Bioinformatics (Oxford, England)[JOURNAL]
Sun
200 papers
OTalign: Optimal Transport Alignment for Remote Protein Homologs Using Protein Language Model Embeddings.
Kim M, Bae H, Jo G … +3 more , Kim K, Yoo J, Joo K
Bioinformatics · 2026 Jun · PMID 42378434 · Publisher ↗
MOTIVATION: Protein sequence alignment is a crucial task in bioinformatics, yet aligning remote homologs with low sequence identity remains a longstanding challenge, particularly due to the difficulty of handling gaps. W...
MOTIVATION: Protein sequence alignment is a crucial task in bioinformatics, yet aligning remote homologs with low sequence identity remains a longstanding challenge, particularly due to the difficulty of handling gaps. We introduce a new method that applies Optimal Transport (OT) theory to sequence alignment, providing a mathematically principled framework for modeling residue matches and gaps. RESULTS: OTalign formulates sequence alignment as an entropy-regularized unbalanced optimal transport (UOT) problem over embeddings derived from protein language models (PLMs). Unlike traditional methods, it introduces position-specific gap penalties that adapt to each sequence pair. On challenging remote-homolog benchmarks (SABmark, MALIDUP, MALISAM), OTalign consistently outperforms baselines (Needleman-Wunsch, HHalign) and recent PLM-based methods (PLMAlign, DeepBLAST), achieving F1 scores of 0.594 on SABmark Superfamily and 0.358 on SABmark Twilight. Furthermore, OTalign provides a quantitative and interpretable metric of how effectively PLM embeddings represent sequence similarity relationships. Finally, its differentiable nature enables end-to-end fine-tuning of PLMs, establishing a framework for learning embeddings explicitly optimized for alignment tasks. AVAILABILITY AND IMPLEMENTATION: This code is available at https://github.com/DeepFoldProtein/OTalign. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
OmicsTransformer: Self-Supervised Masked Consistency and Uncertainty-Aware Fusion for Robust Multi-Omics Prediction.
Feng J, Shan B, Deng J … +7 more , Jiang Z, Peng S, Peng S, Yang J, Wang G, Peng X, Li X
Bioinformatics · 2026 Jun · PMID 42371766 · Publisher ↗
MOTIVATION: Multi-omics integration can improve cancer diagnosis and prognosis, but current models are limited by extreme dimensionality, redundant raw-feature similarities, missing assays, and incomplete pathway priors....
MOTIVATION: Multi-omics integration can improve cancer diagnosis and prognosis, but current models are limited by extreme dimensionality, redundant raw-feature similarities, missing assays, and incomplete pathway priors. We ask whether biologically meaningful patient manifolds can be learned directly from high-dimensional multi-omics data without heuristic graph construction or fixed knowledge-base constraints. RESULTS: We present OmicsTransformer, an end-to-end framework that projects each omics modality into latent patches, enforces masked semantic consistency through an Exponential Cosine Consistency Loss, models global patch dependencies with a Transformer encoder, and fuses modalities by sample-specific uncertainty. Across eight diagnostic and prognostic cohorts, OmicsTransformer achieved strong performance, including 89.4% accuracy for TCGA-BRCA subtyping and 90.6% area under the receiver operating characteristic curve (AUC) for TCGA-LGG grading. It improved recurrence prediction over the pathway-restricted DeepKEGG baseline by approximately 21.5 percentage points in accuracy (ACC) on TCGA-LIHC and 11.1 percentage points in ACC on TCGA-BLCA. Variance-weighted attribution with ensemble stability selection recovered reproducible cross-modal biomarker cores and non-canonical progression drivers. AVAILABILITY AND IMPLEMENTATION: Source code and datasets are freely available at https://github.com/FFJXX/OmicTransformer and https://doi.org/10.6084/m9.figshare.31523905. OmicsTransformer is implemented in PyTorch. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Computational tool choice impacts CRISPR spacer-protospacer detection.
Neri U, Camargo AP, Bushnell B … +2 more , Beeloo R, Roux S
Bioinformatics · 2026 Jul · PMID 42371756 · Full text
MOTIVATION: CRISPR spacer-protospacer matching is widely used to infer host-virus interactions in microbial and viromics studies, but the choice of sequence search or alignment tool and its reporting behavior is often un...
MOTIVATION: CRISPR spacer-protospacer matching is widely used to infer host-virus interactions in microbial and viromics studies, but the choice of sequence search or alignment tool and its reporting behavior is often under-evaluated for this specific task. RESULTS: Using synthetic, semi-synthetic, and real datasets, we benchmarked commonly used tools and observed substantial differences in recall, runtime, and resource usage across distance metrics and thresholds. Our analyses support practical defaults for large-scale spacer-target matching and clarify trade-offs between exhaustive and heuristic approaches. AVAILABILITY: Source code and benchmark workflows are available at https://github.com/UriNeri/spacer_matching_bench. Data and run artifacts are archived on Zenodo (https://doi.org/10.5281/zenodo.15171878).
ARISE: RNA-Anchored Shared-Edge Topology and Hierarchical Fusion for Spatial Multi-Omics Integration.
Wang X, Su Y, Hao G … +3 more , Wang M, Wang Y, Li X
Bioinformatics · 2026 Jun · PMID 42366683 · Publisher ↗
MOTIVATION: Spatial multi-omics technologies jointly profile transcriptomes, proteins and chromatin accessibility in situ, enabling integrative analysis of tissue organization across molecular layers. However, most exist...
MOTIVATION: Spatial multi-omics technologies jointly profile transcriptomes, proteins and chromatin accessibility in situ, enabling integrative analysis of tissue organization across molecular layers. However, most existing graph-based integration methods rely on independently constructed modality-specific k-nearest-neighbor graphs. When auxiliary modalities are sparse or noisy, these graphs can become topologically discordant, propagate spurious edges, weaken cross-modal alignment and reduce spatial domain resolution. RESULTS: We present ARISE (Anchored RNA for Integrated Spatial Embedding), an RNA expression anchored framework for spatial multi-omics integration. ARISE defines a shared-edge topology by intersecting RNA feature-similarity and spatial-proximity graphs, encodes auxiliary modalities on this common scaffold, and integrates them through inside-out hierarchical fusion. We further show theoretically that graph intersection minimizes false-positive edges within a broad class of k-of-r graph fusion rules, providing a principled basis for topology anchoring. Across various spatial multi-omics benchmarks spanning simulated and real datasets in bi-modal and tri-modal settings, ARISE improves spatial domain identification, cross-modal consistency and preservation of tissue structure relative to existing methods. Furthermore, the learned representation supports biologically meaningful downstream analyses, including marker-based domain annotation, pathway enrichment and cis-regulatory inference, indicating that ARISE yields a robust and interpretable framework for spatial multi-omics integration. AVAILABILITY: The source code is available at https://github.com/XiangxiangWang-code/ARISE. The archived version used in this study is available at https://doi.org/10.6084/m9.figshare.32686137.v2.
Interactive exploration of biobank-scale ancestral recombination graphs with Lorax.
Katte P, Corbett-Detig R
Bioinformatics · 2026 Jun · PMID 42366632 · Publisher ↗
MOTIVATION: Ancestral Recombination Graphs (ARGs) provide a comprehensive representation of genetic ancestry and underpin analyses of natural selection, disease association, and population history. However, existing visu...
MOTIVATION: Ancestral Recombination Graphs (ARGs) provide a comprehensive representation of genetic ancestry and underpin analyses of natural selection, disease association, and population history. However, existing visualization tools are limited in scalability and interactivity, making ARGs difficult to explore at biobank scale. RESULTS: We introduce Lorax, a GPU-accelerated, web-native platform for real-time visualization of population-scale ARGs. Lorax integrates genomic position, coalescent time, local genealogy, and metadata, enabling interactive exploration of ancestry and variant inheritance in biobank-scale datasets. AVAILABILITY: Lorax is freely available as a live demo at lorax.ucsc.edu and as a Python package 'lorax-arg' on PyPI. The source code and documentation are available on GitHub at https://github.com/pratikkatte/lorax. SUPPLEMENTARY DATA: Supplementary data is available at supplementary_material.docx.
PepMCP: A Graph-Based Membrane Contact Probability Predictor for Membrane-Lytic Antimicrobial Peptides.
