MASSA Algorithm: automated rational sampling of training and test subsets for QSAR modelling

Abstract

QSAR models capable of predicting biological, toxicity, and pharmacokinetic properties were widely used to search lead bioactive molecules in chemical databases. The dataset’s preparation to build these models has a strong influence on the quality of the generated models, and sampling requires that the original dataset be divided into training (for model training) and test (for statistical evaluation) sets. This sampling can be done randomly or rationally, but the rational division is superior. In this paper, we present MASSA, a Python tool that can be used to automatically sample datasets by exploring the biological, physicochemical, and structural spaces of molecules using PCA, HCA, and K-modes. The proposed algorithm is very useful when the variables used for QSAR are not available or to construct multiple QSAR models with the same training and test sets, producing models with lower variability and better values for validation metrics. These results were obtained even when the descriptors used in the QSAR/QSPR were different from those used in the separation of training and test sets, indicating that this tool can be used to build models for more than one QSAR/QSPR technique. Finally, this tool also generates useful graphical representations that can provide insights into the data.

Aminopyrimidine Derivatives as Multiflavivirus Antiviral Compounds Identified from a Consensus Virtual Screening Approach

“…The lowest energy conformer for each compound was generated using an OMEGA 3.1.1.2 (OpenEye Scientific Software, USA, 2019) followed by ionization state adjustment at pH 7.4 with FixpKa (QUACPAC 2.0.1.2, OpenEye Scientific Software, USA, 2019), selecting a single favorable ionization state. Finally, the remaining compounds ( n = 97) were split into training and test sets (80% and 20%, respectively) using a preliminary version of the MASSA algorithm implemented on the KNIME platform . The most active (lowest half-maximum inhibitory concentration; IC 50 ) compound of each study, herein referred to as 62 (IC 50 of 18 nM) and 106 (IC 50 of 21 nM), was removed from the test set.…”

Understanding the Enzyme (S)-Norcoclaurine Synthase Promiscuity to Aldehydes and Ketones

“…54 The minimum energy conformer of each compound was identified by conformational analysis in the software OMEGA 55 using the MMFF94 force field. The data set was divided into training and test sets with 80 and 20%, respectively, using a preliminary version of the MASSA algorithm 56 implemented in the KNIME Analytics Platform 57 and its RDKit nodes 58 according to previous works following the protocol described in. 59−61 The experimental enzymatic reactivity was codified as 0 (unreactive) and 1 (reactive).…”