Computational Biology and Applied Algorithmics, Max Planck Institute for Informatics, Saarbrücken, Germany.
PLoS One. 2010 Feb 3;5(2):e9044. doi: 10.1371/journal.pone.0009044.
Replication capacity (RC) of specific HIV isolates is occasionally blamed for unexpected treatment responses. However, the role of viral RC in response to antiretroviral therapy is not yet fully understood.
We developed a method for predicting RC from genotype using support vector machines (SVMs) trained on about 300 genotype-RC pairs. Next, we studied the impact of predicted viral RC (pRC) on the change of viral load (VL) and CD4(+) T-cell count (CD4) during the course of therapy on about 3,000 treatment change episodes (TCEs) extracted from the EuResist integrated database. Specifically, linear regression models using either treatment activity scores (TAS), the drug combination, or pRC or any combination of these covariates were trained to predict change in VL and CD4, respectively.
The SVM models achieved a Spearman correlation (rho) of 0.54 between measured RC and pRC. The prediction of change in VL (CD4) was best at 180 (360) days, reaching a correlation of rho = 0.45 (rho = 0.27). In general, pRC was inversely correlated to drug resistance at treatment start (on average rho = -0.38). Inclusion of pRC in the linear regression models significantly improved prediction of virological response to treatment based either on the drug combination or on the TAS (t-test; p-values range from 0.0247 to 4 10(-6)) but not for the model using both TAS and drug combination. For predicting the change in CD4 the improvement derived from inclusion of pRC was not significant.
Viral RC could be predicted from genotype with moderate accuracy and could slightly improve prediction of virological treatment response. However, the observed improvement could simply be a consequence of the significant correlation between pRC and drug resistance.
特定 HIV 分离物的复制能力（RC）偶尔会导致治疗反应出乎意料。然而，病毒 RC 在抗逆转录病毒治疗中的作用尚未完全了解。
我们开发了一种使用支持向量机（SVM）从基因型预测 RC 的方法，该方法是基于大约 300 对基因型-RC 对进行训练的。接下来，我们研究了预测病毒 RC（pRC）对治疗过程中大约 3000 个治疗变化事件（TCE）中病毒载量（VL）和 CD4（+）T 细胞计数（CD4）变化的影响，这些 TCE 是从 EuResist 综合数据库中提取的。具体来说，使用治疗活性评分（TAS）、药物组合或 pRC 或这些协变量的任何组合的线性回归模型来分别训练预测 VL 和 CD4 的变化。
SVM 模型在测量的 RC 和 pRC 之间达到了 0.54 的 Spearman 相关系数（rho）。在 180（360）天时，VL（CD4）的预测效果最佳，达到了 rho=0.45（rho=0.27）的相关性。一般来说，pRC 与治疗开始时的耐药性呈负相关（平均 rho=-0.38）。在基于药物组合或 TAS 的线性回归模型中包含 pRC，显著提高了对病毒学治疗反应的预测（t 检验；p 值范围从 0.0247 到 4 10（-6）），但基于 TAS 和药物组合的模型则不然。对于预测 CD4 的变化，包含 pRC 并没有显著改善。
病毒 RC 可以从基因型中以中等准确度预测，并且可以略微提高对病毒学治疗反应的预测。然而，观察到的改善可能仅仅是由于 pRC 与耐药性之间的显著相关性所致。
