Structural properties and interaction energies affecting drug design. An approach combining molecular simulations,statistics, interaction energies and neural networks |
| |
| Affiliation: | 1. Laboratory of Biochemistry, Department of Medicine, Democritus University of Thrace, 68100 Alexandroupolis, Greece;2. Department of Biochemistry and Biotechnology, University of Thessaly, Ploutonos 26 & Aeolou Greece, 41221 Larisa, Greece;3. Laboratory of Medical Informatics, Department of Medicine, Democritus University of Thrace, 68100 Alexandroupolis, Greece;1. School of Chemistry and Chemical Engineering, Hunan University, Changsha 410082, China;2. Hunan Labour Protection Institute of Nonferrous Metals, Changsha 410014, China;3. School of Chemical Engineering, Ningbo University of Technology, Ningbo 315016, China;1. Department of Chemistry, Faculty of Sciences, Shahid Chamran University of Ahvaz, Ahvaz, Iran;2. Dipartimento di Chimica Inorganica, Vill. S. Agata, Salita Sperone 31, Università di Messina, 98166 Messina, Italy;3. Faculty of Chemistry, University of Isfahan, Isfahan 81746-73441, Iran;1. Institute of Chemistry, Environmental Protection and Biotechnology, Jan Długosz University, Armii Krajowej 13/15 Ave., 42-200, Częstochowa, Poland;2. Faculty of Chemistry, Wrocław University of Technology, Smoluchowskiego 23, 50-370 Wrocław, Poland;1. Department of Chemistry, Jadavpur University, Kolkata 700 032, India;2. Indian Institute of Technology, Kharagpur, Paschim Medinipur, 721302, India;3. Department of Chemistry, Faculty of Science, Tokyo University of Science, 1-3 Kagurazaka, Shinjuku-ku, Tokyo 162-8601, Japan |
| |
| Abstract: | In order to elucidate some basic principles for protein–ligand interactions, a subset of 87 structures of human proteins with their ligands was obtained from the PDB databank. After a short molecular dynamics simulation (to ensure structure stability), a variety of interaction energies and structural parameters were extracted. Linear regression was performed to determine which of these parameters have a potentially significant contribution to the protein–ligand interaction. The parameters exhibiting relatively high correlation coefficients were selected. Important factors seem to be the number of ligand atoms, the ratio of N, O and S atoms to total ligand atoms, the hydrophobic/polar aminoacid ratio and the ratio of cavity size to the sum of ligand plus water atoms in the cavity. An important factor also seems to be the immobile water molecules in the cavity. Nine of these parameters were used as known inputs to train a neural network in the prediction of seven other. Eight structures were left out of the training to test the quality of the predictions. After optimization of the neural network, the predictions were fairly accurate given the relatively small number of structures, especially in the prediction of the number of nitrogen and sulfur atoms of the ligand. |
| |
| Keywords: | Drug design Molecular dynamics simulation Interaction energy Neural networks |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
