Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200607218> ?p ?o ?g. }
- W3200607218 abstract "The trade-off between a machine learning (ML) and deep learning (DL) model's predictability and its interpretability has been a rising concern in central nervous system-related quantitative structure-activity relationship (CNS-QSAR) analysis. Many state-of-the-art predictive modeling failed to provide structural insights due to their black box-like nature. Lack of interpretability and further to provide easy simple rules would be challenging for CNS-QSAR models. To address these issues, we develop a protocol to combine the power of ML and DL to generate a set of simple rules that are easy to interpret with high prediction power. A data set of 940 market drugs (315 CNS-active, 625 CNS-inactive) with support vector machine and graph convolutional network algorithms were used. Individual ML/DL modeling methods were also constructed for comparison. The performance of these models was evaluated using an additional external dataset of 117 market drugs (42 CNS-active, 75 CNS-inactive). Fingerprint-split validation was adopted to ensure model stringency and generalizability. The resulting novel hybrid ensemble model outperformed other constituent traditional QSAR models with an accuracy of 0.96 and an F1 score of 0.95. With the power of the interpretability provided with this protocol, our model laid down a set of simple physicochemical rules to determine whether a compound can be a CNS drug using six sub-structural features. These rules displayed higher classification ability than classical guidelines, with higher specificity and more mechanistic insights than just for blood-brain barrier permeability. This hybrid protocol can potentially be used for other drug property predictions." @default.
- W3200607218 created "2021-09-27" @default.
- W3200607218 creator A5002510581 @default.
- W3200607218 creator A5021255582 @default.
- W3200607218 creator A5031369718 @default.
- W3200607218 creator A5079755039 @default.
- W3200607218 creator A5083021539 @default.
- W3200607218 date "2021-09-17" @default.
- W3200607218 modified "2023-10-16" @default.
- W3200607218 title "Ensemble modeling with machine learning and deep learning to provide interpretable generalized rules for classifying CNS drugs with high prediction power" @default.
- W3200607218 cites W1969235092 @default.
- W3200607218 cites W1971513938 @default.
- W3200607218 cites W1986803728 @default.
- W3200607218 cites W1987202142 @default.
- W3200607218 cites W1987652341 @default.
- W3200607218 cites W1988195734 @default.
- W3200607218 cites W1988691170 @default.
- W3200607218 cites W1995037393 @default.
- W3200607218 cites W1995336204 @default.
- W3200607218 cites W1995944520 @default.
- W3200607218 cites W2003998164 @default.
- W3200607218 cites W2018872680 @default.
- W3200607218 cites W2021431618 @default.
- W3200607218 cites W2036520094 @default.
- W3200607218 cites W2058230408 @default.
- W3200607218 cites W2090851494 @default.
- W3200607218 cites W2126810594 @default.
- W3200607218 cites W2144135270 @default.
- W3200607218 cites W2149298154 @default.
- W3200607218 cites W2159887157 @default.
- W3200607218 cites W2160815625 @default.
- W3200607218 cites W2170417464 @default.
- W3200607218 cites W2300160852 @default.
- W3200607218 cites W2307471347 @default.
- W3200607218 cites W2321980425 @default.
- W3200607218 cites W2334218692 @default.
- W3200607218 cites W2411306173 @default.
- W3200607218 cites W2532759528 @default.
- W3200607218 cites W2577452028 @default.
- W3200607218 cites W2584185934 @default.
- W3200607218 cites W2588523947 @default.
- W3200607218 cites W2596398464 @default.
- W3200607218 cites W2618530766 @default.
- W3200607218 cites W2746640787 @default.
- W3200607218 cites W2801991413 @default.
- W3200607218 cites W2900107325 @default.
- W3200607218 cites W2905012389 @default.
- W3200607218 cites W2921824753 @default.
- W3200607218 cites W2930000980 @default.
- W3200607218 cites W2945796574 @default.
- W3200607218 cites W2949937757 @default.
- W3200607218 cites W2957405451 @default.
- W3200607218 cites W2979759717 @default.
- W3200607218 cites W3011062824 @default.
- W3200607218 cites W3013960002 @default.
- W3200607218 cites W3022708367 @default.
- W3200607218 cites W3096097684 @default.
- W3200607218 cites W3100789280 @default.
- W3200607218 cites W3104508774 @default.
- W3200607218 cites W3112064743 @default.
- W3200607218 cites W3112376181 @default.
- W3200607218 cites W3133632969 @default.
- W3200607218 cites W4229872748 @default.
- W3200607218 cites W4230674625 @default.
- W3200607218 cites W45411166 @default.
- W3200607218 cites W64568169 @default.
- W3200607218 doi "https://doi.org/10.1093/bib/bbab377" @default.
- W3200607218 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34530437" @default.
- W3200607218 hasPublicationYear "2021" @default.
- W3200607218 type Work @default.
- W3200607218 sameAs 3200607218 @default.
- W3200607218 citedByCount "18" @default.
- W3200607218 countsByYear W32006072182022 @default.
- W3200607218 countsByYear W32006072182023 @default.
- W3200607218 crossrefType "journal-article" @default.
- W3200607218 hasAuthorship W3200607218A5002510581 @default.
- W3200607218 hasAuthorship W3200607218A5021255582 @default.
- W3200607218 hasAuthorship W3200607218A5031369718 @default.
- W3200607218 hasAuthorship W3200607218A5079755039 @default.
- W3200607218 hasAuthorship W3200607218A5083021539 @default.
- W3200607218 hasBestOaLocation W32006072181 @default.
- W3200607218 hasConcept C108583219 @default.
- W3200607218 hasConcept C119857082 @default.
- W3200607218 hasConcept C12267149 @default.
- W3200607218 hasConcept C154945302 @default.
- W3200607218 hasConcept C164126121 @default.
- W3200607218 hasConcept C2781067378 @default.
- W3200607218 hasConcept C41008148 @default.
- W3200607218 hasConcept C45942800 @default.
- W3200607218 hasConcept C50644808 @default.
- W3200607218 hasConcept C60644358 @default.
- W3200607218 hasConcept C63222358 @default.
- W3200607218 hasConcept C74187038 @default.
- W3200607218 hasConcept C86803240 @default.
- W3200607218 hasConceptScore W3200607218C108583219 @default.
- W3200607218 hasConceptScore W3200607218C119857082 @default.
- W3200607218 hasConceptScore W3200607218C12267149 @default.
- W3200607218 hasConceptScore W3200607218C154945302 @default.
- W3200607218 hasConceptScore W3200607218C164126121 @default.
- W3200607218 hasConceptScore W3200607218C2781067378 @default.