Trick is to rely on cheaper to measure, but genetically informative phenotypes with tons of variables that allow for effective use of machine learning methods. A kind of middle way. Presumably works well because fewer variables than full marker set of genotypes.
Selection on 'endogenotypes' outperform selection on genotypes? https://www.biorxiv.org/content/early/2018/04/16/302117 … #genomicspic.twitter.com/6mI5vUGh2a
-
-
This Tweet is unavailable.
-
-
And that the useful predictors are less rare among the chemical or spectrometer variables than among the genotypes, for which only like 1 in 100k is relevant or something which requires a lot of penalization to avoid overfitting.
End of conversation
-
-
-
Comparison of Genotypic and Phenotypic Correlations: Cheverud’s Conjecture in Humanshttps://www.biorxiv.org/content/early/2018/03/30/291062 …
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.