Dong R, Awang T, Cao Q … +4 more , Kang K, Wang L, Zhu Z, Song C
Bioinformatics · 2026 Jun · PMID 42360729 · Publisher ↗
MOTIVATION: The membrane-lytic mechanism of antimicrobial peptides (AMPs) is often overlooked during their in silico discovery process, largely due to the lack of a suitable metric for the membrane-binding propensity of...
MOTIVATION: The membrane-lytic mechanism of antimicrobial peptides (AMPs) is often overlooked during their in silico discovery process, largely due to the lack of a suitable metric for the membrane-binding propensity of peptides. Previously, we proposed a characteristic called membrane contact probability (MCP) and applied it to the identification of membrane proteins and membrane-lytic AMPs. However, previous MCP predictors were not trained on short peptides targeting bacterial membranes, which may result in unsatisfactory performance for peptide studies. RESULTS: In this study, we present PepMCP, a peptide-tailored model for predicting MCP values of short peptides. We collected more than 500 membrane-lytic AMPs from the literature, conducted coarse-grained molecular dynamics (MD) simulations for these AMPs, and extracted their residue MCP labels from MD trajectories to train PepMCP. PepMCP employs the GraphSAGE framework to address this node regression task, encoding each peptide sequence as a graph with 4-hop edges. PepMCP achieved a Pearson correlation coefficient of 0.883 and an RMSE of 0.123 on the node-level test set. It can recognize membrane-lytic AMPs with the predicted MCP values for each sequence, thereby facilitating mechanism-driven AMP discovery. Additionally, we provide a database, MemAMPdb, which includes the membrane-lytic AMPs, as well as the PepMCP web server for easy access. AVAILABILITY AND IMPLEMENTATION: The code and data are available at https://github.com/ComputBiophys/PepMCP. SUPPLEMENTARY INFORMATION: Supplementary data are available online.
ARGscape: A modular, interactive tool for manipulation of spatiotemporal ancestral recombination graphs.
Talbot CA, Bradburd GS
Bioinformatics · 2026 Jun · PMID 42348238 · Publisher ↗
SUMMARY: Ancestral recombination graphs (ARGs) are increasingly central to modern population genetics, yet ARG-based methods for spatiotemporal demographic inference remain underutilized in empirical settings due to frag...
SUMMARY: Ancestral recombination graphs (ARGs) are increasingly central to modern population genetics, yet ARG-based methods for spatiotemporal demographic inference remain underutilized in empirical settings due to fragmented workflows and a lack of exploratory tools. ARGscape addresses this by providing a unified framework, seamlessly integrating established and novel tools for ARG simulation, manipulation, and spatiotemporal inference into both graphical and command-line interfaces. ARGscape features dynamic 2- and 3-dimensional visualizations and a novel "spatial diff" visualization for quantitative comparison of ARG-based geographic inference methods. By integrating these various functionalities, ARGscape facilitates novel data exploration and hypothesis generation, bridging the gap between methods development and empirical adoption, and enabling educational uses. AVAILABILITY AND IMPLEMENTATION: ARGscape is available as a Python package on PyPI and as a live website for educational and simple demonstrative purposes at https://www.argscape.com. The source code and documentation are available on GitHub at https://github.com/chris-a-talbot/argscape. SUPPLEMENTARY DATA: Supplementary data is available at Bioinformatics online.
A-liner: linear alignment visualizer for genome comparisons.
Okuno M, Yamamoto T, Ogura Y … +1 more , Itoh T
Bioinformatics · 2026 Jun · PMID 42348220 · Full text
SUMMARY: A-liner is a flexible command-line tool for linear visualization of genome-scale sequence alignments, supporting outputs from multiple aligners and integrated visualization of annotations, highlights, quantitati...
SUMMARY: A-liner is a flexible command-line tool for linear visualization of genome-scale sequence alignments, supporting outputs from multiple aligners and integrated visualization of annotations, highlights, quantitative tracks, and coordinate scales. It is applicable to a wide range of organisms, from bacteria to large eukaryotic genomes, and facilitates efficient generation of publication-ready comparative genome visualizations. AVAILABILITY AND IMPLEMENTATION: The source code and example output files for a-liner are available in the GitHub repository: https://github.com/mokuno3430/a-liner. A-liner v1.1.0 has been archived on Zenodo at https://doi.org/10.5281/zenodo.19702001.
Interacting Species Database (ISDB): comprehensive resource for interspecies interactions at the molecular level.
