Discover, rate, and discuss biology preprints.

The paper introduces ID3, a framework for optimizing mRNA sequences using gradient-based methods, balancing multiple properties while preserving amino acid sequences.

COBRA removes cell-type-specific batch effects in scRNA-seq data, preserving biological differences and improving integration across datasets.

The paper introduces a large dataset of cryo-EM RNA motifs and benchmarks machine learning models for structure prediction.

This paper develops a phenotype-structured model to study how proliferation heterogeneity affects tumor growth and treatment response, showing that optimal proliferation rates shift with tumor size and treatment regimes.

fastCNV predicts copy number variations from spatial transcriptomics and scRNA-seq data, showing high accuracy and speed improvements over existing methods.

Hi-Cformer models multi-scale chromatin contact maps from single-cell Hi-C data, improving cell type separation and imputation of 3D genome features.

This paper shows that ignoring gene-gene interactions in GWAS can lead to false positive results, highlighting the need for more complex models.

scProtoTransformer provides a scalable reference mapping framework across molecular, cellular, and donor levels using a prototype-based Transformer model with improved interpretability and performance.

The paper introduces TOB-QMC, a method for scalable and accurate tree of blobs reconstruction under network multispecies coalescent, improving upon TINNiK in both speed and accuracy.

This paper introduces DiffEnsemble, a diffusion-based framework for modeling protein conformational ensembles, showing improved performance over existing methods.

The paper finetunes gene embeddings from foundation models for temporal clinical transcriptomics data, improving gene network analysis and detection of disease progression and drug response mechanisms.

The paper introduces a calibration method to reduce sample-size bias in linkage disequilibrium estimation, showing improved accuracy in both simulated and real data, especially with small sample sizes.

GDA-Pred improves prediction of IL-6 and IL-13 inducing peptides by using generative AI to augment small datasets, enhancing classifier performance through data expansion.

dioscRi improves transferability of deep learning models for cytometry data by integrating normalization, cell type hierarchies, and clinical outcome prediction.

ViroSeek is a viral detection pipeline for second-generation sequencing data that provides a clear viral taxonomy table through automated quality control, sequence removal, assembly, and quantification.

The paper compares variant effect predictors and MAVEs to understand their agreement and disagreement in assessing genetic variant impacts.

MSI-VISUAL provides interactive tools for MSI analysis, improving visualization and detection of tissue differences in mouse brain and kidney data.

STcompare identifies differentially spatially patterned genes by comparing spatial correlation and fold-change across structurally matched tissues in spatial transcriptomics data.

This paper uses deep learning to predict relationships between 5' and 3' UTRs, finding that highly related pairs are enriched in genes involved in neural development and have distinct sequence and structural features.

DeepPathway predicts pathway expression from H&E images using contrastive learning, validated on prostate cancer and brain tumor datasets.