Latest bioRxiv papers

Category: bioinformatics — Showing 50 items

• Inference of cancer driver mutations from tumor microenvironmentcomposition: a pan-cancer study with cross-platform external validation

  Baker, E. A.; Mehaffy, N. S.

  AI Summary

  • This study investigated whether tumor microenvironment (TME) composition can predict cancer driver mutations across glioblastoma, breast, lung adenocarcinoma, and colorectal cancers using machine learning models trained on RNA-seq data from TCGA.
  • The models were externally validated on independent cohorts, achieving AUC >0.65 for 14 out of 15 driver-cancer pairs, with top performance for ERBB2 in breast cancer (AUC=0.980).
  • TME-predicted ERBB2 status was associated with overall survival in breast cancer, and the study highlighted the complexity of predicting KRAS mutations in lung adenocarcinoma due to co-mutant profiles.

  Abstract

  Cancer driver mutations shape the tumor microenvironment (TME), yet whether TME composition alone can predict genotype has not been systematically evaluated across cancers with external validation. We trained machine learning models to predict driver mutation status from TME cell-type composition signatures derived from bulk transcriptomes. Tissue-specific TME signatures (22-28 programs per cancer) were scored from RNA-seq data in TCGA for glioblastoma (GBM, n=157 total; n=90 EGFR-amplification evaluable), breast cancer (BRCA, n=1,082 total; n=994 evaluable), lung adenocarcinoma (LUAD, n=510 total; n=502 evaluable), and colorectal cancer (CRC, n=592 total; n=524 evaluable), then externally validated on independent cohorts spanning different platforms: CPTAC (GBM, n=65), METABRIC (BRCA, n=1,859), GSE72094 (LUAD, n=442), and GSE39582 (CRC, n=585). Of 15 driver-cancer pairs tested, 14 achieved external AUC >0.65, with top performance for ERBB2 amplification in BRCA (AUC=0.980), BRAF mutation in CRC (0.899), and TP53 mutation in BRCA (0.871). TME-predicted ERBB2 status stratified overall survival in METABRIC (Cox HR=1.73, p=7.95x10^-8). Marginal KRAS performance in LUAD (AUC=0.615) reflected opposing TME profiles in KRAS+STK11 versus KRAS+TP53 co-mutant tumors. These results demonstrate that TME composition encodes sufficient information to infer driver mutations across cancers.

  bioinformatics2026-02-23v1

• GlycoForge generates realistic glycomics data under known ground truth for rigorous method benchmarking

  Hu, S.; Bojar, D.

  AI Summary

  • GlycoForge is introduced as a tool for simulating realistic glycomics data with known ground truths, addressing the challenge of simulating data with controlled effects and biases.
  • It supports the creation of synthetic data with specified motif-level effects, batch effects, and realistic missing data scenarios.
  • The utility of GlycoForge was demonstrated by evaluating batch effect correction algorithms, providing guidelines for their application in real-world glycomics data analysis.

  Abstract

  Quantifying all complex carbohydrates in a sample produces glycomics data, which constitutes compositional data and is stymied by biosynthetic dependencies between glycans, requiring dedicated analytic workflows. Properly assessing such methods frequently requires simulated data with known ground truths and injectable effects. However, simulating glycomics data, especially with control over effects and biases, is still unsolved. Here, we present GlycoForge, a feature-complete solution for simulating comparative glycomics data. GlycoForge supports simulating fully synthetic glycomics data, with specified motif-level effects, drawn from Dirichlet distributions, and templated simulations based on real-world data. We further support the injection of batch effects, both mean and variance shifts, via center-log ratio transformations to maintain compositional closure, and realistic missing data simulation. We showcase the utility of GlycoForge by evaluating batch effect correction algorithms for glycomics data, with automated guidelines for when to use such methods on real-world data. GlycoForge is available as an open-access Python package at https://github.com/BojarLab/GlycoForge.

  bioinformatics2026-02-23v1

• Skip-Zeros Variational Inference in the Million-Cell Era of Single-Cell Transcriptomics

  Shimamura, T.; Yuki, S.; Abe, K.

  AI Summary

  • The study introduces UNISON, a scalable framework for matrix factorization in single-cell RNA sequencing, using skip-zeros variational inference to handle the sparsity of large datasets.
  • UNISON performs inference using only nonzero elements, improving efficiency and scalability, and was tested on over one million cells from the Mouse Organogenesis Cell Atlas.
  • Application to cross-species analysis showed UNISON's ability to distinguish conserved and species-specific transcriptional programs, enhancing understanding of biological processes like glaucoma.

  Abstract

  Combinatorial indexing-based single-cell RNA sequencing methods such as sci-RNA-seq and sci-RNA-seq3 now enable the profiling of millions of cells, producing expression matrices that are both extremely sparse and high-dimensional. Conventional nonnegative matrix factorization (NMF) provides an interpretable framework for uncovering latent biological structures but is computationally prohibitive at this scale, as it requires explicit access to the vast number of zero entries. We introduce UNISON (Unified Sparse-Optimized Nonnegative factorization), a scalable framework for matrix and tensor factorization based on skip-zeros variational inference. By reformulating stochastic variational Bayes updates in terms of sufficient statistics, UNISON performs inference using only nonzero elements, while implicitly accounting for zeros through geometric sampling. This strategy enables efficient parameter estimation without matrix expansion and naturally accommodates multiple experimental contexts. Simulation studies show that UNISON is robust to diverse learning-rate schedules and mini-batch sizes, providing practical guidelines for optimization. Application to the Mouse Organogenesis Cell Atlas demonstrates scalability to over one million cells, yielding latent factors that capture developmental trajectories and lineage-specific signatures with improved interpretability compared to existing methods. Cross-species analysis of aqueous humor outflow pathways across five vertebrate species further highlights UNISON's ability to disentangle conserved from species-specific transcriptional programs and to recover biologically meaningful gene-gene and gene-phenotype relationships relevant to glaucoma. By efficiently exploiting sparsity while preserving interpretability, UNISON establishes a principled and practical solution for integrative, large-scale single-cell transcriptomics.

  bioinformatics2026-02-23v1

• Comprehensive top-down mass spectral repository enables pan-dataset analysis and top-down spectral prediction

  Li, K.; Liu, K.; Fulcher, J. M.; Tang, H.; Liu, X.

  AI Summary

  • The study introduces TopRepo, a comprehensive repository of over 18 million top-down mass spectrometry (TD-MS) spectra from 12 species, creating a large-scale spectral library with over 5 million annotated spectra.
  • TopRepo facilitates pan-dataset analyses of proteoform characteristics like N-terminal processing and mass shifts.
  • The repository enhances proteoform identification via spectral library searching and supports training deep learning models for accurate TD-MS spectral prediction.

  Abstract

  Mass spectral libraries have become essential resources for training deep learning (DL) models for spectral prediction and de novo sequencing in bottom-up mass spectrometry (BU-MS). Compared with BU-MS, top-down MS (TD-MS) offers unique advantages for characterizing intact proteoforms by analyzing proteoforms without enzymatic digestion. Despite these advantages, large-scale spectral libraries for TD-MS are currently lacking. Here we present TopRepo, the first comprehensive repository of TD-MS spectra, comprising more than 18 million spectra acquired from 12 species across eight types of mass spectrometers. Using TopRepo, we constructed a large-scale top-down spectral library containing over 5 million spectra with curated proteoform and fragment-ion annotations. We demonstrate that TopRepo enables pan-dataset analyses of N-terminal processing, mass shifts, and other proteoform characteristics identified by TD-MS. Furthermore, we show that the TopRepo spectral library substantially improves proteoform identification through spectral library searching and supports the training of DL models for high-accuracy top-down spectral prediction.

  bioinformatics2026-02-23v1

• SPrOUT: A computational and targeted sequencing approach for mixed plant DNA identification with Angiosperms353

  Hu, N.; Bullock, M. R.; Jackson, C.; Miller, C.; Hunter, E.; Huff, C.; Chen, Y.; Handy, S.; Johnson, M.

  AI Summary

  • This study introduces SPrOUT, a method using the Angiosperms353 target sequencing kit to identify plant species in mixed samples through phylogenetic inference.
  • The approach achieves high accuracy (98.1-99.6%) and precision (92.9-100%) for in-silico mixes, and 90.7% accuracy with 98.0% precision for mock supplement mixtures.
  • The method effectively identifies taxa in mixed plant DNA samples, providing a practical framework for various applications.

  Abstract

  Premise: The identification of plant species from mixed samples is crucial in various fields, including ecological surveys, conservation efforts, and food and dietary supplement safety. Traditional methods face potential challenges due to the high costs of DNA sequencing, inefficiencies in computational workflows, and incomplete sequence databases. Methods and Results: This study introduces a novel approach using the Angiosperms353 target sequencing kit for efficient taxonomic identification of angiosperm DNA in mixed samples. Our method assembles short pair-end reads for each mixed sample. Using gene sets of Angiosperms353 from 871 species, we apply phylogenetic inference to categorize the variance in phylogenetic distance across genes to identify the presence of taxa in mixed plant samples. The pipeline reaches 98.1 to 99.6% accuracy, 92.9 to 100% precision for identifying unknown taxa in in-silico mixes, and 90.7% accuracy and 98.0% precision for mock supplement mixtures. We explored the parameter cutoffs of the pipeline to offer an empirical range for different applications. Conclusions: The Angiosperms353 and HybPiper assembly proved effective in sorting mixed plant DNA samples. Our method offers a framework for scientific and practical applications in plant species identification in both single and mixed samples.

  bioinformatics2026-02-23v1

• What makes a banana false? How the genome of Ethiopian orphan staple Ensete ventricosum differs from the banana A and B sub-genomes

  Muzemil, S.; Paul, P.; Baxter, L.; Dominguez-Ferreras, A.; Sahu, S. K.; Van Deynze, A.; Mai, G.; Yemataw, Z.; Tesfaye, K.; Ntoukakis, V.; Studholme, D. J.; Grant, M.

  AI Summary

  • The study sequenced the genome of the Ensete ventricosum landrace Mazia, identifying 38,940 protein-coding genes, with the assembly being more complete than the previously published Bedadeti genome.
  • Comparative analysis showed about 25% of the Mazia genome is unique to enset, with distinct functional signatures related to DNA integration, carbohydrate metabolism, disease resistance, and transcriptional regulation.
  • The research highlights the potential for marker-assisted breeding in enset, providing a foundation for improving agronomically important traits through comparative genomics within the Musaceae family.

  Abstract

  Background: Ensete ventricosum, also known as the "tree against hunger" plays a key role in Ethiopian food security and farming systems, feeding more than 20 million people. Since domestication via clonal selection in the south-west Ethiopian highlands, today's diverse enset landraces contribute multiple benefits including food, fibre by-product, animal bedding and cattle fodder to farmers and local communities. Improved genomic resources for this highly drought-tolerant plant are essential to supplement the conventional clonal selection-based breeding programme and pave the way towards targeted breeding. Results: We sequenced the genome of enset landrace Mazia, which is partially resistant/tolerant to Xanthomonas wilt and predicted 38,940 protein-coding genes. The Mazia assembly (540.14 Mb) is more complete than the previously published genome assembly of landrace Bedadeti (451.28 Mb) and displayed 1.41% heterozygosity and 64.64% repetitive DNA content. Comparative analyses with the Bedadeti assembly and chromosome-level genome sequences of the two main banana progenitors (Musa acuminata, AA genome; Musa balbisiana, BB genome) unexpectedly revealed ~25% of the Mazia genome is unique to enset. Gene Ontology (GO) and sequence similarity search analysis of enset-specific protein-coding genes identified distinct functional signatures that underpin the lifestyle, adaptation, and corm productive quality of enset, including functions related to DNA integration, carbohydrate metabolism, disease resistance and transcriptional regulation. In contrast, Musa-specific genes showed enrichment for defence response, protein phosphorylation and fruit development pathways. Focusing on the classical nucleotide binding site leucine rich repeat (NLR) disease resistance genes, we identified and characterised NLRs in enset and Musa species genomes, revealing a considerable expansion in the Musa acuminata genome. We also identified unique genes in enset and banana genomes whose functional and evolutionary roles are yet to be determined. Conclusions: Here, we report a de novo genome assembly for the enset (Ensete ventricosum) landrace Mazia and provide a high-quality annotation of both Mazia and the previously published assembly of the landrace Bedadeti. Collectively, these genomic resources provide a valuable foundation for comparative genomics within the Musaceae family and open new opportunities for the development of marker-assisted breeding strategies to accelerate the improvement of agronomically important traits in enset. Keywords: Ensete ventricosum, Musa, gene families, nucleotide binding site leucine rich repeat (NLR), orphan crop.

  bioinformatics2026-02-23v1

• An Integrated and Configurable End-to-End Pipeline for Longitudinal Cell Painting Analysis

  Zhao, G.

