1197 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.
ReconSIREN is a novel deep learning framework utilizing a Mixture-of-Experts architecture to perform fully \textit{ab initio} CryoEM single-particle analysis that simultaneously resolves preferred orientation artifacts, particle heterogeneity, and conformational flexibility without relying on traditional optimization methods.
This study introduces a topology-driven framework that successfully integrates proteomic and functional data from human engineered cardiac tissues to reveal how epinephrine and doxorubicin exert opposing inotropic effects by differentially modulating energy homeostasis, mitochondrial translation, and proteostasis.
KENT is a portable, offline edge-computing framework utilizing a cluster of NVIDIA Jetson Nano modules to enable fast, GPU-accelerated metagenomic pathogen screening in resource-constrained environments, achieving significant speedups over CPU baselines while maintaining high classification accuracy and abundance estimation fidelity.
FlyAnatoView is a resource that addresses the lack of spatial context in single-cell RNA sequencing data by projecting transcriptomic profiles onto anatomical diagrams of *Drosophila*, thereby restoring information about the specific tissue or organ locations of individual cells.
FilAdh is a unified, degradation-aware computational framework that simultaneously segments focal adhesions and reconstructs actin stress fibers to enable accurate morphometric analysis and spatial classification, outperforming existing methods in benchmark tests while explicitly characterizing how specific imaging imperfections affect structural measurements.
This paper presents an integrated computational strategy for analyzing nanopore protein ionic current signals that combines denoising, segmentation, and machine learning techniques to achieve high accuracy in charge-based binary classification and to model peptide translocation, despite challenges in distinguishing all 20 amino acids.
This study demonstrates that additive-input encoding models used in current Perturb-seq screens fail to generalize to new, held-out perturbation targets, revealing that inferred regulatory operators are not validated for predicting responses to unseen genes despite their mathematical identifiability.
VINTER is a generative vision-language model that unifies histology, gene expression, and spatial neighborhood into a single sequence to accurately annotate and interrogate spatial tissue structures across diverse platforms and resolutions, revealing hidden biological heterogeneity and enabling molecular evidence editing without retraining.
This study evaluates the performance of TGAN and CTGAN models in generating synthetic 6-year longitudinal cardiovascular disease data, finding that while CTGAN generally offers superior fidelity and privacy compared to TGAN and a perturbation baseline, it still requires refinement to better preserve temporal characteristics and performance across younger age groups.
The paper introduces Hyper Screening X, a generative AI framework that integrates structure-based design with automated synthesis hardware to efficiently navigate trillion-scale chemical spaces, successfully identifying first-in-class lead compounds with high synthesis and functional hit rates.