Discover, rate, and discuss biology papers.

GRASP is a graph Transformer that learns molecular structure from ZINC20 data and adapts to ChEMBL bioactivity, achieving better performance than existing models on ADMET prediction tasks.

lisaR organizes gene set enrichment analysis results into semantic categories using LLM-inferred dictionaries, improving interpretability of biological findings.

The paper identifies a 'double-dipping' issue in scRNA-Seq where cell-type clustering and phenotype testing are performed on the same data, leading to inflated false discovery rates, and proposes solutions to mitigate this problem.

This paper introduces LYM-1, a multi-crop yield prediction model for Canadian prairies using extensive yield, weather, and soil data, showing improved predictive performance and revealing agronomically relevant interactions.

MOSAIC learns graph node embeddings by analyzing dominant spectral components of diffusion operators, outperforming existing methods in biomedical graph tasks.

This paper introduces an algorithm to compute minimum-density minimizers for high-throughput sequencing, achieving faster results than brute-force methods.

Meta2Data automates retrieval, standardization, and processing of microbiome sequencing data from public repositories for downstream analysis.

This paper introduces DTi-pKa, a graph neural network that predicts pKa values with thermodynamic consistency and achieves high accuracy on benchmark datasets.

This study identifies stage-dependent changes in autonomic and neurotrophic signaling in alcohol-associated liver disease using bulk and single-cell transcriptomics.

The paper reanalyzes six mouse AD scRNA-seq datasets to identify a reproducible innate immune activation signature across studies.

YGEP provides a cloud platform for genomic evaluation and breeding in yaks, integrating pedigree reconstruction, genotype imputation, and genomic breeding value estimation with high accuracy.

The paper introduces a weighted pathway co-membership method for Reactome pathways, improving gene prioritization in cancer hallmarks by incorporating biological distances and hierarchical structure.

This paper introduces TIDGN, a deep learning method to encode protein dynamics into a transferable latent representation, achieving high AUROC in function prediction across different proteins.

CardamomOT improves gene regulatory network inference and trajectory reconstruction by integrating mechanistic models with optimal transport, using exact time labels and reducing hyperparameters.

The paper provides guidance on analyzing circular data in spatial omics, using case studies to illustrate key considerations and methods.

ASTRA enables zero-shot super-resolution of spatial transcriptomics across different capture geometries, improving accuracy and efficiency compared to existing methods.

STARIT converts spatial transcriptomics data into image tensors for deep learning analysis, enabling subcellular heterogeneity-based cell state identification.

This paper introduces Nagini3D, a 3D image segmentation method combining deep learning and active surfaces for improved shape analysis and consistency across 3D volumes.

The paper identifies improved hydroxymethylfurfural oxidases through iterative computational methods combining molecular simulation and machine learning.