Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304194159> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4304194159 abstract "Inverse protein folding, i.e., designing sequences that fold into a given three-dimensional structure, is one of the fundamental design challenges in bio-engineering and drug discovery. Traditionally, inverse folding mainly involves learning from sequences that have an experimentally resolved structure. However, the known structures cover only a tiny space of the protein sequences, imposing limitations on the model learning. Recently proposed forward folding models, e.g., AlphaFold, offer unprecedented opportunity for accurate estimation of the structure given a protein sequence. Naturally, incorporating a forward folding model as a component of an inverse folding approach offers the potential of significantly improving the inverse folding, as the folding model can provide a feedback on any generated sequence in the form of the predicted protein structure or a structural confidence metric. However, at present, these forward folding models are still prohibitively slow to be a part of the model optimization loop during training. In this work, we propose to perform knowledge distillation on the folding model's confidence metrics, e.g., pTM or pLDDT scores, to obtain a smaller, faster and end-to-end differentiable distilled model, which then can be included as part of the structure consistency regularized inverse folding model training. Moreover, our regularization technique is general enough and can be applied in other design tasks, e.g., sequence-based protein infilling. Extensive experiments show a clear benefit of our method over the non-regularized baselines. For example, in inverse folding design problems we observe up to 3% improvement in sequence recovery and up to 45% improvement in protein diversity, while still preserving structural consistency of the generated sequences." @default.
- W4304194159 created "2022-10-11" @default.
- W4304194159 creator A5035670477 @default.
- W4304194159 creator A5055054658 @default.
- W4304194159 creator A5058823844 @default.
- W4304194159 creator A5064335115 @default.
- W4304194159 date "2022-10-05" @default.
- W4304194159 modified "2023-09-28" @default.
- W4304194159 title "AlphaFold Distillation for Improved Inverse Protein Folding" @default.
- W4304194159 doi "https://doi.org/10.48550/arxiv.2210.03488" @default.
- W4304194159 hasPublicationYear "2022" @default.
- W4304194159 type Work @default.
- W4304194159 citedByCount "0" @default.
- W4304194159 crossrefType "posted-content" @default.
- W4304194159 hasAuthorship W4304194159A5035670477 @default.
- W4304194159 hasAuthorship W4304194159A5055054658 @default.
- W4304194159 hasAuthorship W4304194159A5058823844 @default.
- W4304194159 hasAuthorship W4304194159A5064335115 @default.
- W4304194159 hasBestOaLocation W43041941591 @default.
- W4304194159 hasConcept C11413529 @default.
- W4304194159 hasConcept C119599485 @default.
- W4304194159 hasConcept C121332964 @default.
- W4304194159 hasConcept C127413603 @default.
- W4304194159 hasConcept C152769699 @default.
- W4304194159 hasConcept C154945302 @default.
- W4304194159 hasConcept C18051474 @default.
- W4304194159 hasConcept C185592680 @default.
- W4304194159 hasConcept C204328495 @default.
- W4304194159 hasConcept C207467116 @default.
- W4304194159 hasConcept C2524010 @default.
- W4304194159 hasConcept C2776135515 @default.
- W4304194159 hasConcept C2776545253 @default.
- W4304194159 hasConcept C2778112365 @default.
- W4304194159 hasConcept C33923547 @default.
- W4304194159 hasConcept C41008148 @default.
- W4304194159 hasConcept C46141821 @default.
- W4304194159 hasConcept C47701112 @default.
- W4304194159 hasConcept C55493867 @default.
- W4304194159 hasConceptScore W4304194159C11413529 @default.
- W4304194159 hasConceptScore W4304194159C119599485 @default.
- W4304194159 hasConceptScore W4304194159C121332964 @default.
- W4304194159 hasConceptScore W4304194159C127413603 @default.
- W4304194159 hasConceptScore W4304194159C152769699 @default.
- W4304194159 hasConceptScore W4304194159C154945302 @default.
- W4304194159 hasConceptScore W4304194159C18051474 @default.
- W4304194159 hasConceptScore W4304194159C185592680 @default.
- W4304194159 hasConceptScore W4304194159C204328495 @default.
- W4304194159 hasConceptScore W4304194159C207467116 @default.
- W4304194159 hasConceptScore W4304194159C2524010 @default.
- W4304194159 hasConceptScore W4304194159C2776135515 @default.
- W4304194159 hasConceptScore W4304194159C2776545253 @default.
- W4304194159 hasConceptScore W4304194159C2778112365 @default.
- W4304194159 hasConceptScore W4304194159C33923547 @default.
- W4304194159 hasConceptScore W4304194159C41008148 @default.
- W4304194159 hasConceptScore W4304194159C46141821 @default.
- W4304194159 hasConceptScore W4304194159C47701112 @default.
- W4304194159 hasConceptScore W4304194159C55493867 @default.
- W4304194159 hasLocation W43041941591 @default.
- W4304194159 hasOpenAccess W4304194159 @default.
- W4304194159 hasPrimaryLocation W43041941591 @default.
- W4304194159 hasRelatedWork W1971353143 @default.
- W4304194159 hasRelatedWork W2038819579 @default.
- W4304194159 hasRelatedWork W2066074051 @default.
- W4304194159 hasRelatedWork W2121627241 @default.
- W4304194159 hasRelatedWork W2129020329 @default.
- W4304194159 hasRelatedWork W2171412811 @default.
- W4304194159 hasRelatedWork W2329113412 @default.
- W4304194159 hasRelatedWork W2339136810 @default.
- W4304194159 hasRelatedWork W3044593510 @default.
- W4304194159 hasRelatedWork W3126242177 @default.
- W4304194159 isParatext "false" @default.
- W4304194159 isRetracted "false" @default.
- W4304194159 workType "article" @default.