CTPR#
CTPR (Cross-Trait / Cross-eThnic Penalized Regression) software was originally developed for multi-trait polygenic risk prediction in large cohorts.
Installation#
Kindly follow the tutorial on CTPR User Manual. We used the single-node version of the program rather than the MPI version.
Steps:#
git clone https://github.com/wonilchung/CTPR.git
cd CTPR
tar -xvf ctpr_v1.1.tar.gz
It also requires the installation of the Armadillo package. Kindly follow the steps mentioned on the GitHub page for proper installation and to make a binary for execution.
Hyperparameters#
CTPR relies on multiple packages for deployment on the HPC. Kindly see their reference manual for the details.
Parameter |
Description |
|---|---|
|
Specify output file prefix |
|
Specify dosage file name for training |
|
Specify dosage file extension for training |
|
Specify phenotype file name for training |
|
Specify dosage file name for testing |
|
Specify dosage file extension for testing |
|
Specify phenotype file name for testing |
|
Specify summary file name |
|
Specify summary file extension |
|
Specify the number of phenotypes to be analyzed (default 1) |
|
Specify the number of phenotypes for summary file (default 1) |
|
Specify the numbers of individuals for each phenotype separated by comma (,) in case of multiple phenotypes |
|
Specify the sparsity and cross-trait penalty terms (default 1; 1: Lasso+CTPR; 2: MCP+CTPR) |
|
Specify the number of folds for coordinate descent algorithm (default 5) |
|
Specify proportion of maximum number of non-zero beta (default 0.25) |
|
Specify value for lambda2. If negative value is specified, pre-specified values are used for lambda2 (default -3) |
|
Specify the number of group for MPI mode (default number of MPI nodes) |
|
Specify starting number for MPI files (default 1) |
|
Specify first lambda1 value for MPI mode (default 1) |
|
Specify last lambda1 value for MPI mode (default 100) |
One can specify multiple phenotypes in the phenotype file:
cat samplepheno1.phe | head
-0.0673626135013302 1.8464940664358
0.646335121166089 -0.0718774023739188
0.703839528318071 -0.8078024587687
0.649845260428667 1.61553139091436
-0.50586431843169 -0.454187152936928
0.0449914961045604 -1.46231427204292
0.452109847431944 -0.47829601507506
0.278056622918757 -0.979195320053136
-1.03353595441191 0.414327259623864
1.63628995738167 2.02778714134248
However, we considered only one phenotype. Including more phenotypes can improve performance, and one can specify multiple phenotypes for individuals in the phenotype file.
You need to pass multiple GWAS datasets in the following format:
summary.txt (no header line; columns are marker name, minor allele frequency, beta1, se1, beta2, se2...)
1 0.43139 0.01826 0.01195 0.03643 0.01533
2 0.67261 -0.00978 0.01205 -0.02564 0.01536
3 0.67029 -0.00969 0.01195 0.03246 0.01364
4 0.33718 0.00069 0.01218 -0.02464 0.01467
Here, 1, 2, 3, and 4 are the marker names.
Execution.#
./ctpr \\
--out ./res/test \\
--dos final_5000_train.dose \\
--phe final_pheno_5000_train.phe \\
--dos-test final_5000_test.dose \\
--phe-test final_5000_test.phe \\
--separ-ind 7400,7400 \\
--penalty 1 \\
--lambda2 0
GWAS file processing for CTPR#
When the effect size relates to disease risk and is thus given as an odds ratio (OR) rather than BETA (for continuous traits), the PRS is computed as a product of ORs. To simplify this calculation, take the natural logarithm of the OR so that the PRS can be computed using summation instead.
import os
import pandas as pd
import numpy as np
import sys
#filedirec = sys.argv[1]
filedirec = "SampleData1"
#filedirec = "asthma_19"
#filedirec = "migraine_0"
def check_phenotype_is_binary_or_continous(filedirec):
# Read the processed quality controlled file for a phenotype
df = pd.read_csv(filedirec+os.sep+filedirec+'_QC.fam',sep="\s+",header=None)
column_values = df[5].unique()
if len(set(column_values)) == 2:
return "Binary"
else:
return "Continous"
GWAS = filedirec + os.sep + filedirec+".gz"
df = pd.read_csv(GWAS,compression= "gzip",sep="\s+")
print(df.head().to_markdown())
df.to_csv(filedirec + os.sep +filedirec+".txt",sep="\t",index=False)
if "BETA" in df.columns.to_list():
# For Continous Phenotype.
df = df[['CHR', 'BP', 'SNP', 'A1', 'A2', 'N', 'SE', 'P', 'BETA', 'INFO', 'MAF']]
else:
df["BETA"] = np.log(df["OR"])
df["SE"] = df["SE"]/df["OR"]
df = df[['CHR', 'BP', 'SNP', 'A1', 'A2', 'N', 'SE', 'P', 'BETA', 'INFO', 'MAF']]
print(df.head().to_markdown())
transformed_df = pd.DataFrame({
'markername': df['CHR'].astype(str)+":"+df['BP'].astype(str)+'_' + df['A1'] + '_' + df['A2'],