  AI Summary

  • The study introduces SCALE, an end-to-end pipeline for analyzing longitudinal cell painting data, addressing challenges like imaging variability and time consistency.
  • SCALE integrates nucleus-centered segmentation, quality control, feature extraction, and signal aggregation in a modular framework.
  • The pipeline's effectiveness was demonstrated with a chronic radiation exposure dataset, showing its capability for consistent longitudinal analysis.

  Abstract

  Cell painting assays generate high-dimensional, multi-channel imaging data that enable systematic characterization of cellular phenotypes. Increasingly, such assays are performed in longitudinal settings and under chronic perturbations, introducing additional challenges related to imaging variability, focus-field heterogeneity, and consistency across time points. Existing analysis workflows often require substantial manual adaptation to handle these complexities, limiting scalability and reproducibility. In this paper, we propose SCALE (Stable Cell painting Analysis for Longitudinal Experiments), an integrated, end-to-end analysis pipeline designed for robust longitudinal analysis of cell painting data. The pipeline combines nucleus-centered segmentation, automated quality control, feature extraction, and signal aggregation within a modular and configurable framework. Once assay-specific configurations are specified, the pipeline executes in a fully automated manner from raw images to downstream summary statistics and analysis-ready outputs. We demonstrate the utility of the pipeline using a chronic radiation exposure cell painting dataset, illustrating its ability to support consistent longitudinal comparisons across conditions and time points.

  bioinformatics2026-02-23v1

• LinkDTI: Drug-Target Interactionsprediction through a Link Predictionframework on Biomedical KnowledgeGraph

  Mondal, M.; Arunachalam, S.; Wu, S.; Datta, A.

  AI Summary

  • LinkDTI is a computational framework that predicts drug-target interactions (DTIs) by analyzing connections in a heterogeneous biomedical knowledge graph using a modified GraphSAGE model.
  • It employs negative sampling to balance data and outperforms baseline methods by at least 2.5% in AUROC and AUPRC.
  • The framework identified 945 new potential DTIs, a 49.14% increase over known interactions.

  Abstract

  Computational drug-target interactions (DTI) prediction serves as a valuable tool for drug discovery and repurposing by cost-effectively narrowing down the potential drug-target space. This paper presents LinkDTI, a computational framework that predicts DTIs by identifying connections within a heterogeneous knowledge graph of drugs, proteins, diseases, and side effects. Unlike methods that rely on mathematical techniques like matrix completion or similarity-based scoring, LinkDTI uses an advanced graph-based approach to capture relationships between biomedical entities. Specifically, LinkDTI applies a modified version of the multilayer GraphSAGE model that learns from the heterogeneous knowledge graph and predicts potential drug-target interactions. Our model incorporates negative sampling that balances the data to address the issue of having more negative than positive interactions. Our results show that LinkDTI consistently performs better in AUROC and AUPRC than baseline methods by at least 2.5% across different sampling ratios and conditions. Subsequently, it identifies approximately 945 new potential DTIs, marking a 49.14% increase over known DTIs. Overall, LinkDTI offers a simple yet effective method for integrating diverse biomedical data to identify potential drug-target interactions.

  bioinformatics2026-02-23v1

• Structure-Based TCR-pMHC Binding Prediction and Generalization to Unseen Peptides

  Abeer, A. N. M. N.; Roy, R. S.; Qian, X.; Yoon, B.-J.

  AI Summary

  • This study investigates the generalization performance of graph neural network (GNN)-based classifiers for predicting TCR-pMHC binding, focusing on their accuracy with unseen peptides.
  • The research assesses factors like interaction features and structural uncertainty that affect classifier performance.
  • By designing classifier architecture with auxiliary training objectives, the study shows improved generalization to novel peptides.

  Abstract

  The interaction between T-cell receptors (TCRs) with the peptide-bound major histocompatibility complex (MHC) intricately impacts the functional specificity of T-cell-mediated adaptive immune response. Consequently, implication in immunotherapy has contributed to the ever-growing computational methods for TCR recognition, which have recently attracted structure-based approaches due to advancements in protein structure modeling. Despite access to structural information of the predicted binding interface, graph neural network (GNN)-based TCR-pMHC binding specificity classifiers tend to show poor accuracy for samples with unseen peptides. In this work, we comprehensively assess the potential factors that critically impact the generalization performance of classifiers trained with computationally predicted structures. Specifically, our experiments focus on analyzing the sensitivity of such predictors to the interaction features in the TCR-pMHC interface and the structural uncertainty. Building on the analysis, we demonstrate how the design of classifier architecture with auxiliary training objectives can improve the generalization performance to novel peptides not yet seen during model training. Overall, our work highlights the challenges of unseen peptide generalization from different perspectives of the GNN-based classifier paradigm, showcasing the strengths and weaknesses of the current state-of-the-art approaches in the generalization landscape.

  bioinformatics2026-02-23v1

• A Spatio-Temporal Analysis Framework for Characterizing Radiation-Induced Genomic Instability

  Chopra, K.; Cucinell, C.; Weinberg, R.; Forrester, S.; Brettin, T.; Kilic, O.; Yoon, B.-J.

  AI Summary

  • This study developed an analytical framework to investigate the coupling between structural variants and point mutations in human endothelial cells exposed to chronic low-dose gamma radiation.
  • The framework revealed a 7.13-fold enrichment of doublet base substitutions (DBS) near inversion breakpoints, with this enrichment diminishing with distance.
  • Temporal analysis showed inversions were transient, while DBS persisted, affecting genes critical for genomic stability like DNA damage response and chromatin regulation.

  Abstract

  Chronic low-dose ionizing radiation induces complex genomic instability encompassing both structural variants and point mutations, yet these alterations are typically analyzed as independent events limiting detection of mechanistic coupling between rearrangement formation and localized mutagenesis at breakpoint junctions. This gap is particularly consequential given the widespread occupational and environmental exposure contexts; nuclear energy, medical imaging, and environmental contamination, where coupled genomic alterations may contribute to cancer risk through mechanisms invisible to type-agnostic analyses. We developed an integrated analytical framework combining temporal pattern tracking, breakpoint-proximal mutation enrichment analysis, and systematic testing across all structural variant types to resolve these coupled dynamics across dose and time. Applying this framework to whole-genome sequencing data from primary human endothelial cells (HUVEC) exposed to chronic low-dose gamma radiation (0.001 - 2 mGy/hr) over three weeks, we discovered 7.13-fold enrichment of doublet base substitutions (DBS) within 10bp of inversion breakpoints, a signal absent from other structural variant types. This enrichment decayed sharply with distance (to [~]1.9 fold at 100bp), indicating localized mutagenesis at these junctions. Temporal analysis revealed divergent fates: inversions appeared transiently (100% single-timepoint) while DBS showed greater persistence (9.0% multi-timepoint). Among the INV-DBS events identified, affected genes include 16 high-constraint loci (pLI [≥] 0.9) involved in DNA damage response, signal transduction, and chromatin regulation; pathways critical for maintaining genomic stability. Our framework provides a generalizable approach for investigating structural variant-mutation relationships, with applications to radiation biology, cancer genomics, and mechanistic studies of DNA repair fidelity.

  bioinformatics2026-02-23v1

• art_modern: An Accelerated ART Simulator of Diverse Next-Generation Sequencing Reads

  YU, Z.

  AI Summary

  • The study introduces art_modern, an accelerated version of the ART simulator for next-generation sequencing (NGS) data, enhanced with updated algorithms, SIMD instructions, and parallel processing.
  • art_modern supports simulation of transcriptome profiling with contig-specific coverage and strand information.
  • Benchmarking showed art_modern reduces CPU time by 75-77% and accelerates wall-clock time by 15-24 times compared to the original ART on multi-core systems._

  Abstract

  Fast simulation of next-generation sequencing (NGS) data is vital for software development and benchmarking. Here we describe art_modern, an accelerated ART simulator that can simulate various NGS data. We accelerated ART using updated sampling algorithms, single-instruction multiple-data (SIMD) instruction-set extensions (ISEs), thread- and node-level parallelism, and an asynchronous output writer, while enabling simulation of transcriptome profiling data by supporting contig-specific coverage with strand information. The new implementation was benchmarked against popular performance-oriented NGS simulators, revealing a 75--77% reduction in CPU time and a 15--24 times acceleration in wall-clock time on a multi-core machine compared to the original implementation. With this simulator, the process of developing and benchmarking NGS sequence analysis algorithms can be largely accelerated. Availability and Implementation: The software is implemented in C++17 with CMake as the building system. It can be built and executed on a modern GNU/Linux operating system with Boost, Zlib, and a C++17 compiler, with further acceleration available using Intel OneAPI C++/DPC++ compilers and Intel oneAPI MKL random generators. The software is available at https://github.com/YU-Zhejian/art_modern under the GNU General Public License v3.

  bioinformatics2026-02-23v1

• Universal physical principles govern the deterministic genesis of protein structure

  Chuanyang, L.; Liu, J.; Qiu, X.; Wu, X.; Li, W.; Min, L.; Zhang, G.; Zhang, S.; Zhu, L.

  AI Summary

  • The study introduces ProtGenesis, a framework that models protein genesis as a deterministic process within a discrete structural space, governed by three universal principles: Assembly, Emergence, and Phase-Transition.
  • These principles describe how amino acids form fractal-like structures, how peptides follow spatial trajectories, and how mutations lead to topological phase shifts in protein structure.
  • ProtGenesis provides a mathematical foundation to interpret deep learning models and offers a basis for engineering protein structures.

  Abstract

  The origin of functional proteins remains a fundamental biological enigma. Although Anfinsen's dogma established sequence as the determinant of structure, and deep learning models can predict structures with high fidelity, the physical principles governing protein genesis itself, from prebiotic condensation to functional protein emergence, remain unresolved. This gap leaves a critical disconnect between mechanistic biological insights and artificial intelligence. Herein, we introduce a unified methodological framework ProtGenesis that recasts genesis of protein as a structured, deterministic navigation within a discrete structural space. We identify three universal principles governing this hierarchical organization: the Assembly Principle directs amino acids condensation into multilayer fractal-like architectures; the Emergence Principle ensures nascent peptides' emergence follow deterministic spatial trajectories; and the Phase-Transition Principle describes wherein incremental residue accrual or mutations drives precise topological phase shifts from short-range to long-range order. By quantifying these trajectories with novel tripartite spatial metrics, we reveal that protein genesis is not an abstract continuum but a principle-governed physical process with measurable coordinates. ProtGenesis thus provides an universal interpretable mathematical foundation for decoding "black-box" of deep learning models and establishes a rigorous basis for exploring, understanding, and engineering the molecular blueprint of life.

  bioinformatics2026-02-23v1

• MetaTracer: A nucleotide alignment-based framework for high-resolution taxonomic and transcript assignment in metatranscriptomic data

  Furstenau, T.; Shaffer, I.; Hsu, K.-L. C.; Pearson, T.; Ernst, R. K.; Fofanov, V.

  AI Summary

  • MetaTracer is a tool that performs nucleotide alignment for metatranscriptomic analysis, assigning reads to both taxonomic groups and genes in one pass.
  • It offers improved accuracy and species-level resolution compared to k-mer or protein-based methods by mapping reads to annotated genomic features.
  • Testing on simulated and real dental plaque data showed high accuracy in taxonomic and gene assignment, revealing species-specific transcriptional differences in children with early childhood caries versus healthy controls.

