Probabilistic Random Forest improves bioactivity predictions close to the classification threshold by taking into account experimental uncertainty.
Autor: | Mervin LH; Molecular AI, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK. lewis.mervin1@astrazeneca.com., Trapotsi MA; Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK., Afzal AM; Data Sciences & Quantitative Biology, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK., Barrett IP; Data Sciences & Quantitative Biology, Discovery Sciences, R&D, AstraZeneca, Cambridge, UK., Bender A; Department of Chemistry, Centre for Molecular Informatics, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, UK., Engkvist O; Molecular AI, Discovery Sciences, R&D, AstraZeneca, Gothenburg, Sweden.; Department of Computer Science and Engineering, Chalmers University of Technology, Gothenburg, Sweden. |
---|---|
Jazyk: | angličtina |
Zdroj: | Journal of cheminformatics [J Cheminform] 2021 Aug 19; Vol. 13 (1), pp. 62. Date of Electronic Publication: 2021 Aug 19. |
DOI: | 10.1186/s13321-021-00539-7 |
Abstrakt: | Measurements of protein-ligand interactions have reproducibility limits due to experimental errors. Any model based on such assays will consequentially have such unavoidable errors influencing their performance which should ideally be factored into modelling and output predictions, such as the actual standard deviation of experimental measurements (σ) or the associated comparability of activity values between the aggregated heterogenous activity units (i.e., K (© 2021. The Author(s).) |
Databáze: | MEDLINE |
Externí odkaz: | |
Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |