Skip to main content

Table 7 Top five important descriptors of LC selected by four DT-based ensemble learning models

From: Comparison and improvement of the predictability and interpretability with ensemble learning models in QSPR applications

RFExtraTrees
Selected descriptorsFeature importanceSelected descriptorsFeature importance
HeavyAtomCount0.04649NumRotatableBonds0.03541
NumRotatableBonds0.04381HeavyAtomCount0.03495
wing2_HeavyAtomCount0.04329wing1_NumRotatableBonds0.02801
fr_unbrch_alkane0.03315wing2_HeavyAtomCount0.02700
wing1_NumRotatableBonds0.03218wing1_HeavyAtomCount0.02653
AdaBoostGBM
Selected descriptorsFeature importanceSelected descriptorsFeature importance
HeavyAtomCount0.08812HeavyAtomCount0.07017
NumRotatableBonds0.06759mesogen_HeavyAtomCount0.05329
wing2_HeavyAtomCount0.05722NumRotatableBonds0.04532
wing1_HeavyAtomCount0.04705mesogen_NumRotatableBonds0.02774
mesogen HeavyAtomCount0.04462wing2_HeavyAtomCount0.02718