proteinClassification: working on...

In PengyiYang/ReFraction: A machine learning approach for deterministic identification of protein homologues and splice variants in large-scale MS-based proteomics

Usage

proteinClassification(peptide, svm_model, protein.weight, protein.length, protein.tryptic, protein.pI)

Arguments

peptide
svm_model
protein.weight
protein.length
protein.tryptic
protein.pI

Examples

##---- Should be DIRECTLY executable !! ----
##-- ==>  Define data, use random,
##--	or do  help(data=index)  for the standard data sets.

## The function is currently defined as
function (peptide, svm_model, protein.weight, protein.length, 
    protein.tryptic, protein.pI) 
{
    all.proteins <- unique(unlist(strsplit(as.character(peptide[, 
        "Proteins"]), ";")))
    all.proteins <- all.proteins[-grep("CON__", all.proteins)]
    all.proteins.df <- data.frame(cbind(protein.weight[all.proteins], 
        protein.length[all.proteins], protein.tryptic[all.proteins], 
        protein.pI[all.proteins]))
    rownames(all.proteins.df) <- all.proteins
    protein.regressed <- as.numeric(predict(svm_model, all.proteins.df))
    names(protein.regressed) <- all.proteins
    result <- list()
    result$regressed <- protein.regressed
    return(result)
  }

PengyiYang/ReFraction documentation built on May 14, 2019, 11:01 p.m.