Mederer M, Gautam A, Kohlbacher O … +2 more , Lupas A, Elhabashy H
Bioinformatics · 2026 Jul · PMID 42348219 · Full text
MOTIVATION: Organisms within ecological systems often engage in molecular interactions that mediate key biological processes, such as protein-protein interactions involved in host-pathogen recognition and symbiosis. Char...
MOTIVATION: Organisms within ecological systems often engage in molecular interactions that mediate key biological processes, such as protein-protein interactions involved in host-pathogen recognition and symbiosis. Characterization of these interactions at a molecular level is essential for understanding the mechanistic, evolutionary, and functional basis of interspecies interactions, as well as for informing potential therapeutic interventions. However, progress in this field is significantly impeded by the lack of a comprehensive database of interacting species at molecular resolution and the limited availability of experimental data. RESULTS: We introduce the Interacting Species Database (ISDB), a comprehensive resource that catalogs interspecies interactions, annotated with NCBI taxonomic identifiers, interaction types and known molecular interactions. The ISDB encompasses 858 229 interacting species pairs and 171 713 interspecies protein-protein interactions within 261 287 organisms. ISDB is designed to support researchers in searching for, downloading, and depositing interspecies interaction data, which facilitates the study of ecological dynamics across diverse research domains. AVAILABILITY AND IMPLEMENTATION: The ISDB is available via a web interface (https://www.elhabashylab.org/isdb), open-source code on GitHub (https://github.com/ElhabashyLab/ISDB) under the MIT license and is archived on Zenodo (Version v1.0.1, DOI: 10.5281/zenodo.20162385).
ReadChop: a high-performance demultiplexer for long-read sequencing data.
Jiang C, Xiong Y
Bioinformatics · 2026 Jun · PMID 42348199 · Full text
SUMMARY: Long-read sequencing (LRS) platforms offer extended read lengths but present computational challenges due to high error rates and frequent insertion-deletion (indel) artifacts. While sample multiplexing is essen...
SUMMARY: Long-read sequencing (LRS) platforms offer extended read lengths but present computational challenges due to high error rates and frequent insertion-deletion (indel) artifacts. While sample multiplexing is essential for cost-efficiency, existing demultiplexing solutions face a dichotomy: vendor-provided tools (e.g., Dorado) often lack the structural flexibility required for highly non-canonical designs, while open-source tools (e.g., Cutadapt) often lack the speed or algorithmic robustness to handle custom, high-complexity barcode designs. Here, we present ReadChop, a high-performance demultiplexer implemented in Rust. ReadChop leverages Myers' bit-parallel algorithm to efficiently model indel-rich error profiles and employs a streaming architecture to ensure low memory footprint. Benchmarking demonstrates that ReadChop achieves classification precision exceeding 99.99% on both simulated datasets-even under ultra-high multiplexing conditions (e.g., 13 824-plex)-and empirical SARS-CoV-2 amplicons. Furthermore, it excels in filtering in silico chimeras (0.1% miss rate) and exhibits linear computational scalability on ultra-long templates (up to 100 kb). Crucially, it significantly accelerates execution speeds-being >6 times faster than Dorado, >2 times faster than Nanoplexer, and >30 times faster than Cutadapt-with memory usage consistently below 200 MB. ReadChop provides a flexible, robust solution for processing massive LRS datasets with non-canonical experimental designs. AVAILABILITY AND IMPLEMENTATION: Source code and documentation are freely available under the MIT license at https://github.com/cherryamme/ReadChop.
SegJointGene: joint cell segmentation and spatial gene prioritization by information entropy guided convolutional neural networks.
Ma H, Wang D
Bioinformatics · 2026 Jun · PMID 42345533 · Publisher ↗
MOTIVATION: Spatial sequencing technologies enable the single-cell-level study of molecular organization in tissues. Revealing such spatial patterns relies on accurate cell segmentation. In complex tissues with dense cel...
