QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping
Abstract An affinity fingerprint is the vector consisting of compound’s affinity or potency against the reference panel of protein targets. Here, we present the QAFFP fingerprint, 440 elements long in silico QSAR-based affinity fingerprint, components of which are predicted by Random Forest regressi...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2020-05-01
|
Series: | Journal of Cheminformatics |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s13321-020-00443-6 |
id |
doaj-030fcddcbd334c029e28370217cfcb3d |
---|---|
record_format |
Article |
spelling |
doaj-030fcddcbd334c029e28370217cfcb3d2020-11-25T03:24:01ZengBMCJournal of Cheminformatics1758-29462020-05-0112111610.1186/s13321-020-00443-6QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hoppingC. Škuta0I. Cortés-Ciriano1W. Dehaen2P. Kříž3G. J. P. van Westen4I. V. Tetko5A. Bender6D. Svozil7CZ-OPENSCREEN: National Infrastructure for Chemical Biology, Institute of Molecular Genetics of the ASCR, v. v. i.Centre for Molecular Informatics, Department of Chemistry, University of CambridgeCZ-OPENSCREEN: National Infrastructure for Chemical Biology, Institute of Molecular Genetics of the ASCR, v. v. i.Department of Mathematics, Faculty of Chemical Engineering, University of Chemistry and Technology PragueComputational Drug Discovery, Drug Discovery and Safety, LACDR, Leiden UniversityHelmholtz Zentrum Muenchen – German Research Center for Environmental Health (GmbH) and BIGCHEM GmbHCentre for Molecular Informatics, Department of Chemistry, University of CambridgeCZ-OPENSCREEN: National Infrastructure for Chemical Biology, Institute of Molecular Genetics of the ASCR, v. v. i.Abstract An affinity fingerprint is the vector consisting of compound’s affinity or potency against the reference panel of protein targets. Here, we present the QAFFP fingerprint, 440 elements long in silico QSAR-based affinity fingerprint, components of which are predicted by Random Forest regression models trained on bioactivity data from the ChEMBL database. Both real-valued (rv-QAFFP) and binary (b-QAFFP) versions of the QAFFP fingerprint were implemented and their performance in similarity searching, biological activity classification and scaffold hopping was assessed and compared to that of the 1024 bits long Morgan2 fingerprint (the RDKit implementation of the ECFP4 fingerprint). In both similarity searching and biological activity classification, the QAFFP fingerprint yields retrieval rates, measured by AUC (~ 0.65 and ~ 0.70 for similarity searching depending on data sets, and ~ 0.85 for classification) and EF5 (~ 4.67 and ~ 5.82 for similarity searching depending on data sets, and ~ 2.10 for classification), comparable to that of the Morgan2 fingerprint (similarity searching AUC of ~ 0.57 and ~ 0.66, and EF5 of ~ 4.09 and ~ 6.41, depending on data sets, classification AUC of ~ 0.87, and EF5 of ~ 2.16). However, the QAFFP fingerprint outperforms the Morgan2 fingerprint in scaffold hopping as it is able to retrieve 1146 out of existing 1749 scaffolds, while the Morgan2 fingerprint reveals only 864 scaffolds.http://link.springer.com/article/10.1186/s13321-020-00443-6Affinity fingerprintBiological fingerprintQSARSimilarity searchingBioactivity modelingScaffold hopping |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
C. Škuta I. Cortés-Ciriano W. Dehaen P. Kříž G. J. P. van Westen I. V. Tetko A. Bender D. Svozil |
spellingShingle |
C. Škuta I. Cortés-Ciriano W. Dehaen P. Kříž G. J. P. van Westen I. V. Tetko A. Bender D. Svozil QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping Journal of Cheminformatics Affinity fingerprint Biological fingerprint QSAR Similarity searching Bioactivity modeling Scaffold hopping |
author_facet |
C. Škuta I. Cortés-Ciriano W. Dehaen P. Kříž G. J. P. van Westen I. V. Tetko A. Bender D. Svozil |
author_sort |
C. Škuta |
title |
QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping |
title_short |
QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping |
title_full |
QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping |
title_fullStr |
QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping |
title_full_unstemmed |
QSAR-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping |
title_sort |
qsar-derived affinity fingerprints (part 1): fingerprint construction and modeling performance for similarity searching, bioactivity classification and scaffold hopping |
publisher |
BMC |
series |
Journal of Cheminformatics |
issn |
1758-2946 |
publishDate |
2020-05-01 |
description |
Abstract An affinity fingerprint is the vector consisting of compound’s affinity or potency against the reference panel of protein targets. Here, we present the QAFFP fingerprint, 440 elements long in silico QSAR-based affinity fingerprint, components of which are predicted by Random Forest regression models trained on bioactivity data from the ChEMBL database. Both real-valued (rv-QAFFP) and binary (b-QAFFP) versions of the QAFFP fingerprint were implemented and their performance in similarity searching, biological activity classification and scaffold hopping was assessed and compared to that of the 1024 bits long Morgan2 fingerprint (the RDKit implementation of the ECFP4 fingerprint). In both similarity searching and biological activity classification, the QAFFP fingerprint yields retrieval rates, measured by AUC (~ 0.65 and ~ 0.70 for similarity searching depending on data sets, and ~ 0.85 for classification) and EF5 (~ 4.67 and ~ 5.82 for similarity searching depending on data sets, and ~ 2.10 for classification), comparable to that of the Morgan2 fingerprint (similarity searching AUC of ~ 0.57 and ~ 0.66, and EF5 of ~ 4.09 and ~ 6.41, depending on data sets, classification AUC of ~ 0.87, and EF5 of ~ 2.16). However, the QAFFP fingerprint outperforms the Morgan2 fingerprint in scaffold hopping as it is able to retrieve 1146 out of existing 1749 scaffolds, while the Morgan2 fingerprint reveals only 864 scaffolds. |
topic |
Affinity fingerprint Biological fingerprint QSAR Similarity searching Bioactivity modeling Scaffold hopping |
url |
http://link.springer.com/article/10.1186/s13321-020-00443-6 |
work_keys_str_mv |
AT cskuta qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping AT icortesciriano qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping AT wdehaen qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping AT pkriz qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping AT gjpvanwesten qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping AT ivtetko qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping AT abender qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping AT dsvozil qsarderivedaffinityfingerprintspart1fingerprintconstructionandmodelingperformanceforsimilaritysearchingbioactivityclassificationandscaffoldhopping |
_version_ |
1724604030001348608 |