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.

Graph Neural Networks for Molecular and Materials Representation 10
Overcoming Data Sparsity in Single Cell Sequencing 9
Contextual Embeddings from Protein Language Models 7
Bridging the Usability Gap in Computational Biology 7
Democratizing Bioinformatics Through Graphical and Cloud Abstractions 5
Integrating Heterogeneous Multi-Omics Data Layers 5
Predicting Neoantigen Immunogenicity Beyond Peptide MHC Binding Affinity 4
Algorithmic Optimizations for High Throughput Genomic Processing 4
Parallel and Neural Acceleration of Sequence Alignment 4
Predicting Protein Binding Affinity and Mutational Effects 4
Integrating Biological Prior Knowledge into Genomic Machine Learning 4
Cross-Attention for Biomolecular Interaction Modeling 4
Autonomous Biological Motif Discovery via Attention Mechanisms 4
The Structural Variant Detection Gap 4
Structural Interpretability in Molecular Deep Learning 4

Top Authors

AuthorPapers
Gunnar Ratsch4
Mark Gerstein4
Jaewoo Kang3
Martin Renqiang Min3
Min Wu3
Niko Beerenwinkel3
Travis J Wheeler3
Charlotte Deane2
Chong Wu2
Christof Seiler2
Fuyi Li2
Gary D. Bader2
Jianlin Cheng2
Jianxin Wang2
Ka-Chun Wong2
Karsten Borgwardt2
Ole Winther2
Pingzhao Hu2
Renmin Han2
Sebastian Weichwald2

Impactful Papers

Papers from Bioinformatics 2024 that shaped research clusters.

Foundational

Influential

Papers

Title
Inferring gene regulatory networks from single-cell transcriptomics based on graph embedding
Information-incorporated gene network construction with FDR control
iNGNN-DTI: prediction of drug-target interaction with interpretable nested graph neural network and pretrained molecule models
Insights into the inner workings of transformer models for protein function prediction
In the twilight zone of protein sequence homology: do protein language models learn protein structure?
Investigating alignment-free machine learning methods for HIV-1 subtype classification
Knowledge graph embeddings in the biomedical domain: are they useful? A look at link prediction, rule learning, and downstream polypharmacy tasks
Knowledge mining of brain connectivity in massive literature based on transfer learning
Label-guided seed-chain-extend alignment on annotated De Bruijn graphs
LarvaTagger: manual and automatic tagging of Drosophila larval behaviour
Learning meaningful representation of single-neuron morphology via large-scale pre-training
Lifestyle factors in the biomedical literature: an ontology and comprehensive resources for named entity recognition
LineageVAE: reconstructing historical cell states and transcriptomes toward unobserved progenitors
Literature mining discerns latent disease-gene relationships
longmixr: a tool for robust clustering of high-dimensional cross-sectional and longitudinal variables of mixed data types
Many-core algorithms for high-dimensional gradients on phylogenetic trees
MARS: a motif-based autoregressive model for retrosynthesis prediction
MCDHGN: heterogeneous network-based cancer driver gene prediction and interpretability analysis
Melodia: a Python library for protein structure analysis
MERITS: a web-based integrated Mycobacterial PE/PPE protein database
Metadata-guided feature disentanglement for functional genomics
metaGWASmanager: a toolbox for an automated workflow from phenotypes to meta-analysis in GWAS consortia
MethParquet: an R package for rapid and efficient DNA methylation association analysis adopting Apache Parquet
M-Ionic: prediction of metal-ion-binding sites from sequence using residue embeddings
Modeling metastatic progression from cross-sectional cancer genomics data
Modeling multi-stage disease progression and identifying genetic risk factors via a novel collaborative learning method
Modeling multi-stage disease progression and identifying genetic risk factors via a novel collaborative learning method
Molecular property prediction based on graph structure learning
MolFeSCue: enhancing molecular property prediction in data-limited and imbalanced contexts using few-shot and contrastive learning
MolLM: a unified language model for integrating biomedical text with 2D and 3D molecular representations
MolMVC: Enhancing molecular representations for drug-related tasks through multi-view contrastive learning
MoLPC2: improved prediction of large protein complex structures and stoichiometry using Monte Carlo Tree Search and AlphaFold2
MolPLA: a molecular pretraining framework for learning cores, R-groups and their linker joints
mosGraphGen: a novel tool to generate multi-omics signaling graphs to facilitate integrative and interpretable graph AI model development
MSModDetector: a tool for detecting mass shifts and post-translational modifications in individual ion mass spectrometry data
MULAN: multimodal protein language model for sequence and structure encoding
Multiomics-integrated deep language model enables in silico genome-wide detection of transcription factor binding site in unexplored biosamples
NeoAgDT: optimization of personal neoantigen vaccine composition by digital twin simulation of a cancer cell population
NeoaPred: a deep-learning framework for predicting immunogenic neoantigen based on surface and structural features of peptide–human leukocyte antigen complexes
Novel symmetry-preserving neural network model for phylogenetic inference
NPSV-deep: a deep learning method for genotyping structural variants in short read genome sequencing data
OLB-AC: toward optimizing ligand bioactivities through deep graph learning and activity cliffs
OM2Seq: learning retrieval embeddings for optical genome mapping
Oncotree2vec - a method for embedding and clustering of tumor mutation trees
OncotreeVIS—an interactive graphical user interface for visualizing mutation tree cohorts
Optimal sequencing budget allocation for trajectory reconstruction of single cells
Pair-EGRET: enhancing the prediction of protein–protein interaction sites through graph attention networks and protein language models
Pangenome graph layout by Path-Guided Stochastic Gradient Descent
Partial RNA design
PERFUMES: pipeline to extract RNA functional motifs and exposed structures

« prev Page 3/5 next »