Motif-Based Text Mining of Microbial Metagenome Redundancy Profiling Data for Disease Classification

Figure 4

Heat map of -mer counting profiles of original pneumonia data for 3-class problem (a), data after treating by PMF for 3-class problem, (b) and data after treating by PMF for 2-class problem (c). Rows are retained motifs and columns are disease classes. From left to right are 30 normal, 32 CAP, and 71 HAP samples for 3-class problem and 30 normal 103 pneumonia samples for 2-class problem.

(a)

(b)

(c)