'maf': df['MAF'],
'beta1': df['BETA'],
'se1': df['SE'],
# For other phenotypes one can specific the betas and se here. but we used CTPR for one Phenotype.
#'beta2': original_df['BETA'],
#'se2': original_df['SE'],
'rsid': df['SNP']
})
transformed_df.to_csv(filedirec + os.sep +filedirec+".ctpr",sep="\t",index=False)
print(transformed_df.head().to_markdown())
| | CHR | BP | SNP | A1 | A2 | N | SE | P | OR | INFO | MAF |
|---:|------:|-------:|:-----------|:-----|:-----|-------:|-----------:|---------:|---------:|---------:|---------:|
| 0 | 1 | 756604 | rs3131962 | A | G | 388028 | 0.00301666 | 0.483171 | 0.997887 | 0.890558 | 0.36939 |
| 1 | 1 | 768448 | rs12562034 | A | G | 388028 | 0.00329472 | 0.834808 | 1.00069 | 0.895894 | 0.336846 |
| 2 | 1 | 779322 | rs4040617 | G | A | 388028 | 0.00303344 | 0.42897 | 0.997604 | 0.897508 | 0.377368 |
| 3 | 1 | 801536 | rs79373928 | G | T | 388028 | 0.00841324 | 0.808999 | 1.00204 | 0.908963 | 0.483212 |
| 4 | 1 | 808631 | rs11240779 | G | A | 388028 | 0.00242821 | 0.590265 | 1.00131 | 0.893213 | 0.45041 |
| | CHR | BP | SNP | A1 | A2 | N | SE | P | BETA | INFO | MAF |
|---:|------:|-------:|:-----------|:-----|:-----|-------:|-----------:|---------:|------------:|---------:|---------:|
| 0 | 1 | 756604 | rs3131962 | A | G | 388028 | 0.00302305 | 0.483171 | -0.00211532 | 0.890558 | 0.36939 |
| 1 | 1 | 768448 | rs12562034 | A | G | 388028 | 0.00329246 | 0.834808 | 0.00068708 | 0.895894 | 0.336846 |
| 2 | 1 | 779322 | rs4040617 | G | A | 388028 | 0.00304073 | 0.42897 | -0.00239932 | 0.897508 | 0.377368 |
| 3 | 1 | 801536 | rs79373928 | G | T | 388028 | 0.00839615 | 0.808999 | 0.00203363 | 0.908963 | 0.483212 |
| 4 | 1 | 808631 | rs11240779 | G | A | 388028 | 0.00242504 | 0.590265 | 0.00130747 | 0.893213 | 0.45041 |
| | markername | maf | beta1 | se1 | rsid |
|---:|:-------------|---------:|------------:|-----------:|:-----------|
| 0 | 1:756604_A_G | 0.36939 | -0.00211532 | 0.00302305 | rs3131962 |
| 1 | 1:768448_A_G | 0.336846 | 0.00068708 | 0.00329246 | rs12562034 |
| 2 | 1:779322_G_A | 0.377368 | -0.00239932 | 0.00304073 | rs4040617 |
| 3 | 1:801536_G_T | 0.483212 | 0.00203363 | 0.00839615 | rs79373928 |
| 4 | 1:808631_G_A | 0.45041 | 0.00130747 | 0.00242504 | rs11240779 |
Define Hyperparameters#
Define hyperparameters to be optimized and set initial values.
Extract Valid SNPs from Clumped File#
For Windows, download gwak, and for Linux, the awk command is sufficient. For Windows, GWAK is required. You can download it from here. Get it and place it in the same directory.
Execution Path#
At this stage, we have the genotype training data newtrainfilename = "train_data.QC" and genotype test data newtestfilename = "test_data.QC".
We modified the following variables:
filedirec = "SampleData1"orfiledirec = sys.argv[1]foldnumber = "0"orfoldnumber = sys.argv[2]for HPC.
Only these two variables can be modified to execute the code for specific data and specific folds. Though the code can be executed separately for each fold on HPC and separately for each dataset, it is recommended to execute it for multiple diseases and one fold at a time. Here’s the corrected text in Markdown format:
P-values#
PRS calculation relies on P-values. SNPs with low P-values, indicating a high degree of association with a specific trait, are considered for calculation.
You can modify the code below to consider a specific set of P-values and save the file in the same format.
We considered the following parameters:
Minimum P-value:
1e-10Maximum P-value:
1.0Minimum exponent:
10(Minimum P-value in exponent)Number of intervals:
100(Number of intervals to be considered)
The code generates an array of logarithmically spaced P-values:
import numpy as np
import os
minimumpvalue = 10 # Minimum exponent for P-values
numberofintervals = 100 # Number of intervals to be considered
allpvalues = np.logspace(-minimumpvalue, 0, numberofintervals, endpoint=True) # Generating an array of logarithmically spaced P-values
print("Minimum P-value:", allpvalues[0])
print("Maximum P-value:", allpvalues[-1])
count = 1
with open(os.path.join(folddirec, 'range_list'), 'w') as file:
for value in allpvalues:
file.write(f'pv_{value} 0 {value}\n') # Writing range information to the 'range_list' file
count += 1
pvaluefile = os.path.join(folddirec, 'range_list')
In this code:
minimumpvaluedefines the minimum exponent for P-values.numberofintervalsspecifies how many intervals to consider.allpvaluesgenerates an array of P-values spaced logarithmically.The script writes these P-values to a file named
range_listin the specified directory.
from operator import index
import pandas as pd
import numpy as np
import os
import subprocess
import sys
import pandas as pd
import statsmodels.api as sm
import pandas as pd
from sklearn.metrics import roc_auc_score, confusion_matrix
from statsmodels.stats.contingency_tables import mcnemar
def create_directory(directory):
"""Function to create a directory if it doesn't exist."""
