Ramin Shirali Hossein Zade

This study evaluates the impact of removing repeat-induced overlaps on de novo genome assembly performance using simulated datasets.

The paper benchmarks long-read de novo assemblers for eukaryotic genomes, finding that Flye performs best overall, and longer reads can improve assembly quality depending on genome complexity.

HAT reconstructs haplotypes using short and long reads with a reference genome, outperforming existing tools on yeast and simulated polyploid data.

AntAngioCOOL is an R package that predicts anti-angiogenic peptides using machine learning, achieving 88% sensitivity and 77% specificity on an independent test set.

This paper introduces afpCOOL, a tool for detecting antifreeze proteins using SVM with 4 features, outperforming BLAST and showing the importance of evolutionary features and amino acid composition.