950 papers
The paper introduces ProDive, a GPU-accelerated algorithm that reveals widespread cross-family reuse of short protein fragments, suggesting this phenomenon reflects a universal biophysical requirement for early structure formation during protein folding rather than family-specific functions.
The paper introduces INAEME, a novel bioinformatic workflow that integrates comprehensive mutational events—including phasing, germline variants, and transcript context—to accurately prioritize neoantigen candidates for cancer immunotherapy, as validated across 300 TCGA samples.
This paper introduces STRAND, a parsimonious and interpretable four-feature regression model that significantly improves mRNA in-vial degradation prediction by integrating fine-scale base-pairing log odds with global structural metrics, thereby outperforming existing machine learning and deep learning approaches.
This study benchmarks long-read RNA-seq across bulk and single-cell modalities using matched iNeuron datasets to evaluate sequencing technologies, quantification tools, and depth requirements, ultimately providing practical guidelines for experimental design and establishing a reference dataset for FMR1 biology.
The paper introduces PanTEon, a cross-kingdom deep learning framework comprising a harmonized database and a modular benchmarking platform that enables reproducible, standardized training and evaluation of transposable element classifiers across diverse eukaryotic lineages.
Correlate is a freely accessible, browser-based web application that enables data-driven exploration of gene dependencies and functional links across over 1,000 cancer cell lines by analyzing CRISPR screen data from the Cancer Dependency Map, offering a complementary alternative to knowledge-based network tools.
The study introduces snoFlake, a network model that redefines the functional scope of snoRNAs by identifying noncanonical interactions with RNA-binding proteins, specifically revealing that SNORD22 associates with U5 snRNP components to regulate splicing efficiency at suboptimal exons.
This study employs an integrative in silico approach to design and dynamically evaluate VP4-targeting siRNAs against Rotavirus A, identifying a candidate with optimal structural compatibility and stable interactions with RISC-loading proteins to facilitate future experimental validation.
This paper introduces Nettle, an open-source tool that improves quantitation in data-independent acquisition proteomics by imputing peptide retention time boundaries to integrate chromatographic signals, thereby reducing missing data limitations and enhancing accuracy compared to traditional methods.
PlantCAD2 is a parameter-efficient, plant-specific DNA foundation model pretrained on 65 angiosperm genomes that, despite having fewer parameters than larger generalist models, outperforms them in capturing evolutionary conservation and predicting genomic functions across diverse flowering plant species.
The paper introduces PathogenSurveillance, an open-source, automated Nextflow pipeline designed to streamline whole-genome sequencing-based population genomic analyses and pathogen identification for real-time biosurveillance across diverse organisms and sequencing technologies.
CellWHISPER is a statistically robust and computationally scalable framework that accurately infers direct, contact-mediated cell-cell communication from spatial transcriptomics data by disentangling true signaling interactions from structural proximity, enabling the discovery of tissue- and disease-specific signaling programs such as gap-junction coupling in the brain.
The paper introduces seq2ribo, a hybrid framework combining a structure-aware TASEP simulation with a machine learning polisher to accurately predict ribosome location profiles and protein expression directly from mRNA sequences, thereby enabling de novo mRNA design without reliance on experimental data or genomic context.
This paper introduces the Dynamic Consistency Index (DCI) to identify genes with reproducible temporal trajectories across cell types in trauma-induced scRNA-seq data, demonstrating that integrating DCI-based gene selection with uncertainty-aware recurrent neural networks significantly improves the accuracy and calibration of predicting future gene expression states.
The paper introduces GATSBI, a graph attention-based framework that generates context-aware protein embeddings by integrating diverse biological data and employing task-aligned evaluation protocols, demonstrating superior generalization—particularly for understudied proteins—compared to existing methods that rely on biologically inappropriate data splits.
This study utilizes mass spectrometry to characterize how Ube2j2 deficiency alters the cellular proteome during ER stress, revealing that Ube2j2 influences not only established pathways like ERAD and the UPR but also previously unlinked functions such as RNA metabolism, ER-Golgi transport, and cell-cycle progression.
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.