Discover, rate, and discuss biology preprints.

PromptBio-Bench evaluates LLM-based bioinformatics agents across 244 tasks, showing comparable performance between Biomni and ToolsGenie but declining accuracy with task difficulty.

BrightEyes-FFS provides an open-source platform for analyzing fluorescence fluctuation spectroscopy data with small detector arrays, offering tools for data processing, correlation analysis, and model fitting.

PEPE efficiently extracts multimodal protein embeddings from language models, enabling scalable and memory-efficient generation of large embedding datasets for downstream biological tasks.

PMGen improves peptide-MHC structure prediction and enables structure-guided peptide design, achieving high accuracy and enhancing ML model performance.

The paper develops ML tools to improve genotype-phenotype prediction for opsin genes by introducing new methods and software.

This paper introduces FunBind, a multimodal model for protein function prediction that improves accuracy and enables zero-shot prediction of novel functions.

The paper introduces Membrane Kymograph Generator, a software tool for automated kymograph generation and analysis of membrane dynamics from live-cell imaging data.

This study compares five RNA velocity methods across three datasets to evaluate their performance in predicting cellular states.

CytoSignal detects and quantifies ligand-receptor signaling interactions at cellular resolution from spatial transcriptomic data, enabling spatial gradient analysis and temporal dynamics prediction.

An R-Shiny app built on DataFed lets researchers filter metagenomic sample metadata by location, date and environmental variables, then download only matching sequence files via Globus.

This paper introduces diffusion models for generating synthetic gene expression data and shows they outperform existing methods in predictive performance.

The paper introduces ProteomeLM-HPI, a language model adapted to predict cross-species host-pathogen interactions using proteome context and fine-tuning.

The paper introduces a cohort-HMM marker recruitment pipeline to improve phylogenomic supermatrix construction by addressing biases in orthogroup recovery and paralog filtering across different taxonomic scales.

The paper introduces growthcurves, a Python package and web tools for analyzing biological growth curves with human-in-the-loop workflows, providing automated fitting and interactive inspection.

The paper introduces compPASS, a tool to identify Pol2 failure modes in cancer, revealing rare modes linked to gene regulation and therapy response.

TargetSureR assesses siRNA off-target risks using a seven-dimensional scoring system and enables cross-species model selection for preclinical safety evaluation.

BasalCell provides a project scaffold generator to integrate R and Python ecosystems, enabling reproducible, multi-language bioinformatics workflows with version control and CI/CD.

scTrends classifies and quantifies gene expression trends along pseudotime in single-cell RNA-seq datasets, revealing diverse expression patterns across biological processes.

CLOP-DiT generates synthetic single-cell gene expression profiles from structured biological metadata using contrastive alignment and diffusion models, achieving high steering accuracy but limited cross-dataset variability.

This study shows that determining if a population is measurably evolving or has reached the phylodynamic threshold depends on model assumptions and sampling strategies, not just data, and emphasizes prior sensitivity over tests of temporal signal.