  Abstract

  Summary: MetaTracer is a nucleotide alignment-based tool for metatranscriptomic analysis of complex bacterial communities that assigns sequence reads to both taxonomic groups and expressed genes in a single pass. Full nucleotide-level alignment improves accuracy relative to k-mer-based classifiers and preserves species-level resolution that is often lost in protein-based approaches. By retaining alignment coordinates and mapping reads directly to annotated genomic features, MetaTracer enables direct attribution of gene expression to specific microbial species. On simulated datasets, MetaTracer achieves high accuracy for both taxonomic and gene assignment. Applied to real dental plaque metatranscriptomic datasets, MetaTracer resolves species-specific transcriptional activity and detects reproducible differences in microbial gene expression between children with early childhood caries and healthy controls. Availability and implementation: MetaTracer is implemented as a Python-based workflow wrapper (metatracer v0.1.0) that depends on the mtsv-tools core engine (v2.1.0), which is written in Rust. The required functionality is supported by the v2.1.0 release of mtsv-tools. Both packages are open source under the MIT license and are available at github.com/FofanovLab/metatracer and github.com/FofanovLab/mtsv-tools. Versioned releases are archived at Zenodo (DOI: 10.5281/zenodo.18665766 and DOI: 10.5281/zenodo.18718002). Installation is supported via Bioconda.

  bioinformatics2026-02-23v1

• CellAwareGNN: Single-Cell Enhanced Knowledge Graph Foundation Model for Drug Indication Prediction

  Zhang, X.; Jeong, E.; Yan, C.; Feng, Y.; Lyu, L.; Guo, X.; Chen, Y.

  AI Summary

  • The study introduces CellAwareGNN, a model integrating single-cell genomics into a biomedical knowledge graph (scPrimeKG) to enhance drug indication prediction.
  • CellAwareGNN was evaluated on all diseases in the graph, achieving an AUPRC of 0.826, surpassing TxGNN-U (0.816) and TxGNN (0.799).
  • For autoimmune diseases, CellAwareGNN showed significant improvement, with an AUPRC of 0.864, and suggested specific drug repurposing candidates like Ocrelizumab for Pemphigus.

  Abstract

  Graph foundation models have emerged as powerful tools for drug repurposing by enabling the prediction of novel drug-disease indications from large biomedical knowledge graphs. A representative example is TxGNN, which was previously developed and trained on PrimeKG, a comprehensive biomedical knowledge graph covering over 17,000 diseases. While TxGNN demonstrates strong performance, existing biomedical knowledge graphs largely lack fine-grained, cell-type-specific genomic context. It limits their ability to capture disease mechanisms driven by dysregulated cellular programs, such as immune cell-specific pathways in autoimmune diseases. Moreover, prior evaluations typically test only randomly selected subsets of diseases, leaving many diseases unexamined and limiting conclusions about model performance across the full disease spectrum. To address these limitations, we first update PrimeKG to PrimeKG-U by incorporating expanded and curated biomedical knowledge and then develop TxGNN-U as a stronger graph-based baseline. Building on this foundation, we introduce CellAwareGNN, a graph foundation model that integrates single-cell genomics into PrimeKG-U. We construct a single-cell-enhanced knowledge graph, scPrimeKG, by incorporating cell-type-specific genetic associations from the OneK1K dataset, expanding PrimeKG from approximately 8.1 million edges and 129k nodes to over 14 million edges and 140k nodes. CellAwareGNN is pre-trained on all relation types in scPrimeKG and evaluated on drug indication prediction with explicit coverage of all diseases in the knowledge graph. CellAwareGNN consistently outperforms TxGNN and TxGNN-U. For drug indication prediction, CellAwareGNN achieves an AUPRC of 0.826, representing a 1.2% improvement over TxGNN-U (0.816) and a 3.4% improvement over TxGNN (0.799). Notably, for autoimmune diseases, CellAwareGNN attains an AUPRC of 0.864, improving by 2.0% over TxGNN-U (0.847) and 6.0% over TxGNN (0.815). Importantly, CellAwareGNN prioritizes promising repurposing candidates, including Ocrelizumab for Pemphigus via CD20-expressing B cells, Methotrexate for Pemphigus through DHFR and ATIC activity in T and B cells, and Rosiglitazone for Rheumatoid Arthritis through PPAR-{gamma} activation. These results demonstrate the value of incorporating cell-type-specific genomic context to improve both predictive performance and biological interpretability in graph- based drug repurposing.

  bioinformatics2026-02-23v1

• Hierarchical Multi-Omics Trajectory Prediction forFecal Microbiota Transplantation: A Novel MachineLearning Framework for Small-Sample LongitudinalMulti-Omics Integration

  Zhou, Y.-H.; Sun, G.

  AI Summary

  • The study introduces Hierarchical Multi-Omics Trajectory Prediction (HMOTP), a machine learning framework for predicting patient trajectories post-fecal microbiota transplantation (FMT) using small-sample, longitudinal multi-omics data.
  • HMOTP integrates lipidomics and metagenomics data through hierarchical feature construction and multi-level attention, achieving 96.67% accuracy in predicting treatment outcomes in a cohort of 15 patients.
  • The framework identified key biomarkers and cross-omics associations, demonstrating its utility in personalized medicine and biological discovery in FMT applications.

  Abstract

  Fecal microbiota transplantation (FMT) has emerged as a highly effective treatment for recurrent Clostridioides difficile infection and is being actively investigated for numerous other conditions. While multi-omics studies have revealed dynamic changes in microbial communities and host metabolism following FMT, existing approaches are primarily descriptive and lack the ability to predict individual patient trajectories or identify early biomarkers of treatment response. Small-sample, multi-omics, longitudinal prediction problems present unique computational challenges: high dimensionality, multi-omics integration, temporal dynamics, and interpretability. Here, we present Hierarchical Multi-Omics Trajectory Prediction (HMOTP), a novel machine learning framework specifically designed for small-sample, multi-omics, longitudinal prediction that addresses these challenges through hierarchical feature construction using domain knowledge, multi-level attention mechanisms, and patient-specific trajectory prediction. HMOTP integrates multi-omics data at multiple biological levels (raw features, aggregated classes/categories, and cross-level interactions) while preserving biological interpretability. The framework employs multi-head attention to learn feature importance at different hierarchy levels and integrates information across omics layers. Patient-specific trajectory prediction enables personalized predictions despite limited sample sizes through transfer learning. We evaluated HMOTP on a cohort of 15 patients with recurrent Clostridioides difficile infection who underwent fecal microbiota transplantation, with comprehensive lipidomics (397 features) and metagenomics (10,634 pathways) profiling at four timepoints spanning six months. Using leave-one-patient-out cross-validation, HMOTP achieved 96.67% {+/-} 10.54% accuracy, outperforming baseline methods including Random Forest (91.33% {+/-} 21.33%) and Logistic Regression (86.33% {+/-} 24.67%). The framework demonstrated robust generalization across timepoints. Through hierarchical interpretability, HMOTP identified key biomarkers and revealed mechanistically informative cross-omics associations, including 324 strong correlations (|r| > 0.7) involving top-predictive biomarkers, demonstrating its utility for both prediction and biological discovery in FMT applications. HMOTP provides a generalizable framework applicable to other small-sample multi-omics problems, offering a powerful tool for personalized medicine applications.

  bioinformatics2026-02-23v1

• A PLUM Job: Peptide modeLs for Understanding and engineering antiMicrobial therapeutics

  Banerjee, P.; Friedberg, I.; Rued, B. E.; Eulenstein, O.

  AI Summary

  • The study addresses the need for new antimicrobial strategies by developing PLUM, a structured conditional Variational Autoencoder for designing antimicrobial peptides (AMPs).
  • PLUM allows for controlled generation of AMPs by disentangling sequence, function, and length, producing peptides 5-35 amino acids long.
  • Compared to HydrAMP, PLUM achieved a 7% higher AMP yield, 14% increased diversity, and 37% more AMPs in prototype-conditioned generation, with low predicted toxicity.

  Abstract

  Motivation: Antibiotic-resistant infections in humans and animals are rising, creating an urgent need for new antimicrobial strategies. This challenge extends beyond clinical settings to food production systems; the Centers for Disease Control and Prevention estimates that foodborne pathogens cause over 48 million illnesses annually in the U.S. alone. Antimicrobial peptides (AMPs) are a promising alternative due to their broad activity and lower risk of resistance. However, rational design remains challenging, particularly when simultaneously controlling sequence, function, and peptide length. Results: We introduce Peptide modeLs for Understanding and engineering antiMicrobial therapeutics (PLUM), a structured conditional Variational Autoencoder for controlled AMP generation. PLUM disentangles sequence, function, and length within its latent space, enabling both *de novo* and prototype-conditioned generation of peptides 5-35 amino acids long, thereby capturing larger functional domains. Across 45,000 generated peptides, PLUM: * Achieved the highest AMP yield (0.885), **7% higher** than HydrAMP * Increased AMP diversity by 14%compared with HydrAMP * Maintained the highest non-AMP sequence yield (0.895), 19% higher than HydrAMP. For prototype-conditioned generation, PLUM produced 37% more AMPs than HydrAMP, generating sequences that closely matched real peptide compositions while exhibiting low predicted toxicity. Integrated AMP classifiers enabled robust evaluation of identity and potency across diverse bacterial targets. These results establish PLUM as a scalable and versatile platform for designing antimicrobial peptides and next-generation therapeutics. Availability: https://github.com/priyamayur/PLUM

  bioinformatics2026-02-23v1

• EES-Transformer: A Dual-Path Transformer for Tissue Classification and Gene Representation Learning from Extreme Expression Sets

  Park, J.-S.; Lee, Y.; Kang, Y. J.

  AI Summary

  • The EES-Transformer V2 uses a dual-path architecture to classify tissues and learn gene representations from extreme gene expression sets in Arabidopsis thaliana RNA-seq data.
  • It achieves 91-92% accuracy in classifying 47 tissue types, significantly outperforming the 2.1% random baseline.
  • Analysis revealed tissue-specific gene relationships, with attention highlighting 3,524 gene-tissue associations and showing that tissue identity is encoded in gene pairs rather than single genes.

  Abstract

  Accurate tissue classification from gene expression data is fundamental to transcriptomic analysis. Here we introduce EES-Transformer V2, a dual-path transformer architecture that learns from Extreme Expression Sets (EES); sequences of genes at expression extremes (above 95th or below 5th percentile). The architecture separates tissue classification from masked language modeling through independent branches: the classification branch operates without tissue label information, while the generative branch receives tissue conditioning. This design enables fair evaluation of classification performance while learning tissue-specific gene relationships. Applied to 12,212 Arabidopsis thaliana RNA-seq samples spanning 47 tissue types, EES-Transformer achieves 91-92% classification accuracy (varying across evaluation runs due to stochastic input masking); substantially above the 2.1% random baseline. Attention-based analysis identifies 3,524 gene-tissue high-attention associations whose importance patterns reflect known biology. Critically, while individual high-attention genes appear broadly across tissues, gene pairs from attention-derived regulatory networks show higher tissue specificity: pollen gene pairs show a 2.7-fold enrichment over single-gene rates, and root and leaf pairs each show 1.5-fold enrichment. This finding reveals that tissue identity is encoded in combinatorial gene expression patterns rather than individual genes. Attention-derived gene regulatory networks exhibit scale-free topology and biologically coherent hub gene programs, with pollen networks consisting entirely of DOWN-DOWN interactions among silenced vegetative genes. EES-Transformer provides accurate tissue classification, interpretable gene importance scores, and attention-derived regulatory networks for biological discovery.

  bioinformatics2026-02-23v1

• Pro-GAT: Reconnecting Fragmented PROTACs Using Graph Attention Transformer

  Vemuri, S.; Bijigiri, L. P.; Gogte, S.; Kondaparthi, V.

  AI Summary

  • The study addresses the issue of chemically invalid or disconnected linker structures in PROTACs generated by diffusion-based models, which fail to maintain local bonding requirements.
  • Pro-GAT, a graph attention-based framework, was developed to repair these disconnected PROTAC candidates by predicting coordinate corrections and atom-type modifications.
  • When integrated with DiffPROTACs and DiffLinker, Pro-GAT increased the percentage of chemically valid PROTAC candidates from 76.70% to 83.92% and 63.16% to 68.73%, respectively, while maintaining high uniqueness levels.

