Automated prediction of HIV drug resistance from genotype data

• Published in: BMC bioinformatics Vol. 17 Suppl 8; no. Suppl 8; p. 278
• Main Authors: Shen, ChenHsiang, Yu, Xiaxia, Harrison, Robert W, Weber, Irene T
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 31.08.2016; BioMed Central
• Subjects: Algorithms; Anti-HIV Agents - pharmacology; Automation; Computational Biology - methods; Databases, Genetic; Drug resistance; Drug Resistance, Viral - drug effects; Drug Resistance, Viral - genetics; Drug therapy; Genetic aspects; Genotype; HIV infection; HIV Infections - drug therapy; HIV Protease - genetics; HIV Protease Inhibitors - pharmacology; HIV Reverse Transcriptase - antagonists & inhibitors; HIV Reverse Transcriptase - chemistry; HIV-1 - drug effects; HIV-1 - genetics; Humans; Machine learning; Reverse Transcriptase Inhibitors - pharmacology; Risk factors; United States; Automation; Supervised machine learning; HIV/AIDS drugs; Drug resistance prediction; Encoding structure and sequence
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-016-1114-6

HIV/AIDS is a serious threat to public health. The emergence of drug resistance mutations diminishes the effectiveness of drug therapy for HIV/AIDS. Developing a computational prediction of drug resistance phenotype will enable efficient and timely selection of the best treatment regimens. A unified encoding of protein sequence and structure was used as the feature vector for predicting phenotypic resistance from genotype data. Two machine learning algorithms, Random Forest and K-nearest neighbor, were used. The prediction accuracies were examined by five-fold cross-validation on the genotype-phenotype datasets. A supervised machine learning approach for automatic prediction of drug resistance was developed to handle genotype-phenotype datasets of HIV protease (PR) and reverse transcriptase (RT). It predicts the drug resistance phenotype and its relative severity from a query sequence. The accuracy of the classification was higher than 0.973 for eight PR inhibitors and 0.986 for ten RT inhibitors, respectively. The overall cross-validated regression R(2)-values for the severity of drug resistance were 0.772-0.953 for 8 PR inhibitors and 0.773-0.995 for 10 RT inhibitors. Machine learning using a unified encoding of sequence and protein structure as a feature vector provides an accurate prediction of drug resistance from genotype data. A practical webserver for clinicians has been implemented.