Zhenglin Du

Classification of dog breeds using convolutional neural network models and support vector machine

This study improves dog breed classification accuracy using a combination of CNN features, PCA, GWO, and SVM, achieving 95.24% and 99.34% accuracy for 120 and 76 breeds respectively.

Enhancing Variant Calling in Whole Exome Sequencing (WES) Data Using Population-Matched Reference Genomes

This study evaluates the impact of population-specific reference genomes on variant calling in WES data from Chinese tumor samples, finding improved accuracy with the YAO reference.

T2T-YAO: a Telomere-to-telomere Assembled Diploid Reference Genome for Han Chinese

The paper presents T2T-YAO, a telomere-to-telomere diploid reference genome for a Han Chinese male, offering improved haplotype resolution and genetic diversity compared to T2T-CHM13.

Pan-genome and Haplotype Map of Cultivars and Their Wild Ancestors Provides Insights into Adaptive Evolution of Cassava (Manihot esculenta Crantz)

The paper constructs nearly T2T genomes and a pan-genome of cassava cultivars and wild ancestors, revealing domestication genes and evolutionary insights.

The global landscape of SARS-CoV-2 genomes, variants, and haplotypes in 2019nCoVR

The paper describes the 2019nCoVR resource, which curates and analyzes SARS-CoV-2 genomes, variants, and haplotypes globally, providing daily updates and integration with literature and databases.