Skip to main content

Table 2 The performance of SVM with exclusion of certain amino acids. The SVM models were trained using codon composition, codon bias and amino acid composition as sequence attributes respectively, excluding His, Arg, Asn and Ser from the training datasets.

From: Support vector machine for classification of meiotic recombination hotspots and coldspots in Saccharomyces cerevisiae based on codon composition

Attributes Sensitivity (%) Specificity (%) OP (%) Accuracy (%)
FCU 86.1 68.8 77.5 83.8
RSCU 84.2 65.6 74.9 81.6
FAAU 61.4 50.0 55.7 59.8