Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386565977> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4386565977 endingPage "15" @default.
- W4386565977 startingPage "8" @default.
- W4386565977 abstract "Protein-ligand interaction (PLI) is a critical step for drug discovery. Recently, protein pretrained language models (PLMs) have showcased exceptional performance across a wide range of protein-related tasks. However, a significant heterogeneity exists between the PLM and PLI tasks, leading to a degree of uncertainty. In this study, we propose a method that quantitatively assesses the significance of protein PLMs in PLI prediction. Specifically, we analyze the performance of three widely-used protein PLMs (TAPE, ESM-1b, and ProtTrans) on three PLI tasks (PDBbind, Kinase, and DUD-E). The model with pre-training consistently achieves improved performance and decreased time cost, demonstrating that enhance both the accuracy and efficiency of PLI prediction. By quantitatively assessing the transferability, the optimal PLM for each PLI task is identified without the need for costly transfer experiments. Additionally, we examine the contributions of PLMs on the distribution of feature space, highlighting the improved discriminability after pre-training. Our findings provide insights into the mechanisms underlying PLMs in PLI prediction and pave the way for the design of more interpretable and accurate PLMs in the future. Code and data are freely available at https://github.com/brian-zZZ/PLM-PLI." @default.
- W4386565977 created "2023-09-10" @default.
- W4386565977 creator A5016796771 @default.
- W4386565977 creator A5017001198 @default.
- W4386565977 creator A5040027560 @default.
- W4386565977 creator A5080862674 @default.
- W4386565977 date "2023-11-01" @default.
- W4386565977 modified "2023-10-17" @default.
- W4386565977 title "Does protein pretrained language model facilitate the prediction of protein-ligand interaction?" @default.
- W4386565977 cites W1968319881 @default.
- W4386565977 cites W2092285329 @default.
- W4386565977 cites W2157331557 @default.
- W4386565977 cites W2194775991 @default.
- W4386565977 cites W2781821160 @default.
- W4386565977 cites W2785947426 @default.
- W4386565977 cites W2790808809 @default.
- W4386565977 cites W2899788782 @default.
- W4386565977 cites W2964206522 @default.
- W4386565977 cites W2968734407 @default.
- W4386565977 cites W3028589594 @default.
- W4386565977 cites W3104705366 @default.
- W4386565977 cites W3106340866 @default.
- W4386565977 cites W3127104022 @default.
- W4386565977 cites W3133458480 @default.
- W4386565977 cites W3156083564 @default.
- W4386565977 cites W3177500196 @default.
- W4386565977 cites W4205773061 @default.
- W4386565977 cites W4294875307 @default.
- W4386565977 doi "https://doi.org/10.1016/j.ymeth.2023.08.016" @default.
- W4386565977 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37690736" @default.
- W4386565977 hasPublicationYear "2023" @default.
- W4386565977 type Work @default.
- W4386565977 citedByCount "0" @default.
- W4386565977 crossrefType "journal-article" @default.
- W4386565977 hasAuthorship W4386565977A5016796771 @default.
- W4386565977 hasAuthorship W4386565977A5017001198 @default.
- W4386565977 hasAuthorship W4386565977A5040027560 @default.
- W4386565977 hasAuthorship W4386565977A5080862674 @default.
- W4386565977 hasConcept C119857082 @default.
- W4386565977 hasConcept C138885662 @default.
- W4386565977 hasConcept C140331021 @default.
- W4386565977 hasConcept C154945302 @default.
- W4386565977 hasConcept C162324750 @default.
- W4386565977 hasConcept C187736073 @default.
- W4386565977 hasConcept C2776401178 @default.
- W4386565977 hasConcept C2780451532 @default.
- W4386565977 hasConcept C41008148 @default.
- W4386565977 hasConcept C41895202 @default.
- W4386565977 hasConcept C51632099 @default.
- W4386565977 hasConcept C61272859 @default.
- W4386565977 hasConcept C70721500 @default.
- W4386565977 hasConcept C86803240 @default.
- W4386565977 hasConceptScore W4386565977C119857082 @default.
- W4386565977 hasConceptScore W4386565977C138885662 @default.
- W4386565977 hasConceptScore W4386565977C140331021 @default.
- W4386565977 hasConceptScore W4386565977C154945302 @default.
- W4386565977 hasConceptScore W4386565977C162324750 @default.
- W4386565977 hasConceptScore W4386565977C187736073 @default.
- W4386565977 hasConceptScore W4386565977C2776401178 @default.
- W4386565977 hasConceptScore W4386565977C2780451532 @default.
- W4386565977 hasConceptScore W4386565977C41008148 @default.
- W4386565977 hasConceptScore W4386565977C41895202 @default.
- W4386565977 hasConceptScore W4386565977C51632099 @default.
- W4386565977 hasConceptScore W4386565977C61272859 @default.
- W4386565977 hasConceptScore W4386565977C70721500 @default.
- W4386565977 hasConceptScore W4386565977C86803240 @default.
- W4386565977 hasFunder F4320321001 @default.
- W4386565977 hasFunder F4320321133 @default.
- W4386565977 hasFunder F4320326705 @default.
- W4386565977 hasFunder F4320335777 @default.
- W4386565977 hasFunder F4320336026 @default.
- W4386565977 hasFunder F4320337111 @default.
- W4386565977 hasLocation W43865659771 @default.
- W4386565977 hasLocation W43865659772 @default.
- W4386565977 hasOpenAccess W4386565977 @default.
- W4386565977 hasPrimaryLocation W43865659771 @default.
- W4386565977 hasRelatedWork W2081647779 @default.
- W4386565977 hasRelatedWork W2961085424 @default.
- W4386565977 hasRelatedWork W3046775127 @default.
- W4386565977 hasRelatedWork W3170094116 @default.
- W4386565977 hasRelatedWork W4285260836 @default.
- W4386565977 hasRelatedWork W4286629047 @default.
- W4386565977 hasRelatedWork W4306321456 @default.
- W4386565977 hasRelatedWork W4306674287 @default.
- W4386565977 hasRelatedWork W4372266204 @default.
- W4386565977 hasRelatedWork W4224009465 @default.
- W4386565977 hasVolume "219" @default.
- W4386565977 isParatext "false" @default.
- W4386565977 isRetracted "false" @default.
- W4386565977 workType "article" @default.