974 papers
This paper introduces ViSNet-PIMA, a novel machine learning force field that utilizes a physics-informed multipole aggregator to effectively model non-local interactions, significantly outperforming state-of-the-art methods in biomolecular energy and force predictions and enhancing the accuracy of AI-based molecular dynamics simulations.
RNASTOP is a novel deep learning framework that significantly improves the accuracy of mRNA chemical stability prediction and enables rational sequence optimization, thereby accelerating the development of stable and effective mRNA therapeutics.
This study utilizes computational molecular docking and immunoinformatics to identify PfCyRPA, PfMSP10, and PfCSP as top *Plasmodium falciparum* antigen candidates for malaria vaccine design by evaluating their interactions with human T-cell receptors.
This study utilizes multi-dataset transcriptomic analysis and machine learning to identify robust molecular signatures, specifically highlighting vitamin D metabolism and inflammatory pathways, as core mechanisms and diagnostic biomarkers for frailty.
The paper introduces CLIPepPI, a scalable, structure-informed dual-encoder model leveraging contrastive learning and protein language models to accurately predict domain-peptide specificity directly from sequence, overcoming data scarcity and enabling large-scale proteomic applications such as variant-effect prediction.
This paper introduces differentiable GSEA (dGSEA), a scalable and numerically stable surrogate for classical Gene Set Enrichment Analysis that enables pathway-level supervision in transcriptomic prediction models by replacing discrete ranking operations with differentiable approximations, thereby bridging the gap between gene-wise training objectives and pathway-level interpretation.
The paper introduces ECHO, a user-friendly, Snakemake-based pipeline that leverages Oxford Nanopore sequencing to enable comprehensive, reproducible, and scalable end-to-end (epi)genetic profiling of the human repeatome.
The paper introduces scCChain, a transformer-based framework that maps spatial cell-cell communication by constructing and scoring tailored chains of cells to identify interpretable communication programs and localize interaction hotspots at both spot and single-cell resolutions.
The paper introduces HViLM, the first foundation model for pan-viral genomic analysis, which achieves state-of-the-art performance in predicting pathogenicity, host tropism, and transmissibility across diverse viral families through continued pre-training on 5 million non-redundant viral sequences and parameter-efficient fine-tuning.
This study systematically benchmarks five machine learning-based variant annotation methods across UK Biobank data, revealing that CADD v1.6 achieves the best signal separation while AlphaMissense shows calibration issues, ultimately providing practical guidance for method selection and a new framework for calibration assessment in rare variant association testing.
This study demonstrates that because agreement among computational variant effect predictors does not correlate with their accuracy against experimental data, prioritizing proteins with high inter-predictor disagreement is an effective strategy for selecting targets for resource-intensive experimental characterization to maximize informational value.
The paper introduces ISdetector, a scalable and robust bioinformatics pipeline that outperforms existing tools in precisely mapping insertion sequences and detecting associated structural variations in bacterial and archaeal genomes using short-read sequencing data.
This paper introduces Pro2RNA, a multimodal reverse-translation language model that integrates protein, taxonomy, and RNA representations to generate host-adapted, species-specific mRNA coding sequences, outperforming existing optimization methods in benchmark evaluations.
This paper demonstrates that applying temperature scaling and epistemic neural networks significantly improves the reliability of transformer-based genomic language models when facing distribution shifts, such as noisy data or novel variants, across diverse genomic prediction tasks.
This study demonstrates that unsupervised embeddings from the pretrained Evo2 genome language model capture meaningful host-range signals for bacteriophages, achieving competitive retrieval performance that is further enhanced when combined with traditional alignment and k-mer-based methods in a hybrid pipeline.
PanXpress is a unified, efficient, and accurate framework for bacterial gene expression quantification that utilizes a pan-transcriptomic gapped k-mer index to overcome reference bias in mixed-strain samples by directly constructing references from genomic data and outperforming existing tools in precision, speed, and memory usage.
This study presents an AI-assisted curation tool integrated with MorphoBank that leverages Large Language Models to automate the extraction and standardization of morphological character data into NEXUS format, thereby significantly enhancing data accuracy, efficiency, and FAIR compliance in biological and paleontological research.
SOORENA is a two-stage transformer model that systematically identifies and classifies protein autoregulation in millions of PubMed abstracts, generating a comprehensive, interactive database to bridge literature mining and systems biology for improved network modeling.
GatorSC is a unified, self-supervised representation learning framework that integrates multi-scale cell and gene graphs via a Mixture-of-Experts architecture to produce robust embeddings, outperforming state-of-the-art methods in cell clustering, gene imputation, and biological discovery across diverse single-cell RNA sequencing datasets.
This study analyzes nucleic acid sequences from the Zag meteorite, revealing that they exhibit constrained complexity and low-dimensional structure distinct from both known biological patterns and random models, suggesting an unusual origin that warrants further independent investigation.