, each forming an independent lineage characterized by unique functional features. We also identify common constraints shared across multiple tyrosine kinase families which warrant the designation of three new subgroups: Src Module (SrcM), Insulin Receptor Kinase-Like (IRKL), and Fibroblast, Platelet-derived, Vascular, and growth factor Receptors (FPVR). Subgroup-specific constraints reflect shared autoinhibitory interactions involved in kinase conformational regulation. Conservation analyses describe how diverse tyrosine kinase signaling functions arose through the addition of family-specific motifs upon subgroup-specific features and co-evolving protein domains. We propose the oldest tyrosine kinases, IRKL, SrcM, and Csk, originated from unicellular pre-metazoans and were co-opted for complex multicellular functions. The increased frequency of oncogenic variants in more recent tyrosine kinases suggests that lineage-specific functionalities are selectively altered in human cancers.

evolutionary biology↗

bioRxiv2021

KinOrtho: a method for mapping human kinase orthologs across the tree of life and illuminating understudied kinases

Protein kinases are among the largest druggable family of signaling proteins, involved in various human diseases, including cancers and neurodegenerative disorders. Despite their clinical relevance, nearly 30% of the 545 human protein kinases remain highly understudied. Comparative genomics is a powerful approach for predicting and investigating the functions of understudied kinases. However, an incomplete knowledge of kinase orthologs across fully sequenced kinomes severely limits the application of comparative approaches for illuminating understudied kinases. Here, we propose KinOrtho, a query- and graph-based orthology inference method that combines full-length and domain-based approaches to map one-to-one kinase orthologs across 17 thousand species. Using multiple metrics, we show that KinOrtho performed better than existing methods in identifying kinase orthologs across evolutionarily divergent species and eliminated potential false positives by flagging sequences without a proper kinase domain for further evaluation. We demonstrate the advantage of using domain-based approaches for identifying domain fusion events, highlighting a case between an understudied serine/threonine kinase TAOK1 and a metabolic kinase PIK3C2A with high co-expression in human cells. We also identify evolutionary fission events involving the understudied OBSCN kinase domains, further highlighting the value of domain-based orthology inference approaches. Using KinOrtho-defined orthologs, Gene Ontology annotations, and machine learning, we propose putative biological functions of several understudied kinases, including the role of TP53RK in cell cycle checkpoint(s), the involvement of TSSK3 and TSSK6 in acrosomal vesicle localization, and potential functions for the ULK4 pseudokinase in neuronal development. The well-curated kinome ortholog set can serve as a valuable resource for illuminating understudied kinases, and the KinOrtho framework can be extended to any gene-family of interest.

evolutionary biology↗

bioRxiv2021

A reservoir of stem-like CD8 T cells in the tumor-draining lymph node maintains the ongoing anti-tumor immune response

"Stem-like" TCF1+ CD8+ T cells (TSL) are necessary for long-term maintenance of T cell responses and the efficacy of immunotherapy but, as tumors contain signals that should drive T-cell terminal-differentiation, how these cells are maintained in tumors remains unclear. We found that a small number of TCF1+ tumor-specific CD8+ T cells were present in tumors throughout development. Yet, most intratumoral T cells differentiated as tumors progressed, corresponding with an immunologic shift in the tumor microenvironment (TME) from "hot" to "cold". By contrast, most tumor-specific CD8+ T cells in tumor-draining lymph nodes (dLNs) had functions and gene expression signatures similar to TSL from chronic LCMV infection and this population was stable over time, despite the changes in the TME. dLN T cells were the precursors of their more-differentiated intratumoral counterparts, and maintenance of TCF1 by intratumoral T cells required continuous migration from dLNs. Finally, TSL CD8 T cells were also present in LNs from lung adenocarcinoma patients, suggesting this population is also relevant in human disease. Thus, we propose that the dLN TSL reservoir has a critical function during tumor development in sustaining antitumor T cells during tumor development and protecting them from the terminal differentiation that occurs in the TME.

immunology↗

bioRxiv2020

Third generation sequencing revises the molecular karyotype for Toxoplasma gondii and identifies emerging copy number variants in sexual recombinants.

