Skip to main content

Table 4 3F model selection on genotype-phenotype data up to September 2006

From: Cross-validated stepwise regression for identification of novel non-nucleoside reverse transcriptase inhibitor resistance associated mutations

   3F Model generationa 3F Model selectionb
drug # 3F Models # lower SBC # lower AIC lower SBC c lower AIC d N test ase 3F model selected e
Nucleoside RT inhibitorsf AZT 300 86 0 yes no 800 0.103 296
  3TC 150 60 34 yes no 807 0.037 99
  ddI 150 20 70 no yes 807 0.049 83
  d4T 120 41 35 yes no 806 0.040 81
  ABC 200 111 53 yes no 807 0.038 95
  FTC 80 28 22 yes yes 804 0.071 76
  TDF 400 66 196 no yes 807 0.039 298
NNRTIg NVP 400 93 0 yes no 801 0.089 391
  EFV 500 101 0 yes no 807 0.246 386
  ETR 700 49 0 yes no 777 0.113 656
Protease inhibitors IDV 485 50 51 yes yes 805 0.075 482
  NFV 375 64 6 yes yes 808 0.063 375
  SQV 600 53 0 yes no 807 0.092 575
  APV 1000 0 656 no yes 808 0.060 709
  LPV 500 205 28 yes no 807 0.157 319
  ATV 1275 0 2 no yes 805 0.117 1158h
  TPV 1000 641 142 yes no 806 0.059 428
  DRV 1000 823 799 yes yes 816 0.096 707
  1. aThe number of 3F models generated was arbitrary but taken large enough such that at least one 3F model was found with a lower SBC or AIC than the reference on the genotype-phenotype data set up to July 2006.
  2. bFrom the remaining 3F models with lower SBC or AIC than the reference, the 3F model was then selected with the lowest average squared error (ase) on an unseen genotype-phenotype data set collected between July and September 2006 (test set) containing approximately 800 samples.
  3. cSBC of the selected 3F model < SBC reference on the test set (yes/no).
  4. dAIC of the selected 3F model < AIC reference on the test set (yes/no).
  5. eThe number of different random divisions used in the stepwise regression in the selected 3F model.
  6. fFor the nucleoside RT inhibitors the number of random divisions needed was less than 100, with exception of AZT and TDF.
  7. gFor the non-nucleoside RT inhibitors most random divisions were needed for ETR.
  8. hATV was the only drug for which more than 1000 different random divisions were needed.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us