Bioinformatics 2022

217 papers
Bioinformatics in 2022 featured research focused on multi-view data integration, RNA structural analysis, and the application of natural language processing to biomedical data. A significant portion of the work addressed the challenges of single-cell sequencing, including the integrative analysis of parallel scRNA-seq and scATAC-seq data through weighted multi-view learning frameworks and methods for batch-effect removal in large-scale gene-expression datasets. Computational efficiency was a recurring theme, evidenced by the development of GPU-accelerated pipelines for methylation calling and beam search methods for fast RNA consensus secondary structure prediction. Other research directions included the use of nucleotide language models to predict RNA–protein interactions and the development of NLP-enabled text-mining systems for extracting biomedical entity relations. Prolific authors such as Michiaki Hamada, Kun Han, and Minhao Yang contributed to these developments, which also spanned mass spectrometry data storage and network-based analysis of cancer heterogeneity. These contributions reflect a trend toward integrating diverse data types and leveraging machine learning techniques to improve the speed and accuracy of biological data processing.

Top Research Directions

Research directions most represented by Bioinformatics 2022 papers.

Overcoming Data Sparsity in Single Cell Sequencing 5
Graph Neural Networks for Molecular and Materials Representation 4
Contextual Embeddings from Protein Language Models 3
Structural Interpretability in Molecular Deep Learning 3
Learning Molecular Properties from Sparse Experimental Data 3
Graph Attention Mechanisms for Adaptive Feature Aggregation 3
Heterogeneous Network Fusion for Biomedical Discovery 3
Biologically Constrained Latent Representations 2
Integrating Biological Prior Knowledge into Genomic Machine Learning 2
Data Parallel Gibbs Sampling for Scalable Bayesian Inference 2
Data Quality Dependency in Predictive Modeling 2
Self-Supervised Molecular Pretraining 2
Fusing Graphs and Sequences for Molecular Representation 2
Correcting Technical Batch Effects for Cross-Study Biological Integration 2
Scaling Spatial and Single-Cell Omics to Millions of Cells 2

Top Authors

AuthorPapers
Charlotte Deane4
Jianxin Wang3
Ka-Chun Wong3
Pietro Lio3
Surag Nair3
Xiangtao Li3
Chengkun Wu2
Guoxian Yu2
Ilan Shomorony2
Jaewoo Kang2
Jinhua Zhu2
Junzhou Huang2
Karsten Borgwardt2
Lijun Wu2
Min Wu2
Nigel Collier2
Niko Beerenwinkel2
Renmin Han2
Wancen Mu2
Wen Zhang2

Impactful Papers

Papers from Bioinformatics 2022 that shaped research clusters.

Foundational

Influential

Papers

Title
pcnaDeep: a fast and robust single-cell tracking method using deep-learning mediated cell cycle profiling
PDMDA: predicting deep-level miRNA-disease associations with graph neural networks and sequence features
PheneBank: a literature-based database of phenotypes
PhyloCSF++: a fast and user-friendly implementation of PhyloCSF with annotation tools
PhyloPGM: boosting regulatory function prediction accuracy using evolutionary information
PiLSL: pairwise interaction learning-based graph neural network for synthetic lethality prediction in human cancers
PltDB: a blood platelets-based gene expression database for disease investigation
Powerful and interpretable control of false discoveries in two-group differential expression studies
Predicting cancer drug response using parallel heterogeneous graph convolutional networks with neighborhood interactions
Prediction of recovery from multiple organ dysfunction syndrome in pediatric sepsis patients
Prediction of RNA–protein interactions using a nucleotide language model
Pre-training graph neural networks for link prediction in biomedical networks
PrioriTree: a utility for improving phylodynamic analyses in BEAST
Prior knowledge facilitates low homologous protein secondary structure prediction with DSM distillation
ProteinBERT: a universal deep-learning model of protein sequence and function
P-smoother: efficient PBWT smoothing of large haplotype panels
ptairMS: real-time processing and analysis of PTR-TOF-MS data for biomarker discovery in exhaled breath
reComBat: batch-effect removal in large-scale multi-source gene-expression data integration
Relational graph convolutional networks for predicting blood-brain barrier penetration of drug molecules
ResPAN: a powerful batch correction model for scRNA-seq data through residual adversarial networks
Robust identification of temporal biomarkers in longitudinal omics studies
RoDiCE: robust differential protein co-expression analysis for cancer complexome
SALAI-Net: species-agnostic local ancestry inference network
SCANCell reveals diverse inter-cluster interaction patterns in systemic lupus erythematosus across the disease spectrum
scAWMV: an adaptively weighted multi-view learning framework for the integrative analysis of parallel scRNA-seq and scATAC-seq data
scPreGAN, a deep generative model for predicting the response of single-cell expression to perturbation
scPretrain: multi-task self-supervised learning for cell-type classification
scWMC: weighted matrix completion-based imputation of scRNA-seq data via prior subspace information
SD2: spatially resolved transcriptomics deconvolution through integration of dropout and spatial information
SECEDO: SNV-based subclone detection using ultra-low coverage single-cell DNA sequencing
Self-supervised learning of cell type specificity from immunohistochemical images
SEPA: signaling entropy-based algorithm to evaluate personalized pathway activation for survival analysis on pan-cancer data
Seq-SetNet: directly exploiting multiple sequence alignment for protein secondary structure prediction
Sequence tagging for biomedical extractive question answering
SeqWho: reliable, rapid determination of sequence file identity using k-mer frequencies in Random Forest classifiers
Simulation and annotation of global acronyms
Single-cell mutation calling and phylogenetic tree reconstruction with loss and recurrence
Small molecule generation via disentangled representation learning
springD2A: capturing uncertainty in disease-drug association prediction with model integration
SSpro/ACCpro 6: almost perfect prediction of protein secondary structure and relative solvent accessibility using profiles, deep learning and structural similarity
Steer'n'Detect: fast 2D template detection with accurate orientation estimation
STracking: a free and open-source Python library for particle tracking and analysis
Structure-aware Protein Self-supervised Learning
Supervised capacity preserving mapping: a clustering guided visualization method for scRNA-seq data
Supervised graph co-contrastive learning for drug-target interaction prediction
Synthetic-to-real: instance segmentation of clinical cluster cells with unlabeled synthetic training
Systematic comparison of ranking aggregation methods for gene lists in experimental results
TargetNet: functional microRNA target prediction with deep neural networks
Telogator: a method for reporting chromosome-specific telomere lengths from long reads
TGSA: protein-protein association-based twin graph neural networks for drug response prediction with similarity augmentation

« prev Page 4/5 next »