Chemical Graph Theory for Property Modeling in QSAR and QSPR—Charming QSAR & QSPR

Abstract

Quantitative structure-activity relationship (QSAR) and Quantitative structure-property relationship (QSPR) are mathematical models for the prediction of the chemical, physical or biological properties of chemical compounds. Usually, they are based on structural (grounded on fragment contribution) or calculated (centered on QSAR three-dimensional (QSAR-3D) or chemical descriptors) parameters. Hereby, we describe a Graph Theory approach for generating and mining molecular fragments to be used in QSAR or QSPR modeling based exclusively on fragment contributions. Merging of Molecular Graph Theory, Simplified Molecular Input Line Entry Specification (SMILES) notation, and the connection table data allows a precise way to differentiate and count the molecular fragments. Machine learning strategies generated models with outstanding root mean square error (RMSE) and R2 values. We also present the software Charming QSAR & QSPR, written in Python, for the property prediction of chemical compounds while using this approach.

Fragment‐based drug discovery—the importance of high‐quality molecule libraries

“…An interesting approach for quantitative structure–activity or structure–property relation modelling (QSAR/QSPR) utilising chemical graph theory combined with SMILES notation was recently reported [ 48 ]. In this method, a graph (a set of nodes, representing atoms, and edges representing bonds) is built using the connectivity information of an input molecule and molecular fragments are obtained from the possible subgraphs.…”

“…All unique fragments obtained in a data set of structures can be collated, and counts of each fragment in individual molecules can then be used as descriptors in QSAR/QSPR models. Interestingly, fragments associated with activity in trained models could be retrieved [ 48 ] suggesting this could also be used as another plausible approach to fragment selection, though we are unaware of an example of this use in library construction. The Reymond group also previously reported the ‘chemical universe’ database GDB‐17, comprising enumeration of all chemical graphs consisting of C, N, O, S and halogens up to 17 heavy atoms [ 49 ].…”

Connecting SiO4 in Silicate and Silicate Chain Networks to Compute Kulli Temperature Indices

“…Many applications of topological indices are used in theoretical chemistry, particularly QSPR/QSAR research. Many well-known researchers have investigated topological indices in order to learn more about various graph families [ 9 ]. In qualitative structure property relationships (QSPR) and qualitative structure activity relationships (QSAR), topological indices are used directly as simple numerical descriptors in comparison with physical, biological, or chemical parameters of molecules, which is an advantage of the chemical industry.…”

SiO4 characterization in a chain and C6 H6 embedded in a Non-kekulean structure for Kulli Temperature indices

“…Many applications of topological indices are used in theoretical chemistry, particularly QSPR/QSAR research, [9]. Many well-known researchers have investigated topological indices in order to learn more about various graph families [7,19]. For example, in Qualitative Structure Property Relationships (QSPR) and Qualitative Structure Activity Relationships (QSAR), topological indices are employed as handy numerical descriptors in comparison with biological, physical or chemical parameters of molecules, which is an advantage of chemical industry, [15,13].…”