MOTIVATION: Spatial sequencing technologies enable the single-cell-level study of molecular organization in tissues. Revealing such spatial patterns relies on accurate cell segmentation. In complex tissues with dense cell packing, segmentation based solely on nuclear staining is insufficient for accurate cell boundary detection. This limitation arises because accurate segmentation necessitates the delineation of cell morphology, which is driven by molecular activities such as cytoskeletal dynamics, cell-cell adhesion, and intercellular signaling. Thus, integrating molecular information, including gene or protein expression, has the potential to improve segmentation, but remains computationally challenging. RESULTS: To address this, we developed SegJointGene, a deep learning framework that jointly performs cell segmentation and spatial gene prioritization by integrating nuclei-based images with spatial gene or protein expression data. SegJointGene designs an information-entropy-guided convolutional neural network together with a computational information discarding score to identify genes that are important for cell-type-specific segmentation. The model iteratively refines gene prioritization and cell boundaries, producing convergent segmentation results along with prioritized spatial genes or proteins across cell types. We applied and benchmarked SegJointGene on both simulation and real spatial datasets, including spatial transcriptomics from the mouse hippocampus and distinct regions of the whole mouse brain, as well as spatial proteomics data from human tonsil. Across datasets, SegJointGene outperformed existing methods by 5-20% in accurately assigning molecular signals to cell boundaries. Robustness analyses further demonstrated stable performance across varying gene numbers and imaging resolutions. In addition, the genes prioritized by SegJointGene were enriched for structural, developmental, and synaptic signaling pathways, supporting their relevance to spatial tissue organization. AVAILABILITY: The source code and data are available at https://github.com/daifengwanglab/segjointgene. SUPPLEMENTARY INFORMATION: Supplementary figures, notes and data descriptions are available in Supplementalmaterials.pdf.
Prevalence aware feature selection improves biomarker identification in microbiome studies.
Yang R, Li Y, Sankaran K … +5 more , Mace TA, Hart PA, Ma Q, Wang XW, Ke S
Bioinformatics · 2026 Jul · PMID 42340677 · Full text
MOTIVATION: Identifying robust microbial biomarkers is crucial for disease diagnosis and prediction, elucidation of biological mechanisms, and development of targeted therapies. Machine learning-based approaches, particu...
MOTIVATION: Identifying robust microbial biomarkers is crucial for disease diagnosis and prediction, elucidation of biological mechanisms, and development of targeted therapies. Machine learning-based approaches, particularly the random forest model, have been widely used for biomarker identification during sample stratification. However, those biomarkers often vary considerably for the same disease, limiting their practical applicability. A robust framework for reliable biomarker identification in microbiome research is needed. To address this gap, we proposed a prevalence-aware feature selection framework (ParSlet) that incorporates a universal scaling relationship between taxon prevalence and selection frequency. RESULTS: We first identified a universal exponential scaling law linking the probability of a taxon being consistently recognized as a biomarker versus its prevalence. Then, we integrated this scaling law with taxa prevalence into the biomarker identification using random forest. We systematically evaluated this approach in both simulated microbiome datasets and real-world microbiome datasets and compared it with existing methods, finding that our integrated approach generally improved feature stability and reproducibility of biomarker identification. In colorectal cancer (CRC) datasets, our method robustly identified well-established microbial biomarkers such as Ruminococcus, Clostridium_XVIII, and Faecalibacterium. Integrating a prevalence-based scaling adjustment into feature importance enhances the stability of microbiome biomarker identification. This approach holds promise for enabling more reliable disease diagnostics, uncovering generalizable microbial signatures across cohorts, and guiding the development of targeted microbiome-based interventions. AVAILABILITY AND IMPLEMENTATION: ParSlet is available at https://github.com/KelabatOSU/Feature_selection.
Hotgenes: an R package for reducing bottlenecks in bulk omics data exploration and collaboration.
Virgen-Slane R
Bioinformatics · 2026 Jun · PMID 42340674 · Publisher ↗
SUMMARY: A critical part of omics analysis is the transition from early data exploration to final interpretation, often including different analytical platforms and the proliferation of figures, tables, and files. To min...
SUMMARY: A critical part of omics analysis is the transition from early data exploration to final interpretation, often including different analytical platforms and the proliferation of figures, tables, and files. To minimize potential errors and delays that can occur during this process, we have developed an R package called "Hotgenes" that contains a wide range of flexible utilities available in a single modular Shiny application. With Hotgenes, differential expression results generated from bulk omics platforms can be imported and shared among collaborators with minimal coding. Furthermore, the modular Hotgenes user interface can be customized by advanced users to fit the needs of their evolving pipelines. AVAILABILITY AND IMPLEMENTATION: Hotgenes is implemented in R and is freely available at https://github.com/pfizer-opensource/Open-Hotgenes. A permanent archived version is available at https://doi.org/10.5281/zenodo.20129460. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
FFixR: A Machine Learning Framework for Accurate Somatic Mutation Calling from FFPE RNA-Seq Data in Cancer.
