TY - JOUR
T1 - The Melting Point Profile of Organic Molecules
T2 - A Chemoinformatic Approach
AU - Carrera, Gonçalo Valente da Silva Marino
N1 - info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F50006%2F2020/PT#
info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDP%2F50006%2F2020/PT#
PY - 2022/11
Y1 - 2022/11
N2 - The combination of the generical molecular maps of atom-level properties (MOLMAPs) encoding approach and the Random Forest algorithm (RF) is applied in order to model, predict, and interpret the structural motifs responsible for a certain organic molecule's melting point (mp) profile. A high-quality database is used for model build-up and evaluation of predictive ability. The obtained results for the complete independent test set (R2 = 0.811, MAE = 31.99 K, RMS = 43.98 K) are comparable or better than reference works. The form of codification represents implicitly the structure of a given molecule and highlights the interactions responsible for a certain melting point profile. This generical encoding approach groups different structural motifs based on its calculated atomic-based properties leading to good predictive ability for structurally different chemical systems not contained in the training set.
AB - The combination of the generical molecular maps of atom-level properties (MOLMAPs) encoding approach and the Random Forest algorithm (RF) is applied in order to model, predict, and interpret the structural motifs responsible for a certain organic molecule's melting point (mp) profile. A high-quality database is used for model build-up and evaluation of predictive ability. The obtained results for the complete independent test set (R2 = 0.811, MAE = 31.99 K, RMS = 43.98 K) are comparable or better than reference works. The form of codification represents implicitly the structure of a given molecule and highlights the interactions responsible for a certain melting point profile. This generical encoding approach groups different structural motifs based on its calculated atomic-based properties leading to good predictive ability for structurally different chemical systems not contained in the training set.
KW - chemoinformatics
KW - codification
KW - kohonen neural-networks
KW - melting points
KW - organic molecules
KW - qspr
KW - random forests
UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85139858922&origin=resultslist&sort=plf-t&src=s&st1=10.1002%2fadts.202200503&sid=bb30ded74e77777cda338de499f086f1&sot=b&sdt=b&sl=27&s=DOI%2810.1002%2fadts.202200503%29&relpos=0&citeCnt=0&searchTerm=
U2 - 10.1002/adts.202200503
DO - 10.1002/adts.202200503
M3 - Article
SN - 2513-0390
VL - 5
JO - Advanced Theory and Simulations
JF - Advanced Theory and Simulations
IS - 11
M1 - 2200503
ER -