if not os.path.exists(directory): # Checking if the directory doesn't exist
os.makedirs(directory) # Creating the directory if it doesn't exist
return directory # Returning the created or existing directory
#foldnumber = sys.argv[1]
foldnumber = "0" # Setting 'foldnumber' to "0"
folddirec = filedirec + os.sep + "Fold_" + foldnumber # Creating a directory path for the specific fold
trainfilename = "train_data" # Setting the name of the training data file
newtrainfilename = "train_data.QC" # Setting the name of the new training data file
testfilename = "test_data" # Setting the name of the test data file
newtestfilename = "test_data.QC" # Setting the name of the new test data file
# Number of PCA to be included as a covariate.
numberofpca = ["6"] # Setting the number of PCA components to be included
# Clumping parameters.
clump_p1 = [1] # List containing clump parameter 'p1'
clump_r2 = [0.1] # List containing clump parameter 'r2'
clump_kb = [200] # List containing clump parameter 'kb'
# Pruning parameters.
p_window_size = [200] # List containing pruning parameter 'window_size'
p_slide_size = [50] # List containing pruning parameter 'slide_size'
p_LD_threshold = [0.25] # List containing pruning parameter 'LD_threshold'
# Kindly note that the number of p-values to be considered varies, and the actual p-value depends on the dataset as well.
# We will specify the range list here.
minimumpvalue = 10 # Minimum p-value in exponent
numberofintervals = 20 # Number of intervals to be considered
allpvalues = np.logspace(-minimumpvalue, 0, numberofintervals, endpoint=True) # Generating an array of logarithmically spaced p-values
count = 1
with open(folddirec + os.sep + 'range_list', 'w') as file:
for value in allpvalues:
file.write(f'pv_{value} 0 {value}\n') # Writing range information to the 'range_list' file
count = count + 1
pvaluefile = folddirec + os.sep + 'range_list'
# Initializing an empty DataFrame with specified column names
prs_result = pd.DataFrame(columns=["clump_p1", "clump_r2", "clump_kb", "p_window_size", "p_slide_size", "p_LD_threshold",
"pvalue", "numberofpca","numberofvariants","Train_pure_prs", "Train_null_model", "Train_best_model",
"Test_pure_prs", "Test_null_model", "Test_best_model"])
Define Helper Functions#
Perform Clumping and Pruning
Calculate PCA Using Plink
Fit Binary Phenotype and Save Results
Fit Continuous Phenotype and Save Results
import os
import subprocess
import pandas as pd
import statsmodels.api as sm
from sklearn.metrics import explained_variance_score
def perform_clumping_and_pruning_on_individual_data(traindirec, newtrainfilename,numberofpca, p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile):
command = [
"./plink",
"--bfile", traindirec+os.sep+newtrainfilename,
"--indep-pairwise", p1_val, p2_val, p3_val,
"--out", traindirec+os.sep+trainfilename
]
subprocess.run(command)
# First perform pruning and then clumping and the pruning.
command = [
"./plink",
"--bfile", traindirec+os.sep+newtrainfilename,
"--clump-p1", c1_val,
"--extract", traindirec+os.sep+trainfilename+".prune.in",
"--clump-r2", c2_val,
"--clump-kb", c3_val,
"--clump", filedirec+os.sep+filedirec+".txt",
"--clump-snp-field", "SNP",
"--clump-field", "P",
"--out", traindirec+os.sep+trainfilename
]
subprocess.run(command)
# Extract the valid SNPs from th clumped file.
# For windows download gwak for linux awk commmand is sufficient.
### For windows require GWAK.
### https://sourceforge.net/projects/gnuwin32/
##3 Get it and place it in the same direc.
#os.system("gawk "+"\""+"NR!=1{print $3}"+"\" "+ traindirec+os.sep+trainfilename+".clumped > "+traindirec+os.sep+trainfilename+".valid.snp")
#print("gawk "+"\""+"NR!=1{print $3}"+"\" "+ traindirec+os.sep+trainfilename+".clumped > "+traindirec+os.sep+trainfilename+".valid.snp")
#Linux:
command = f"awk 'NR!=1{{print $3}}' {traindirec}{os.sep}{trainfilename}.clumped > {traindirec}{os.sep}{trainfilename}.valid.snp"
os.system(command)
command = [
"./plink",
"--make-bed",
"--bfile", traindirec+os.sep+newtrainfilename,
"--indep-pairwise", p1_val, p2_val, p3_val,
"--extract", traindirec+os.sep+trainfilename+".valid.snp",
"--out", traindirec+os.sep+newtrainfilename+".clumped.pruned"
]
subprocess.run(command)
command = [
"./plink",
"--make-bed",
"--bfile", traindirec+os.sep+testfilename,
"--indep-pairwise", p1_val, p2_val, p3_val,
"--extract", traindirec+os.sep+trainfilename+".valid.snp",
"--out", traindirec+os.sep+testfilename+".clumped.pruned"
]
subprocess.run(command)
def calculate_pca_for_traindata_testdata_for_clumped_pruned_snps(traindirec, newtrainfilename,p):
# Calculate the PRS for the test data using the same set of SNPs and also calculate the PCA.
# Also extract the PCA at this point.
# PCA are calculated afer clumping and pruining.
command = [
"./plink",
"--bfile", folddirec+os.sep+testfilename+".clumped.pruned",
# Select the final variants after clumping and pruning.
"--extract", traindirec+os.sep+trainfilename+".valid.snp",
"--pca", p,
"--out", folddirec+os.sep+testfilename
]
subprocess.run(command)
