940 papers
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.
The paper introduces scLongTree, a scalable and accurate computational tool designed to infer subclonal evolutionary trees from longitudinal single-cell DNA sequencing data, demonstrating superior performance over existing methods on both simulated and real-world cancer datasets.
The paper introduces **rnaends**, an R package designed to facilitate the analysis of exact RNA ends at nucleotide resolution by providing a comprehensive workflow for processing, quantifying, and interpreting RNA-end sequencing data to study diverse aspects of RNA metabolism such as transcription start sites, degradation dynamics, and post-transcriptional modifications.
This paper introduces Coherent Denoising, a novel ensemble-based diffusion framework that synthesizes missing biomedical modalities from available data to overcome dataset sparsity, thereby enabling high-fidelity multimodal integration, robust predictive modeling, and counterfactual analysis for precision oncology using a large-scale TCGA cohort.
COMPASS is a deterministic, ontology-free web-based framework that converts gene expression into stable, interpretable pathway activity scores without requiring permutation or reference cohorts, offering improved robustness and discrimination compared to existing single-sample enrichment methods for precision medicine applications.
AEGIS is an open-source, user-friendly Python toolkit that standardizes inconsistent genome annotation files, extracts specific genomic features, and facilitates robust comparative genomics by integrating multiple evidence lines to resolve gene ID correspondences and structural variations.
This study identifies and characterizes orphan genes in *Meloidogyne* root-knot nematodes, revealing that they constitute 18% of the genome, originate through both high divergence and *de novo* birth, and possess distinct molecular features suggesting a critical role in the nematodes' global parasitism.
The paper proposes DyGraphTrans, a memory-efficient and interpretable dynamic graph representation learning framework that models patient Electronic Health Records as temporal graphs to effectively predict disease progression and mortality while capturing both local temporal dependencies and global trends.
PRIZM is a data-efficient, two-phase workflow that leverages small experimental datasets to select optimal zero-shot foundation models for ranking and prioritizing protein variants, successfully identifying improved thermostability and activity in enzyme engineering case studies.
This paper presents a unified, high-quality spatial transcriptomic dataset generated via the Stereo-seq platform across ten mouse organs, providing matched histological images, cell-type annotations, and multi-resolution expression matrices to serve as a standardized resource for developing and benchmarking deep learning models in spatial biology.