Significantly Improved HIV Inhibitor Efficacy Prediction Employing Proteochemometric Models Generated From Antivirogram Data

Infection with HIV cannot currently be cured; however it can be controlled by combination treatment with multiple anti-retroviral drugs. Given different viral genotypes for virtually each individual patient, the question now arises which drug combination to use to achieve effective treatment. With the availability of viral genotypic data and clinical phenotypic data, it has become possible to create computational models able to predict an optimal treatment regimen for an individual patient. Current models are based only on sequence data derived from viral genotyping; chemical similarity of drugs is not considered. To explore the added value of chemical similarity inclusion we applied proteochemometric models, combining chemical and protein target properties in a single bioactivity model. Our dataset was a large scale clinical database of genotypic and phenotypic information (in total ca. 300,000 drug-mutant bioactivity data points, 4 (NNRTI), 8 (NRTI) or 9 (PI) drugs, and 10,700 (NNRTI) 10,500 (NRTI) or 27,000 (PI) mutants). Our models achieved a prediction error below 0.5 Log Fold Change. Moreover, when directly compared with previously published sequence data, derived models PCM performed better in resistance classification and prediction of Log Fold Change (0.76 log units versus 0.91). Furthermore, we were able to successfully confirm both known and identify previously unpublished, resistance-conferring mutations of HIV Reverse Transcriptase (e.g. K102Y, T216M) and HIV Protease (e.g. Q18N, N88G) from our dataset. Finally, we applied our models prospectively to the public HIV resistance database from Stanford University obtaining a correct resistance prediction rate of 84% on the full set (compared to 80% in previous work on a high quality subset). We conclude that proteochemometric models are able to accurately predict the phenotypic resistance based on genotypic data even for novel mutants and mixtures. Furthermore, we add an applicability domain to the prediction, informing the user about the reliability of predictions. Author Summary: Infection with the human immunodeficiency virus (HIV) currently cannot be cured. It can however be contained through treatment with a combination of several anti-viral drugs. Yet, during treatment resistance can occur which leads to drugs becoming ineffective. Through a combination of drugs, this resistance can be deferred indefinitely. The optimal combination of drugs depends on the specific strain of HIV with which the patient is infected. Previously, methods have been developed that predict a personalized treatment regimen based on the genetic sequence (genotype) of the virus via the use of computer modeling, corner stone of the methods is drug affinity prediction. Here we have applied proteochemometric modeling which takes this genetic information into account, but also includes chemical description of the drugs that are now clinically available. We show that this combined technique performs better than models that only include genetic information. Our approach leads to personalized treatment predictions with a higher reliability compared to the current state of the art. In addition, we include a reliability measure which allows each prediction to be assessed for reliability. Finally we describe mutations of the HIV genome that were not previously described in literature and lead to resistance to treatment.