Human immunodeficiency virus (HIV) causes acquired immunodeficiency syndrome (AIDS) and leads to over one million of deaths annually. Highly active antiretroviral treatment (HAART) is a gold standard in the HIV/AIDS therapy. Nucleoside and non-nucleoside inhibitors of HIV reverse transcriptase (RT) are important component of HAART, but their effect depends on the HIV susceptibility/resistance. HIV resistance mainly occurs due to mutations leading to conformational changes in the three-dimensional structure of HIV RT. The aim of our work was to develop and test a computational method for prediction of HIV resistance associated with the mutations in HIV RT. Earlier we have developed a method for prediction of HIV type 1 (HIV-1) resistance; it is based on the usage of position-specific descriptors. These descriptors are generated using the particular amino acid residue and its position; the position of certain residue is determined in a multiple alignment. The training set consisted of more than 1900 sequences of HIV RT from the Stanford HIV Drug Resistance database; for these HIV RT variants experimental data on their resistance to ten inhibitors are presented. Balanced accuracy of prediction varies from 80% to 99% depending on the method of classification (support vector machine, Naive Bayes, random forest, convolutional neural networks) and the drug, resistance to which is obtained. Maximal balanced accuracy was obtained for prediction of resistance to zidovudine, stavudine, didanosine and efavirenz by the random forest classifier. Average accuracy of prediction is 89%.
VICh, iavliaiushchiĭsia prichinoĭ cindroma priobretennogo immunodefitsita cheloveka (SPID), privodit k smerti bolee milliona chelovek ezhegodno. Vysokoaktivnaia antiretrovirusnaia terapiia (VAART) iavliaetsia zolotym standartom terapii protiv VICh. Nukleozidnye (NIOT) i nenukleozidnye (NNIOT) ingibitory obratnoĭ transkriptazy (OT) VICh iavliaiutsia odnim iz osnovnykh komponentov VAART. Éffektivnost' terapii vo mnogom opredeliaetsia ustoĭchivost'iu shtammov virusa, voznikaiushcheĭ v rezul'tate tochechnykh mutatsiĭ, kotorye privodiat k izmeneniiam v prostranstvennoĭ strukture belkov VICh. Tsel'iu dannoĭ raboty iavlialas' razrabotka komp'iuternogo podkhoda k prognozirovaniiu ustoĭchivosti varianta VICh s izvestnoĭ posledovatel'nost'iu aminokislot k konkretnomu antiretrovirusnomu preparatu iz gruppy ingibitorov OT VICh. Ranee nami byl razrabotan metod komp'iuternogo prognoza ustoĭchivosti variantov VICh k preparatu na osnove pozitsionno-spetsifichnykh deskriptorov, v kotorykh uchityvalsia odnobukvennyĭ kod aminokisloty i pozitsiia, opredeliaemaia v rezul'tate mnozhestvennogo vyravnivaniia razlichnykh variantov VICh. V dannoĭ rabote predlagaetsia ispol'zovat' v kachestve deskriptorov aminokislotnoĭ posledovatel'nosti pentapeptidnye fragmenty, chto pozvoliaet ne provodit' predvaritel'no vyravnivanie posledovatel'nosteĭ dlia polucheniia otsenki rezistentnosti mutantnogo shtamma. V kachestve obuchaiushcheĭ vyborki ispol'zovali posledovatel'nosti aminokislot bolee 1900 variantov OT VICh iz bazy dannykh HIV Drug Resistance Database, dlia kotorykh izvestny rezul'taty testov na ustoĭchivost' v otnoshenii 10 preparatov. Primenenie metodov mashinnogo obucheniia (metod opornykh vektorov, Baĭesovskiĭ podkhod, “sluchaĭnyĭ les”, iskusstvennye neĭronnye seti) pozvolilo dostich' maksimal'noĭ tochnosti prognoza 99%, pri sredneĭ tochnosti prognoza 89%.
Keywords: HIV/AIDS; inhibitors; resistance; reverse transcriptase.