Profiling and analysis of chemical compounds using pointwise mutual information
Abstract Pointwise mutual information (PMI) is a measure of association used in information theory. In this paper, PMI is used to characterize several publicly available databases (DrugBank, ChEMBL, PubChem and ZINC) in terms of association strength between compound structural features resulting in...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-01-01
|
Series: | Journal of Cheminformatics |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13321-020-00483-y |
id |
doaj-7a902a0450124fa7804e687ae8a97e09 |
---|---|
record_format |
Article |
spelling |
doaj-7a902a0450124fa7804e687ae8a97e092021-01-17T12:52:30ZengBMCJournal of Cheminformatics1758-29462021-01-0113111810.1186/s13321-020-00483-yProfiling and analysis of chemical compounds using pointwise mutual informationI. Čmelo0M. Voršilák1D. Svozil2CZ-OPENSCREEN National Infrastructure for Chemical Biology, Department of Informatics and Chemistry, Faculty of Chemical Technology, University of Chemistry and Technology PragueCZ-OPENSCREEN National Infrastructure for Chemical Biology, Department of Informatics and Chemistry, Faculty of Chemical Technology, University of Chemistry and Technology PragueCZ-OPENSCREEN National Infrastructure for Chemical Biology, Department of Informatics and Chemistry, Faculty of Chemical Technology, University of Chemistry and Technology PragueAbstract Pointwise mutual information (PMI) is a measure of association used in information theory. In this paper, PMI is used to characterize several publicly available databases (DrugBank, ChEMBL, PubChem and ZINC) in terms of association strength between compound structural features resulting in database PMI interrelation profiles. As structural features, substructure fragments obtained by coding individual compounds as MACCS, PubChemKey and ECFP fingerprints are used. The analysis of publicly available databases reveals, in accord with other studies, unusual properties of DrugBank compounds which further confirms the validity of PMI profiling approach. Z-standardized relative feature tightness (ZRFT), a PMI-derived measure that quantifies how well the given compound’s feature combinations fit these in a particular compound set, is applied for the analysis of compound synthetic accessibility (SA), as well as for the classification of compounds as easy (ES) and hard (HS) to synthesize. ZRFT value distributions are compared with these of SYBA and SAScore. The analysis of ZRFT values of structurally complex compounds in the SAVI database reveals oligopeptide structures that are mispredicted by SAScore as HS, while correctly predicted by ZRFT and SYBA as ES. Compared to SAScore, SYBA and random forest, ZRFT predictions are less accurate, though by a narrow margin (Acc ZRFT = 94.5%, Acc SYBA = 98.8%, Acc SAScore = 99.0%, Acc RF = 97.3%). However, ZRFT ability to distinguish between ES and HS compounds is surprisingly high considering that while SYBA, SAScore and random forest are dedicated SA models, ZRFT is a generic measurement that merely quantifies the strength of interrelations between structural feature pairs. The results presented in the current work indicate that structural feature co-occurrence, quantified by PMI or ZRFT, contains a significant amount of information relevant to physico-chemical properties of organic compounds.https://doi.org/10.1186/s13321-020-00483-yHashed fingerprintStructural keyInformation theoryPointwise mutual informationSynthetic accessibility |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
I. Čmelo M. Voršilák D. Svozil |
spellingShingle |
I. Čmelo M. Voršilák D. Svozil Profiling and analysis of chemical compounds using pointwise mutual information Journal of Cheminformatics Hashed fingerprint Structural key Information theory Pointwise mutual information Synthetic accessibility |
author_facet |
I. Čmelo M. Voršilák D. Svozil |
author_sort |
I. Čmelo |
title |
Profiling and analysis of chemical compounds using pointwise mutual information |
title_short |
Profiling and analysis of chemical compounds using pointwise mutual information |
title_full |
Profiling and analysis of chemical compounds using pointwise mutual information |
title_fullStr |
Profiling and analysis of chemical compounds using pointwise mutual information |
title_full_unstemmed |
Profiling and analysis of chemical compounds using pointwise mutual information |
title_sort |
profiling and analysis of chemical compounds using pointwise mutual information |
publisher |
BMC |
series |
Journal of Cheminformatics |
issn |
1758-2946 |
publishDate |
2021-01-01 |
description |
Abstract Pointwise mutual information (PMI) is a measure of association used in information theory. In this paper, PMI is used to characterize several publicly available databases (DrugBank, ChEMBL, PubChem and ZINC) in terms of association strength between compound structural features resulting in database PMI interrelation profiles. As structural features, substructure fragments obtained by coding individual compounds as MACCS, PubChemKey and ECFP fingerprints are used. The analysis of publicly available databases reveals, in accord with other studies, unusual properties of DrugBank compounds which further confirms the validity of PMI profiling approach. Z-standardized relative feature tightness (ZRFT), a PMI-derived measure that quantifies how well the given compound’s feature combinations fit these in a particular compound set, is applied for the analysis of compound synthetic accessibility (SA), as well as for the classification of compounds as easy (ES) and hard (HS) to synthesize. ZRFT value distributions are compared with these of SYBA and SAScore. The analysis of ZRFT values of structurally complex compounds in the SAVI database reveals oligopeptide structures that are mispredicted by SAScore as HS, while correctly predicted by ZRFT and SYBA as ES. Compared to SAScore, SYBA and random forest, ZRFT predictions are less accurate, though by a narrow margin (Acc ZRFT = 94.5%, Acc SYBA = 98.8%, Acc SAScore = 99.0%, Acc RF = 97.3%). However, ZRFT ability to distinguish between ES and HS compounds is surprisingly high considering that while SYBA, SAScore and random forest are dedicated SA models, ZRFT is a generic measurement that merely quantifies the strength of interrelations between structural feature pairs. The results presented in the current work indicate that structural feature co-occurrence, quantified by PMI or ZRFT, contains a significant amount of information relevant to physico-chemical properties of organic compounds. |
topic |
Hashed fingerprint Structural key Information theory Pointwise mutual information Synthetic accessibility |
url |
https://doi.org/10.1186/s13321-020-00483-y |
work_keys_str_mv |
AT icmelo profilingandanalysisofchemicalcompoundsusingpointwisemutualinformation AT mvorsilak profilingandanalysisofchemicalcompoundsusingpointwisemutualinformation AT dsvozil profilingandanalysisofchemicalcompoundsusingpointwisemutualinformation |
_version_ |
1724334278451396608 |