  Abstract

  PROTACs work by bringing together a protein-of-interest ligand and an E3 ligase recruiter to trigger targeted degradation. However, Diffusion-based generative models frequently produce chemically invalid or disconnected linker structures that satisfy global geometric constraints but violate local bonding requirements. These models operate in continuous coordinate space and therefore lack explicit mechanisms for enforcing discrete chemical connectivity under fixed-anchor constraints. Invalid, disconnected outputs recur rather than being a rare exception, such that naive resampling is not an effective method to obtain valid chimeras. Pro-GAT is a graph attention-based framework for geometry-preserving molecular graph repair, capable of functioning on chemically disconnected diffusion-generated PROTAC candidates by predicting bounded coordinate corrections and constrained atom-type modifications using geometry-aware graph attention network (GAT) layers. The proposed model is trained on PROTAC datasets with added disconnections to overcome systematic connectivity failures in diffusion-based PROTAC generation with fixed anchors. When combined with DiffPROTACs and DiffLinker, Pro-GAT improves the percentage of chemically valid candidates in the aggregated output from 76.70% to 83.92% and 63.16% to 68.73% while maintaining 80.18% and 63.80% uniqueness levels of valid candidates respectively, thus facilitating the generation of usable PROTAC candidates from invalid diffusion samples. Pro-GAT was used in a case study of the 7Z76 ternary complex to repair DiffPROTACs and DiffLinker generated samples, which gave rise to connected chimeras whose docking scores were comparable to the original 7Z76 structure.

  bioinformatics2026-02-23v1

• BacTaxID: A universal framework for standardized bacterial classification

  Fernandez-de-Bobadilla, M. D.; Lanza, V. F.

  AI Summary

  • BacTaxID is a universal framework for bacterial classification using whole-genome k-mer-based sketches, which organizes strains into hierarchical clusters based on user-defined similarity thresholds.
  • It provides a direct quantitative link to Average Nucleotide Identity (ANI), showing universal concordance with species and sub-species classifications across 2.3 million genomes from 67 genera.
  • BacTaxID outperforms traditional methods in capturing strain-level diversity and replicates SNP and cgMLST-based definitions in surveillance and outbreak scenarios.

  Abstract

  Bacterial strain typing is key to surveillance, outbreak investigation and microbial ecology, yet current systems remain species-specific, reference-dependent and lack a universal, interpretable metric of genomic relatedness. Here, we introduce BacTaxID, a fully configurable, whole-genome k-mer-based framework that encodes each genome as a numeric sketch and organizes strains into hierarchical clusters with user-defined similarity thresholds. BacTaxID distances are strictly proportional to Average Nucleotide Identity (ANI), providing a direct quantitative link between vectorial typing and genome-wide divergence. Applied to 2.3 million genomes from All the Bacteria across 67 genera, BacTaxID demonstrates universal concordance species and sub-species classification systems, while capturing finer strain-level diversity than traditional reference-based approaches. In simulated surveillance and real outbreak datasets, BacTaxID reproduces SNP and cgMLST-based definitions while enabling rapid, scalable screening. Precomputed genus-level schemes and an open implementation provide a practical, genus-agnostic alternative to classical typing systems for standardized bacterial classification.

  bioinformatics2026-02-22v3

• Protenix-v1: Toward High-Accuracy Open-Source Biomolecular Structure Prediction

  Zhang, Y.; Gong, C.; Zhang, H.; Ma, W.; Liu, Z.; Chen, X.; Guan, J.; Wang, L.; Yang, Y.; Xia, Y.; Xiao, W.

  AI Summary

  • Protenix-v1 (PX-v1) is an open-source biomolecular structure prediction model that outperforms AlphaFold3 with the same constraints, showing improved accuracy with increased sampling budget.
  • It includes features like protein template integration and RNA MSA support, with a variant, Protenix-v1-20250630, trained on a larger dataset for enhanced accuracy.
  • The study also addresses benchmarking limitations by providing updated evaluation tools and year-stratified benchmarks for more reliable assessments.

  Abstract

  We introduce Protenix-v1 (PX-v1), the first open-source structure prediction model to attain superior performance to AlphaFold3 while strictly adhering to the same training data cutoff, model size, and inference budget. Beyond standard evaluations, we highlight the effectiveness of inference-time scaling behavior, demonstrating that increasing the sampling budget yields consistent improvements in prediction quality--a behavior previously seen in AlphaFold3 but not in other open-source models. In addition to improved accuracy, Protenix-v1 incorporates key capabilities including protein template integration and RNA MSA support. Furthermore, to better support real-world applications such as drug discovery, we additionally release Protenix-v1-20250630, a variant trained on a larger dataset (cutoff: June 30, 2025), delivering further improved prediction accuracy. Finally, we identify the limitations of current benchmarking tools and we provide updated evaluation tools and year-stratified benchmarks to facilitate more reliable and transparent assessment within the community. Collectively, these contributions provide a robust foundation for the Protenix series and the broader field.

  bioinformatics2026-02-22v3

• Deciphering Features of Metalloprotease Cleavage Targets Using Protein Structure Prediction

  Chung, D. S.; Park, J.; Choi, W.; Hong, D.

  AI Summary

  • The study developed a computational model using protein structure prediction to identify and classify substrates of ADAM10, a metalloprotease, and predict its cleavage sites.
  • The model analyzed predicted protein complexes, focusing on protein-protein interactions, structural information of cleavage sites, and spatial relationships with metal ions.
  • Results showed the model's effectiveness in substrate classification and cleavage site prediction, with potential applications to other ADAM family members and metalloproteases.

  Abstract

  Metalloproteases are a class of enzymes that utilize metal ions within their active sites to catalyze the hydrolysis of peptide bonds in proteins. Among these, ADAM10 (A Disintegrin and Metalloproteinase 10), a member of the ADAM family, plays a crucial role in mediating intracellular signaling by cleaving specific substrates, thereby influencing a variety of physiological and pathological processes. The mechanisms underlying the activity of ADAM10 present significant opportunities for the development of novel therapeutic strategies aimed at disease intervention. However, the information available to identify the substrate and cleavage sites of ADAM10 is still insufficient. Therefore, it is essential to identify and classify the features of substrates and to elucidate cleavage sites through experimental approaches. However, these studies across numerous proteins present significant challenges. To address the promise of these investigations, we developed a model that leverages protein structure prediction to decipher substrate features, classify substrates, and predict cleavage sites. Through the analysis of predicted protein complexes between ADAM10 and its substrates using PDB files, we evaluated protein-protein interaction (PPI) data, the structural information of cleavage sites, and the spatial relationships between the cleavage sites and metal ions. Finally, we present a computational model that effectively classifies substrates and accurately predicts cleavage sites in this study. Our study demonstrates the potential for application not only to ADAM10 but also to other members of the ADAM family and, more broadly, to additional metalloproteases. By leveraging computed protein structural information, our approach offers a novel perspective for substrate classification.

  bioinformatics2026-02-22v2

• Cellects, a software to quantify cell expansion and motion

  Boussard, A.; Petit, M.; Arrufat, P.; Dussutour, A.; Perez-Escudero, A.

  AI Summary

  • Cellects is an open-source software designed for automated quantification of cell expansion, motion, and morphology from 2D and time-lapse images across various biological systems.
  • It features a graphical interface for interactive parameter tuning, visualization, and batch processing, with customization options via a Python API.
  • The software outputs quantitative data like area and trajectory in .csv format, facilitating statistical analysis and integration into existing research workflows.

  Abstract

  Cellects is a user-friendly and open-source software for automated quantification of biological growth, motion, and morphology from 2D image data and time-lapse sequences (2D + t), acquired under a wide range of experimental conditions and biological systems (from fungal colonies to unicellular branching networks). The software is available as a stand-alone version, featuring a graphical interface that supports interactive parameter tuning, visualization, validation, and batch processing. The analysis pipeline can be extended and customized using a dedicated Python API. The typical inputs and outputs are as follows. Cellects is designed to process grayscale or color images originating from standard microscopy, macroscopic imaging setups, or camera-based platforms. The software supports single or multiple organisms growing or moving in one or several arenas and can analyze multiple folders sequentially. All quantitative results (area, circularity, orientation axes, centroid trajectories, oscillations, network topology) are exported as standardized .csv files suitable for downstream statistical analysis, ensuring reproducibility and integration into existing workflows.

  bioinformatics2026-02-22v2

• Bacterial protein function prediction via multimodal deep learning

  Muzio, G.; Adamer, M.; Fernandez, L.; Miklautz, L.; Borgwardt, K.; Avican, K.

  AI Summary

  • Developed DeepEST, a multimodal deep learning framework to predict bacterial protein functions by assigning GO terms, using gene expression, location, and protein structure.
  • DeepEST integrates a multi-layer perceptron for expression/location data and a structure-based predictor, enhanced by a novel masked loss function for bacterial species.
  • DeepEST outperformed existing methods on a 25-species benchmark and predicted functions for unclassified proteins in 25 human bacterial pathogens.

  Abstract

  Bacterial proteins are specialized with extensive functional diversity for survival in diverse and stressful environments. A significant portion of these proteins remains functionally uncharacterized, limiting our understanding of bacterial survival mechanisms. Hence, we developed Deep Expression STructure (DeepEST), a multimodal deep learning framework designed to accurately predict protein function in bacteria by assigning Gene Ontology (GO) terms. DeepEST comprises two modules: a multi-layer perceptron that takes gene expression and gene location as input features, and a protein structure-based predictor. Within DeepEST, we integrated these modules through a learnable weighted linear combination and introduced a novel masked loss function to fine-tune the structure-based predictor for bacterial species. These modeling choices are particularly well suited for bacteria due to the spatial organization of their circular genomes. Functionally related genes frequently co-localize and are co-transcribed within operons, allowing transcription dynamics to serve as crucial, condition-dependent regulatory signals. We show that DeepEST outperforms existing protein function prediction methods on a 25-species benchmark, relying solely on amino acid sequence or protein structure. Moreover, DeepEST predicts GO terms for unclassified hypothetical proteins across 25 human bacterial pathogens, facilitating the design of experimental setups for characterization studies. By combining expression, localization, and structure information in a unified deep learning framework, DeepEST bridges organism-specific data integration and structure-based transfer learning, providing a method tailored for bacterial protein function prediction in settings with structural and multi-condition expression data.

  bioinformatics2026-02-22v2

• Bias in genome-wide association test statistics due to omitted interactions

  Yelmen, B.; Güler, M. N.; Estonian Biobank Research Team, ; Kollo, T.; Möls, M.; Charpiat, G.; Jay, F.

  AI Summary

  • This study investigates how omitting interaction terms in linear models used for GWAS can bias test statistics, specifically by altering the mean and variance of the null statistic.
  • Through mathematical derivation and simulation using Estonian Biobank data, the study shows that ignoring epistasis can lead to an anti-conservative regime, inflating significance.
  • The findings suggest that GWAS results based on linear models might include spurious associations, urging caution in their interpretation.

  Abstract

  Over the past two decades, genome-wide association studies (GWAS) enabled the discovery of thousands of variants associated with many complex human traits. However, conventional GWAS are still widely performed with linear models with the assumption that the genetic effects are predominantly additive. In this work, we investigate the test statistic behavior when linear models are used to obtain significant genotype-phenotype associations without accounting for epistasis. We first algebraically derive mean and variance shift in the null statistic due to the omitted interaction term, and define the boundary between conservative (i.e., deflated statistic tail) and anti-conservative (i.e., inflated statistic tail) regimes for the common GWAS significance threshold. We then perform phenotype simulation analyses using the Estonian Biobank genotypes and validate the mathematical model. We demonstrate that the anti-conservative regime is plausible under realistic parameter settings and models omitting interaction terms can produce spurious significance. Our findings suggest caution when interpreting statistically significant signals reported in the literature based on linear models, especially for large-scale GWAS.

  bioinformatics2026-02-22v2

• STELAR-X: Scaling Coalescent-Based Species Tree Inference to 100,000 Species and Beyond

  Saha, A.; Bayzid, M. S.

  AI Summary

  • STELAR-X is introduced as a scalable, triplet-based phylogenetic inference algorithm for species tree reconstruction under the multispecies coalescent model, optimized for ultra-large datasets.
  • It achieves O(nk) memory complexity for n species and k gene trees, significantly reducing both running time and memory usage compared to existing methods like ASTRAL-MP.
  • Experiments showed STELAR-X analyzed datasets with 100,000 taxa in 8.5 hours and 100,000 genes in 4 minutes, demonstrating unprecedented scalability.

  Abstract

  Summary methods reconstruct species trees from collections of gene trees by accounting for gene tree discordance, and offer a statistically consistent framework for phylogenomic inference under the multispecies coalescent model. While existing triplet- and quartet-based approaches such as ASTRAL and STELAR have provable statistical consistency, their running time and memory usage restrict their applicability to ultra-large datasets. We introduce STELAR-X, a statistically consistent and highly scalable triplet-based phylogenetic inference algorithm that achieves an asymptotically optimal memory complexity of O(nk) for n species and k gene trees--essentially matching the input size and allowing analyses to remain feasible as long as the input trees fit in memory--while also substantially reducing running time. STELAR-X achieves this by a comprehensive re-engineering of the underlying data structures and algorithms. We introduce a novel, compact integer tuple-based encoding of tree bipartitions and efficient procedures for rapid pre-computation of bipartition weights. We further leverage GPU parallelism for fast pre-computation of necessary weights. This improved and redesigned computational framework underpins a dynamic programming algorithm with substantially reduced computational overhead. Extensive experiments demonstrate that STELAR-X achieves unprecedented scalability. On simulated datasets with 10,000 taxa and 1,000 gene trees, STELAR-X runs 712x faster than ASTRAL-MP (the most scalable variant of ASTRAL) while using 7.5x less CPU memory. Most significantly, STELAR-X analyzed a dataset of 100,000 taxa and 1,000 genes in 8.5 hours using 86 GB RAM, and a 100,000-gene dataset with 1000 taxa in just 4 minutes using 106 GB RAM -- scales that were previously intractable for statistically consistent summary methods. STELAR-X is publicly available at <a href="https://github.com/aaniksahaa/STELAR-X">https://github.com/aaniksahaa/STELAR-X</a>.

  bioinformatics2026-02-22v2

• Protenix-v1: Toward High-Accuracy Open-Source Biomolecular Structure Prediction

  Zhang, Y.; Gong, C.; Zhang, H.; Ma, W.; Liu, Z.; Chen, X.; Guan, J.; Wang, L.; Yang, Y.; Xia, Y.; Xiao, W.

  AI Summary

  • Protenix-v1 (PX-v1) is introduced as an open-source biomolecular structure prediction model that outperforms AlphaFold3 with the same constraints.
  • It shows improved prediction quality with increased sampling budget and includes features like protein template integration and RNA MSA support.
  • A variant, Protenix-v1-20250630, trained on a larger dataset, offers enhanced accuracy, and new evaluation tools are provided for better benchmarking.

  Abstract

  We introduce Protenix-v1 (PX-v1), the first open-source structure prediction model to attain superior performance to AlphaFold3 while strictly adhering to the same training data cutoff, model size, and inference budget. Beyond standard evaluations, we highlight the effectiveness of inference-time scaling behavior, demonstrating that increasing the sampling budget yields consistent improvements in prediction quality--a behavior previously seen in AlphaFold3 but not in other open-source models. In addition to improved accuracy, Protenix-v1 incorporates key capabilities including protein template integration and RNA MSA support. Furthermore, to better support real-world applications such as drug discovery, we additionally release Protenix-v1-20250630, a variant trained on a larger dataset (cutoff: June 30, 2025), delivering further improved prediction accuracy. Finally, we identify the limitations of current benchmarking tools and we provide updated evaluation tools and year-stratified benchmarks to facilitate more reliable and transparent assessment within the community. Collectively, these contributions provide a robust foundation for the Protenix series and the broader field.

  bioinformatics2026-02-22v2

• Leveraging Large Language Models to Extract Prognostic Pathology Features in Ewing Sarcoma

  Huang, J.; Batool, A.; Gu, Z.; Zhao, Z.; Yao, B.; Black, J.; Davis, J.; al-Ibraheemi, A.; DuBois, S.; Barkauskas, D.; Ramakrishnan, S.; Hall, D.; Grohar, P.; Xie, Y.; Xiao, G.; Leavey, P. J.

  AI Summary

  • The study aimed to use Large Language Models (LLMs) to extract prognostic histologic features from pathology reports of Ewing sarcoma patients from six COG trials.
  • The LLM achieved high accuracy (94-98.1%) in extracting 17 IHC markers, surpassing human annotators in some cases.
  • Survival analysis revealed NSE as a negative prognostic marker (HR 2.15) and S100 as a positive one (HR 0.58), suggesting potential for refining risk stratification in Ewing sarcoma.

  Abstract

  Background: Current risk stratification for Ewing sarcoma relies heavily on clinical factors such as metastatic status, failing to capture histologic heterogeneity as a potential prognostic indicator. Although pathology reports contain rich biological data, this information remains locked in unstructured narrative text, limiting large-scale retrospective analyses. We aimed to validate the utility of Large Language Models (LLMs) for scalable data abstraction and to identify prognostic histologic features from a large multi-institutional cohort. Methods: We conducted a retrospective cohort study using data from six Children's Oncology Group (COG) clinical trials. We utilized an LLM-based pipeline (OpenAI o3) to extract structured variables, including immunohistochemical (IHC) markers and CD99 staining patterns - from digitized, Optical Character Recognition (OCR)-processed pathology reports. Extraction accuracy was validated against a human-annotated ground truth (n=200) and cross-validated against senior experts (n=48). We assessed the association between extracted features and Overall Survival (OS) using Kaplan-Meier analysis and multivariable Cox proportional hazards regression, adjusting for metastatic status. Findings: We analyzed 931 diagnostic pathology reports spanning over 19-years. The LLM achieved a weighted average accuracy of 94% across 17 IHC markers; in a cross-validation subset, the LLM outperformed human annotators (weighted average accuracy over 15 IHC markers: LLM o3: 98.1%, a resident specialist 91.4%, and a senior expert 95.9%). Survival analysis identified Neuron-Specific Enolase (NSE) and S100 as significant prognostic biomarkers. After adjusting for metastatic status, NSE positivity was associated with significantly inferior survival (HR 2.15, 95% CI 1.15 - 4.02, p=0.016); this risk was most pronounced in patients with non-metastatic disease (HR 5.64, p=0.0055). Conversely, S100 positivity was associated with improved survival (HR 0.58, 95% CI 0.34-1.00, p=0.046). Interpretation: LLM-assisted extraction of pathology variables is highly accurate and scalable, capable of unlocking "dark data" from historical clinical trials. We identified NSE as a potent risk factor and S100 as a protective marker in Ewing sarcoma, particularly in localized disease. These findings suggest that AI-derived histologic data can refine risk stratification and, if validated, warrant inclusion in future prospective trials.

  bioinformatics2026-02-22v1

• Hybrid MD-generative modeling expands RNA ensembles to include cryptic ligand-binding conformations: application to HIV-1 TAR

  Kurisaki, I.; Hamada, M.

  AI Summary

  • The study uses Molearn, a hybrid MD-generative deep learning model, to explore cryptic ligand-binding conformations in apo RNA structures, focusing on HIV-1 TAR.
  • Molearn was trained on apo TAR conformations to generate a diverse ensemble, from which potential MV2003-binding conformations were identified.
  • Docking simulations showed that these generated conformations could bind MV2003 with interaction scores similar to those from NMR structures, demonstrating the model's ability to predict novel ligand-binding RNA states.

  Abstract

  Cryptic ligand-binding sites--absent in apo structures but formed upon conformational rearrangement--offer high specificity for RNA-ligand recognition, yet remain rare among experimentally resolved RNA-ligand complex structures and difficult to predict in silico. We apply Molearn, a hybrid molecular dynamics-generative deep learning model, to expand apo RNA conformational ensembles to include cryptic states. Focusing on the paradigmatic HIV-1 TAR-MV2003 system, Molearn was trained exclusively on apo TAR conformations and used to generate a diverse ensemble of TAR structures. Candidate cryptic MV2003-binding conformations were subsequently identified using post-generation geometric analyses. Docking simulations of these conformations with MV2003 yielded binding poses with RNA-ligand interaction scores comparable to those of NMR-derived complexes. Notably, this work provides the first demonstration that a generative modeling framework can access cryptic RNA conformations that are ligand-binding competent and have not been observed in prior molecular-dynamics and deep-learning studies.

  bioinformatics2026-02-21v7

• Defining the Active Conformation of Typical Protein Kinase Domains from Substrate-Bound PDB Structures Enables Active-State AlphaFold2 Models for All 437 Human Catalytic Protein Kinases

  Gizzio, J.; Faezov, B.; Xu, Q.; Dunbrack, R. L.

  AI Summary

  • The study aimed to define the active conformation of human protein kinase domains by analyzing 248 substrate-bound kinase structures, identifying criteria for the active state.
  • Using these criteria, only 30% of the 437 human catalytic kinases were found in active form in the PDB.
  • AlphaFold2 was employed to model all 437 kinases in their active form, with 71% of models achieving a backbone RMSD < 1.0 Å to benchmark structures, enhancing understanding of kinase activity in diseases like cancer.

  Abstract

  Humans have 437 catalytically competent protein kinase domains with the typical kinase fold, similar to the structure of Protein Kinase A (PKA). The active form of a kinase must satisfy requirements for binding ATP, magnesium, and substrate. From structural bioinformatics analysis of 248 crystal structures of 54 unique substrate-bound kinases, we derived structural criteria for the active form of typical protein kinases. We include well-known requirements on the DFG motif of the activation loop and the N-terminal domain salt bridge, but also on the positions of the N-terminal and C-erminal segments of the activation loop that must be placed appropriately to bind substrate. With these criteria, only 130 of the 437 human catalytic protein kinases (30%) are in the Protein Data Bank in their active form. Because the active forms of catalytic kinases are needed for understanding substrate specificity and the effects of mutations on catalytic activity in cancer and other diseases, we used AlphaFold2 to produce models of all 437 human protein kinases in the active form. This was accomplished with templates from the PDB that resemble substrate-bound structures, shallow multiple sequence alignments of orthologs and close paralogs of the query protein, and application of the active-kinase criteria to the output models. We selected models for each kinase based on intramolecular ipSAE scores of the activation loop residues of these models, demonstrating that the highest scoring models have the lowest or close to the lowest RMSD to 29 non-redundant substrate-bound structures in the PDB. A larger benchmark of 117 active kinase structures with solved activation loops in the PDB shows that 71% of the highest scoring AlphaFold2 models had backbone RMSD < 1.0 [A] to the benchmark structures and 92% were within 2.0 [A]. Models for all 437 catalytic kinases are available at https://dunbrack.fccc.edu/kincore/activemodels. We believe they may be useful for interpreting mutations leading to constitutive catalytic activity in cancer as well as for templates for modeling substrate and inhibitor binding for molecules which bind to the active state.

  bioinformatics2026-02-21v2

• DynaBiomeX: An Interpretable Dual-Strategy Deep Learning Framework for Architectural Noise Filtration in Sparse Longitudinal Microbiome Data

  Qureshi, A.; Wahid, A.; Qazi, S.; Shahzad, M. K. K.

  AI Summary

  • DynaBiomeX is a dual-strategy deep learning framework designed to filter noise in sparse longitudinal microbiome data, integrating Stacking Ensembles (Bi-LSTM, GRU) and an adapted Temporal Fusion Transformer (TFT).
  • It was validated on 1,871 hematopoietic cell transplantation patients to detect gut dysbiosis, with the ensembles acting as high-sensitivity screeners (ROC-AUC = 0.912) and the TFT as a precision Sentinel (Precision = 1.0, MCC = 0.646).
  • The TFT showed superior calibration (ECE = 0.0085), and ablation studies confirmed robustness without clinical covariates (ROC-AUC > 0.81).

