Prediction of HIV-1 sensitivity to broadly neutralizing antibodies shows a trend towards resistance over time

Treatment with broadly neutralizing antibodies (bNAbs) has proven effective against HIV-1 infections in humanized mice, non-human primates, and humans. Due to the high mutation rate of HIV-1, resistance testing of the patient’s viral strains to the bNAbs is still inevitable. So far, bNAb resistance can only be tested in expensive and time-consuming neutralization experiments. Here, we introduce well-performing computational models that predict the neutralization response of HIV-1 to bNAbs given only the envelope sequence of the virus. Using non-linear support vector machines based on a string kernel, the models learnt even the important binding sites of bNAbs with more complex epitopes, i.e., the CD4 binding site targeting bNAbs, proving thereby the biological relevance of the models. To increase the interpretability of the models, we additionally provide a new kind of motif logo for each query sequence, visualizing those residues of the test sequence that influenced the prediction outcome the most. Moreover, we predicted the neutralization sensitivity of around 34,000 HIV-1 samples from different time points to a broad range of bNAbs, enabling the first analysis of HIV resistance to bNAbs on a global scale. The analysis showed for many of the bNAbs a trend towards antibody resistance over time, which had previously only been discovered for a small non-representative subset of the global HIV-1 population.Author summary: Several sequence-based approaches exist to predict the epitope of broadly neutralizing antibodies (bNAbs) against HIV based on the correlation between variation in the viral sequence and neutralization response to the antibody. Though the potential epitope sites can be used to predict the neutralization response, the methods are not optimized for the task, using additional structural information, additional preselection steps to identify the epitope sites, and assuming independence and/or only linear relationship between the potential sites and the neutralization response. To model also the neutralization response to bNAbs with more complex binding sites, including for example several non-consecutive residues or accompanying conformational changes, we used non-linear, multivariate machine learning techniques. Though we used only the viral sequence information, the models learnt the corresponding binding sites of the bNAbs. In general only few residues were learnt to be responsible for a change in neutralization response, which can additionally reduce the sequencing cost for application in clinical routine. We propose our tailored models to aid the patient selection process for current clinical trials for bNAb immunotherapy, but also as a basis to predict the best combinations of bNAbs, which will be required for routine clinical practice in the future.