Discover, rate, and verify biology preprints.

Predicting Differential Protein-Protein Interactions

The paper develops a random forest model to predict differential protein-protein interactions between experimental conditions using MINT embeddings and mass spectrometry data.

DeepPhage: leveraging the power of NGS phage display data, an in-depth analysis for the identification of Eu3+-binding peptides

DeepPhage identifies Eu3+-binding peptides from NGS phage display data by analyzing sequence biases and comparing multiple experimental conditions.

Instance-Wise Contrastive Graph Neural Network Enables the Discovery of Novel Aedes aegypti Larvicidal Compounds

This paper introduces a contrastive graph neural network to discover novel larvicidal compounds against Aedes aegypti, identifying LC-79 as a potent and selective candidate.

Harness engineering enables a multi-agent LLM system to generate cross-domain hypotheses beyond single-investigator reach

The paper demonstrates that a well-designed prompting system outperforms model upgrades in generating scientific hypotheses, introducing a framework to create falsifiable, cross-domain hypotheses.

A comprehensive map of the sequence basis of transcription initiation in humans

The paper develops deep learning models to predict transcription initiation patterns from DNA sequences across human tissues and cancers.

Serum nutritional-metabolic recovery during tuberculosis treatment across BMI-defined undernutrition strata: A longitudinal proteomic reanalysis

This study reanalyzes longitudinal serum proteomics data from tuberculosis patients to assess how nutritional-metabolic recovery during treatment varies by baseline BMI, finding no significant BMI-dependent trajectories but an overall increase in a 36-protein summary axis.

LPT: Orchestrating bounded agentic loops for automated protein binder design

LPT uses bounded agentic loops with LLMs and a curated database to design protein binders from natural language prompts, achieving high success rates with low computational costs.

Agentic cryo-EM structure determination with CryoPilot

CryoPilot uses two language model agents to automate cryo-EM structure determination, improving resolution and model accuracy through adaptive decision-making.

GaussF: An Unbiased Gaussian Framework for High-Precision Transcript Quantification with a Programmable Self-Benchmark Model

GaussF improves isoform quantification by using a theoretical Gaussian model to correct sequencing biases without empirical data, outperforming existing tools.

Digital twins forecast individual immune trajectories

The paper introduces ImmuneTwins, a digital twin framework that personalizes immune response models for individuals, improving prediction accuracy of immune trajectory changes.

Multivariate Mutual Information based Feature Selection for Predicting Histone Post-Translational Modifications in Epigenetic Datasets

This paper introduces multivariate mutual information (MMI) for selecting histone PTM features to predict epigenetic data, showing improved accuracy over traditional methods.

When Does Active Learning Improve ADMET Prediction? A Multi-Endpoint Benchmark

This paper benchmarks active learning strategies for ADMET prediction, finding benefits vary by endpoint and strategy, with Deep Ensembles showing better predictive performance than MC Dropout.

GLESKit: an MCP-based system for gene-level biomedical investigation and evidence synthesis

GLESKit is a gene-centered system that synthesizes biomedical evidence by integrating multiple data types, achieving high report quality and performance in benchmark tasks.

SYMBIO-SCAN, a full-length 16S rRNA gene-based workflow optimized for bacterial symbiont detection and discovery from long read sequencing

SYMBIO-SCAN identifies high-quality full-length 16S rRNA gene sequences from long reads to discover bacterial symbionts in beetles, revealing novel genera and species.

Does a map-level insulation constraint improve sequence-based prediction of 3D genome folding? A Stage 1 Registered Report with a reverse-complement-equivariant state-space model (HiFold-Mamba)

The paper evaluates whether insulation-based losses improve sequence-based prediction of 3D genome folding using a reverse-complement-equivariant state-space model, finding improvements in boundary and loop prediction.

flashscenic: Accelerated GRN Analysis with RegDiffusion for Large-Scale Single-Cell Data

flashscenic accelerates single-cell GRN analysis using GPU acceleration, improving speed and enabling benchmarking of integration strategies in AML data.

iGEX: an interactive Gene EXpression exploration platform for the analysis of transcriptomic and proteomic datasets

iGEX provides an interactive platform for exploring transcriptomic and proteomic datasets, enabling comparison of expression patterns across experiments and public resources.

Influenza A virus H5Nx genotypes assigned by genetic similarity are incongruent with global phylogenies

This paper evaluates H5Nx influenza virus genotyping tools and finds they often group viruses with distinct evolutionary histories due to reassortment and reference bias.

Task-Dependent Performance of GNNs and Pretrained Models in ADMET Prediction

The paper benchmarks GNNs, pretrained models, and fingerprints for ADMET prediction under fair evaluation, finding no single model dominates and highlighting the importance of endpoint-specific selection and leakage-controlled testing.

BaitBench: a comprehensive tool for building, as-sessing, and predicting outcomes for hybrid capture enrichment probes

BaitBench is a tool for designing, assessing, and simulating hybrid capture probes, validated with high correlation to real data.