Additional file 4 of Machine-learning analysis reveals an important role for negative selection in shaping cancer aneuploidy landscapes
dataset
posted on 2024-08-15, 06:15 authored by Juman Jubran, Rachel Slutsky, Nir Rozenblum, Lior Rokach, Uri Ben-David, Esti Yeger-LotemAdditional file 4: Table S3. SHAP value per feature of each instance of chromosome-arm and tumor type in the gain and loss models.
Funding
Israel Science Foundation Ben-Gurion University Grant European Research Council Starting Grant BSF Project Grant Israel Cancer Research Fund European Molecular Biology Organization
History
Usage metrics
Categories
Keywords
one paralog interactionlearning analysis revealsdefine 20 typesconfirming known drivers24 cancer typesquantitative analysis highlightscancer cell linesshaping aneuploidy landscapesselective aneuploidy patternsmachine learning modelsaneuploidy landscapesselective featuresaneuploidy researchcolon cancercancer developmentvice versatop predictorsrevealing klf5relative contributionprimary tumorspositive selectiononcogene densitynormal tissuesnegative selectionmodel gainsloss patternsimportant roleimportant driverhuman cclsgenomic propertiesgenomic attributesgain patternsfully understoodfind compensationfeatures correspondingchromosomes withinchr13q gainccls ),better predictoralso identifyabnormal number
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC