a machine learning approach for identifying amino acid signatures in the hiv env gene predictive of dementia机器学习方法对于识别氨基酸签名的艾滋病毒env基因预测痴呆.pdfVIP

A Machine Learning Approach for Identifying Amino Acid Signatures in the HIV Env Gene Predictive of Dementia 1 1,2 Alexander G. Holman , Dana Gabuzda * 1 Department of Cancer Immunology and AIDS, Dana-Farber Cancer Institute, Boston, Massachusetts, United States of America, 2 Department of Neurology (Microbiology, and Immunobiology), Harvard Medical School, Boston, Massachusetts, United States of America Abstract The identification of nucleotide sequence variations in viral pathogens linked to disease and clinical outcomes is important for developing vaccines and therapies. However, identifying these genetic variations in rapidly evolving pathogens adapting to selection pressures unique to each host presents several challenges. Machine learning tools provide new opportunities to address these challenges. In HIV infection, virus replicating within the brain causes HIV-associated dementia (HAD) and milder forms of neurocognitive impairment in 20–30% of patients with unsuppressed viremia. HIV neurotropism is primarily determined by the viral envelope (env) gene. To identify amino acid signatures in the HIV env gene predictive of HAD, we developed a machine learning pipeline using the PART rule-learning algorithm and C4.5 decision tree inducer to train a classifier on a meta-dataset (n = 860 env sequences from 78 patients: 40 HAD, 38 non-HAD). To increase the flexibility and biological relevance of our analysis, we included 4 numeric factors describing amino acid hydrophobicity, polarity, bulkiness, and charge, in addition to amino acid identities. The classifier had 75% predictive accuracy in leave-one-out cross-validation, and identified 5 signatures associated with HAD diagnosis (p,0.05, Fisher’s exact test). These HAD signatures were found in the majority of brain seq