Skip to main content

Table 6 Performance of composition-based programs

From: A comparative evaluation of sequence classification programs

Program PhyloPythia 961 bp PhymmBL 243 bp RAIphy 238 bp Mean Training
Percentage of sequence classified
NBC 100 100 100 100  
PhyloPythiaS 3.5 3.1 3.3 3.3  
PhymmBL 100 99.7 100 99.9  
RAIphy 100 100 100 100  
Sensitivity (percentage)
NBC 95.4 97.5 99.4 97.4  
PhyloPythiaS 3.1 1.8 2.2 2.4  
PhymmBL 48.4 96.8 81.9 75.7  
RAIphy 54.8 31.8 48.0 44.9  
Precision (percentage)
NBC 95.4 97.5 99.4 97.4  
PhyloPythiaS 88.1 58.5 66.1 70.9  
PhymmBL 48.4 97.0 81.9 75.8  
RAIphy 54.8 31.8 48.0 44.9  
CPU Runtime (minutes)
NBC1 13496 3595 17573 11555 1217
PhyloPythiaS2 297 180 506 328 4320
PhymmBL1 15600 1035 23508 13381 2880
RAIphy3 105 25 122 84 30
Memory Usage (Megabytes of RAM)
NBC 200 200 200 200  
PhyloPythiaS4 100 100 100   100
PhymmBL4 100 100 100 100  
RAIphy 500 335 400 412  
  1. Measurements of sensitivity, precision, and resource consumption on three simulated data sets.
  2. 1analysis performed on an AMD Opteron 250 (2.4 GHz) Sun Fire V40z with 32 GB RAM.
  3. 2analysis perfomed on an AMD Opteron 248 (2.2 GHz) workstation with 8 GB RAM.
  4. 3analysis performed on a 2.66 GHz Intel Core i7 MacBook Pro running Mac OS X 10.7.1 with 8 GB 1067 MHz DDR3 RAM.
  5. 4input sequences were broken up into smaller files.