FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4367366132> ?p ?o ?g. }

• W4367366132 abstract "Abstract Morphological profiling is a powerful technology that enables unbiased characterization of cellular states through image-based screening. Inspired by recent progress in self-supervised learning (SSL), we sought to explore the potential benefits of using SSL in this domain and conducted a comprehensive benchmark study of recent SSL methods for learning representations from Cell Painting images without segmentation. We trained DINO, MAE, and SimCLR on subsets of the JUMP-CP consortium data, one of the largest publicly available Cell Painting image sets, and observed improved model performance with larger and more heterogeneous training sets. Our best model (DINO) surpassed the widely used profiling tool CellProfiler by 29% in mean average precision (mAP) on classifying chemical perturbations and significantly accelerated feature extraction by 50x, at a lower cost. Moreover, DINO outperformed CellProfiler in clustering gene families on an independent gene overexpression dataset. Our findings indicate that SSL methods can improve the efficiency and performance of morphological profiling, offering the potential to expedite drug discovery and reduce compute costs." @default.
• W4367366132 created "2023-04-30" @default.
• W4367366132 creator A5008365398 @default.
• W4367366132 creator A5031519705 @default.
• W4367366132 creator A5049867936 @default.
• W4367366132 creator A5055709980 @default.
• W4367366132 creator A5082993419 @default.
• W4367366132 date "2023-04-29" @default.
• W4367366132 modified "2023-10-06" @default.
• W4367366132 title "Self-supervision advances morphological profiling by unlocking powerful image representations" @default.
• W4367366132 cites W1185588434 @default.
• W4367366132 cites W1965092590 @default.
• W4367366132 cites W1972748508 @default.
• W4367366132 cites W1987971958 @default.
• W4367366132 cites W2012746420 @default.
• W4367366132 cites W2108303909 @default.
• W4367366132 cites W2144963196 @default.
• W4367366132 cites W2167279371 @default.
• W4367366132 cites W2183389629 @default.
• W4367366132 cites W2321533354 @default.
• W4367366132 cites W2337926734 @default.
• W4367366132 cites W2340102874 @default.
• W4367366132 cites W2509141893 @default.
• W4367366132 cites W2548971603 @default.
• W4367366132 cites W2596519089 @default.
• W4367366132 cites W2605025138 @default.
• W4367366132 cites W2728842897 @default.
• W4367366132 cites W2751625431 @default.
• W4367366132 cites W2807209585 @default.
• W4367366132 cites W2811106513 @default.
• W4367366132 cites W2971686199 @default.
• W4367366132 cites W2975634117 @default.
• W4367366132 cites W2984472267 @default.
• W4367366132 cites W2998120965 @default.
• W4367366132 cites W3016970897 @default.
• W4367366132 cites W3023371261 @default.
• W4367366132 cites W3034781633 @default.
• W4367366132 cites W3035524453 @default.
• W4367366132 cites W3136205387 @default.
• W4367366132 cites W3159481202 @default.
• W4367366132 cites W3172942063 @default.
• W4367366132 cites W3182677297 @default.
• W4367366132 cites W3195203505 @default.
• W4367366132 cites W4205733013 @default.
• W4367366132 cites W4220809164 @default.
• W4367366132 cites W4225598893 @default.
• W4367366132 cites W4232866872 @default.
• W4367366132 cites W4287510106 @default.
• W4367366132 cites W4291666467 @default.
• W4367366132 cites W4297977478 @default.
• W4367366132 cites W4312742553 @default.
• W4367366132 cites W4312891522 @default.
• W4367366132 cites W4313156423 @default.
• W4367366132 cites W4360951525 @default.
• W4367366132 doi "https://doi.org/10.1101/2023.04.28.538691" @default.
• W4367366132 hasPublicationYear "2023" @default.
• W4367366132 type Work @default.
• W4367366132 citedByCount "3" @default.
• W4367366132 countsByYear W43673661322023 @default.
• W4367366132 crossrefType "posted-content" @default.
• W4367366132 hasAuthorship W4367366132A5008365398 @default.
• W4367366132 hasAuthorship W4367366132A5031519705 @default.
• W4367366132 hasAuthorship W4367366132A5049867936 @default.
• W4367366132 hasAuthorship W4367366132A5055709980 @default.
• W4367366132 hasAuthorship W4367366132A5082993419 @default.
• W4367366132 hasBestOaLocation W43673661321 @default.
• W4367366132 hasConcept C111919701 @default.
• W4367366132 hasConcept C119857082 @default.
• W4367366132 hasConcept C124101348 @default.
• W4367366132 hasConcept C153180895 @default.
• W4367366132 hasConcept C154945302 @default.
• W4367366132 hasConcept C185798385 @default.
• W4367366132 hasConcept C187191949 @default.
• W4367366132 hasConcept C205649164 @default.
• W4367366132 hasConcept C41008148 @default.
• W4367366132 hasConcept C58640448 @default.
• W4367366132 hasConcept C73555534 @default.
• W4367366132 hasConcept C89600930 @default.
• W4367366132 hasConceptScore W4367366132C111919701 @default.
• W4367366132 hasConceptScore W4367366132C119857082 @default.
• W4367366132 hasConceptScore W4367366132C124101348 @default.
• W4367366132 hasConceptScore W4367366132C153180895 @default.
• W4367366132 hasConceptScore W4367366132C154945302 @default.
• W4367366132 hasConceptScore W4367366132C185798385 @default.
• W4367366132 hasConceptScore W4367366132C187191949 @default.
• W4367366132 hasConceptScore W4367366132C205649164 @default.
• W4367366132 hasConceptScore W4367366132C41008148 @default.
• W4367366132 hasConceptScore W4367366132C58640448 @default.
• W4367366132 hasConceptScore W4367366132C73555534 @default.
• W4367366132 hasConceptScore W4367366132C89600930 @default.
• W4367366132 hasLocation W43673661321 @default.
• W4367366132 hasOpenAccess W4367366132 @default.
• W4367366132 hasPrimaryLocation W43673661321 @default.
• W4367366132 hasRelatedWork W112744582 @default.
• W4367366132 hasRelatedWork W1485630101 @default.
• W4367366132 hasRelatedWork W2145546708 @default.
• W4367366132 hasRelatedWork W2348361596 @default.
• W4367366132 hasRelatedWork W2498017833 @default.
• W4367366132 hasRelatedWork W2961085424 @default.
• W4367366132 hasRelatedWork W3208517261 @default.

• next