1012 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.
This paper introduces an interactive framework for benchmarking scientific coding agents using spatial transcriptomics alignment tasks, revealing that while richer environmental context increases tool exploration, it can degrade performance by inducing fragile workflows and unnecessary transformations, thereby highlighting the need to evaluate agent traces alongside final outputs.
LeafRank is a novel phylodynamic framework that leverages single-cell DNA-seq phylogenies and a multi-type branching process model to infer the relative fitness of individual cells in chromosomally unstable tumors, successfully quantifying growth heterogeneity and revealing that fitness in whole-genome duplication lineages is acquired through subsequent alterations rather than immediate advantages.
Rectangle is a robust and scalable Python framework that leverages multiscale deconvolution and explicit modeling of unknown content to accurately resolve cell phenotypes in bulk RNA-seq data using single-cell references, thereby enabling high-resolution cellular profiling at population scales.
This paper demonstrates that coding agents can automatically generate interpretable, zero-shot single-cell embedding models by extracting and composing literature-cited gene programs into named axes, achieving biological quality comparable to data-driven methods while ensuring inherent batch robustness and interpretability without requiring training or prior gene-set databases.
EZSolver is a template-free, generative framework that leverages flow matching and evaluator-guided bidirectional search to accurately predict polar enzymatic reaction mechanisms for out-of-distribution chemistry, overcoming the generalization limitations of traditional rule-based models.
This study presents PredHLM, a quantitative and interpretable XGBoost-based machine learning model trained on nearly 12,000 compounds that accurately predicts human liver microsome metabolic half-life and identifies key chemical drivers to support rapid decision-making in early drug discovery.
The paper introduces stGP, a statistical framework that decomposes spatiotemporal transcriptomic data into temporal and spatial components to identify interpretable, cell-type-specific gene programs, thereby revealing how dynamic tissue architectures and localized cellular responses evolve across time and anatomical niches.
The paper introduces DL4DR, a two-tower residual late-fusion deep learning model that predicts pan-breast-cancer drug responses by encoding cell lines as genomic images and combining molecular representations, thereby achieving superior generalization to unseen cell lines and cancer types while identifying novel genomic drivers without relying on cell line identities.
The paper introduces hmSEEKR, a k-mer-based hidden Markov model that scans transcriptomes to identify non-linear, domain-level sequence similarities in long noncoding RNAs, thereby enabling the discovery of functionally related RNA domains and their associated protein interaction networks without requiring prior knowledge of sequence alignment.
The paper introduces AllTheBacteria, a comprehensive community resource that uniformly processes nearly 2.5 million public bacterial genomes to enable large-scale biological research and successfully demonstrates its utility by discovering and validating novel peptide antibiotics through AI-driven mining.