FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313339550> ?p ?o ?g. }

• W4313339550 abstract "A de novo molecular design workflow can be used together with technologies such as reinforcement learning to navigate the chemical space. A bottleneck in the workflow that remains to be solved is how to integrate human feedback in the exploration of the chemical space to optimize molecules. A human drug designer still needs to design the goal, expressed as a scoring function for the molecules that captures the designer's implicit knowledge about the optimization task. Little support for this task exists and, consequently, a chemist usually resorts to iteratively building the objective function of multi-parameter optimization (MPO) in de novo design. We propose a principled approach to use human-in-the-loop machine learning to help the chemist to adapt the MPO scoring function to better match their goal. An advantage is that the method can learn the scoring function directly from the user's feedback while they browse the output of the molecule generator, instead of the current manual tuning of the scoring function with trial and error. The proposed method uses a probabilistic model that captures the user's idea and uncertainty about the scoring function, and it uses active learning to interact with the user. We present two case studies for this: In the first use-case, the parameters of an MPO are learned, and in the second use-case a non-parametric component of the scoring function to capture human domain knowledge is developed. The results show the effectiveness of the methods in two simulated example cases with an oracle, achieving significant improvement in less than 200 feedback queries, for the goals of a high QED score and identifying potent molecules for the DRD2 receptor, respectively. We further demonstrate the performance gains with a medicinal chemist interacting with the system." @default.
• W4313339550 created "2023-01-06" @default.
• W4313339550 creator A5007032257 @default.
• W4313339550 creator A5018305257 @default.
• W4313339550 creator A5028024125 @default.
• W4313339550 creator A5028101182 @default.
• W4313339550 creator A5037354462 @default.
• W4313339550 creator A5046421751 @default.
• W4313339550 creator A5055735688 @default.
• W4313339550 creator A5076975589 @default.
• W4313339550 creator A5085143594 @default.
• W4313339550 date "2022-12-28" @default.
• W4313339550 modified "2023-10-11" @default.
• W4313339550 title "Human-in-the-loop assisted de novo molecular design" @default.
• W4313339550 cites W1975147762 @default.
• W4313339550 cites W1988037271 @default.
• W4313339550 cites W2027065525 @default.
• W4313339550 cites W2034549041 @default.
• W4313339550 cites W2039522160 @default.
• W4313339550 cites W2040030948 @default.
• W4313339550 cites W2081301924 @default.
• W4313339550 cites W2125426232 @default.
• W4313339550 cites W2160592148 @default.
• W4313339550 cites W2166566250 @default.
• W4313339550 cites W2168405694 @default.
• W4313339550 cites W2300160852 @default.
• W4313339550 cites W2319060767 @default.
• W4313339550 cites W2563271136 @default.
• W4313339550 cites W2593632281 @default.
• W4313339550 cites W2606395562 @default.
• W4313339550 cites W2613206385 @default.
• W4313339550 cites W2736137960 @default.
• W4313339550 cites W2773785180 @default.
• W4313339550 cites W2790808809 @default.
• W4313339550 cites W2914542247 @default.
• W4313339550 cites W2924337219 @default.
• W4313339550 cites W2949676527 @default.
• W4313339550 cites W2956961449 @default.
• W4313339550 cites W3013657235 @default.
• W4313339550 cites W3021177445 @default.
• W4313339550 cites W3026536569 @default.
• W4313339550 cites W3094686696 @default.
• W4313339550 cites W3098967121 @default.
• W4313339550 cites W3123775255 @default.
• W4313339550 cites W3162554793 @default.
• W4313339550 cites W3192495122 @default.
• W4313339550 cites W3209173593 @default.
• W4313339550 cites W3212543990 @default.
• W4313339550 cites W4206530644 @default.
• W4313339550 cites W4206547457 @default.
• W4313339550 cites W4206723194 @default.
• W4313339550 cites W4211049957 @default.
• W4313339550 cites W4232762624 @default.
• W4313339550 cites W4285027310 @default.
• W4313339550 doi "https://doi.org/10.1186/s13321-022-00667-8" @default.
• W4313339550 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36578043" @default.
• W4313339550 hasPublicationYear "2022" @default.
• W4313339550 type Work @default.
• W4313339550 citedByCount "6" @default.
• W4313339550 countsByYear W43133395502023 @default.
• W4313339550 crossrefType "journal-article" @default.
• W4313339550 hasAuthorship W4313339550A5007032257 @default.
• W4313339550 hasAuthorship W4313339550A5018305257 @default.
• W4313339550 hasAuthorship W4313339550A5028024125 @default.
• W4313339550 hasAuthorship W4313339550A5028101182 @default.
• W4313339550 hasAuthorship W4313339550A5037354462 @default.
• W4313339550 hasAuthorship W4313339550A5046421751 @default.
• W4313339550 hasAuthorship W4313339550A5055735688 @default.
• W4313339550 hasAuthorship W4313339550A5076975589 @default.
• W4313339550 hasAuthorship W4313339550A5085143594 @default.
• W4313339550 hasBestOaLocation W43133395501 @default.
• W4313339550 hasConcept C115903868 @default.
• W4313339550 hasConcept C119857082 @default.
• W4313339550 hasConcept C124101348 @default.
• W4313339550 hasConcept C127413603 @default.
• W4313339550 hasConcept C14036430 @default.
• W4313339550 hasConcept C154945302 @default.
• W4313339550 hasConcept C177212765 @default.
• W4313339550 hasConcept C201995342 @default.
• W4313339550 hasConcept C207685749 @default.
• W4313339550 hasConcept C2778049539 @default.
• W4313339550 hasConcept C2780451532 @default.
• W4313339550 hasConcept C2780626000 @default.
• W4313339550 hasConcept C41008148 @default.
• W4313339550 hasConcept C49937458 @default.
• W4313339550 hasConcept C55166926 @default.
• W4313339550 hasConcept C60644358 @default.
• W4313339550 hasConcept C74187038 @default.
• W4313339550 hasConcept C77088390 @default.
• W4313339550 hasConcept C78458016 @default.
• W4313339550 hasConcept C86803240 @default.
• W4313339550 hasConcept C99726746 @default.
• W4313339550 hasConceptScore W4313339550C115903868 @default.
• W4313339550 hasConceptScore W4313339550C119857082 @default.
• W4313339550 hasConceptScore W4313339550C124101348 @default.
• W4313339550 hasConceptScore W4313339550C127413603 @default.
• W4313339550 hasConceptScore W4313339550C14036430 @default.
• W4313339550 hasConceptScore W4313339550C154945302 @default.
• W4313339550 hasConceptScore W4313339550C177212765 @default.
• W4313339550 hasConceptScore W4313339550C201995342 @default.

• next