  Abstract

  Longitudinal microbiome datasets present unique challenges due to extreme sparsity, zero-inflation, and non-stationary behavior. Conventional Recurrent Neural Networks (RNNs) struggle to distinguish structural from sampling zeros in these contexts, limiting their utility for Clinical Decision Support (CDS). We introduce DynaBiomeX, an interpretable framework specifically developed for sparse biomedical time-series. It integrates Stacking Ensembles (Bi-LSTM, GRU) with an adapted Temporal Fusion Transformer (TFT) in a unified Screener-Sentinel workflow. The Ensembles optimize collective decision boundaries to maximize sensitivity and minimize missed cases. Concurrently, the TFT functions as a Physiological Gatekeeper, utilizing Gated Residual Networks (GRN) to actively filter stochastic noise from real biological signals. We validated this approach on a multi-modal dataset of 1,871 hematopoietic cell transplantation (HCT) patients to detect gut dysbiosis. Stacking ensembles maximized discriminative performance (ROC-AUC = 0.912), effectively serving as high-sensitivity screeners. In contrast, the Adapted TFT functioned as a precision Sentinel, achieving zero false positives (Precision = 1.0) and high stability (MCC = 0.646). Crucially, the TFT demonstrated superior probabilistic reliability with a low Expected Calibration Error (ECE = 0.0085), addressing the "black-box" overconfidence typical of deep learning models. Ablation studies confirmed predictive robustness even without clinical covariates (ROC-AUC > 0.81). DynaBiomeX couples sensitive screening with precise, calibrated validation to robustly analyze sparse longitudinal data. Validated on microbiome dysbiosis, this framework offers a scalable template for zero-inflated domains like single-cell sequencing and EHR monitoring.

  bioinformatics2026-02-21v2

• ProteoMapper: Alignment-Aware Identification and Quantitative Analysis of Contextual Motif-Domain Patterns in Protein Families

  Sefa, S. M.; Sarkar, J.; Robin, A. H. K.; Uddin, M.

  AI Summary

  • ProteoMapper integrates domain annotation with motif detection to analyze spatial relationships in protein families, introducing metrics like positional conservation scoring and Motif-Domain Coverage Score (MDCS).
  • The tool processes alignments in Excel format, providing rapid analysis and color-coded reports, validated across three protein families with high accuracy.
  • In Arabidopsis ERD6-like sugar transporters, MDCS analysis showed PROSITE signatures PS00216 and PS00217 are fully domain-embedded but differ in evolutionary conservation, suggesting subfunctionalization.

  Abstract

  Protein function depends on interactions between structural domains and regulatory motifs. Yet current tools analyze these elements separately, hindering investigation of disease mutations affecting evolutionarily conserved, structurally constrained motifs. We present ProteoMapper, a computational framework integrating HMMER-based domain annotation with user-defined motif detection to quantify motif-domain spatial relationships in protein families. ProteoMapper introduces two discovery metrics: (1) positional conservation scoring, identifying motifs at identical alignment coordinates in [&ge;] N% of sequences (default 60%), indicating purifying selection; (2) Motif-Domain Coverage Score (MDCS), quantifying motif embedding within Pfam domains (MDCS=1: fully embedded; MDCS=0: extra-domain). The platform processes Excel-formatted alignments without programming requirements, delivering color-coded reports with conserved motif positions, domain boundaries, and MDCS values. Parallel execution of sequence batches enables rapid analysis (8 motifs were searched in 150 sequences with complete Pfam scanning in <6 seconds on standard hardware). Validation across three protein families confirmed technical accuracy and biological insight. In PLATZ transcription factors (24 proteins), domain predictions achieved 0.94 mean intersection-over-union versus published annotations, exactly reproducing 22 of 23 reported spans. In Arabidopsis ERD6-like sugar transporters (17 proteins), MDCS analysis revealed canonical PROSITE signatures PS00216 and PS00217 are equally domain-embedded (MDCS=1.0) but evolutionarily divergent. PS00217 shows positional conservation (58.8% of sequences) while PS00216 exhibits dispersal, suggesting subfunctionalization. In tomato actin-depolymerizing factors (11 proteins), domain detection achieved 100% sensitivity with >93% positional concordance. ProteoMapper enables hypothesis-driven investigation of evolutionary constraints, regulatory mechanisms, and variant effect prediction in biomedical and functional proteomics. Source code, documentation, and test results with datasets at https://github.com/sifullah0/ProteoMapper.

  bioinformatics2026-02-20v1

• Geometric-aware and interpretable deep learning for single-cell batch correction via explicit disentanglement and optimal transport

  Jiang, C.; Zheng, R.; Ji, Y.; Cao, S.; Fang, Y.; Wang, Z.; Wang, R.; Liang, S.; Tao, S.

  AI Summary

  • The study introduces iDLC, a deep learning framework for single-cell RNA sequencing batch correction, using explicit feature disentanglement and optimal transport for dual-level correction.
  • iDLC separates biological from technical components in a structured latent space and uses mutual nearest neighbors for geometric alignment.
  • Evaluations on various datasets show iDLC effectively removes batch effects, preserves cell subtypes, and outperforms existing methods in both correction and biological fidelity.

  Abstract

  Single-cell RNA sequencing enables high-resolution characterization of cellular heterogeneity, yet integrating datasets from diverse sources remains challenging due to batch effects. Current methods rely on implicit feature disentanglement and and lack geometric constraintsoften result in under-correction, over-correction, or compromised biological fidelity. Here, we present iDLC, an interpretable deep learning framework that performs dual-level correction through explicit feature disentanglement and optimal transport - regularized adversarial alignment. iDLC separates biological and technical components within a structured latent space, then leverages high-confidence mutual nearest neighbor pairs to guide geometrically constrained distribution alignment. Systematic evaluation across pancreatic cancer datasets with varying batch effect intensities, multi-source human immune cells, and large-scale cross-species atlases demonstrates that iDLC robustly eliminates complex batch effects while preserving fine-grained cell subtypes, continuous developmental trajectories, and rare populations. The framework scales efficiently to datasets exceeding one million cells and consistently outperforms existing methods in both batch correction and biological conservation metrics. iDLC provides a principled and reliable tool for constructing unified single-cell reference atlases across diverse experimental conditions and biological systems.

  bioinformatics2026-02-20v1

• OT-knn: a neighborhood-aware optimal transport framework for aligning spatial transcriptomics data

  Song, J.; Li, Q.

  AI Summary

  • OT-knn is introduced as a method for aligning spatial transcriptomics (ST) data by integrating local neighborhood information into an optimal transport framework.
  • It reconstructs each spot using its k-nearest neighbors to capture microenvironment context, enhancing robustness against noise and variability.
  • Evaluations on simulated and real datasets, including human and mouse brain data, show OT-knn achieves accurate alignment despite spatial deformation, donor heterogeneity, and developmental variation.

  Abstract

  Spatial transcriptomics (ST) measures gene expression while preserving spatial context within tissues, enabling detailed characterization of tissue organization. As ST technologies advance, aligning datasets across tissue sections, individuals, platforms, and developmental stages has become increasingly important but remains challenging due to sparse expression, biological heterogeneity, and geometric distortions between slices. We introduce OT-knn, a method for ST alignment that integrates local neighborhood information within an optimal transport framework. Rather than relying solely on single-spot expression, OT-knn reconstructs each spot using its spatial k-nearest neighbors, capturing microenvironment context that is more robust to noise and variability. These representations are then used to derive probabilistic correspondences between slices. We evaluate OT-knn using simulated data with known ground-truth alignment and real datasets from multiple ST platforms, including human dorsolateral prefrontal cortex data (10x Genomics Visium), mouse brain aging data with both within-donor and cross-donor comparisons (MERFISH), and a multi-stage axolotl brain dataset (Stereo-seq). Across these settings, OT-knn achieves accurate and robust alignment, particularly in the presence of spatial deformation, donor heterogeneity, and developmental variation.

  bioinformatics2026-02-20v1

• SuperCell2.0 enables semi-supervised construction of multimodal metacell atlases

  Herault, L.; Gabriel, A. A.; Duc, B.; Dolfi, B.; Shah, A.; Joyce, J. A.; Gfeller, D.

  AI Summary

  • SuperCell2.0 is introduced as a workflow for constructing semi-supervised multimodal metacells from large single-cell datasets.
  • It was found that multimodal metacells outperform single-modality metacells, enhancing inter-modality consistency and integration of multiomic data.
  • The workflow identified interferon-primed monocytes and macrophages in blood and tumor samples, with markers used to characterize this population in healthy donors.

  Abstract

  Multimodal single-cell atlases comprising hundreds of thousands of cells provide unique resources for exploring complex biological tissues and generating testable hypotheses. To streamline the analysis of such large datasets, we introduce SuperCell2.0, a robust workflow to build (semi-)supervised multimodal metacells. We demonstrate that multimodal metacells outperform metacells built with a single modality, improve inter-modality consistency, and facilitate integration of multiomic single-cell datasets. SuperCell2.0 can further leverage full or partial cell type annotations to improve metacell quality. This workflow enables us to construct multimodal metacell atlases from blood and tumor samples and identifies interferon-primed monocytes and macrophages in the circulation and in the tumor microenvironment. Markers derived from the metacell analysis enable us to sort and phenotypically characterize this population in healthy donors. Overall, our work demonstrates how SuperCell2.0 facilitates the analysis of large multimodal single-cell atlases.

  bioinformatics2026-02-20v1

• wavess 1.2: Presenting an HLA-aware within-host virus sequence simulation framework

  Lapp, Z.; Leitner, T.

  AI Summary

  • The study extends the wavess framework to simulate within-host virus sequence evolution by incorporating an HLA-aware CD8+ CTL response and variable recombination rates.
  • This allows for more accurate modeling of virus sequences, especially in regions influenced by CTLs, and supports investigations into how these mechanisms affect within-host evolution.

  Abstract

  Motivation: Understanding how virus sequences are shaped by selection can inform vaccine design and transmission inference. Modeling within-host evolution to interrogate these questions requires a detailed mechanistic framework that accurately captures sequence diversification. The CD8+ cytotoxic T-lymphocyte (CTL) response plays an important role in immune-mediated selection and can leave strong signatures in virus sequences; however, existing sequence-based within-host virus modeling frameworks do not explicitly include an HLA-aware CTL response. Results: We extended our previously published within-host sequence evolution simulator, wavess, to include an explicit CTL response, and share a method for identifying HLA-specific CTL epitopes given a founder virus sequence. We also updated the model to permit a variable recombination rate, which allows for modeling recombination hotspots, non-adjacent genes, and segmented genomes. These extensions to wavess allow for more accurate simulation of viruses and virus genes, particularly in regions of the genome where the immune response is dominated by CTLs (rather than antibodies). It also provides the foundation for investigations of how these newly-added biological mechanisms influence within-host evolution. Availability and implementation: The core of wavess is written in Python 3, with helper functions written in R. It is available at https://github.com/MolEvolEpid/wavess.

  bioinformatics2026-02-20v1

• Prediction of ligand-dependent conformational sampling of ABC transporters by AlphaFold3 and correlation to experimental structures and energetics

  Tang, Q.; Mchaourab, H.; Wu, T.; Soubasis, B.

  AI Summary

  • This study uses AlphaFold3 to predict nucleotide-dependent conformational changes in ABC transporters, comparing these predictions to experimental structures.
  • AlphaFold3 accurately samples known conformations and correlates with experimental dynamics, also predicting previously unobserved conformations.
  • The study suggests that AlphaFold3's predictions might extrapolate from known structures, as sequence determinants influence the predicted conformational changes.

  Abstract

  AlphaFold3 architecture represented an important leap relative to Alphafold2 by enabling the inclusion of protein ligands in the prediction network. Ligand-dependent structural rearrangements are inherently difficult to predict computationally as they imply transitions between states separated by large energy differences. Here we apply AlphaFold3 to predict nucleotide-dependent changes in the conformational cycle of representative ABC transporters that have been extensively investigated by experimental structural biology techniques. We show that under similar conditions, AlphaFold3 predictions sample experimentally observed conformations. Moreover, the heterogeneity of these predictions correlates with experimental measures of dynamics obtained from multiple techniques. For couple of the tested transporters, the implied relative energetics of the conformations mirror their experimental counterpart. Remarkably, AlphaFold3 predicts previously unobserved conformations that have been implied to be sampled by ABC transporters. Finally, we report preliminary results showing that postulated sequence determinants of conformational changes modify the predictions of AlphaFold3. Although hundreds of ABC transporter structures have been determined and were included in the training data of AF3, we propose that aspects of its predictions reflect extrapolation of principles learned from these structures.

  bioinformatics2026-02-20v1

• A New Sparse Bayesian Quantile Neural Network-based Approach and Its Application to Discover Physiological Sweet Spots in the Canadian Longitudinal Study on Aging

  Min, J.; Vishnyakova, O.; Brooks-Wilson, A.; Elliott, L. T.

