##################################################################
###Estimating TP/TN prediction rates and AUC for mixed proteing###
##################################################################

#######################
###Files description###
#######################
TP_full.txt - true positives validation set. Contains CADD/PP2/SIFT scores and fixed predictions of all new HGMD (professional version, experimentally validated DM category) missense mutations data that was not used to generate MSC. 

FP_full.txt - false positives validation set. Contains CADD/PP2/SIFT scores and fixed predictions of all private missense variants in WES data of 97 patients for which the disease-causing mutation was previously experimentally validated and published, and removed from the set.

match*.py - python scripts to extract TP/TN predictions for the different methods and protein sets.

FP_MSC*.txt - FP input for ROC curves and prediction rates estimate, generated by match_FP*.py.

TP_MSC*.txt - TP input for ROC curves and prediction rates estimate, generated by match_TP*.py.

mixed_genes.txt - all validation set's "mixed proteins" genes.

04-06_genes.txt - all validation set's "mixed proteins with 04-06 ratio" genes.

ROC_CADD2_mixed_all.r - generating ROC curves and AUC estimates based on FP_MSC*.txt and TP_MSC*.txt files for "mixed proteins".

ROC_CADD2_mixed_04-06.r - generating ROC curves and AUC estimates based on FP_MSC*.txt and TP_MSC*.txt files for "mixed proteins with 04-06 ratio".

Prediction_rates_mixed_full - summary of TP/TN prediction rates for "mixed proteins".

Prediction_rates_mixed_04-06 - summary of TP/TN prediction rates for "mixed proteins with 04-06 ratio".

AUC_mixed_all - summary of AUC for "mixed proteins".

AUC_mixed_all - summary of AUC for "mixed proteins with 04-06 ratio".

ROC_mixed_all.pdf - ROC curve figure for "mixed proteins".

ROC_mixed_04-06.pdf - ROC curve figure for "mixed proteins with 04-06 ratio".