949 papers
By introducing a functional-space alignment framework (BGC Block Aligner) and a curated benchmark (SideroBank), this study reveals that siderophore biosynthesis is a pervasive trait across over 60% of bacterial genomes, where ecological lifestyle rather than phylogenetic relatedness drives the global distribution and evolution of these iron-acquisition systems.
The authors developed markeR, an open-source R toolkit for systematically evaluating and benchmarking gene sets as phenotypic markers across diverse datasets, demonstrating its utility through a comprehensive analysis of senescence signatures that revealed significant variability in their performance and highlighted the tool's capacity to uncover context-specific biological insights.
This paper introduces LongevityBench, a comprehensive benchmark designed to evaluate state-of-the-art large language models on their ability to interpret diverse aging-related biodata and grasp fundamental biological principles of aging, ultimately revealing their current limitations and outlining strategies to enhance their utility in longevity research.
TFBindFormer is a hybrid cross-attention transformer that significantly improves the accuracy and scalability of transcription factor-DNA binding predictions by explicitly integrating DNA genomic features with TF-specific protein sequence and structural information, outperforming existing DNA-only models across diverse cell types and genomic contexts.
TSvelo is a novel RNA velocity framework that utilizes interpretable neural ordinary differential equations to model the cascade of gene regulation, transcription, and splicing, thereby overcoming the limitations of existing methods to precisely capture complex gene dynamics and infer unified latent time across single cells and multi-lineage datasets.
This study validates the ActTrust(R) accelerometer as a simple, cost-effective tool for estimating energy expenditure and classifying physical activity intensity in young adults by demonstrating its strong correlation with treadmill speed and metabolic equivalents, as well as its high accuracy in predicting activity levels comparable to the widely used ActiGraph(R) GT3X+.
This paper introduces a framework that validates and aggregates the distinct outputs of multiple Active Module Identification algorithms using spectral clustering and Greedy Conductance-based Merging to overcome the limitations of single-algorithm approaches and reveal cohesive biological modules, including hidden genes, in genetic interaction networks.
The paper introduces GRASP, a parameter-efficient framework that utilizes gene- and relation-specific soft prompts to enhance the scalability and generalizability of large language models for inferring diverse gene network interactions.
The paper introduces CRIS, a centralized database that addresses challenges in RNA structure and interaction data by providing rigorously curated, standardized, and high-quality datasets from crosslinking-based technologies to enhance reproducibility, facilitate comparative analysis, and support deep learning applications in the AI era.
The paper introduces KNexPHENIX, a customized PHENIX-based workflow that consistently improves the stereochemical quality of both cryo-EM and X-ray crystallographic structural models while maintaining map correlation and preventing overfitting, offering a practical and accessible solution for generating high-quality models for deposition.
The paper introduces HEIMDALL, a unified framework that disentangles single-cell foundation model tokenization strategies to demonstrate that robust generalization across diverse biological distribution shifts depends on specific design choices regarding gene identity, expression encoding, and ordering rather than a single universal tokenizer.
This paper demonstrates that heterogeneous observation depths in single-cell data create spurious topological artifacts in manifold inference, and proposes using topological stability descriptors to identify trustworthy regimes for reconstructing cell-state transitions.
This paper introduces a broadly applicable definition of correct gene tree tagging that accounts for deep coalescence and uses it to analyze the statistical properties and simulation accuracy of the ASTRAL-pro method under the DLCoal model.
This study demonstrates that combining reduced amino acid alphabets with Byte Pair Encoding tokenization significantly enhances the computational efficiency of protein language models by shortening input sequences and accelerating training, while maintaining or even improving predictive performance across diverse downstream tasks.
This study introduces Cyclome, a comprehensive computational framework that unifies a curated dataset of 930 cyclic peptides with novel topology-aware algorithms and machine learning models to predict thermal stability and identify critical metal-binding capabilities, thereby advancing the design of stable cyclic peptide therapeutics and tools for mineral recovery.
Pipette is a multi-agent AI framework that leverages a literature-derived Skill Graph to guide natural language-driven generation of biologically valid, reproducible, and end-to-end bioinformatics workflows, effectively lowering the computational expertise barrier for genomic data analysis.
This study demonstrates that Variational Autoencoders effectively cluster biological and biomedical data by leveraging their inherent latent space representations and reconstruction likelihood to identify typical samples and anomalies, offering a principled alternative to traditional clustering methods.
The paper introduces VASCIF, a structure-aware framework utilizing Masked Graph Attention and adaptive transfer learning to achieve state-of-the-art, interpretable, and efficient prediction of antibody-antigen structural interfaces, thereby overcoming challenges related to data scarcity and computational cost in antibody discovery.
HiReS is an open-source, deep learning-based workflow that overcomes memory limitations to enable automated, high-resolution morphometric trait extraction from full-size plankton images, demonstrating strong agreement with manual measurements and improved statistical reliability at low sampling depths.