Bioinformatics 2021

229 papers
In 2021, research published in Bioinformatics emphasized RNA structural biology and the integration of machine learning for molecular modeling. Key research directions included the modeling of pseudoknots and non-canonical RNA base pairs, as well as RNA 3D structure prediction and design under conditions of data scarcity. Methodological trends featured the application of 3D fully convolutional neural networks for drug design and interpretable graph variational autoencoders for generating tertiary protein structures. The year's contributions also highlighted advancements in spatial transcriptomics via diffusion-based modeling and the use of reinforcement learning for biomedical event extraction. Computational tools such as the dynamic positional Burrows–Wheeler transform (d-PBWT) and methods for mapping orthologous gene pairs at the exon level were also prominent. Prolific authors, including Rui Fan, Shaojie Zhang, and Yaoqi Zhou, contributed to diverse areas ranging from protein-peptide binding prediction to the identification of interconnected communities in gene co-expression networks. These works reflect a broader shift toward using deep learning and spatial modeling to address complex biological datasets.

Top Research Directions

Research directions most represented by Bioinformatics 2021 papers.

Graph Neural Networks for Molecular and Materials Representation 5
Modeling Proteins as Residue Proximity Graphs 4
1D Convolutional Networks as Automated Biological Motif Detectors 3
Decoupled Modular Frameworks for Rapid Scientific Experimentation 3
Overcoming Data Sparsity in Single Cell Sequencing 3
Heterogeneous Network Fusion for Biomedical Discovery 3
Predicting Neoantigen Immunogenicity Beyond Peptide MHC Binding Affinity 2
Uncovering Highly Divergent Sequences in the Viral Dark Matter 2
De Novo Protein Design via Generative Sequence Modeling 2
Bridging the Usability Gap in Computational Biology 2
Structural Interpretability in Molecular Deep Learning 2
Democratizing Bioinformatics Through Graphical and Cloud Abstractions 2
The Algorithmic Frontier of Accuracy and Computational Efficiency 2
Resolving Cellular Heterogeneity Masked by Bulk Sequencing 2
Integrating Evolutionary Sequences with Geometric Protein Structures 2

Top Authors

AuthorPapers
Carl Kingsford4
Charlotte Deane4
Mark Gerstein4
Jimeng Sun3
Kexin Huang3
Min Xu3
Aidong Zhang2
Andreas Hellander2
Chen Li2
Elena Tutubalina2
Geoffrey I. Webb2
Gesine Reinert2
Jeff Bilmes2
Jianlin Cheng2
Jianxin Wang2
Jiawei Luo2
Jie Zheng2
Jionglong Su2
Jiuyong Li2
Ka-Chun Wong2

Impactful Papers

Papers from Bioinformatics 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
IMIX: a multivariate mixture model approach to association analysis through multi-omics data integration
Impact of lossy compression of nanopore raw signal data on basecalling and consensus accuracy
Improved protein model quality assessment by integrating sequential and pairwise features using deep learning
Improving circRNA-disease association prediction by sequence and ontology representations with convolutional and recurrent neural networks
Improving deep learning-based protein distance prediction in CASP14
Improving sequence-based modeling of protein families using secondary-structure quality assessment
InDeep: 3D fully convolutional neural networks to assist in silico drug design on protein–protein interactions
Inferring perturbation profiles of cancer samples
sepal: identifying transcript profiles with spatial patterns by diffusion-based modeling
ISMB/ECCB 2021 proceedings
IsoResolve: predicting splice isoform functions by integrating gene and isoform-level features with domain adaptation
JEDI: circular RNA prediction based on junction encoders and deep interaction among splice sites
KG4SL: knowledge graph neural network for synthetic lethality prediction in human cancers
KIMI: Knockoff Inference for Motif Identification from molecular sequences with controlled false discovery rate
Knowledge enhanced LSTM for coreference resolution on biomedical texts
LDpred2: better, faster, stronger
Learning embedding features based on multisense-scaled attention architecture to improve the predictive performance of anticancer peptides
Learning graph representations of biochemical networks and its application to enzymatic link prediction
Learning sparse log-ratios for high-throughput sequencing data
lgpr: an interpretable non-parametric method for inferring covariate effects from longitudinal data
Light attention predicts protein location from the language of life
lncLocator 2.0: a cell-line-specific subcellular localization predictor for long non-coding RNAs with interpretable deep learning
Long reads capture simultaneous enhancer-promoter methylation status for cell-type deconvolution
Machine learning optimization of peptides for presentation by class II MHCs
MANIEA: a microbial association network inference method based on improved Eclat association rule mining algorithm
Maximum likelihood reconstruction of ancestral networks by integer linear programming
Mediation analysis for survival data with high-dimensional mediators
Medical concept normalization in clinical trials with drug and disease representation learning
MetaTX: deciphering the distribution of mRNA-related features in the presence of isoform ambiguity, with applications in epitranscriptome analysis
Methylscaper: an R/Shiny app for joint visualization of DNA methylation and nucleosome occupancy in single-molecule and single-cell data
Minirmd: accurate and fast duplicate removal tool for short reads via multiple minimizers
mirTime: identifying condition-specific targets of microRNA in time-series transcript data using Gaussian process model and spherical vector clustering
mlr3proba: an R package for machine learning in survival analysis
MMAP: a cloud computing platform for mining the maximum accuracy of predicting phenotypes from genotypes
MMpred: a distance-assisted multimodal conformation sampling for de novo protein structure prediction
Modeling circRNA expression pattern with integrated sequence and epigenetic features demonstrates the potential involvement of H3K79me2 in circRNA expression
Modeling multifunctionality of genes with secondary gene co-expression networks in human brain provides novel disease insights
Model learning to identify systemic regulators of the peripheral circadian clock
MolTrans: Molecular Interaction Transformer for drug-target interaction prediction
MONACO: accurate biological network alignment through optimal neighborhood matching between focal nodes
MOSAIC: a joint modeling methodology for combined circadian and non-circadian analysis of multi-omics data
mspack: efficient lossless and lossy mass spectrometry data compression
MUFFIN: multi-scale feature fusion for drug-drug interaction prediction
MUGAN: multi-GPU accelerated AmpliconNoise server for rapid microbial diversity assessment
MultiDTI: drug-target interaction prediction based on multi-modal representation learning to bridge the gap between new chemical entities and known heterogeneous network
Multi-layered network-based pathway activity inference using directed random walks: application to predicting clinical outcomes in urologic cancer
MultiNanopolish: refined grouping method for reducing redundant calculations in Nanopolish
Nanopore base calling on the edge
Narrative scientific data visualization in an immersive environment
NetQuilt: deep multispecies network-based protein function prediction using homology-informed network similarity

« prev Page 3/5 next »