command = [
"./plink",
"--bfile", traindirec+os.sep+newtrainfilename+".clumped.pruned",
# Select the final variants after clumping and pruning.
"--extract", traindirec+os.sep+trainfilename+".valid.snp",
"--pca", p,
"--out", traindirec+os.sep+trainfilename
]
subprocess.run(command)
# This function fit the binary model on the PRS.
def fit_binary_phenotype_on_PRS(traindirec, newtrainfilename,p, p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile,f,lambdaa,penalty,withoutsum):
threshold_values = allpvalues
# Merge the covariates, pca and phenotypes.
tempphenotype_train = pd.read_table(traindirec+os.sep+newtrainfilename+".clumped.pruned"+".fam", sep="\s+",header=None)
phenotype_train = pd.DataFrame()
phenotype_train["Phenotype"] = tempphenotype_train[5].values
pcs_train = pd.read_table(traindirec+os.sep+trainfilename+".eigenvec", sep="\s+",header=None, names=["FID", "IID"] + [f"PC{str(i)}" for i in range(1, int(p)+1)])
covariate_train = pd.read_table(traindirec+os.sep+trainfilename+".cov",sep="\s+")
covariate_train.fillna(0, inplace=True)
covariate_train = covariate_train[covariate_train["FID"].isin(pcs_train["FID"].values) & covariate_train["IID"].isin(pcs_train["IID"].values)]
covariate_train['FID'] = covariate_train['FID'].astype(str)
pcs_train['FID'] = pcs_train['FID'].astype(str)
covariate_train['IID'] = covariate_train['IID'].astype(str)
pcs_train['IID'] = pcs_train['IID'].astype(str)
covandpcs_train = pd.merge(covariate_train, pcs_train, on=["FID","IID"])
covandpcs_train.fillna(0, inplace=True)
## Scale the covariates!
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import explained_variance_score
scaler = MinMaxScaler()
normalized_values_train = scaler.fit_transform(covandpcs_train.iloc[:, 2:])
#covandpcs_train.iloc[:, 2:] = normalized_values_test
tempphenotype_test = pd.read_table(traindirec+os.sep+testfilename+".clumped.pruned"+".fam", sep="\s+",header=None)
phenotype_test= pd.DataFrame()
phenotype_test["Phenotype"] = tempphenotype_test[5].values
pcs_test = pd.read_table(traindirec+os.sep+testfilename+".eigenvec", sep="\s+",header=None, names=["FID", "IID"] + [f"PC{str(i)}" for i in range(1, int(p)+1)])
covariate_test = pd.read_table(traindirec+os.sep+testfilename+".cov",sep="\s+")
covariate_test.fillna(0, inplace=True)
covariate_test = covariate_test[covariate_test["FID"].isin(pcs_test["FID"].values) & covariate_test["IID"].isin(pcs_test["IID"].values)]
covariate_test['FID'] = covariate_test['FID'].astype(str)
pcs_test['FID'] = pcs_test['FID'].astype(str)
covariate_test['IID'] = covariate_test['IID'].astype(str)
pcs_test['IID'] = pcs_test['IID'].astype(str)
covandpcs_test = pd.merge(covariate_test, pcs_test, on=["FID","IID"])
covandpcs_test.fillna(0, inplace=True)
normalized_values_test = scaler.transform(covandpcs_test.iloc[:, 2:])
#covandpcs_test.iloc[:, 2:] = normalized_values_test
tempalphas = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]
l1weights = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]
tempalphas = [0.1]
l1weights = [0.1]
phenotype_train["Phenotype"] = phenotype_train["Phenotype"].replace({1: 0, 2: 1})
phenotype_test["Phenotype"] = phenotype_test["Phenotype"].replace({1: 0, 2: 1})
for tempalpha in tempalphas:
for l1weight in l1weights:
try:
null_model = sm.Logit(phenotype_train["Phenotype"], sm.add_constant(covandpcs_train.iloc[:, 2:])).fit_regularized(alpha=tempalpha, L1_wt=l1weight)
#null_model = sm.Logit(phenotype_train["Phenotype"], sm.add_constant(covandpcs_train.iloc[:, 2:])).fit()
except:
print("XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX")
continue
train_null_predicted = null_model.predict(sm.add_constant(covandpcs_train.iloc[:, 2:]))
from sklearn.metrics import roc_auc_score, confusion_matrix
from sklearn.metrics import r2_score
test_null_predicted = null_model.predict(sm.add_constant(covandpcs_test.iloc[:, 2:]))
global prs_result
for i in threshold_values:
try:
prs_train = pd.read_table(traindirec+os.sep+Name+os.sep+"train_data.pv_"+f"{i}.profile", sep="\s+", usecols=["FID", "IID", "SCORE"])
except:
continue
prs_train['FID'] = prs_train['FID'].astype(str)
prs_train['IID'] = prs_train['IID'].astype(str)
try:
prs_test = pd.read_table(traindirec+os.sep+Name+os.sep+"test_data.pv_"+f"{i}.profile", sep="\s+", usecols=["FID", "IID", "SCORE"])
except:
continue
prs_test['FID'] = prs_test['FID'].astype(str)
prs_test['IID'] = prs_test['IID'].astype(str)