Livne O, Yizhak K
Bioinformatics · 2026 Jun · PMID 42340671 · Publisher ↗
MOTIVATION: Formalin-fixed paraffin-embedded (FFPE) tissues are widely used in clinical and research settings, yet their use for detecting somatic mutations from RNA sequencing (RNA-seq) is hindered by artefactual mutati...
MOTIVATION: Formalin-fixed paraffin-embedded (FFPE) tissues are widely used in clinical and research settings, yet their use for detecting somatic mutations from RNA sequencing (RNA-seq) is hindered by artefactual mutations introduced by cytosine deamination and strand-specific damage. Existing FFPE noise-filtering tools are tailored to DNA-seq and rely on strand bias, rendering them unsuitable for RNA-seq. Here, we present FFixR, a machine learning-based framework that filters FFPE-induced artefacts from RNA-seq data without requiring matched-normal samples. RESULTS: Trained on FFPE melanoma samples with matched DNA, FFixR leverages allele-specific read counts, variant features, and mutational signature probabilities. FFixR removed up to 98% of artefactual mutations while maintaining ∼92% recall of true variants. SHAP analysis revealed key feature interactions guiding model decisions. When applied to independent cohorts, FFixR restored the correlation between RNA- and DNA-derived tumor mutational burden (R2 = 0.881) and recovered biologically meaningful mutational signatures. FFixR enables accurate somatic variant calling from FFPE RNA-seq data, expanding the utility of archival samples for research and clinical applications. AVAILABILITY AND IMPLEMENTATION: FFixR tool is freely available on the web at https://github.com/yizhak-lab-ccg/FFixR and https://doi.org/10.6084/m9.figshare.31998315. The repository also includes a readme file describing the inputs, outputs and the entire pipeline. The results presented here were produced using v1.0.0. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
DruGUI 2.0: Mapping Protein Druggability with Probe-Based Molecular Dynamics.
Ventura C, Lee JY, Bogetti AT … +3 more , Banerjee A, Licht M, Bahar I
Bioinformatics · 2026 Jun · PMID 42340669 · Publisher ↗
SUMMARY: We introduce DruGUI 2.0, a drug discovery tool for assessing the druggability of proteins, integrated into the ProDy application programming interface (API). DruGUI 2.0 is developed to facilitate the search for...
SUMMARY: We introduce DruGUI 2.0, a drug discovery tool for assessing the druggability of proteins, integrated into the ProDy application programming interface (API). DruGUI 2.0 is developed to facilitate the search for druggable sites while allowing for proteins' conformational flexibility. Simulations in explicit solvent, with an option to include membrane, are carried out in the presence of probe molecules selected from an expanded library of small molecules containing drug-like fragments. Druggable sites beyond orthosteric sites are identifiable, as well as the probes that show high affinity to bind to those sites. Characterization of the composition and position of the probes helps build pharmacophore models and estimate relative binding affinities. As a Python module with enhanced visualization features, DruGUI 2.0 complements, and benefits from, the vast collection of protein sequence, structure, and dynamics analyses modules accessible in ProDy. Case studies in the Supplemental Material showcase the utility of DruGUI 2.0 applied to both soluble targets and membrane proteins. AVAILABILITY: ProDy is open-sourced and freely available under MIT License from https://github.com/prody/ProDy. The code version of DruGUI 2.0 used for simulations is available on Zenodo : 10.5281/zenodo.20511357. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online. TUTORIAL: http://www.bahargroup.org/prody/tutorials/drugui2_tutorial/index.html.
Inferring Dynamic Information from Protein Structures by Gaussian Integrals and Deep Learning.
Vilicich F, Bottino N, Su Z … +2 more , Yin S, Wu Y
Bioinformatics · 2026 Jun · PMID 42340665 · Publisher ↗
MOTIVATION: Protein dynamics are central to function, but experiments and molecular dynamics (MD) simulations remain costly, low-throughput, and difficult to compare across protocols. Scalable structure-based methods are...
