Developing Collaborative QSAR Models Without Sharing Structures
| Autor: | Peter Gedeck, Suzanne Skolnik, Stephane Rodde |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0301 basic medicine
Quantitative structure–activity relationship Computer science General Chemical Engineering Quantitative Structure-Activity Relationship Library and Information Sciences Intellectual property Machine learning computer.software_genre 01 natural sciences 03 medical and health sciences Linear regression Confidentiality Training set business.industry General Chemistry Models Theoretical 0104 chemical sciences Computer Science Applications Data set 010404 medicinal & biomolecular chemistry 030104 developmental biology Artificial intelligence Data mining business computer Applicability domain Diversity (business) |
| Zdroj: | Journal of Chemical Information and Modeling. 57:1847-1858 |
| ISSN: | 1549-960X 1549-9596 |
| Popis: | It is widely understood that QSAR models greatly improve if more data are used. However, irrespective of model quality, once chemical structures diverge too far from the initial data set, the predictive performance of a model degrades quickly. To increase the applicability domain we need to increase the diversity of the training set. This can be achieved by combining data from diverse sources. Public data can be easily included; however, proprietary data may be more difficult to add due to intellectual property concerns. In this contribution, we will present a method for the collaborative development of linear regression models that addresses this problem. The method differs from other past approaches, because data are only shared in an aggregated form. This prohibits access to individual data points and therefore avoids the disclosure of confidential structural information. The final models are equivalent to models that were built with combined data sets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|