HIV-1 tropism prediction by the XGboost and HMM methods

• Published in: Scientific reports Vol. 9; no. 1; pp. 9997 - 8
• Main Authors: Chen, Xiang, Wang, Zhi-Xin, Pan, Xian-Ming
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 10.07.2019; Nature Publishing Group
• Subjects: 45; 45/23; 692/699/255/1901; 692/700/139; Area Under Curve; CCR5 protein; Computational Biology - methods; CXCR4 protein; Genotype; HIV; HIV Envelope Protein gp120 - chemistry; HIV Envelope Protein gp120 - genetics; HIV Envelope Protein gp120 - metabolism; HIV Infections - metabolism; HIV Infections - virology; HIV-1 - genetics; HIV-1 - physiology; Human immunodeficiency virus; Humanities and Social Sciences; Humans; Machine Learning; Markov Chains; multidisciplinary; Phenotype; Receptors, CXCR4 - metabolism; Receptors, CXCR5 - metabolism; Science; Science (multidisciplinary); Software; Tropism; Viral Tropism
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-019-46420-4

Human Immunodeficiency Virus 1 (HIV-1) co-receptor usage, called tropism, is associated with disease progression towards AIDS. Furthermore, the recently developed and developing drugs against co-receptors CCR5 or CXCR4 open a new thought for HIV-1 therapy. Thus, knowledge about tropism is critical for illness diagnosis and regimen prescription. To improve tropism prediction accuracy, we developed two novel methods, the extreme gradient boosting based XGBpred and the hidden Markov model based HMMpred. Both XGBpred and HMMpred achieved higher specificities (72.56% and 72.09%) than the state-of-the-art methods Geno2pheno (61.6%) and G2p_str (68.60%) in a 10-fold cross validation test at the same sensitivity of 93.73%. Moreover, XGBpred had more outstanding performances (with AUCs 0.9483, 0.9464) than HMMpred (0.8829, 0.8774) on the Hivcopred and Newdb (created in this work) datasets containing larger proportions of hard-to-predict dual tropic samples in the X4-using tropic samples. Therefore, we recommend the use of our novel method XGBpred to predict tropism. The two methods and datasets are available via http://spg.med.tsinghua.edu.cn:23334/XGBpred/. In addition, our models identified that positions 5, 11, 13, 18, 22, 24, and 25 were correlated with HIV-1 tropism.