MOTIVATION: Protein dynamics are central to function, but experiments and molecular dynamics (MD) simulations remain costly, low-throughput, and difficult to compare across protocols. Scalable structure-based methods are needed to infer dynamics from static protein structures. RESULTS: We present a deep learning framework that predicts protein dynamics from 30-dimensional Gaussian integral (GI) descriptors of Cα backbone topology. Using 1,374 ATLAS protein chains with MD-derived RMSF, GI stratified proteins into fold-relevant clusters enriched for secondary structure, sequence homology, and ECOD families. An attention-based 1D-CNN classified flexible versus non-flexible proteins with test AUC = 0.772 and separated slow-mode- from fast-mode-dominated dynamics with AUC = 0.91. Regression models recovered mean RMSF (Pearson r = 0.72; R² = 0.46) and slow-mode RMSF more accurately (Pearson r = 0.83; R² = 0.62), supporting rapid inference of flexibility and collective-motion bias. AVAILABILITY AND IMPLEMENTATION: Code and data are available on GitHub at: https://github.com/fvilicich/gaussian_integral/blob/main/gaussian_integral_classification.ipynb. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Introducing non-enzymatic crosslinks into atomistic simulations of collagen fibrils.
Giannetti G, Pils J, Gräter F … +2 more , Monego D, Dellago C
Bioinformatics · 2026 Jun · PMID 42334941 · Publisher ↗
MOTIVATION: Collagen fibrils are the primary load-bearing units of connective tissues. However, generating atomistic, simulation-ready models remains challenging due to collagen's hierarchical organization and the divers...
MOTIVATION: Collagen fibrils are the primary load-bearing units of connective tissues. However, generating atomistic, simulation-ready models remains challenging due to collagen's hierarchical organization and the diversity of its crosslinking network across tissues, ages, and metabolic states. Notably, non-enzymatic advanced glycation end-product (AGE) crosslinks-central to aging and diabetic complications-are largely absent from current atomistic fibril modelling workflows. RESULTS: Here, we present an extension of the ColBuilder framework to generate atomistic collagen fibril models that incorporate three representative AGE-derived crosslinks (glucosepane, pentosidine, and MOLD) alongside enzymatic crosslinks. Amber99-compatible parameters are provided and assessed against QM-optimized reference geometries using all-atom molecular dynamics (MD) simulations. As proof-of-concept, we examine the mechanical response of single D-period collagen microfibrils featuring enzymatic-only, AGE-only, and mixed crosslink patterns in molecular dynamics simulations under force, and observe that AGE crosslinks differently impact the fibril structure compared to enzymatic crosslinks. The extension to ColBuilder can aid future structure-based research on collagen aging. AVAILABILITY AND IMPLEMENTATION: ColBuilder is available as an open-source Python command-line package at https://github.com/graeter-group/colbuilder.
CycleVI: isolating cell cycle variation with an interpretable deep generative model.
Mozdzanowski P, Tarbier M, S Jeuken G
Bioinformatics · 2026 Jun · PMID 42334940 · Full text
MOTIVATION: Cell cycle progression is a dominant source of variation in single-cell RNA sequencing (scRNA-seq) data, often obscuring other transcriptional signals of interest. Several methods have been developed to infer...
MOTIVATION: Cell cycle progression is a dominant source of variation in single-cell RNA sequencing (scRNA-seq) data, often obscuring other transcriptional signals of interest. Several methods have been developed to infer continuous cell cycle phase from transcriptomic data, but their estimates tend to be unstable when proliferation is intertwined with other biological processes or technical sources of heterogeneity. RESULTS: We present CycleVI, a deep generative model that disentangles cell cycle-driven variation from other signals in scRNA-seq data using a partitioned latent representation with a dedicated circular subspace. CycleVI accurately infers a continuous cell cycle phase, validated against orthogonal protein-level measurements, and yields a residual latent space free of cell cycle artefacts. This disentangled representation helps resolve biological processes intertwined with the cell cycle, clarifying hematopoietic differentiation and preserving drug-response signals better than standard cell cycle regression. By isolating cell cycle-related variation rather than removing it, CycleVI provides a principled framework for analysing cellular heterogeneity in proliferating systems. AVAILABILITY: CycleVI is available at www.github.com/jeuken/CycleVI, or through the ' cyclevi' Python package.