pheno_prs_train = pd.merge(covandpcs_train, prs_train, on=["FID", "IID"])
pheno_prs_test = pd.merge(covandpcs_test, prs_test, on=["FID", "IID"])
try:
model = sm.Logit(phenotype_train["Phenotype"], sm.add_constant(pheno_prs_train.iloc[:, 2:])).fit_regularized(alpha=tempalpha, L1_wt=l1weight)
#model = sm.Logit(phenotype_train["Phenotype"], sm.add_constant(pheno_prs_train.iloc[:, 2:])).fit()
except:
continue
train_best_predicted = model.predict(sm.add_constant(pheno_prs_train.iloc[:, 2:]))
test_best_predicted = model.predict(sm.add_constant(pheno_prs_test.iloc[:, 2:]))
from sklearn.metrics import roc_auc_score, confusion_matrix
prs_result = prs_result._append({
"clump_p1": c1_val,
"clump_r2": c2_val,
"clump_kb": c3_val,
"p_window_size": p1_val,
"p_slide_size": p2_val,
"p_LD_threshold": p3_val,
"pvalue": i,
"numberofpca":p,
"tempalpha":str(tempalpha),
"l1weight":str(l1weight),
#"numberofvariants": len(pd.read_csv(traindirec+os.sep+newtrainfilename+".clumped.pruned.bim")),
"CTPR_f":str(f),
"CTPR_lamda":str(lambdaa),
"CTPR_penalty":str(penalty),
"CTPR_withoutsum":str(withoutsum),
"Train_pure_prs":roc_auc_score(phenotype_train["Phenotype"].values,prs_train['SCORE'].values),
"Train_null_model":roc_auc_score(phenotype_train["Phenotype"].values,train_null_predicted.values),
"Train_best_model":roc_auc_score(phenotype_train["Phenotype"].values,train_best_predicted.values),
"Test_pure_prs":roc_auc_score(phenotype_test["Phenotype"].values,prs_test['SCORE'].values),
"Test_null_model":roc_auc_score(phenotype_test["Phenotype"].values,test_null_predicted.values),
"Test_best_model":roc_auc_score(phenotype_test["Phenotype"].values,test_best_predicted.values),
}, ignore_index=True)
prs_result.to_csv(traindirec+os.sep+Name+os.sep+"Results.csv",index=False)
return
# This function fit the binary model on the PRS.
def fit_continous_phenotype_on_PRS(traindirec, newtrainfilename,p, p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile,f,lambdaa,penalty,withoutsum):
threshold_values = allpvalues
# Merge the covariates, pca and phenotypes.
tempphenotype_train = pd.read_table(traindirec+os.sep+newtrainfilename+".clumped.pruned"+".fam", sep="\s+",header=None)
phenotype_train = pd.DataFrame()
phenotype_train["Phenotype"] = tempphenotype_train[5].values
pcs_train = pd.read_table(traindirec+os.sep+trainfilename+".eigenvec", sep="\s+",header=None, names=["FID", "IID"] + [f"PC{str(i)}" for i in range(1, int(p)+1)])
covariate_train = pd.read_table(traindirec+os.sep+trainfilename+".cov",sep="\s+")
covariate_train.fillna(0, inplace=True)
covariate_train = covariate_train[covariate_train["FID"].isin(pcs_train["FID"].values) & covariate_train["IID"].isin(pcs_train["IID"].values)]
covariate_train['FID'] = covariate_train['FID'].astype(str)
pcs_train['FID'] = pcs_train['FID'].astype(str)
covariate_train['IID'] = covariate_train['IID'].astype(str)
pcs_train['IID'] = pcs_train['IID'].astype(str)
covandpcs_train = pd.merge(covariate_train, pcs_train, on=["FID","IID"])
covandpcs_train.fillna(0, inplace=True)
## Scale the covariates!
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import explained_variance_score
scaler = MinMaxScaler()
normalized_values_train = scaler.fit_transform(covandpcs_train.iloc[:, 2:])
#covandpcs_train.iloc[:, 2:] = normalized_values_test
tempphenotype_test = pd.read_table(traindirec+os.sep+testfilename+".clumped.pruned"+".fam", sep="\s+",header=None)
phenotype_test= pd.DataFrame()
phenotype_test["Phenotype"] = tempphenotype_test[5].values
pcs_test = pd.read_table(traindirec+os.sep+testfilename+".eigenvec", sep="\s+",header=None, names=["FID", "IID"] + [f"PC{str(i)}" for i in range(1, int(p)+1)])
covariate_test = pd.read_table(traindirec+os.sep+testfilename+".cov",sep="\s+")
covariate_test.fillna(0, inplace=True)
covariate_test = covariate_test[covariate_test["FID"].isin(pcs_test["FID"].values) & covariate_test["IID"].isin(pcs_test["IID"].values)]
covariate_test['FID'] = covariate_test['FID'].astype(str)
pcs_test['FID'] = pcs_test['FID'].astype(str)
covariate_test['IID'] = covariate_test['IID'].astype(str)
pcs_test['IID'] = pcs_test['IID'].astype(str)
covandpcs_test = pd.merge(covariate_test, pcs_test, on=["FID","IID"])
covandpcs_test.fillna(0, inplace=True)
normalized_values_test = scaler.transform(covandpcs_test.iloc[:, 2:])
#covandpcs_test.iloc[:, 2:] = normalized_values_test
tempalphas = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]
l1weights = [0.1,0.2,0.3,0.4,0.5,0.6,0.7,0.8,0.9]
tempalphas = [0.1]
l1weights = [0.1]
#phenotype_train["Phenotype"] = phenotype_train["Phenotype"].replace({1: 0, 2: 1})
#phenotype_test["Phenotype"] = phenotype_test["Phenotype"].replace({1: 0, 2: 1})
for tempalpha in tempalphas:
for l1weight in l1weights:
try:
#null_model = sm.OLS(phenotype_train["Phenotype"], sm.add_constant(covandpcs_train.iloc[:, 2:])).fit_regularized(alpha=tempalpha, L1_wt=l1weight)
null_model = sm.OLS(phenotype_train["Phenotype"], sm.add_constant(covandpcs_train.iloc[:, 2:])).fit()
#null_model = sm.OLS(phenotype_train["Phenotype"], sm.add_constant(covandpcs_train.iloc[:, 2:])).fit()
except:
print("XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX")
continue
train_null_predicted = null_model.predict(sm.add_constant(covandpcs_train.iloc[:, 2:]))
from sklearn.metrics import roc_auc_score, confusion_matrix
from sklearn.metrics import r2_score
test_null_predicted = null_model.predict(sm.add_constant(covandpcs_test.iloc[:, 2:]))
global prs_result
for i in threshold_values:
try:
prs_train = pd.read_table(traindirec+os.sep+Name+os.sep+"train_data.pv_"+f"{i}.profile", sep="\s+", usecols=["FID", "IID", "SCORE"])
except:
continue
prs_train['FID'] = prs_train['FID'].astype(str)
prs_train['IID'] = prs_train['IID'].astype(str)
try:
prs_test = pd.read_table(traindirec+os.sep+Name+os.sep+"test_data.pv_"+f"{i}.profile", sep="\s+", usecols=["FID", "IID", "SCORE"])
except:
continue
prs_test['FID'] = prs_test['FID'].astype(str)
prs_test['IID'] = prs_test['IID'].astype(str)
pheno_prs_train = pd.merge(covandpcs_train, prs_train, on=["FID", "IID"])
pheno_prs_test = pd.merge(covandpcs_test, prs_test, on=["FID", "IID"])
try:
#model = sm.OLS(phenotype_train["Phenotype"], sm.add_constant(pheno_prs_train.iloc[:, 2:])).fit_regularized(alpha=tempalpha, L1_wt=l1weight)
model = sm.OLS(phenotype_train["Phenotype"], sm.add_constant(pheno_prs_train.iloc[:, 2:])).fit()
except:
continue
train_best_predicted = model.predict(sm.add_constant(pheno_prs_train.iloc[:, 2:]))
test_best_predicted = model.predict(sm.add_constant(pheno_prs_test.iloc[:, 2:]))
from sklearn.metrics import roc_auc_score, confusion_matrix
prs_result = prs_result._append({
"clump_p1": c1_val,
"clump_r2": c2_val,
"clump_kb": c3_val,
"p_window_size": p1_val,
"p_slide_size": p2_val,
"p_LD_threshold": p3_val,
"pvalue": i,
"numberofpca":p,
"tempalpha":str(tempalpha),
"l1weight":str(l1weight),
#"numberofvariants": len(pd.read_csv(traindirec+os.sep+newtrainfilename+".clumped.pruned.bim")),
"CTPR_f":str(f),
"CTPR_lamda":str(lambdaa),
"CTPR_penalty":str(penalty),
"CTPR_withoutsum":str(withoutsum),
"Train_pure_prs":explained_variance_score(phenotype_train["Phenotype"],prs_train['SCORE'].values),
"Train_null_model":explained_variance_score(phenotype_train["Phenotype"],train_null_predicted),
"Train_best_model":explained_variance_score(phenotype_train["Phenotype"],train_best_predicted),
"Test_pure_prs":explained_variance_score(phenotype_test["Phenotype"],prs_test['SCORE'].values),
"Test_null_model":explained_variance_score(phenotype_test["Phenotype"],test_null_predicted),
"Test_best_model":explained_variance_score(phenotype_test["Phenotype"],test_best_predicted),
}, ignore_index=True)
prs_result.to_csv(traindirec+os.sep+Name+os.sep+"Results.csv",index=False)
return
Execute CTPR#
# Define a global variable to store results
prs_result = pd.DataFrame()
def transform_ctpr_data(traindirec, newtrainfilename,numberofpca,f,lambdaa,penalty,withoutsum, p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile):
### First perform clumping on the file and save the clumpled file.
perform_clumping_and_pruning_on_individual_data(traindirec, newtrainfilename,p, p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile)
#newtrainfilename = newtrainfilename+".clumped.pruned"
#testfilename = testfilename+".clumped.pruned"
#clupmedfile = traindirec+os.sep+newtrainfilename+".clump"
#prunedfile = traindirec+os.sep+newtrainfilename+".clumped.pruned"
# Also extract the PCA at this point for both test and training data.
calculate_pca_for_traindata_testdata_for_clumped_pruned_snps(traindirec, newtrainfilename,p)
#Extract p-values from the GWAS file.
# Command for Linux.
os.system("awk "+"\'"+"{print $3,$8}"+"\'"+" ./"+filedirec+os.sep+filedirec+".txt > ./"+traindirec+os.sep+"SNP.pvalue")
# Command for windows.
### For windows get GWAK.
### https://sourceforge.net/projects/gnuwin32/
##3 Get it and place it in the same direc.
