Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385858237> ?p ?o ?g. }
- W4385858237 endingPage "5076" @default.
- W4385858237 startingPage "5066" @default.
- W4385858237 abstract "Generative artificial intelligence algorithms have shown to be successful in exploring large chemical spaces and designing novel and diverse molecules. There has been considerable interest in developing predictive models using artificial intelligence for drug-like properties, which can potentially reduce the late-stage attrition of drug candidates or predict the properties of novel AI-designed molecules. Concurrently, it is important to understand the contribution of functional groups toward these properties and modify them to obtain property-optimized lead compounds. As a result, there is an increasing interest in the development of explainable property prediction models. However, current explainable approaches are mostly atom-based, where, often, only a fraction of a fragment is shown to be significant. To address the above challenges, we have developed a novel domain-aware molecular fragmentation approach termed post-processing of BRICS (pBRICS), which can fragment small molecules into their functional groups. Multitask models were developed to predict various properties, including the absorption, distribution, metabolism, excretion, and toxicity (ADMET) properties. The fragment importance was explained using the gradient-weighted class activation mapping (Grad-CAM) approach. The method was validated on data sets of experimentally available matched molecular pairs (MMPs). The explanations from the model can be useful for medicinal chemists to identify the fragments responsible for poor drug-like properties and optimize the molecule. The explainability approach was also used to identify the reason behind false positive and false negative MMP predictions. Based on evidence from the existing literature and our analysis, some of these mispredictions were justified. We propose that the quantity, quality, and diversity of the training data will improve the accuracy of property prediction algorithms for novel molecules." @default.
- W4385858237 created "2023-08-17" @default.
- W4385858237 creator A5016790815 @default.
- W4385858237 creator A5027584199 @default.
- W4385858237 creator A5042990614 @default.
- W4385858237 creator A5054798716 @default.
- W4385858237 creator A5065141890 @default.
- W4385858237 date "2023-08-16" @default.
- W4385858237 modified "2023-10-17" @default.
- W4385858237 title "pBRICS: A Novel Fragmentation Method for Explainable Property Prediction of Drug-Like Small Molecules" @default.
- W4385858237 cites W1505823450 @default.
- W4385858237 cites W1663154925 @default.
- W4385858237 cites W1895993106 @default.
- W4385858237 cites W1980260989 @default.
- W4385858237 cites W1991286793 @default.
- W4385858237 cites W2020859943 @default.
- W4385858237 cites W2021431618 @default.
- W4385858237 cites W2022476850 @default.
- W4385858237 cites W2060531713 @default.
- W4385858237 cites W2088837113 @default.
- W4385858237 cites W2159887157 @default.
- W4385858237 cites W2200017991 @default.
- W4385858237 cites W2275489486 @default.
- W4385858237 cites W2282821441 @default.
- W4385858237 cites W2497748342 @default.
- W4385858237 cites W2578240541 @default.
- W4385858237 cites W2593436234 @default.
- W4385858237 cites W2610148085 @default.
- W4385858237 cites W2742081931 @default.
- W4385858237 cites W2791355014 @default.
- W4385858237 cites W2801088198 @default.
- W4385858237 cites W2810023675 @default.
- W4385858237 cites W2888936354 @default.
- W4385858237 cites W2946697697 @default.
- W4385858237 cites W2962858109 @default.
- W4385858237 cites W2971690404 @default.
- W4385858237 cites W2979481854 @default.
- W4385858237 cites W3007309629 @default.
- W4385858237 cites W3019676419 @default.
- W4385858237 cites W3090171308 @default.
- W4385858237 cites W3100358278 @default.
- W4385858237 cites W3110901318 @default.
- W4385858237 cites W3125566655 @default.
- W4385858237 cites W3131648425 @default.
- W4385858237 cites W3137551757 @default.
- W4385858237 cites W3141797743 @default.
- W4385858237 cites W3154258817 @default.
- W4385858237 cites W3175318380 @default.
- W4385858237 cites W3182837219 @default.
- W4385858237 cites W3201677331 @default.
- W4385858237 cites W4220982113 @default.
- W4385858237 cites W4280510131 @default.
- W4385858237 cites W4293199734 @default.
- W4385858237 cites W4297460924 @default.
- W4385858237 cites W4304759443 @default.
- W4385858237 cites W4310603653 @default.
- W4385858237 cites W4310709716 @default.
- W4385858237 cites W4313703134 @default.
- W4385858237 cites W4361000628 @default.
- W4385858237 doi "https://doi.org/10.1021/acs.jcim.3c00689" @default.
- W4385858237 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37585609" @default.
- W4385858237 hasPublicationYear "2023" @default.
- W4385858237 type Work @default.
- W4385858237 citedByCount "0" @default.
- W4385858237 crossrefType "journal-article" @default.
- W4385858237 hasAuthorship W4385858237A5016790815 @default.
- W4385858237 hasAuthorship W4385858237A5027584199 @default.
- W4385858237 hasAuthorship W4385858237A5042990614 @default.
- W4385858237 hasAuthorship W4385858237A5054798716 @default.
- W4385858237 hasAuthorship W4385858237A5065141890 @default.
- W4385858237 hasConcept C107908354 @default.
- W4385858237 hasConcept C111919701 @default.
- W4385858237 hasConcept C11413529 @default.
- W4385858237 hasConcept C119857082 @default.
- W4385858237 hasConcept C154945302 @default.
- W4385858237 hasConcept C164126121 @default.
- W4385858237 hasConcept C185592680 @default.
- W4385858237 hasConcept C191015642 @default.
- W4385858237 hasConcept C2776235265 @default.
- W4385858237 hasConcept C41008148 @default.
- W4385858237 hasConcept C55493867 @default.
- W4385858237 hasConcept C74187038 @default.
- W4385858237 hasConcept C99726746 @default.
- W4385858237 hasConceptScore W4385858237C107908354 @default.
- W4385858237 hasConceptScore W4385858237C111919701 @default.
- W4385858237 hasConceptScore W4385858237C11413529 @default.
- W4385858237 hasConceptScore W4385858237C119857082 @default.
- W4385858237 hasConceptScore W4385858237C154945302 @default.
- W4385858237 hasConceptScore W4385858237C164126121 @default.
- W4385858237 hasConceptScore W4385858237C185592680 @default.
- W4385858237 hasConceptScore W4385858237C191015642 @default.
- W4385858237 hasConceptScore W4385858237C2776235265 @default.
- W4385858237 hasConceptScore W4385858237C41008148 @default.
- W4385858237 hasConceptScore W4385858237C55493867 @default.
- W4385858237 hasConceptScore W4385858237C74187038 @default.
- W4385858237 hasConceptScore W4385858237C99726746 @default.
- W4385858237 hasIssue "16" @default.
- W4385858237 hasLocation W43858582371 @default.