Toxoplasma gondii is an obligate intracellular parasite that has a significant impact on human health, especially in the immunocompromised. This parasite is also a useful genetic model for intracellular parasitism given its ease of culture in the laboratory and relevant animal models. However, as for many other eukaryotes, the T. gondii genome is incomplete, containing hundreds of sequence gaps due to the presence of repetitive and/or uncloneable sequences that prevent complete telomere-to-telomere de novo chromosome assembly. Here, we report the first use of single molecule DNA sequencing to generate near complete de novo genome assemblies for T. gondii and its near relative, N. caninum. Using the Oxford Nanopore Minion platform, we dramatically improved the contiguity of the T. gondii genome (N50 of [~]6.6Mb) and increased overall assembled sequence compared to current reference sequences by [~]2 Mb. Multiple complete chromosomes were fully assembled as evidenced by clear telomeric repeats on the end of each contig. Interestingly, for all of the Toxoplasma gondii strains that we sequenced (RH, CTG, IIxIII F1 progeny clones CL13, S27, S21, and S26), the largest contig ranged in size between 11.9 and 12.1 Mb in size, which is larger than any previously reported T. gondii chromosome. This was due to a repeatable and consistent fusion of chromosomes VIIb and VIII. These data were further validated by mapping existing T. gondii ME49 Hi-C data to our assembly, providing parallel lines of evidence that the T. gondii karyotype consists of 13, rather than 14, chromosomes. In addition revising the molecular karyotype we were also able to resolve hundreds of repeats derived from both coding and non-coding tandem sequence expansions. For well-known host-targeting effector loci like rhoptry protein 5 (ROP5) and ROP38, we were also able to accurately determine the precise gene count, order and orientation using established assembly approaches and the most likely primary sequence of each using our own assembly correction scripts tailored to correcting homopolymeric run errors in tandem sequence arrays. Finally, when we compared the T. gondii and N. caninum assemblies we found that while the 13 chromosome karyotype was conserved, we determined that previously unidentified large scale translocation events occurred in T. gondii and N. caninum since their most recent common ancestry.

genomics↗

bioRxiv2019

Deep evolutionary analysis reveals the design principles of fold A glycosyltransferases

Glycosyltransferases (GTs) are prevalent across the tree of life and regulate nearly all aspects of cellular functions by catalyzing synthesis of glycosidic linkages between diverse donor and acceptor substrates. Despite the availability of GT sequences from diverse organisms, the evolutionary basis for their complex and diverse modes of catalytic and regulatory functions remain enigmatic. Here, based on deep mining of over half a million GT-A fold sequences from diverse organisms, we define a minimal core component shared among functionally diverse enzymes. We find that variations in the common core and the emergence of hypervariable loops extending from the core contributed to the evolution of catalytic and functional diversity. We provide a phylogenetic framework relating diverse GT-A fold families for the first time and show that inverting and retaining mechanisms emerged multiple times independently during the course of evolution. We identify conserved modes of donor and acceptor recognition in evolutionarily divergent families and pinpoint the sequence and structural features for functional specialization. Using the evolutionary information encoded in primary sequences, we trained a machine learning classifier to predict donor specificity with nearly 88% accuracy and deployed it for the annotation of understudied GTs in five model organisms. Our studies provide an evolutionary framework for investigating the complex relationships connecting GT-A fold sequence, structure, function and regulation.

bioinformatics↗

bioRxiv2019

Quantitative Structure-Mutation-Activity Relationship Tests (QSMART) Model for Protein Kinase Inhibitor Response Prediction

Predicting drug sensitivity profiles from genotypes is a major challenge in personalized medicine. Machine learning and deep neural network methods have shown promise in addressing this challenge, but the "black-box" nature of these methods precludes a mechanistic understanding of how and which genomic and proteomic features contribute to the observed drug sensitivity profiles. Here we provide a combination of statistical and neural network framework that not only estimates drug IC50 in cancer cell lines with high accuracy (R2 = 0.861 and RMSE = 0.818) but also identifies features contributing to the accuracy, thereby enhancing explainability. Our framework, termed QSMART, uses a multi-component approach that includes (1) collecting drug fingerprints, cancer cell lines multi-omics features, and drug responses, (2) testing the statistical significance of interaction terms, (3) selecting features by Lasso with Bayesian information criterion, and (4) using neural networks to predict drug response. We evaluate the contribution of each of these components and use a case study to explain the biological relevance of several selected features to protein kinase inhibitor response in non-small cell lung cancer cells. Specifically, we illustrate how interaction terms that capture associations between drugs and mutant kinases quantitatively contribute to the response of two EGFR inhibitors (afatinib and lapatinib) in non-small cell lung cancer cells. Although we have tested QSMART on protein kinase inhibitors, it can be extended across the proteome to investigate the complex relationships connecting genotypes and drug sensitivity profiles.

bioinformatics↗