Bioinformatics 2024
204 papers
Bioinformatics 2024 published 80 papers centered on the intersection of advanced computational methods and biological discovery. A primary focus was the development of generalist medical AI and multimodal foundation models, alongside research into the application of large language models (LLMs) to genomic data. Key themes included named entity recognition as a text generation task, surface-centric geometric learning for molecular interactions, and the use of network priors for biological data integration. Technical investigations also addressed the formatting bottleneck in LLMs and precise span boundary detection in information extraction.
Specific research outputs included FAVOR-GPT, a generative interface for genome variant annotations, and MULAN, a multimodal protein language model for sequence and structure encoding. Other work focused on interpretable cell type annotation frameworks, drug-target interaction prediction via DrugLAMP, and the visualization of alternative polyadenylation dynamics. Prolific contributors to this year's edition included Travis J. Wheeler, Lars Juhl Jensen, and Xin Gao. These studies collectively advanced methodologies for modeling disease progression and tissue-specificity scoring, reflecting a trend toward integrating structural, sequence, and clinical data.
Top Research Directions
Research directions most represented by Bioinformatics 2024 papers.
Top Authors
Impactful Papers
Papers from Bioinformatics 2024 that shaped research clusters.
Foundational
Effect of tokenization on transformers for biological sequences
foundational
Single Nucleotide Tokenization for Genom
Influential
FAVOR-GPT: a generative natural language interface to whole genome variant functional annotations
influential
Natural Language Interfaces for Complex
Modeling metastatic progression from cross-sectional cancer genomics data
influential
Reconstructing Evolutionary Trajectories
GPro: generative AI-empowered toolkit for promoter design
influential
De Novo Protein Design via Generative Se
HELM-GPT: de novo macrocyclic peptide design using generative pre-trained transformer
influential
Targeting Intrinsically Disordered Prote
MolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few
influential
Adaptive Margins for Contrastive and Met
FAVOR-GPT: a generative natural language interface to whole genome variant functional annotations
influential
Grounding Language Models with External
Investigating alignment-free machine learning methods for HIV-1 subtype classification
influential
Minority Class Oversampling for Imbalanc
Hi-GeoMVP: a hierarchical geometry-enhanced deep learning model for drug response prediction
influential
Heterogeneous Network Integration for Bi
DeepRSMA: a cross-fusion-based deep learning method for RNA–small molecule binding affinity predicti
influential
Multi-View Molecular Representation Lear
RetroCaptioner: beyond attention in end-to-end retrosynthesis transformer via contrastively captione
influential
Fusing Graphs and Sequences for Molecula
Papers
« prev Page 5/5