  AI Summary

  • The study introduces Q-FSNet and Q-DirichNet, neural network frameworks integrating quantile regression for identifying physiological sweet spots in high-dimensional data.
  • Using data from the Canadian Longitudinal Study on Aging, these methods identified 25 metabolites with optimal ranges that minimize biological age acceleration.
  • The findings suggest dietary and gut microbiome-derived metabolites as potential biomarkers for healthy aging, supported by existing literature.

  Abstract

  Identifying physiological sweet spots (optimal ranges for homeostasis) is essential for precision medicine. However, traditional statistical methods often rely on globally linear or locally jagged models that struggle to capture the smooth, non-linear nature of biological regulation in high-dimensional data. We present the Quantile Feature Selection Network (Q-FSNet), a neural network-based framework that integrates quantile regression, feature selection, and uncertainty estimation to identify biomarkers with sweet spots. Unlike traditional methods, Q-FSNet learns continuous response curves without requiring pre-specified number of change points. We further introduce Quantile Dirichlet Network (Q-DirichNet), a fully Bayesian extension that utilizes Dirichlet priors to automate feature shrinkage. Using data from the Canadian Longitudinal Study on Aging, we identified 25 metabolites with distinct homeostatic ranges for which biological age acceleration is minimized. The metabolites with sweet spots for biological aging include some derived from diet or produced by the gut microbiome; this highlights their potential for knowledge translation and public health impact. Our results, corroborated by existing literature, demonstrate that these sparse neural network-based methods offer a scalable and interpretable tool for discovering metabolic signatures of healthy aging vs. dysregulation in large-scale omics research.

  bioinformatics2026-02-20v1

• Chemical Probes in Scientific Literature: Expanding and Validating Target-Disease Evidence

  Adasme, M. F.; Ochoa, D.; Lopez, I.; Do, H.-M.-A.; McDonagh, E. M.; O'Boyle, N. M.; Leach, A. R.; Zdrazil, B.

  AI Summary

  • This study systematically analyzed over 18 million articles to quantify the impact of 561 chemical probes, identifying 5,558 unique target-disease associations.
  • Findings showed chemical probe evidence precedes structured data by 1-7 years, revealed 353 new T-D pairs, and 135 high-confidence associations for therapeutic repurposing in rare diseases.
  • Chemical probes were crucial for validating target-disease associations, enhancing evidence beyond correlative data like RNA expression.

  Abstract

  Chemical probes are indispensable tools for validating therapeutic hypotheses, yet their broader impact on early-stage drug discovery remains unquantified. To our knowledge, this study represents the first systematic, large-scale investigation of the chemical probe literature. By screening over 18 million articles using a high-quality dictionary of 561 chemical probes, we identified 20,000 articles mentioning a chemical probe which resulted in 5,558 unique target-disease (T-D) associations. Our analysis yields four principal findings that redefine the utility of these chemicals: First, we show that chemical probe evidence typically precedes the appearance of structured data in major knowledge bases by 1-7 years, providing a crucial lead time for target prioritisation. Second, we identified 353 T-D pairs (6.4%) with no prior evidence in the Open Targets Platform, highlighting the approach's discovery potential. Third, the application of strict novelty filters uncovered 135 new high-confidence associations between targets and diseases, revealing distinct opportunities for therapeutic repurposing in non-oncological, rare autoimmune diseases, and diseases without effective therapies due to complex biology or high treatment resistance. Finally, we demonstrate that chemical probes are essential for strengthening evidence, providing functional validation for associations previously supported only by weaker, correlative data such as RNA expression or animal models. Collectively, these findings illustrate that chemical probes catalyse early therapeutic discovery, emphasising the importance of cataloguing existing probes and identifying new ones.

  bioinformatics2026-02-20v1

• Differential analysis of image-based chromatin tracing data with Dory

  Ma, Z.; Liu, M.; Wang, S.; Wang, S.; Zang, C.

  AI Summary

  • Dory is a statistical method designed for differential analysis of chromatin tracing data to identify spatial pattern differences between two groups.
  • It quantifies pairwise spatial distances and uses multi-level statistical tests to detect significant structural changes, producing a differential score matrix.
  • Application of Dory revealed associations between chromatin structural changes and alterations in A/B compartments, promoter-enhancer interactions, and gene expression.

  Abstract

  Spatial organization of the genome plays a vital role in defining cell identity and regulating gene expression. The three-dimensional (3D) genome structure can be measured by sequencing-based techniques such as Hi-C usually on the cell population level or by imaging-based techniques such as chromatin tracing at the single-cell level. Chromatin tracing is a multiplexed DNA fluorescence in situ hybridization (FISH)-based method that can directly map the 3D positions of genomic loci along individual chromosomes at single-molecule resolution. However, few computational tools are available for statistical differential analysis of chromatin tracing data, which are inherently high-dimensional, highly variable and contain many missing values. Here, we present Dory, a statistical method for identifying differential spatial patterns between two groups of chromatin traces. Dory quantifies pairwise spatial distances among genomic regions in a chromatin trace and applies multi-level statistical tests to detect significant structural differences between the two groups of traces. It produces a differential score matrix highlighting region pairs with significant distance difference. Applying Dory to multiple chromatin tracing datasets, we found that the detected chromatin structural changes were associated with alterations in A/B compartments and promoter-enhancer interactions correlated with differential gene expression. Dory is a robust and user-friendly computational tool for quantitative analysis of imaging-based 3D genome data that enables systematic exploration of chromatin architecture and its roles in gene regulation.

  bioinformatics2026-02-20v1

• Learning heritable multimodal brain representation via contrastive learning

  Xia, T.; Zhao, X.; Islam, S. S. M.; Mohammed, K. K.; Xie, Z.; Zhi, D.

  AI Summary

  • This study introduces a multimodal contrastive learning framework using paired T1- and T2-weighted MRIs to derive heritable brain representations.
  • The approach improves prediction of traditional imaging-derived phenotypes, age, and brain disorders compared to single-modality models.
  • GWAS on these representations showed increased genetic loci overlap, revealing shared biological targets and enhancing genetic discovery.

  Abstract

  Magnetic resonance imaging (MRI)-derived phenotypes (IDP) has enabled the discovery of numerous genomic loci associated with brain structure and function. However, most existing IDPs and learned representations are derived from a single imaging modality, missing complementary information across modalities and potentially limiting the scope of genetic discovery. Here, we introduce a multimodal contrastive learning framework to derive heritable representations from paired T1- and T2-weighted MRIs. Unlike single-modality reconstruction-based models, we designed a momentum-based contrastive learning framework. As a result, our approach offers improved prediction of traditional IDPs, age, and brain disorders. Notably, genome-wide association studies (GWAS) of the learned representations reveal a substantially higher overlap of genetic loci across modalities, indicating improved alignment of their underlying genetic architecture. Analysis of the GWAS loci identified shared protein and drug targets, yielding meaningful biological insights. Overall, our framework learns shared representations across brain imaging modalities that exhibit anatomical and genetic coherence.

  bioinformatics2026-02-20v1

• SpecLig: Energy-Guided Hierarchical Model for Target-Specific 3D Ligand Design

  Zhang, P.; Han, R.; Kong, X.; Chen, T.; Ma, J.

  AI Summary

  • SpecLig is introduced as a framework for generating small molecules and peptides with enhanced target affinity and specificity, addressing the issue of promiscuous binding in structure-based models.
  • It uses a hierarchical SE(3)-equivariant variational autoencoder and an energy-guided geometric latent-diffusion model, incorporating chemical priors to favor pocket-complementary fragment combinations.
  • Evaluations show that SpecLig's ligands bind with high specificity and affinity, with real applications demonstrating reduced off-target risks.

  Abstract

  Structure-based generative models often optimize single-target affinity with ignorance of specificity, resulting in the generation of high-affinity candidates that exhibit promiscuous binding across unrelated targets. This decoupling of affinity and specificity not only compromises therapeutic efficacy but also elevates off-target risks that constrain translational potential. Therefore, we introduce SpecLig, a unified structure-based framework that jointly generates small molecules and peptides with improved target affinity and specificity. SpecLig represents a complex as a block-based graph, combining a hierarchical SE(3)-equivariant variational autoencoder with an energy-guided geometric latent-diffusion model. Chemical priors derived from block-block contact statistics are explicitly incorporated, biasing generation towards pocket-complementary fragment combinations. We benchmark SpecLig on peptide and small-molecule tasks using standard public datasets and propose precision/breadth testing paradigms to quantify specificity. Across multiple evaluations, ligand candidates generated by SpecLig usually bind to the target pocket with high specificity and affinity while maintaining competitive advantages in other attributes. Ablations indicate that both hierarchical representation and energy guidance contribute to success. Finally, we present multiple real applications that demonstrate how SpecLig improves ligands in natural complexes to mitigate potential off-target risks. SpecLig, therefore, provides a practical route to prioritize higher-specificity designs for downstream experimental validation. The codes are available at: https://github.com/CQ-zhang-2016/SpecLig.

  bioinformatics2026-02-19v3

• A statistical framework for defining synergistic anticancer drug interactions

  Dias, D.; Zobolas, J.; Ianevski, A.; Aittokallio, T.

  AI Summary

  • The study developed a statistical framework to identify significant synergistic anticancer drug interactions by establishing reference null distributions from a large dataset of over 2,000 drug combinations across 125 cancer cell lines.
  • This approach allowed for the calculation of empirical p-values, confirming known synergistic combinations and revealing novel ones that were previously overlooked.
  • The framework was also applied to a smaller dataset, demonstrating its general applicability in detecting significant drug combination effects.

  Abstract

  Synergistic drug combinations have the potential to delay drug resistance and improve clinical outcomes. However, current cell-based screens lack robust statistical assessment to identify significant synergistic interactions for downstream experimental or clinical validation. Leveraging a large-scale dataset that systematically evaluated more than 2,000 drug combinations across 125 pan-cancer cell lines, we established reference null distributions separately for various synergy metrics and cancer types. These data-driven reference distributions enable estimation of empirical p-values to assess the significance of observed drug combination effects, thereby standardizing synergy detection in future studies. The statistical evaluation confirmed key synergistic combinations and uncovered novel combination effects that met stringent statistical criteria, yet were overlooked in the original analyses. We revealed cell context-specific drug combination effects across the tissue types and differences in statistical behavior of the synergy metrics. To demonstrate the general applicability of our approach to smaller-scale studies, we applied the reference distributions to evaluate the significance of combination effects in an independent dataset. We provide a fast and statistically rigorous approach to detecting synergistic drug interactions in combinatorial screens.

  bioinformatics2026-02-19v3

• The practical impact of numerical variability on structural MRI measures of Parkinson's disease

  Chatelain, Y. M. B.; Sokołowski, A.; Sharp, M.; Poline, J.-B.; Glatard, T.

  AI Summary

  • The study investigated how numerical variability in MRI analyses affects structural measures in Parkinson's disease using FreeSurfer to simulate computational differences.
  • Numerical variability was found to be significant, reaching up to one-third of population variability, impacting statistical conclusions.
  • A tool was developed to estimate the Numerical-Population Variability Ratio (NPVR), revealing a high probability of false positives and negatives in existing Parkinson's disease MRI studies due to numerical variability.

  Abstract

  Numerical variability is rarely quantified in neuroimaging despite many biomarkers relying on subtle morphometric differences across individuals. We instrumented FreeSurfer, a widely used neuroimaging pipeline, to simulate numerical differences across computational environments, and used it to measure numerical variability in MRI analyses of Parkinson's disease patients and controls. In multiple cortical and subcortical regions, numerical variation reached nearly one-third of the population variability, altering statistical conclusions about group differences and clinical associations. To assess the impact of numerical noise in existing studies, we developed a practical tool that estimates the Numerical-Population Variability Ratio (NPVR) in a study, and propagates the resulting numerical uncertainty to common statistics and associated p-values. By applying this framework to thirteen previously published studies reporting MRI measures of Parkinson's disease, we quantified the probability of numerically induced false positives and false negatives in the literature, highlighting a substantial impact of numerical variability on MRI measures of Parkinson's disease. These results underscore the importance of systematically evaluating numerical stability in neuroimaging and provides a practical framework to do so.

  bioinformatics2026-02-19v2

• Pioneer and Altimeter: Fast Analysis of DIA Proteomics Data Optimized for Narrow Isolation Windows

  Wamsley, N. T.; Wilkerson, E. M.; Major, M. B.; Goldfarb, D.