MetagenomicKG: a knowledge graph for metagenomic applications.
Ma C, Liu S, Won S … +1 more , Koslicki D
Bioinformatics · 2026 Jul · PMID 42334937 · Full text
MOTIVATION: The sheer volume and variety of genomic content within microbial communities makes metagenomics a field rich in biomedical knowledge. To traverse these complex communities and their vast unknowns, metagenomic...
MOTIVATION: The sheer volume and variety of genomic content within microbial communities makes metagenomics a field rich in biomedical knowledge. To traverse these complex communities and their vast unknowns, metagenomic studies often depend on distinct reference databases, such as the Genome Taxonomy Database (GTDB), the Kyoto Encyclopedia of Genes and Genomes (KEGG), and the Bacterial and Viral Bioinformatics Resource Center (BV-BRC), for various analytical purposes. These databases are crucial for the genetic and functional annotation of microbial communities. Nevertheless, the inconsistent nomenclature or identifiers of these databases present challenges for effective integration, representation, and utilization. Knowledge graphs (KGs) offer an appropriate solution by organizing biological entities from different databases to standardized identifiers, allowing their interrelations to be captured into a cohesive network regardless of the naming conventions used in each source. The graph structure not only facilitates the unveiling of hidden patterns but also enriches our biological understanding with deeper insights. Despite KGs having shown potential in various biomedical fields, their application in metagenomics remains underexplored. RESULTS: We present MetagenomicKG, a novel knowledge graph specifically tailored for metagenomic analysis. MetagenomicKG integrates taxonomic, functional, and pathogenesis-related information on the human microbiome sourced from various databases, and further connects these with existing biomedical KGs to expand the biological network. Through various case studies involving the human microbiome, we demonstrate its utility in enabling hypothesis generation regarding the relationships between microbes and diseases, generating sample-specific graph embeddings, and providing robust pathogen prediction. CODE AVAILABILITY: The source code and technical details for constructing the MetagenomicKG and reproducing all analyses are available on GitHub at https://github.com/KoslickiLab/MetagenomicKG. The data used in this manuscript, including the pre-built files and use case input data, are archived on Zenodo with DOI: 10.5281/zenodo.17546861.
DiaReport: Reproducible workflow for differential expression analysis and interactive reporting in DIA-based proteomics.
Argentini A, Fernández E, Pauwels J … +1 more , Gevaert K
Bioinformatics · 2026 Jun · PMID 42332842 · Publisher ↗
MOTIVATION: Data-independent acquisition (DIA) has become the preferred data acquisition method for mass spectrometry-based proteomics, yet, reproducible workflows for differential expression (DE) analysis and results re...
MOTIVATION: Data-independent acquisition (DIA) has become the preferred data acquisition method for mass spectrometry-based proteomics, yet, reproducible workflows for differential expression (DE) analysis and results reporting remain limited. We present DiaReport, an R package that performs precursor- and protein-level DE analysis from DIA-NN output using MSqRob and QFeatures, while generating high-quality, interactive HTML reports through Quarto. DiaReport integrates precursor data, filtering of missing values, normalization, protein summarization and statistical modeling within a single function, supporting both simple pairwise as well as complex experimental designs. The package provides structured outputs and configuration files to ensure computational reproducibility across different studies. To accommodate diverse research needs, DiaReport includes multiple reporting templates tailored to different proteomic applications. Applying DiaReport to an extracellular vesicle (EV) proteomics dataset demonstrates its ability to efficiently analyze DIA data and provide rapid insights into sample quality and protein level differences. AVAILABILITY: DiaReport is an open-source R package available at https://github.com/Gevaert-Lab/diareport (DOI: 10.5281/zenodo.20120604). The package is platform-independent and distributed under the MIT license. Reports are generated using Quarto and require only standard R dependencies. Detailed documentation, installation guides and usage vignettes are provided within the repository. The interactive HTML reports discussed in this study, including the UPS2 benchmark and EV case study, are archived on Zenodo (DOI: 10.5281/zenodo.20122506 and 10.5281/zenodo.20123378). SUPPLEMENTARY INFORMATION: Figure S1 (Benchmarking performance of DiaReport); Table S1 (Guidance for missing value filtering strategies); and Table S2 (Indicative runtimes across different cohort sizes and storage configurations) are available at Bioinformatics online.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe