Discover, rate, and discuss biology preprints.

The paper shows a sequence-only pipeline using TabPFN achieves high accuracy in multi-activity antimicrobial peptide profiling, outperforming complex deep models.

HyperSketch provides a structure-aware genomic similarity method using de Bruijn graphs and Hyperdimensional Computing, achieving high-resolution strain clustering and deep evolutionary scaling.

ReTIF improves RNA-compound interaction prediction and binding-site localization by using task-specific interaction representations, outperforming baselines in multiple evaluation scenarios.

This paper identifies systematic prediction bias in aging clocks and introduces a constrained optimization framework to improve calibration and downstream inference.

This paper identifies natural inhibitors of a membrane protein involved in biofilm formation in Vibrio cholerae through structural modeling, functional analysis, and virtual screening.

gVCF2CNV converts gVCF files into CNV-compatible signals for large-scale WGS cohorts, achieving high precision in detecting deletions and duplications.

PromptBio is an AI platform that translates research objectives into executable workflows, enabling reproducible and adaptable biomedical analyses.

MErlin integrates bacterial methylome data with other omics data to produce gene-level evidence and reports, using a modular toolkit and LLM interface.

OmniSyn generates and optimizes target-specific molecules with synthesis traces using a sequence-conditioned LLM, achieving state-of-the-art performance on drug discovery benchmarks.

multiTEMPTED jointly reduces dimensionality of longitudinal multi-omic data, capturing modality-specific temporal dynamics and outperforms existing methods in speed and accuracy.

This study uses genomic feature extraction and machine learning to identify environmental adaptations in prokaryotes, revealing gene and ncRNA associations with salinity, temperature, oxygen, and pH preferences.

GIN-CRC-Pareto identifies miRNA-target interactions in colorectal cancer using a graph-based multi-task learning framework, outperforming existing methods in accuracy and AUC.

RevPert predicts genetic drivers of transcriptomic state transitions by ranking genetic perturbations based on their expression signatures matching observed transcriptomic shifts.

platpy provides a spatial-first framework for analyzing spatial transcriptomic data, improving efficiency and reducing errors in multi-layer spatial analysis.

This study investigates how hypoxia affects DNA nanocage uptake in cells and zebrafish, finding that surface charge engineering can improve delivery under hypoxic conditions.

PoolParty is a Python package that simplifies the design of DNA sequence libraries for assays like DMS and MPRA, offering a structured and reproducible approach.

This paper uses relational graph convolutional networks to integrate ceRNA and copy number variation data for glioblastoma biomarker discovery, identifying five novel candidate biomarkers.

This paper evaluates how dimensionality reduction methods affect trajectory geometry by testing their path-preservation across different point-density thresholds on linear and cyclic single-cell datasets.

This study computationally evaluates how adding the LRLLR motif to different peptides affects their membrane translocation, showing that compatibility determines success.

The paper introduces CL-pLMM, a method for integrating clustered multiview biomedical data, and shows it improves prediction in longitudinal proteomic and metabolomic studies.