Fig. 5
From: iMOKA: k-mer based software to analyze large collections of sequencing data
iMOKA identifies DE genes and transcripts between chemorefractory and chemosensitive DLBCL patients. a The features output by all benchmarked approaches are evaluated for their capacity to classify response to chemotherapy. RF’s oob scores are plotted as a function of the number of the best features output by each approach. iMOKA reach the highest score thanks to the five k-mers with 100% of individual accuracy. b iMOKA GUI screenshot showing the detail of the splicing site of the gene ZBTB17, where the isoform NM_001242884 is detected as an event of interest by iMOKA, present in the RefSeq but not in GENCODE. c Five k-mers able to separate the responsive patients from the chemorefractory ones. k-mer normalized counts and the respective gene counts available in Fig. S6