Fig. 4From: Semi-supervised learning for somatic variant calling and peptide identification in personalized cancer immunotherapyExpected TP count at different multiplexing rates for SNVQ, Strelka, 2CP, and PLATO run using AutoML, spies-based classification threshold selection, and 50% bootstrap support. The dots represent TP counts from the actual AccessArray resequencing experiment reported in Table 1. P1–P4 denote the sequencing datasets generated for four different ovarian cancer patientsBack to article page