1199 papers
Bioinformatics sits at the exciting intersection where biology meets data science, using powerful computer tools to decode the vast complexity of living systems. From mapping the human genome to tracking how viruses evolve, this field transforms raw biological information into actionable insights that drive modern medicine and research forward without requiring a supercomputer to understand the basics.
On Gist.Science, we ensure you never miss a breakthrough by processing every new preprint in this category directly from bioRxiv. Our team provides both plain-language explanations and detailed technical summaries for each paper, making cutting-edge discoveries accessible to everyone regardless of their background.
Below are the latest bioinformatics papers added from bioRxiv, ready for you to explore with clarity and depth.
The paper introduces CLASPP, a unified model for predicting diverse post-translational modifications that overcomes data imbalance challenges through contrastive learning, hierarchical data curation, and a multi-stage training strategy to improve prediction accuracy across various organisms.
BacteReason is a fine-tuned large language model that predicts bacterial antibiotic susceptibility and provides mechanistic rationales by leveraging a knowledge-grounded teacher model, resulting in significantly improved prediction accuracy over baseline approaches.
The paper introduces GLOF, a large-scale, expert-curated benchmark dataset comprising over 112,000 missense variants across nearly 3,000 human genes, which classifies variants as gain-of-function, loss-of-function, or neutral to facilitate the development and evaluation of computational methods for predicting variant mechanisms.
VelocityFM is a novel short-horizon protein trajectory predictor that utilizes rectified flow matching in velocity space to generate geometrically valid, clash-free, and fold-preserving dynamic conformations for unseen proteins, achieving high structural accuracy with a median TM-score of 0.929.
The paper introduces GLEAM, a web-based, code-free software toolkit built on the Galaxy workbench that enables biomedical researchers to perform rigorous, reproducible, and accessible supervised machine learning analyses across diverse data types while adhering to best practices.
This paper presents a scalable, GPU-accelerated pangenome construction method that leverages protein language model embeddings and advanced clustering to outperform existing tools like SCARAP in generating functionally coherent and specific protein clusters, particularly on experimentally validated datasets.
Ontologizer 3 is a freely available, cross-platform desktop application that facilitates Gene Ontology enrichment analysis by offering both frequentist and Bayesian methods, with the latter demonstrating superior precision in identifying causal terms by accounting for hierarchical gene set overlaps.
The authors developed an open-source, UNet-based automated segmentation tool named 'OCTOPUS' that achieves high accuracy in detecting retinal dysplasia in mouse OCT scans, thereby streamlining preclinical screening and standardizing assessments across laboratories.
This paper proposes a training-free ensemble method that combines ProteinMPNN with the antibody-specific language model IgLM to significantly improve amino acid recovery and sequence diversity in antibody inverse folding, effectively bridging the gap between general structural models and specialized antibody design.
This study integrates single-cell RNA and ATAC sequencing across clear cell renal cell carcinoma (ccRCC) grades to reveal that epigenetic changes precede metabolic and invasive shifts, while defining a robust CBG prognostic signature and mapping the dynamic evolution of immune exhaustion and intercellular communication networks.