#os.system("gawk "+"\""+"{print $3,$8}"+"\""+" ./"+filedirec+os.sep+filedirec+".txt > ./"+traindirec+os.sep+"SNP.pvalue")
#print("gawk "+"\""+"{print $3,$8}"+"\""+" ./"+filedirec+os.sep+filedirec+".txt > ./"+traindirec+os.sep+"SNP.pvalue")
#exit(0)
# Delete files generated in the previous iteration.
files_to_remove = [
traindirec+os.sep+"CTPR.beta",
]
# Loop through the files and directories and remove them if they exist
for file_path in files_to_remove:
if os.path.exists(file_path):
if os.path.isfile(file_path):
os.remove(file_path)
print(f"Removed file: {file_path}")
elif os.path.isdir(file_path):
shutil.rmtree(file_path)
print(f"Removed directory: {file_path}")
else:
print(f"File or directory does not exist: {file_path}")
# Here we are going to transform the data for CTPR.
# It except the data in dosage information.
# We recoded the genotype data using Plink.
bfile = traindirec+os.sep+newtrainfilename+".clumped.pruned"
famfile = traindirec+os.sep+newtrainfilename+".clumped.pruned"+".fam"
plink_command = [
"./plink",
"--bfile", bfile,
"--keep",famfile,
"--recodeA",
"--out", traindirec+os.sep+newtrainfilename+".clumped.pruned"+"_CTPR"
]
# CTPR needs data in dosage form.
subprocess.run(plink_command)
prunedfile = traindirec+os.sep+newtrainfilename+".clumped.pruned"+"_CTPR"
# Remove header, replace, NA with 0, and remove '' from the file.
os.system("cut -d "+"'"+" "+"'"+" -f 7- "+ prunedfile+".raw" +" | tail -n +2 | sed 's/NA/0/g' > "+prunedfile+".CTPR")
# Convert the space into tabs in the file.
os.system("awk '{gsub(/ /,"+"\""+"\t"+"\""+"); print}' "+prunedfile+".CTPR > "+ prunedfile+".dose")
# Transform the GWAS.
bim = pd.read_csv(traindirec+os.sep+newtrainfilename+".clumped.pruned"+".bim",header=None,sep="\s+")[1].values
gwas = pd.read_csv(filedirec+os.sep+filedirec+".ctpr",sep="\s+")
# Here we have to ensure that the number of SNPs in the GWAS and bim file are the same.
gwas = gwas[gwas["rsid"].isin(bim)]
del gwas["rsid"]
#print(gwas.head())
#exit(0)
#gwas = gwas[gwas["CHR"].isin([22])]
#gwas = gwas[['MAF','OR','SE']]
#gwas["OR"] = np.log(gwas["OR"])
#gwas['OR'] = np.(gwas['OR']).replace({np.nan: 0})
#gwas.reset_index(drop=True, inplace=True)
#gwas.index += 1
gwas.to_csv(traindirec+os.sep+filedirec+".ctprnew",sep="\t",header=False,index=False)
print(len(gwas))
print(gwas.head())
#exit(0)
# Transform the Phenotype file.
pheno = pd.read_csv(traindirec+os.sep+newtrainfilename+".clumped.pruned"+".fam",sep="\s+",header=None)
# Kindly note, we have t
pheno[5].to_csv(traindirec+os.sep+trainfilename+"_CTPR.phe",index=False,header = False)
#exit(0)
if withoutsum==True:
command = [
'./CTPR/ctpr', # Replace with the actual executable or script you are running
'--out', traindirec+os.sep+"CTPR",
'--dos', prunedfile+".dose",
'--nfold',str(f),
'--lambda2',str(lambdaa),
'--phe', traindirec+os.sep+trainfilename+"_CTPR.phe",
'--num-phe', '1',
'--penalty',str(penalty)
]
#print(" ".join(command))
os.system("LD_LIBRARY_PATH=/data/ascher01/uqmmune1/miniconda3/envs/genetics/lib/ " + " ".join(command))
else:
command = [
'./CTPR/ctpr', # Replace with the actual executable or script you are running
'--out', traindirec+os.sep+"CTPR",
'--dos', prunedfile+".dose",
'--nfold',str(f),
'--lambda2',str(lambdaa),
'--phe', traindirec+os.sep+trainfilename+"_CTPR.phe",
'--sum', traindirec+os.sep+filedirec+".ctprnew",
'--num-phe', '1',
'--penalty',str(penalty)
]
#print(" ".join(command))
os.system("LD_LIBRARY_PATH=/data/ascher01/uqmmune1/miniconda3/envs/genetics/lib/ " + " ".join(command))
try:
newbeta = pd.read_csv(traindirec+os.sep+"CTPR.beta",sep="\s+",header=None)
except:
print("GWAS not generated!")
return
df = pd.read_csv(filedirec + os.sep + filedirec+".gz",compression= "gzip",sep="\s+")
gwas = pd.read_csv(traindirec+os.sep+filedirec+".ctprnew",sep="\t",header=None)
df["marker"] = df['CHR'].astype(str)+":"+df['BP'].astype(str)+'_' + df['A1'].astype(str) + '_' + df['A2'].astype(str)
print(df["marker"])
print(gwas[0])
df = df[df["marker"].isin(gwas[0].values)]
df["newbeta"] = newbeta[0].values[1:]
del df["marker"]
print(df.head())
df = df.iloc[:,[2,3,11]]
if check_phenotype_is_binary_or_continous(filedirec)=="Binary":
df["newbeta"] = np.exp(df["newbeta"])
df["newbeta"].replace([np.inf, -np.inf], 0, inplace=True)
df["newbeta"].fillna(0, inplace=True)
else:
pass
print(df.iloc[:,[0,1,2]])
df.iloc[:,[0,1,2]].to_csv(traindirec+os.sep+".finalctpr",sep="\t",index=False)
