Support Vector Machines‐Based Quantitative Structure—Property Relationship for the Prediction of Heat Capacity.

Abstract

The support vector machine (SVM), as a novel type of learning machine, for the first time, was used to develop a Quantitative Structure-Property Relationship (QSPR) model of the heat capacity of a diverse set of 182 compounds based on the molecular descriptors calculated from the structure alone. Multiple linear regression (MLR) and radial basis function networks (RBFNNs) were also utilized to construct quantitative linear and nonlinear models to compare with the results obtained by SVM. The root-mean-square (rms) errors in heat capacity predictions for the whole data set given by MLR, RBFNNs, and SVM were 4.648, 4.337, and 2.931 heat capacity units, respectively. The prediction results are in good agreement with the experimental value of heat capacity; also, the results reveal the superiority of the SVM over MLR and RBFNNs models.

Viscosity of ionic liquids: Database, observation, and quantitative structure‐property relationship analysis

“…D 1 , Randic index (order 2), which has the most important effect on the viscosity, is defined as $ R(\Gamma ) = \sum\nolimits_{v_i \sim v_j } {{1 \over {\sqrt {\delta _i \delta _j } }}} $ , where δ i denotes the degree of the vertex v i 85. The descriptor encodes the size, shape, and degree of branching in the cations and also relates to the dispersion interaction among ions 8687 and this descriptor indicates the effect of hydrogen‐bonding ability of cation on the viscosity 88…”

QSAR Models for the Prediction of Binding Affinities to Human Serum Albumin Using the Heuristic Method and a Support Vector Machine

“…Due to its remarkable generalization performance, the SVM has attracted attention and gained extensive application, such as pattern recognition problems, 16,17 drug design, 18 QSAR, 19 and quantitativestructure-propertyrelationship(QSPR)analysis. [20][21][22][23] In the present work, the CODESSA program was used for the calculation of the descriptors and for the statistical analysis to obtain the multiparameter QSAR equations describing the binding affinities of drugs. The heuristic method (HM) in the CODESSA program and the SVM were utilized to establish a quantitative linear and nonlinear relationship between the binding affinity and the molecular structure, respectively.…”

Machine learning approaches for predicting compounds that interact with therapeutic and ADMET related proteins

“…Apart from predicting whether or not a compound is an inhibitor or agonist or substrate of a protein, ML methods can also be used for predicting the activity level by incorporation of regression‐based algorithms 17, 109, 110. Table 3 summarizes the performance of several regression methods for predicting inhibitors, agonists, and substrates of proteins of pharmaceutical relevance.…”