Machine learning meets pKa

Abstract

<ns4:p>We present a small molecule pK<ns4:sub>a</ns4:sub> prediction tool entirely written in Python. It predicts the macroscopic pK<ns4:sub>a</ns4:sub> value and is trained on a literature compilation of monoprotic compounds. Different machine learning models were tested and random forest performed best given a five-fold cross-validation (mean absolute error=0.682, root mean squared error=1.032, correlation coefficient r<ns4:sup>2</ns4:sup> =0.82). We test our model on two external validation sets, where our model performs comparable to Marvin and is better than a recently published open source model. Our Python tool and all data is freely available at <ns4:ext-link xmlns:ns3="http://www.w3.org/1999/xlink" ext-link-type="uri" ns3:href="https://github.com/czodrowskilab/Machine-learning-meets-pKa">https://github.com/czodrowskilab/Machine-learning-meets-pKa</ns4:ext-link>.</ns4:p>

Topics & Concepts