Consensus strategies have been widely applied in many different scientific fields, based on the assumption that the fusion of several sources of information increases the outcome reliability. Despite the widespread application of consensus approaches, their advantages in quantitative structure-activity relationship (QSAR) modeling have not been thoroughly evaluated, mainly due to the lack of appropriate large-scale data sets. In this study, we evaluated the advantages and drawbacks of consensus approaches compared to single classification QSAR models. To this end, we used a data set of three properties (androgen receptor binding, agonism, and antagonism) for approximately 4000 molecules with predictions performed by more than 20 QSAR models, made available in a large-scale collaborative project. The individual QSAR models were compared with two consensus approaches, majority voting and the Bayes consensus with discrete probability distributions, in both protective and nonprotective forms. Consensus strategies proved to be more accurate and to better cover the analyzed chemical space than individual QSARs on average, thus motivating their widespread application for property prediction. Scripts and data to reproduce the results of this study are available for download.

Valsecchi, C., Grisoni, F., Consonni, V., Ballabio, D. (2020). Consensus versus Individual QSARs in Classification: Comparison on a Large-Scale Case Study. JOURNAL OF CHEMICAL INFORMATION AND MODELING, 60(3), 1215-1223 [10.1021/acs.jcim.9b01057].

Consensus versus Individual QSARs in Classification: Comparison on a Large-Scale Case Study

Valsecchi, Cecile
Primo
;
Grisoni, Francesca
Secondo
;
Consonni, Viviana
Penultimo
;
Ballabio, Davide
Ultimo
2020

Abstract

Consensus strategies have been widely applied in many different scientific fields, based on the assumption that the fusion of several sources of information increases the outcome reliability. Despite the widespread application of consensus approaches, their advantages in quantitative structure-activity relationship (QSAR) modeling have not been thoroughly evaluated, mainly due to the lack of appropriate large-scale data sets. In this study, we evaluated the advantages and drawbacks of consensus approaches compared to single classification QSAR models. To this end, we used a data set of three properties (androgen receptor binding, agonism, and antagonism) for approximately 4000 molecules with predictions performed by more than 20 QSAR models, made available in a large-scale collaborative project. The individual QSAR models were compared with two consensus approaches, majority voting and the Bayes consensus with discrete probability distributions, in both protective and nonprotective forms. Consensus strategies proved to be more accurate and to better cover the analyzed chemical space than individual QSARs on average, thus motivating their widespread application for property prediction. Scripts and data to reproduce the results of this study are available for download.
Articolo in rivista - Articolo scientifico
QSAR; consensus; data fusion; machine learning; chemometrics
English
2020
60
3
1215
1223
open
Valsecchi, C., Grisoni, F., Consonni, V., Ballabio, D. (2020). Consensus versus Individual QSARs in Classification: Comparison on a Large-Scale Case Study. JOURNAL OF CHEMICAL INFORMATION AND MODELING, 60(3), 1215-1223 [10.1021/acs.jcim.9b01057].
File in questo prodotto:
File Dimensione Formato  
Valsecchi-2020.pdf

accesso aperto

Tipologia di allegato: Publisher’s Version (Version of Record, VoR)
Dimensione 3.17 MB
Formato Adobe PDF
3.17 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/265670
Citazioni
  • Scopus 27
  • ???jsp.display-item.citation.isi??? 25
Social impact