search

CRI-iAtlas / ImmuneSubtypeClassifier

An R package for classification of immune subtypes, in cancer, using gene expression data.
Other
40 stars 23 forks source link

input data #12

Closed crispinhiley closed 3 years ago

crispinhiley commented 3 years ago

many thanks for providing this helpful package. Can you tell me what the input values should be for the matrix. Raw counts? TPM etc? I see from the previous version you say it is sensitive to this. Would be grateful for advice

Gibbsdavidl commented 3 years ago

Hi, thanks! It shouldn't really matter anymore. For the most part it's based on comparing pairs of genes within a sample. if G1 > G2 then feature = 1 else feature = 0. Then those features are used in prediction. Also, there's a couple features that are also found within sample like quartile. is gene in the upper quartile? feature = 4, etc. I really need to finish up this paper, but see: https://www.biorxiv.org/content/10.1101/2020.01.17.910950v1

crispinhiley commented 3 years ago

thanks so much for replying so quickly. will have a look

Crispin