Discover, rate, and discuss biology papers.

PostChicago provides a workflow for analyzing and comparing chromatin interactions from Capture-(Hi)C data, including quality control and visualization of metaprofiles.

The paper introduces an improved protocol and software for sequence-specific direct RNA sequencing of non-polyadenylated RNAs, validated on human rRNA and other RNA species.

IsoGraph identifies age-associated transcript-usage signals in human brain transcriptomes, distinguishing them from gene abundance and cellular composition effects.

CRISCross improves CRISPR-Cas9 off-target prediction by integrating epigenetic features with sequence data across cell types, showing better performance than sequence-only models.

Perturb-Seqr integrates multiple Connectivity Mapping datasets to enable drug and target discovery by searching for gene expression signatures of drug and gene perturbations.

GenDiMug is a multigraph framework for analyzing genomic organization and multi-omics data across scales, revealing gene expression clumping and circadian regulation in a photosynthetic alga.

The paper evaluates how AI systems handle version changes in oncology guidelines, finding that retrieval from multiple versions can lead to outdated answers, and introduces a verification system to reduce errors.

This paper introduces a method to accelerate optimum contribution selection by approximating genomic relationship matrices with low-rank structures, achieving significant speedups while maintaining accuracy.

EvSpark improves decoding speed for hybrid DNA models by speculative decoding with parallel verification, achieving significant speedups across real and synthetic prompts.

The paper introduces a method for protein design that connects reasoning and generation through structural states, achieving high performance on a benchmark.

GLARE is a TE classifier that outperforms existing methods across multiple taxonomic groups and sequence quality conditions using a genomic language model fine-tuned on harmonized reference data.

kitAb provides an automated framework for antibody developability modeling and landscape analysis, showing comparable performance to existing methods while being faster.

MetworkPy provides a Python package for objective-free graph- and information-theoretic analysis of genome-scale metabolic models to identify metabolic features perturbed by transcription factors.

SCARSE is a machine learning framework that improves peptide engineering by combining ESM2 embeddings with Gaussian process regression, outperforming baselines in low-data regimes and enabling efficient active learning.

RiboFlow v2 improves ribosome profiling analysis by incorporating genome alignment and configurable handling of multimapping reads, revealing gene-specific differences in coverage and translation efficiency.

TurbOmics is a web-based platform that enables multi-omics integration of metabolomics, proteomics, and transcriptomics data, addressing limitations in metabolomics annotation and accessibility.

The paper characterizes HPV integration structures in oropharyngeal cancer and links Type2 integration to oncogenic features and aggressive tumor behavior.

ReconSIREN is a deep learning framework that improves CryoEM map accuracy by addressing preferred orientation errors in heterogeneous samples.

Winnow-tax improves taxonomic profiling of low-coverage shotgun metagenomes by combining sensitive read-level classification with genome-level confirmation, achieving better precision-sensitivity balance than existing methods.