  AI Summary

  • The study introduces Pioneer and Altimeter, tools designed for fast analysis of DIA proteomics data, addressing challenges posed by narrow isolation windows in mass spectrometry.
  • Altimeter models fragment intensity as a function of collision energy, allowing spectral library reuse, while Pioneer re-isotopes spectra and uses advanced techniques for efficient analysis.
  • These tools enable high-confidence protein identification and quantification, performing analyses 2-6 times faster while controlling false-discovery rates across various experimental setups.

  Abstract

  Advances in mass spectrometry have enabled increasingly fast data-independent acquisition (DIA) experiments, producing datasets whose scale and complexity challenge existing analysis tools. Those same advances have also led to the use of narrow isolation windows, which alter MS2 spectra via fragment isotope effects and give rise to systematic deviations from spectral libraries. Here we introduce Pioneer and Altimeter, open-source tools for fast DIA analysis with explicit modeling of isolation-window effects. Altimeter predicts deisotoped fragment intensity as a continuous function of collision energy, allowing a single spectral library to be reused across datasets. Pioneer re-isotopes predicted spectra per scan and combines an intensity-aware fragment index, spectral deconvolution, and dual-window quantification for fast, spectrum-centric DIA analysis. Across instruments, experimental designs, and sample inputs, Pioneer enables high-confidence identification and precise quantification at scale, completing analyses 2-6x faster and maintaining conservative false-discovery rate control.

  bioinformatics2026-02-19v2

• Harnessing DNA Foundation Models for Cross-Species Transcription Factor Binding Site Prediction in Plant Genomes

  Haghani, M.; Dhulipalla, K. V.; Li, S.

  AI Summary

  • This study evaluates the performance of DNA foundation models (DNABERT-2, AgroNT, HyenaDNA) in predicting transcription factor binding sites (TFBSs) in plant genomes using Arabidopsis thaliana and Sisymbrium irio data.
  • The models were benchmarked against specialized methods like DeepBind and BERT-TFBS.
  • HyenaDNA showed superior predictive accuracy and computational efficiency, suggesting potential for scalable genome-wide TFBS prediction in plants.

  Abstract

  Accurate prediction of transcription factor binding sites (TFBSs) is crucial for understanding gene regulation. While experimental methods like ChIP-seq and DAP-seq are informative, they are labor-intensive and species-specific. Recent advancements in large-scale pretrained DNA foundation models have shown promise in overcoming these limitations. This study evaluates the performance of three such models, DNABERT-2, AgroNT, and HyenaDNA, in predicting TFBSs in plants. Using Arabidopsis thaliana and Sisymbrium irio DAP-seq data, we benchmark their accuracy against specialized methods like DeepBind and BERT-TFBS. Our results demonstrate that foundation models, particularly HyenaDNA, offer superior predictive accuracy and computational efficiency, highlighting their potential for scalable, genome-wide TFBS prediction in plants.

  bioinformatics2026-02-19v2

• Fine-tuning protein language models on human spatial constraint improves variant effect prediction by reducing wild-type sequence bias

  Bajracharya, G.; Capra, J. A.

  AI Summary

  • The study introduces Human Spatial Constraint (HuSC), which quantifies intraspecies constraint on missense variants by integrating human genetic variation with 3D protein structures.
  • Fine-tuning protein language models (PLMs) on HuSC scores enhances prediction of variant effects by reducing bias towards wild-type sequences.
  • HuSC outperforms traditional conservation metrics in predicting pathogenic variants and improves variant fitness predictions across different taxa and assays.

  Abstract

  Protein language models (PLMs) achieve state-of-the-art performance in predicting effects of missense variants, yet they do not explicitly consider variation within the human population. Here, we introduce Human Spatial Constraint (HuSC), a framework for quantifying intraspecies constraint on missense variants that integrates population-scale human genetic variation with 3D protein structures. We then fine-tune PLMs on HuSC scores. HuSC models the expected frequency of missense variation under neutral evolution and compares it to observed variation, accounting for both variation in mutational processes and 3D structural context. HuSC outperforms traditional inter- and intraspecies conservation metrics in predicting pathogenic variants. By focusing on intraspecies variation, HuSC reveals protein sites under human-specific constraint that cannot be captured by interspecies models. Integrating this intraspecies perspective into PLMs by fine-tuning on HuSC scores improves the prediction of variant fitness from deep mutational scans across diverse taxa and functional assay types. The improvement after fine-tuning comes largely from reducing bias toward wild-type sequences in regions that tolerate variation. Together, these results demonstrate that combining intraspecies constraint with cross-species PLMs improves their performance in variant-effect interpretation.

  bioinformatics2026-02-19v2

• Convergence of Angiotensin Signaling on Lung Pericyte and Stromal Behaviors

  Benjamin, K. J. M.; Gonye, E.; Sauler, M.; Gidner, S.; Malinina, A.; Neptune, E. R.

  AI Summary

  • The study investigated the expression of angiotensin receptors AGTR1 and AGTR2 in human lung tissue using bulk and single-nucleus transcriptomics, finding AGTR1 in lung pericytes and AGTR2 in alveolar epithelial type 2 cells.
  • AGTR1 expression in pericytes was linked to pericyte behaviors; its inhibition restored pericyte numbers in an emphysema model, suggesting a role in airspace repair.
  • In COPD, AGTR1 showed dysregulated expression in stromal cells, and angiotensin II with cigarette smoke exposure impaired pericyte migration and proliferation.

  Abstract

  The renin-angiotensin system is a well-characterized regulator of tissue homeostasis whose clinical relevance has expanded to include lung disorders such as chronic obstructive pulmonary disease (COPD)-associated emphysema, idiopathic pulmonary fibrosis, and COVID-19. Despite this interest, the cell-specific localization of angiotensin receptors in the human lung has remained poorly defined, in part due to limitations of available antibody reagents. Here, we define the expression patterns of the two predominant angiotensin receptors, AGTR1 and AGTR2, using complementary bulk and single-nucleus transcriptomic datasets from human lung tissue. We demonstrate that these receptors exhibit mutually exclusive, compartment-specific localization, with AGTR1 expressed in lung pericytes and AGTR2 expressed in alveolar epithelial type 2 cells. AGTR1 is detectable in isolated lung pericytes, and spatial colocalization with pericyte markers confirmed within the airspace microvasculature compartment by RNAscope. Airspace pericyte abundance was reduced in an experimental emphysema model but restored by pharmacologic attenuation of AGTR1 signaling commensurate with airspace repair. In COPD lungs, AGTR1 expression showed heterogeneous, disease-associated dysregulation across stromal populations, including upregulation in alveolar fibroblasts. Bulk transcriptomics also revealed aging-associated redistribution of AGTR1 expression into stromal compartments. Angiotensin II and cigarette smoke impaired pericyte migration toward endothelial cells, while combined exposure suppressed pericyte proliferation. Together, these findings identify AGTR1 as a new highly selective marker of lung pericytes and a regulator of pericyte behaviors within the airspace microvasculature. These findings provide a cell-resolved framework for angiotensin signaling with direct relevance to airspace resilience and therapeutic targeting.

  bioinformatics2026-02-19v2

• Investigating the topological motifs of inversions in pangenome graphs

  Romain, S.; Dubois, S.; Legeai, F.; Lemaitre, C.

  AI Summary

  • This study investigated how inversions are represented in pangenome graphs, focusing on identifying topological motifs for inversion bubbles.
  • Two motifs were identified: path-explicit and alignment-rescued, and a tool was developed to annotate these from bubble-caller outputs.
  • Analysis across four pipelines showed significant differences in inversion representation, with low recovery rates in real human datasets, indicating challenges in pangenomic inversion analysis.

  Abstract

  Background: Pangenome graphs are increasingly used in genetic diversity analyses because they reduce reference bias in read mapping and enhance variant discovery and genotyping from SNPs to Structural Variants. In pangenome graphs, variants appear as bubbles, which can be detected by dedicated bubble calling tools. Although these tools report essential information on the variant bubbles, such as their position and allele walks in the graph, they do not annotate the type of the detected variants. While simple SNPs, insertions, and deletions are easily distinguishable by allele size, large balanced variants like inversions are harder to differentiate among the large number of unannotated bubbles and remain underexplored in pangenome graph benchmarks and analyses. Results: In this work we focused on inversions, which have been drawing renewed attention in evolutionary genomics studies in the past years, and aimed to assess how this type of variant is handled by state of the art pangenome graph pipelines. We identified two distinct topological motifs for inversion bubbles: one path-explicit and one alignment-rescued, and developed a tool to annotate them from bubble-caller outputs. We constructed pangenome graphs with both simulated data and real data using four state of the art pipelines, and assessed the impact of inversion size, genome divergence and variant density on inversion representation and accuracy. Conclusions: Our results reveal substantial differences between pipelines in simulated graphs, with some inversions either misrepresented or lost. In addition, recovery rates are strikingly low in real human datasets, highlighting major challenges in analyzing inversions through pangenomic approaches.

  bioinformatics2026-02-19v2

• jazzPanda: A hybrid approach to find spatial markergenes in imaging-based spatial transcriptomics data

  Jin, X.; Putri, G. H.; Cheng, J.; Asselin-Labat, M.-L.; Smyth, G. K.; Phipson, B.

  AI Summary

  • The study introduces jazzPanda, a hybrid method for identifying spatial marker genes in imaging-based spatial transcriptomics, which integrates spatial coordinates of gene detections and cells.
  • jazzPanda uses a binning approach to pseudobulk gene detections and cells within clusters, enhancing marker gene analysis through linear models.
  • Testing on datasets from Xenium, CosMx, and MERSCOPE showed that jazzPanda's marker genes have strong spatial correlation and increased specificity compared to existing methods.

  Abstract

  Spatial transcriptomics enables the understanding of the spatial architecture of tissues, providing deeper insight into tissue structure and cellular neighbourhoods. A crucial step in the analysis of spatial data is cell type identification. In single cell RNA-sequencing (scRNA-seq) analysis, cells are clustered according to their transcriptional similarity, and marker genes for each cluster identified. Marker analysis identifies genes highly expressed in each cluster compared to the remaining clusters, and these marker genes are used to annotate clusters with cell types. For spatial data, there are limited software tools for appropriate marker gene detection methods that account for the spatial distribution of gene expression. Tools developed for scRNA-seq ignore spatial information for the cells and genes. We have developed a hybrid approach to prioritize marker genes that uses the spatial coordinates of gene detections and cells making up clusters. We propose a binning approach that effectively "pseudobulks" gene detections and cells within clusters that can then be used as input into linear models for marker analysis. Our approach can account for multiple samples and background noise. We have tested our methods on several public datasets from di!erent platforms including Xenium, CosMx and MERSCOPE. The marker genes detected by our method show strong spatial correlation with the corresponding clusters and have increased specificity compared to other methods. The method is implemented in the jazzPanda R Bioconductor package and is publicly available (https://bioconductor.org/packages/jazzPanda).

  bioinformatics2026-02-19v2

• Differential analysis of genomics count data with edge*

  Pachter, L.

  AI Summary

  • The study addresses the integration of edgeR, a tool for differential expression analysis, into the Python ecosystem, which is prevalent in single-cell genomics.
  • They developed edgePython, a Python version of edgeR 4.8.2, incorporating a negative binomial gamma mixed model for multi-subject single-cell analysis and empirical Bayes shrinkage for cell-level dispersion.
  • Key findings include the successful adaptation of edgeR to Python, enhancing its utility in single-cell genomic studies.

  Abstract

  The edgeR Bioconductor package is one of the most widely used tools for differential expression analysis of count-based genomics data. Despite its popularity, the R-only implementation limits its integration with the Python centric ecosystem that has become dominant in single-cell genomics. We present edgePython, a Python port of edgeR 4.8.2 that extends the framework with a negative binomial gamma mixed model for multi-subject single-cell analysis and empirical Bayes shrinkage of cell-level dispersion.

  bioinformatics2026-02-19v2