856 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 authors developed the Structural Novelty Index (SNI), an AI-driven framework that successfully identified and experimentally validated an unexpected undecameric assembly of NRC immune receptors, demonstrating a scalable method for discovering atypical protein complexes beyond canonical architectures.
This paper proposes an unsupervised framework leveraging large language models and contrastive learning to characterize SARS-CoV-2 spike protein sequences, demonstrating improved clustering performance in predicting emerging variants compared to previous approaches.
The paper introduces cryoPANDA, a massive dataset of over 37 million annotated cryo-EM particles from 252 diverse experiments, designed to overcome current data limitations and accelerate the development of data-driven methods for structural biology.
This paper presents a fully data-driven subspace one-class classification framework that models healthy plasma proteomic profiles to robustly detect diverse diseases without requiring diseased training samples, thereby overcoming class imbalance challenges in high-dimensional clinical data.
This paper presents a CASP16 case study by LCBio demonstrating that while expert-guided workflows can achieve competitive rankings in RNA multimer prediction, current methods exhibit a hierarchical decline in accuracy where reliable local features fail to translate into precise global architectures due to persistent challenges in modeling multi-helix junctions and non-canonical interactions.
This paper introduces linearPOA, a parallel and memory-efficient framework that utilizes a divide-and-conquer strategy to achieve linear space complexity for Partial Order Alignment, significantly reducing memory consumption compared to existing quadratic algorithms when handling ultra-long, error-prone sequencing reads.
This study introduces PanBART, a species-specific transformer model trained on the gene content and order of *Escherichia coli* and *Streptococcus pneumoniae*, demonstrating its superior ability to unsupervisedly learn population structures, identify emergent lineages, predict antibiotic resistance gene uptake, and analyze gene co-selection for critical genomic surveillance tasks.
This paper presents a conditional variational autoencoder pipeline that integrates QSAR-guided surrogate-weighted fine-tuning and cross-entropy optimization to overcome data scarcity and circular dependency challenges, successfully generating targeted antimicrobial peptides with high predicted efficacy and favorable structural properties.
This study employs an integrative systems pharmacology approach to characterize the molecular heterogeneity of antiphospholipid syndrome, identifying Type I interferon signaling and myeloid-like B cell reprogramming as key druggable axes that enable patient stratification and the repurposing of existing therapies for precision medicine.
The paper introduces BioChirp, an open-source framework that combines LLM-based query interpretation with deterministic graph-based retrieval to recover more biomedical associations with higher reproducibility than conventional LLM-based systems.