############### # Supplementary Code 2 # Estimation of the number of known human complexes derived by HT methods # Programming language: R v.2.15.2 # Written by: Antonio Mora (antoniocmora@gmail.com) # May. 2013 ############### # The following piece of code uses the iRefR R package to estimate the number of known human complexes derived by High-Throughput (HT) methods. The list of complexes comes from iRefIndex, which consolidates 13 primary protein interaction databases. We assume that interactions reported in papers with an lpr-score > 22 correspond to HT experiments. For more information regarding the lpr-score, refer to: Mora, A., Donaldson, I., iRefR: an R package to manipulate the iRefIndex consolidated protein interaction database, BMC Bioinformatics. 2011; 12: 455 library(iRefR) irefindex_curr_human = get_irefindex("9606", "9.0", getwd()) # 401140 records human_human_list = data.frame(irefindex_curr_human$taxa, irefindex_curr_human$taxb) tmp = do.call(`paste`, c(unname(human_human_list), list(sep="."))) irefindex_curr_hh = irefindex_curr_human[tmp=="taxid:9606(Homo sapiens).taxid:9606(Homo sapiens)" | tmp=="-.taxid:9606(Homo sapiens)",] irefindex_curr_hh = irefindex_curr_hh[-which(irefindex_curr_hh$edgetype=="X" & (as.character(irefindex_curr_hh[,1])==as.character(irefindex_curr_hh[,2]))==TRUE),] # 347753 records MITAB_complex = select_interaction_type("complex", irefindex_curr_hh) # 58854 LT_complex = select_confidence("lpr", c(1:22), MITAB_complex) # 33503 percentage_HT = (dim(MITAB_complex) - dim(LT_complex)) / dim(MITAB_complex) # 0.431