This file contains the MATLAB code and data to reproduce the consensus (high level data fusion) described in the following manuscript: C. Valsecchi, F. Grisoni, V. Consonni, D. Ballabio (2020), Consensus versus individual QSARs in classification: comparison on a large-scale case study, Journal of Chemical Information and Modelling, 60, 1215-1223Â [link]. The present study was based on the outcome of a large collaborative project (Collaborative Modeling Project of Androgen Receptor Activity, CoMPARA), which produced three data sets containing experimental values on Androgen Receptor (AR) modulation and corresponding QSAR predictions, namely: (i) binding to AR (34 QSAR models), (ii) AR antagonism (22 QSAR models), and (iii) AR agonism (21 QSAR models). The aim of the study was the systematic investigation of the advantages of consensus strategies compared to single QSAR models. To this end, approaches with varying level of complexity (majority voting and Bayesian methods, in both protective and non-protective versions) were considered.
Conditions and warranty
The toolbox is freeware and may be used if proper reference is given to the authors. Please, refer to the following paper:
C. Valsecchi, F. Grisoni, V. Consonni, D. Ballabio (2020), Consensus versus individual QSARs in classification: comparison on a large-scale case study, Journal of Chemical Information and Modelling, , 60, 1215-1223Â [link]
Download
Fill in the following form. Your personal data will be used only for notification via email of new releases of the toolbox and will not be communicated to external third parties. Once the form has been submitted, open the rar file and extract the files. Have a look to the readme.txt file for further details. If you experience any problem to downlaod the toolbox, write to davide.ballabio@unimib.it.