Chien‐Yu Chen

CyriPanel improves CYP2D6 genotyping accuracy using assay-matched diploid references and structural inference, achieving higher concordance than Aldy 4 in benchmark tests.

Graph-KIR estimates KIR gene copy numbers and calls 7-digit alleles from WGS data with high accuracy, outperforming existing tools.

The paper identifies 335 novel T cell receptor alleles in 47 pangenome reference individuals using the gAIRR Suite, significantly expanding the IMGT database.

gAIRR-wgs accurately calls T cell receptor alleles from whole genome sequencing data, identifying novel alleles and population-specific diversity patterns.

TypeAssembly annotates complex genes in haplotype assemblies by estimating copy numbers and typing alleles, successfully applied to 41 genes, 17 KIR genes, and 15 pharmacogenes across 466 assemblies.

The paper evaluates somatic mutation detection methods across different sequencing and analysis pipelines to identify false negatives in drug-resistant mutations.

This paper introduces a deep learning model using multiple instance learning to predict gene mutations from whole slide images of AML without manual annotations, achieving high AUC scores for NPM1 and FLT3-ITD mutations.

This paper evaluates the concordance of variant annotations from three tools on ClinVar variants, highlighting inconsistencies in pathogenicity interpretation.

The paper develops a tool to analyze KIR gene diversity using pangenome assemblies and identifies novel alleles and structural variants in human genomes.

ChromBERT identifies chromatin state motifs using a BERT-based model pre-trained on human chromatin data, revealing biologically relevant patterns across multiple tasks.

This study evaluates how well protein structure prediction tools detect structural changes caused by pathogenic nonsynonymous single nucleotide variants.

This paper compares ancestry-specific and multi-ancestry polygenic risk scores for LDL prediction in East Asian populations using UK Biobank and Taiwan Biobank data, finding that multi-ancestry models are more generalizable.

PGSbuilder provides a web platform for GWAS and PRS analysis, enabling medical professionals to assess genetic risk using variant annotations and multiple PRS methods.

This study reanalyzes 1,496 Taiwanese whole genome sequences to identify novel variants and clinically relevant genetic markers with potential medical implications.

This paper introduces MHCfovea, a deep learning framework that connects HLA alleles with binding motifs, revealing critical polymorphic residues for antigen discovery and vaccine design.

ezGeno automates deep neural network design for genomic data analysis, outperforming existing tools in efficiency and accuracy for tasks like TF binding prediction and enhancer activity prediction.

The paper introduces gAIRR Suite, a toolset for profiling germline adaptive immune receptor repertoire, achieving high accuracy in allele calling and discovering novel alleles across multiple datasets.

This study develops a deep learning model to predict enhancer activity in new cell types by integrating DNase data across multiple cell types.

GenEpi detects gene-based epistasis using machine learning, outperforming existing methods on simulated data and identifying disease-related variants in Alzheimer's disease.

This study evaluates how de novo transcriptome assembly quality affects RNA-Seq quantification accuracy and introduces a tool to assess quantification results.

variant2literature searches biomedical literature for genetic variants by processing images and normalizing variant formats to improve recall.

SeqsLab annotates and interprets genetic variants from large personal genome cohorts using Spark for scalability and integrates with public databases for variant analysis.

This study uses comparative and population genomics to analyze Phellinus noxius, revealing its genetic diversity, mating system, and evolutionary patterns.

The paper uses a network-based approach to analyze eQTLs across 13 tissues, identifying cis- and trans-eQTLs and linking SNPs to biological processes and disease associations.