TY - JOUR
T1 - Machine learning prediction of inter-fragment interaction energies between ligand and amino-acid residues on the fragment molecular orbital calculations for Janus kinase – inhibitor complex
AU - Tokutomi, Shusuke
AU - Shimamura, Kohei
AU - Fukuzawa, Kaori
AU - Tanaka, Shigenori
N1 - Funding Information:
We would like to acknowledge the Grants-in-Aid for Scientific Research (Nos. 17H06353 and 18K03825 ) from the Ministry of Education, Cultute, Sports, Science and Technology (MEXT), Japan. This research was performed in the activities of the FMO drug design consortium (FMODD). The results of FMO calculations were obtained using the K computer (project ID: hp180147 and hp190119).
Funding Information:
We would like to acknowledge the Grants-in-Aid for Scientific Research (Nos. 17H06353 and 18K03825) from the Ministry of Education, Cultute, Sports, Science and Technology (MEXT), Japan. This research was performed in the activities of the FMO drug design consortium (FMODD). The results of FMO calculations were obtained using the K computer (project ID: hp180147 and hp190119).
Publisher Copyright:
© 2020 Elsevier B.V.
PY - 2020/10/16
Y1 - 2020/10/16
N2 - Inter-Fragment Interaction Energies (IFIEs) obtained by Fragment Molecular Orbital (FMO) method can quantitatively measure the effective interactions between ligand and residues in protein, which are therefore useful for drug discovery. However, it has not been clarified whether the IFIEs can be reproduced using only geometrical (e.g., interatomic distances) information of biomolecular complex without resort to explicit FMO calculations. In this study, through machine learning technique, we propose a highly accurate reproduction or prediction scheme for ligand-protein IFIEs using only the distance information as descriptors, thereby drastically saving the computational cost in FMO analysis for a variety of conformations.
AB - Inter-Fragment Interaction Energies (IFIEs) obtained by Fragment Molecular Orbital (FMO) method can quantitatively measure the effective interactions between ligand and residues in protein, which are therefore useful for drug discovery. However, it has not been clarified whether the IFIEs can be reproduced using only geometrical (e.g., interatomic distances) information of biomolecular complex without resort to explicit FMO calculations. In this study, through machine learning technique, we propose a highly accurate reproduction or prediction scheme for ligand-protein IFIEs using only the distance information as descriptors, thereby drastically saving the computational cost in FMO analysis for a variety of conformations.
KW - Fragment molecular orbital method (FMO)
KW - Inter-fragment interaction energy (IFIE)
KW - Janus kinase (JAK)
KW - Ligand-protein complex
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=85089727495&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089727495&partnerID=8YFLogxK
U2 - 10.1016/j.cplett.2020.137883
DO - 10.1016/j.cplett.2020.137883
M3 - Article
AN - SCOPUS:85089727495
VL - 757
JO - Chemical Physics Letters
JF - Chemical Physics Letters
SN - 0009-2614
M1 - 137883
ER -