FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3203558910> ?p ?o ?g. }

• W3203558910 abstract "Generative chemical language models (CLMs) can be used for de novo molecular structure generation. These CLMs learn from the structural information of known molecules to generate new ones. In this paper, we show that “hybrid” CLMs can additionally leverage the bioactivity information available for the training compounds. To computationally design ligands of phosphoinositide 3-kinase gamma (PI3Kγ), we created a large collection of virtual molecules with a generative CLM. This primary virtual compound library was further refined using a CLM-based classifier for bioactivity prediction. This second hybrid CLM was pretrained with patented molecular structures and fine-tuned with known PI3Kγ binders and non-binders by transfer learning. Several of the computer-generated molecular designs were commercially available, which allowed for fast prescreening and preliminary experimental validation. A new PI3Kγ ligand with sub-micromolar activity was identified. The results positively advocate hybrid CLMs for virtual compound screening and activity-focused molecular design in low-data situations." @default.
• W3203558910 created "2021-10-11" @default.
• W3203558910 creator A5015697006 @default.
• W3203558910 creator A5026925271 @default.
• W3203558910 creator A5028135456 @default.
• W3203558910 creator A5078946433 @default.
• W3203558910 date "2021-10-04" @default.
• W3203558910 modified "2023-09-27" @default.
• W3203558910 title "Leveraging molecular structure and bioactivity with chemical language models for drug design" @default.
• W3203558910 cites W129457532 @default.
• W3203558910 cites W1605923270 @default.
• W3203558910 cites W1975147762 @default.
• W3203558910 cites W1988037271 @default.
• W3203558910 cites W1988111902 @default.
• W3203558910 cites W1997176810 @default.
• W3203558910 cites W2014582878 @default.
• W3203558910 cites W2041686943 @default.
• W3203558910 cites W2059912458 @default.
• W3203558910 cites W2060531713 @default.
• W3203558910 cites W2064675550 @default.
• W3203558910 cites W2099071242 @default.
• W3203558910 cites W2114704115 @default.
• W3203558910 cites W2128186735 @default.
• W3203558910 cites W2132339004 @default.
• W3203558910 cites W2254686952 @default.
• W3203558910 cites W2256578114 @default.
• W3203558910 cites W2309693750 @default.
• W3203558910 cites W2325811289 @default.
• W3203558910 cites W2328672918 @default.
• W3203558910 cites W2520601585 @default.
• W3203558910 cites W2558999090 @default.
• W3203558910 cites W2578240541 @default.
• W3203558910 cites W2586256972 @default.
• W3203558910 cites W2592262780 @default.
• W3203558910 cites W2594328795 @default.
• W3203558910 cites W2610148085 @default.
• W3203558910 cites W2765224015 @default.
• W3203558910 cites W2775714759 @default.
• W3203558910 cites W2784270883 @default.
• W3203558910 cites W2883583109 @default.
• W3203558910 cites W2887447356 @default.
• W3203558910 cites W2889555425 @default.
• W3203558910 cites W2890507936 @default.
• W3203558910 cites W2897337442 @default.
• W3203558910 cites W2901719664 @default.
• W3203558910 cites W2914635984 @default.
• W3203558910 cites W2923057410 @default.
• W3203558910 cites W29374554 @default.
• W3203558910 cites W2953798723 @default.
• W3203558910 cites W2963121966 @default.
• W3203558910 cites W2963238274 @default.
• W3203558910 cites W2982209755 @default.
• W3203558910 cites W3006953393 @default.
• W3203558910 cites W3011286504 @default.
• W3203558910 cites W3044724994 @default.
• W3203558910 cites W3098269892 @default.
• W3203558910 cites W3100751385 @default.
• W3203558910 cites W3127493072 @default.
• W3203558910 cites W3133523400 @default.
• W3203558910 cites W3174777205 @default.
• W3203558910 cites W3185391990 @default.
• W3203558910 cites W3185456481 @default.
• W3203558910 cites W2963459876 @default.
• W3203558910 doi "https://doi.org/10.33774/chemrxiv-2021-xzgst" @default.
• W3203558910 hasPublicationYear "2021" @default.
• W3203558910 type Work @default.
• W3203558910 sameAs 3203558910 @default.
• W3203558910 citedByCount "0" @default.
• W3203558910 crossrefType "posted-content" @default.
• W3203558910 hasAuthorship W3203558910A5015697006 @default.
• W3203558910 hasAuthorship W3203558910A5026925271 @default.
• W3203558910 hasAuthorship W3203558910A5028135456 @default.
• W3203558910 hasAuthorship W3203558910A5078946433 @default.
• W3203558910 hasBestOaLocation W32035589101 @default.
• W3203558910 hasConcept C103697762 @default.
• W3203558910 hasConcept C153083717 @default.
• W3203558910 hasConcept C154945302 @default.
• W3203558910 hasConcept C167966045 @default.
• W3203558910 hasConcept C185592680 @default.
• W3203558910 hasConcept C21951064 @default.
• W3203558910 hasConcept C39890363 @default.
• W3203558910 hasConcept C41008148 @default.
• W3203558910 hasConcept C55493867 @default.
• W3203558910 hasConcept C70721500 @default.
• W3203558910 hasConcept C74187038 @default.
• W3203558910 hasConcept C86803240 @default.
• W3203558910 hasConceptScore W3203558910C103697762 @default.
• W3203558910 hasConceptScore W3203558910C153083717 @default.
• W3203558910 hasConceptScore W3203558910C154945302 @default.
• W3203558910 hasConceptScore W3203558910C167966045 @default.
• W3203558910 hasConceptScore W3203558910C185592680 @default.
• W3203558910 hasConceptScore W3203558910C21951064 @default.
• W3203558910 hasConceptScore W3203558910C39890363 @default.
• W3203558910 hasConceptScore W3203558910C41008148 @default.
• W3203558910 hasConceptScore W3203558910C55493867 @default.
• W3203558910 hasConceptScore W3203558910C70721500 @default.
• W3203558910 hasConceptScore W3203558910C74187038 @default.
• W3203558910 hasConceptScore W3203558910C86803240 @default.
• W3203558910 hasLocation W32035589101 @default.
• W3203558910 hasOpenAccess W3203558910 @default.

• next