FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3041381957> ?p ?o ?g. }

• W3041381957 abstract "De novo molecular design attempts to search over the chemical space for molecules with the desired property. Recently, deep learning has gained considerable attention as a promising approach to solve the problem. In this paper, we propose expert-guided learning (GEGL), a simple yet novel framework for training a deep neural network (DNN) to generate highly-rewarding molecules. Our main idea is to design a genetic expert improvement procedure, which generates high-quality targets for imitation learning of the DNN. Extensive experiments show that GEGL significantly improves over state-of-the-art methods. For example, GEGL manages to solve the penalized octanol-water partition coefficient optimization with a score of 31.40, while the best-known score in the literature is 27.22. Besides, for the GuacaMol benchmark with 20 tasks, our method achieves the highest score for 19 tasks, in comparison with state-of-the-art methods, and newly obtains the perfect score for three tasks." @default.
• W3041381957 created "2020-07-16" @default.
• W3041381957 creator A5033954037 @default.
• W3041381957 creator A5035397475 @default.
• W3041381957 creator A5035865220 @default.
• W3041381957 creator A5041027404 @default.
• W3041381957 date "2020-07-04" @default.
• W3041381957 modified "2023-09-27" @default.
• W3041381957 title "Guiding Deep Molecular Optimization with Genetic Exploration" @default.
• W3041381957 cites W1500036797 @default.
• W3041381957 cites W1562424368 @default.
• W3041381957 cites W1592238003 @default.
• W3041381957 cites W1969390039 @default.
• W3041381957 cites W1975147762 @default.
• W3041381957 cites W1978661986 @default.
• W3041381957 cites W1999738209 @default.
• W3041381957 cites W2017254234 @default.
• W3041381957 cites W2027482274 @default.
• W3041381957 cites W2034549041 @default.
• W3041381957 cites W2041686943 @default.
• W3041381957 cites W2064675550 @default.
• W3041381957 cites W2074978477 @default.
• W3041381957 cites W2080914508 @default.
• W3041381957 cites W2096541451 @default.
• W3041381957 cites W2096729078 @default.
• W3041381957 cites W2107160601 @default.
• W3041381957 cites W2111174053 @default.
• W3041381957 cites W2160592148 @default.
• W3041381957 cites W2478294658 @default.
• W3041381957 cites W2546950329 @default.
• W3041381957 cites W2578240541 @default.
• W3041381957 cites W259799208 @default.
• W3041381957 cites W2604808481 @default.
• W3041381957 cites W2618625858 @default.
• W3041381957 cites W2763220183 @default.
• W3041381957 cites W2766447205 @default.
• W3041381957 cites W2783104350 @default.
• W3041381957 cites W2786785157 @default.
• W3041381957 cites W2792783390 @default.
• W3041381957 cites W2793826631 @default.
• W3041381957 cites W2807691742 @default.
• W3041381957 cites W2901454299 @default.
• W3041381957 cites W2913423296 @default.
• W3041381957 cites W2914542247 @default.
• W3041381957 cites W2931903779 @default.
• W3041381957 cites W2946838154 @default.
• W3041381957 cites W2947643486 @default.
• W3041381957 cites W2951358838 @default.
• W3041381957 cites W2952332632 @default.
• W3041381957 cites W2954007457 @default.
• W3041381957 cites W2956961449 @default.
• W3041381957 cites W2963085895 @default.
• W3041381957 cites W2963121966 @default.
• W3041381957 cites W2963124123 @default.
• W3041381957 cites W2963521729 @default.
• W3041381957 cites W2963642149 @default.
• W3041381957 cites W2963662739 @default.
• W3041381957 cites W2963676163 @default.
• W3041381957 cites W2963819570 @default.
• W3041381957 cites W2964121744 @default.
• W3041381957 cites W2970081200 @default.
• W3041381957 cites W2985931096 @default.
• W3041381957 cites W2994860160 @default.
• W3041381957 cites W2996091952 @default.
• W3041381957 cites W2996314716 @default.
• W3041381957 cites W3014154196 @default.
• W3041381957 cites W3019734328 @default.
• W3041381957 cites W3023600056 @default.
• W3041381957 cites W3035314354 @default.
• W3041381957 cites W3100839802 @default.
• W3041381957 cites W3104255923 @default.
• W3041381957 cites W3104956673 @default.
• W3041381957 cites W3116865743 @default.
• W3041381957 cites W635830827 @default.
• W3041381957 cites W636519060 @default.
• W3041381957 cites W2114043088 @default.
• W3041381957 hasPublicationYear "2020" @default.
• W3041381957 type Work @default.
• W3041381957 sameAs 3041381957 @default.
• W3041381957 citedByCount "2" @default.
• W3041381957 countsByYear W30413819572020 @default.
• W3041381957 countsByYear W30413819572021 @default.
• W3041381957 crossrefType "posted-content" @default.
• W3041381957 hasAuthorship W3041381957A5033954037 @default.
• W3041381957 hasAuthorship W3041381957A5035397475 @default.
• W3041381957 hasAuthorship W3041381957A5035865220 @default.
• W3041381957 hasAuthorship W3041381957A5041027404 @default.
• W3041381957 hasConcept C108583219 @default.
• W3041381957 hasConcept C111472728 @default.
• W3041381957 hasConcept C114614502 @default.
• W3041381957 hasConcept C119857082 @default.
• W3041381957 hasConcept C13280743 @default.
• W3041381957 hasConcept C138885662 @default.
• W3041381957 hasConcept C154945302 @default.
• W3041381957 hasConcept C185798385 @default.
• W3041381957 hasConcept C189950617 @default.
• W3041381957 hasConcept C205649164 @default.
• W3041381957 hasConcept C2780586882 @default.
• W3041381957 hasConcept C33923547 @default.
• W3041381957 hasConcept C41008148 @default.

• next