Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287207811> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W4287207811 abstract "To enable personalized cancer treatment, machine learning models have been developed to predict drug response as a function of tumor and drug features. However, most algorithm development efforts have relied on cross validation within a single study to assess model accuracy. While an essential first step, cross validation within a biological data set typically provides an overly optimistic estimate of the prediction performance on independent test sets. To provide a more rigorous assessment of model generalizability between different studies, we use machine learning to analyze five publicly available cell line-based data sets: NCI60, CTRP, GDSC, CCLE and gCSI. Based on observed experimental variability across studies, we explore estimates of prediction upper bounds. We report performance results of a variety of machine learning models, with a multitasking deep neural network achieving the best cross-study generalizability. By multiple measures, models trained on CTRP yield the most accurate predictions on the remaining testing data, and gCSI is the most predictable among the cell line data sets included in this study. With these experiments and further simulations on partial data, two lessons emerge: (1) differences in viability assays can limit model generalizability across studies, and (2) drug diversity, more than tumor diversity, is crucial for raising model generalizability in preclinical screening." @default.
- W4287207811 created "2022-07-25" @default.
- W4287207811 creator A5003294409 @default.
- W4287207811 creator A5017591427 @default.
- W4287207811 creator A5017932766 @default.
- W4287207811 creator A5018962507 @default.
- W4287207811 creator A5020370754 @default.
- W4287207811 creator A5020776475 @default.
- W4287207811 creator A5023060808 @default.
- W4287207811 creator A5035849909 @default.
- W4287207811 creator A5039059226 @default.
- W4287207811 creator A5039869327 @default.
- W4287207811 creator A5040025864 @default.
- W4287207811 creator A5041200743 @default.
- W4287207811 creator A5044153234 @default.
- W4287207811 creator A5044581351 @default.
- W4287207811 creator A5046241574 @default.
- W4287207811 creator A5046675967 @default.
- W4287207811 creator A5049471852 @default.
- W4287207811 creator A5052430047 @default.
- W4287207811 creator A5053682943 @default.
- W4287207811 creator A5065877660 @default.
- W4287207811 creator A5068721920 @default.
- W4287207811 creator A5086975677 @default.
- W4287207811 creator A5088879250 @default.
- W4287207811 creator A5090753616 @default.
- W4287207811 date "2021-04-18" @default.
- W4287207811 modified "2023-09-26" @default.
- W4287207811 title "A cross-study analysis of drug response prediction in cancer cell lines" @default.
- W4287207811 hasPublicationYear "2021" @default.
- W4287207811 type Work @default.
- W4287207811 citedByCount "0" @default.
- W4287207811 crossrefType "posted-content" @default.
- W4287207811 hasAuthorship W4287207811A5003294409 @default.
- W4287207811 hasAuthorship W4287207811A5017591427 @default.
- W4287207811 hasAuthorship W4287207811A5017932766 @default.
- W4287207811 hasAuthorship W4287207811A5018962507 @default.
- W4287207811 hasAuthorship W4287207811A5020370754 @default.
- W4287207811 hasAuthorship W4287207811A5020776475 @default.
- W4287207811 hasAuthorship W4287207811A5023060808 @default.
- W4287207811 hasAuthorship W4287207811A5035849909 @default.
- W4287207811 hasAuthorship W4287207811A5039059226 @default.
- W4287207811 hasAuthorship W4287207811A5039869327 @default.
- W4287207811 hasAuthorship W4287207811A5040025864 @default.
- W4287207811 hasAuthorship W4287207811A5041200743 @default.
- W4287207811 hasAuthorship W4287207811A5044153234 @default.
- W4287207811 hasAuthorship W4287207811A5044581351 @default.
- W4287207811 hasAuthorship W4287207811A5046241574 @default.
- W4287207811 hasAuthorship W4287207811A5046675967 @default.
- W4287207811 hasAuthorship W4287207811A5049471852 @default.
- W4287207811 hasAuthorship W4287207811A5052430047 @default.
- W4287207811 hasAuthorship W4287207811A5053682943 @default.
- W4287207811 hasAuthorship W4287207811A5065877660 @default.
- W4287207811 hasAuthorship W4287207811A5068721920 @default.
- W4287207811 hasAuthorship W4287207811A5086975677 @default.
- W4287207811 hasAuthorship W4287207811A5088879250 @default.
- W4287207811 hasAuthorship W4287207811A5090753616 @default.
- W4287207811 hasBestOaLocation W42872078111 @default.
- W4287207811 hasConcept C105795698 @default.
- W4287207811 hasConcept C107418235 @default.
- W4287207811 hasConcept C119857082 @default.
- W4287207811 hasConcept C124101348 @default.
- W4287207811 hasConcept C154945302 @default.
- W4287207811 hasConcept C15744967 @default.
- W4287207811 hasConcept C180747234 @default.
- W4287207811 hasConcept C27158222 @default.
- W4287207811 hasConcept C33923547 @default.
- W4287207811 hasConcept C41008148 @default.
- W4287207811 hasConceptScore W4287207811C105795698 @default.
- W4287207811 hasConceptScore W4287207811C107418235 @default.
- W4287207811 hasConceptScore W4287207811C119857082 @default.
- W4287207811 hasConceptScore W4287207811C124101348 @default.
- W4287207811 hasConceptScore W4287207811C154945302 @default.
- W4287207811 hasConceptScore W4287207811C15744967 @default.
- W4287207811 hasConceptScore W4287207811C180747234 @default.
- W4287207811 hasConceptScore W4287207811C27158222 @default.
- W4287207811 hasConceptScore W4287207811C33923547 @default.
- W4287207811 hasConceptScore W4287207811C41008148 @default.
- W4287207811 hasLocation W42872078111 @default.
- W4287207811 hasOpenAccess W4287207811 @default.
- W4287207811 hasPrimaryLocation W42872078111 @default.
- W4287207811 hasRelatedWork W10719664 @default.
- W4287207811 hasRelatedWork W12165144 @default.
- W4287207811 hasRelatedWork W13536281 @default.
- W4287207811 hasRelatedWork W15008681 @default.
- W4287207811 hasRelatedWork W1549441 @default.
- W4287207811 hasRelatedWork W193554 @default.
- W4287207811 hasRelatedWork W317670 @default.
- W4287207811 hasRelatedWork W3989876 @default.
- W4287207811 hasRelatedWork W6266756 @default.
- W4287207811 hasRelatedWork W8198582 @default.
- W4287207811 isParatext "false" @default.
- W4287207811 isRetracted "false" @default.
- W4287207811 workType "article" @default.