974 papers
LigandForge is a freely accessible web server that enables structure-guided de novo drug design by integrating structural validation, fragment assembly, and multi-objective optimization to generate synthesis-ready lead compounds without requiring local software installation or programming expertise.
This study reveals that conserved water molecules act as critical structural ligands whose disruption by pathogenic single nucleotide polymorphisms, particularly within ligand-binding sites, drives protein dysfunction and disease, a mechanism experimentally validated in Gaucher disease.
This study demonstrates that integrating single amino acid variants and accessory proteome variability into a DIA-NN workflow significantly enhances protein identification and coverage in *Legionella pneumophila* proteomics, enabling more accurate bacterial proteotyping and a deeper understanding of allelic diversity.
The paper introduces **muat**, a portable, transformer-based software distributed via Docker and Bioconda that enables accurate, transferable tumour classification and representation learning from somatic variants across diverse sequencing datasets and secure processing environments without requiring retraining.
This paper introduces GenomeAnonymizer, a novel method that generates privacy-preserving Somatic Tumor Twins (STTs) from tumor-normal DNA sequences, effectively removing germline variants while retaining critical somatic information to enable open data sharing and accelerate oncology research and clinical decision-making.
PANDA is an end-to-end graphical pipeline that reconstructs contiguous single-molecule methylation patterns from targeted bisulfite amplicon sequencing data by linking unmerged paired-end reads, thereby enabling the analysis of epiallelic heterogeneity and long-range phasing that conventional site-wise averaging methods obscure.
OncoMORPHIA is a free, browser-based web platform that integrates 3D protein structure visualization with clinical, survival, and AI-driven functional annotations to enable researchers to explore cancer mutations across ten public databases without requiring specialized bioinformatics expertise.
DeepTrio is a deep learning-based variant caller that analyzes child-mother-father trios by learning directly from sequence data without explicit inheritance priors, achieving higher accuracy than DeepVariant across Illumina and PacBio HiFi platforms, particularly at lower coverages.
SSAlign is a novel, ultrafast, and highly sensitive protein structure search tool that leverages protein language models and a two-stage alignment strategy to significantly outperform existing methods like Foldseek in both speed and accuracy, thereby enabling efficient large-scale structural analysis and drug discovery.
The paper demonstrates that the Ankh-score method, which utilizes protein language model embeddings, outperforms both AlphaFold3-based structural alignments and traditional BLOSUM matrix methods in generating accurate protein sequence alignments.
This study evaluates three weight optimisation approaches (linear transformation, Nelder-Mead, and Bayesian) for weighted ensembles of genomic prediction models in maize, finding that while these methods generally improve prediction accuracy over naive equal-weight ensembles—particularly when optimal weights differ significantly from equal distribution—no single approach demonstrated clear superiority across all scenarios.
This study benchmarks three agentic bioinformatics systems on a complex protein-retrieval task involving coccolithophore calcification, revealing that while some agents generate larger protein sets, the Codex system achieves superior performance through a better balance of sensitivity and specificity, higher relevance, and greater repeatability.
This study identifies a critical methodological flaw where immunopeptidomics datasets are contaminated by computational predictions, causing a recursive bias that inflates benchmark performance while failing in clinical applications, and proposes the deepMHCflare model trained on clean data to successfully overcome this limitation and improve T-cell epitope discovery.
The paper introduces CLEAR, a Bayesian gene set enrichment framework that jointly models gene sets using continuous gene-level statistics to reduce redundancy and improve sensitivity compared to traditional threshold-based or independent-set approaches.
This paper introduces the Generalised Pretrained Cytometry Transformer (GPCT), an interpretable foundation model that leverages a novel pretraining regime to learn transferable cellular representations from heterogeneous marker panels, thereby overcoming scalability limitations and enabling high-accuracy, biologically validated sample-level predictions across diverse flow cytometry datasets.
The paper introduces DESPOT, an anisotropic knowledge-based scoring framework that models directional preferences and steric exclusion by inverting the probabilistic formulation of atom interactions, thereby significantly outperforming traditional isotropic methods in protein-ligand pose discrimination and virtual screening.
This paper introduces StriMap, a structure-informed deep learning framework that accurately models TCR-peptide-HLA interactions to enable the identification of antigenic drivers in autoimmunity and the prioritization of targets for immunotherapy, as demonstrated by its successful discovery of validated molecular mimics linking ankylosing spondylitis and inflammatory bowel disease.
CardamomOT is a unified mechanistic optimal transport framework that overcomes previous limitations in inferring gene regulatory networks and reconstructing unobserved protein trajectories from single-cell RNA sequencing time series, thereby enabling accurate generative modeling of cellular responses to perturbations.
The paper introduces TRACE, a multimodal framework that employs CLIP-style intra-entity contrastive alignment to stabilize TCR-peptide binding predictions by regularizing noisy structural data against strong sequence embeddings, thereby demonstrating that constrained modality interaction is more critical than naive fusion for robust bioinformatics performance.
This study demonstrates that nanopore sequencing of 10x Genomics multiome libraries enables full-length transcript profiling and accurate genetic demultiplexing, successfully recovering a substantial portion of transcription start sites compared to traditional short-read 5' assays.