FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4362664882> ?p ?o ?g. }

• W4362664882 endingPage "444" @default.
• W4362664882 startingPage "432" @default.
• W4362664882 abstract "Abstract Despite tremendous progress of generative models in the natural sciences, their controllability remains challenging. One fundamentally missing aspect of molecular or protein generative models is an inductive bias that can reflect continuous properties of interest. To that end, we propose the Regression Transformer (RT), a method that abstracts regression as a conditional sequence modelling problem. This introduces a new direction for multitask language models, seamlessly bridging sequence regression and conditional sequence generation. We demonstrate that, despite using a nominal-scale training objective, the RT matches or surpasses the performance of conventional regression models in property prediction of small molecules, proteins and chemical reactions. Critically, priming the same model with continuous properties yields a competitive conditional generative model that outperforms specialized approaches in a substructure-constrained, property-driven molecule generation benchmark. Our dichotomous approach is facilitated by an alternating training scheme that enables the model to decorate seed sequences on the basis of desired property constraints, for example, to optimize reaction yield. We expect that the RT’s capability to jointly tackle predictive and generative tasks in biochemistry can find applications in property-driven, local exploration of the chemical or protein space. Such multitask approaches will pave the road towards foundation models in materials design." @default.
• W4362664882 created "2023-04-07" @default.
• W4362664882 creator A5002562002 @default.
• W4362664882 creator A5005561269 @default.
• W4362664882 date "2023-04-06" @default.
• W4362664882 modified "2023-10-01" @default.
• W4362664882 title "Regression Transformer enables concurrent sequence regression and generation for molecular language modelling" @default.
• W4362664882 cites W1902237438 @default.
• W4362664882 cites W1975147762 @default.
• W4362664882 cites W1988037271 @default.
• W4362664882 cites W1997868832 @default.
• W4362664882 cites W2034549041 @default.
• W4362664882 cites W2060531713 @default.
• W4362664882 cites W2379594833 @default.
• W4362664882 cites W2594183968 @default.
• W4362664882 cites W2622206241 @default.
• W4362664882 cites W2735621019 @default.
• W4362664882 cites W2769423117 @default.
• W4362664882 cites W2784918212 @default.
• W4362664882 cites W2785942661 @default.
• W4362664882 cites W2900090807 @default.
• W4362664882 cites W2945551948 @default.
• W4362664882 cites W2950784811 @default.
• W4362664882 cites W2964110616 @default.
• W4362664882 cites W2973114758 @default.
• W4362664882 cites W2980789587 @default.
• W4362664882 cites W2998571806 @default.
• W4362664882 cites W3012519883 @default.
• W4362664882 cites W3025593963 @default.
• W4362664882 cites W3037888463 @default.
• W4362664882 cites W3045928028 @default.
• W4362664882 cites W3098269892 @default.
• W4362664882 cites W3099414221 @default.
• W4362664882 cites W3102094970 @default.
• W4362664882 cites W3103092523 @default.
• W4362664882 cites W3108004614 @default.
• W4362664882 cites W3112376646 @default.
• W4362664882 cites W3112776819 @default.
• W4362664882 cites W3118349318 @default.
• W4362664882 cites W3123901912 @default.
• W4362664882 cites W3130227682 @default.
• W4362664882 cites W3146384714 @default.
• W4362664882 cites W3146944767 @default.
• W4362664882 cites W3147983081 @default.
• W4362664882 cites W3163970098 @default.
• W4362664882 cites W3165630607 @default.
• W4362664882 cites W3167734706 @default.
• W4362664882 cites W3177828909 @default.
• W4362664882 cites W3205470891 @default.
• W4362664882 cites W3209056694 @default.
• W4362664882 cites W3212417448 @default.
• W4362664882 cites W4200256006 @default.
• W4362664882 cites W4205773061 @default.
• W4362664882 cites W4220902634 @default.
• W4362664882 cites W4224060952 @default.
• W4362664882 cites W4226159083 @default.
• W4362664882 cites W4283794074 @default.
• W4362664882 cites W4288804596 @default.
• W4362664882 cites W4297779993 @default.
• W4362664882 cites W4313531775 @default.
• W4362664882 cites W4318071656 @default.
• W4362664882 cites W4320495593 @default.
• W4362664882 doi "https://doi.org/10.1038/s42256-023-00639-z" @default.
• W4362664882 hasPublicationYear "2023" @default.
• W4362664882 type Work @default.
• W4362664882 citedByCount "5" @default.
• W4362664882 countsByYear W43626648822023 @default.
• W4362664882 crossrefType "journal-article" @default.
• W4362664882 hasAuthorship W4362664882A5002562002 @default.
• W4362664882 hasAuthorship W4362664882A5005561269 @default.
• W4362664882 hasBestOaLocation W43626648821 @default.
• W4362664882 hasConcept C105795698 @default.
• W4362664882 hasConcept C111472728 @default.
• W4362664882 hasConcept C119857082 @default.
• W4362664882 hasConcept C138885662 @default.
• W4362664882 hasConcept C154945302 @default.
• W4362664882 hasConcept C167966045 @default.
• W4362664882 hasConcept C189950617 @default.
• W4362664882 hasConcept C2778112365 @default.
• W4362664882 hasConcept C33923547 @default.
• W4362664882 hasConcept C39890363 @default.
• W4362664882 hasConcept C41008148 @default.
• W4362664882 hasConcept C54355233 @default.
• W4362664882 hasConcept C83546350 @default.
• W4362664882 hasConcept C86803240 @default.
• W4362664882 hasConceptScore W4362664882C105795698 @default.
• W4362664882 hasConceptScore W4362664882C111472728 @default.
• W4362664882 hasConceptScore W4362664882C119857082 @default.
• W4362664882 hasConceptScore W4362664882C138885662 @default.
• W4362664882 hasConceptScore W4362664882C154945302 @default.
• W4362664882 hasConceptScore W4362664882C167966045 @default.
• W4362664882 hasConceptScore W4362664882C189950617 @default.
• W4362664882 hasConceptScore W4362664882C2778112365 @default.
• W4362664882 hasConceptScore W4362664882C33923547 @default.
• W4362664882 hasConceptScore W4362664882C39890363 @default.
• W4362664882 hasConceptScore W4362664882C41008148 @default.
• W4362664882 hasConceptScore W4362664882C54355233 @default.
• W4362664882 hasConceptScore W4362664882C83546350 @default.

• next