Skip to main content
Figure 7 | BMC Bioinformatics

Figure 7

From: Application of nonnegative matrix factorization to improve profile-profile alignment features for fold recognition and remote homolog detection

Figure 7

Mean ROC scores with various number of basis vectors. The performance of fold recognition depends on the number of NMF basis vectors. On average, the value of 70 is optimal. The mean ROC score of each case is 0.82, 0.85, 0.86, 0.83, 0.69, and 0.60 for 50, 65, 70, 75, 85, and 100 basis vectors, respectively. The optimized number of NMF basis vectors differs in each fold.

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us