# Caluclate Plink Score.
command = [
"./plink",
"--bfile", traindirec+os.sep+newtrainfilename+".clumped.pruned",
### SNP column = 3, Effect allele column 1 = 4, OR column=9
"--score", traindirec+os.sep+".finalctpr", "1", "2", "3", "header",
"--q-score-range", traindirec+os.sep+"range_list",traindirec+os.sep+"SNP.pvalue",
"--extract", traindirec+os.sep+trainfilename+".valid.snp",
"--out", traindirec+os.sep+Name+os.sep+trainfilename
]
#exit(0)
subprocess.run(command)
command = [
"./plink",
"--bfile", folddirec+os.sep+testfilename+".clumped.pruned",
### SNP column = 3, Effect allele column 1 = 4, Beta column=12
"--score", traindirec+os.sep+".finalctpr", "1", "2", "3", "header",
"--q-score-range", traindirec+os.sep+"range_list",traindirec+os.sep+"SNP.pvalue",
"--extract", traindirec+os.sep+trainfilename+".valid.snp",
"--out", folddirec+os.sep+Name+os.sep+testfilename
]
subprocess.run(command)
# At this stage the scores are finalizied.
# The next step is to fit the model and find the explained variance by each profile.
# Load the PCA and Load the Covariates for trainingdatafirst.
if check_phenotype_is_binary_or_continous(filedirec)=="Binary":
print("Binary Phenotype!")
fit_binary_phenotype_on_PRS(traindirec, newtrainfilename,p, p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile,f,lambdaa,penalty,withoutsum)
else:
print("Continous Phenotype!")
fit_continous_phenotype_on_PRS(traindirec, newtrainfilename,p, p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile,f,lambdaa,penalty,withoutsum)
result_directory = "ctpr"
create_directory(folddirec+os.sep+result_directory)
folds = [ 5]
lambdaas = [-1,-2]
penalties = [1,2]
withoutsums =[True,False]
folds = [ 5]
lambdaas = [-1]
penalties = [1]
withoutsums =[True]
for p1_val in p_window_size:
for p2_val in p_slide_size:
for p3_val in p_LD_threshold:
for c1_val in clump_p1:
for c2_val in clump_r2:
for c3_val in clump_kb:
for p in numberofpca:
for f in folds:
for lambdaa in lambdaas:
for penalty in penalties:
for withoutsum in withoutsums:
transform_ctpr_data(folddirec, newtrainfilename, p,f,lambdaa,penalty, withoutsum,str(p1_val), str(p2_val), str(p3_val), str(c1_val), str(c2_val), str(c3_val), result_directory, pvaluefile)
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/train_data.log.
Options in effect:
--bfile SampleData1/Fold_0/train_data.QC
--indep-pairwise 200 50 0.25
--out SampleData1/Fold_0/train_data
63761 MB RAM detected; reserving 31880 MB for main workspace.
491952 variants loaded from .bim file.
380 people (183 males, 197 females) loaded from .fam.
380 phenotype values loaded from .fam.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 380 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is 0.999894.
491952 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
Pruned 18860 variants from chromosome 1, leaving 20363.
Pruned 19645 variants from chromosome 2, leaving 20067.
Pruned 16414 variants from chromosome 3, leaving 17080.
Pruned 15404 variants from chromosome 4, leaving 16035.
Pruned 14196 variants from chromosome 5, leaving 15379.
Pruned 19368 variants from chromosome 6, leaving 14770.
Pruned 13110 variants from chromosome 7, leaving 13997.
Pruned 12431 variants from chromosome 8, leaving 12966.
Pruned 9982 variants from chromosome 9, leaving 11477.
Pruned 11999 variants from chromosome 10, leaving 12850.
Pruned 12156 variants from chromosome 11, leaving 12221.
Pruned 10979 variants from chromosome 12, leaving 12050.
Pruned 7923 variants from chromosome 13, leaving 9247.
Pruned 7624 variants from chromosome 14, leaving 8448.
Pruned 7387 variants from chromosome 15, leaving 8145.
Pruned 8063 variants from chromosome 16, leaving 8955.
Pruned 7483 variants from chromosome 17, leaving 8361.
Pruned 6767 variants from chromosome 18, leaving 8240.
Pruned 6438 variants from chromosome 19, leaving 6432.
Pruned 5972 variants from chromosome 20, leaving 7202.
Pruned 3426 variants from chromosome 21, leaving 4102.
Pruned 3801 variants from chromosome 22, leaving 4137.
Pruning complete. 239428 of 491952 variants removed.
Marker lists written to SampleData1/Fold_0/train_data.prune.in and
SampleData1/Fold_0/train_data.prune.out .
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/train_data.log.
Options in effect:
--bfile SampleData1/Fold_0/train_data.QC
--clump SampleData1/SampleData1.txt
--clump-field P
--clump-kb 200
--clump-p1 1
--clump-r2 0.1
--clump-snp-field SNP
--extract SampleData1/Fold_0/train_data.prune.in
--out SampleData1/Fold_0/train_data
63761 MB RAM detected; reserving 31880 MB for main workspace.
491952 variants loaded from .bim file.
380 people (183 males, 197 females) loaded from .fam.
380 phenotype values loaded from .fam.
--extract: 252524 variants remaining.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 380 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is 0.999894.
252524 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--clump: 172878 clumps formed from 252524 top variants.
Results written to SampleData1/Fold_0/train_data.clumped .
Warning: 'rs3134762' is missing from the main dataset, and is a top variant.
Warning: 'rs3132505' is missing from the main dataset, and is a top variant.
Warning: 'rs3130424' is missing from the main dataset, and is a top variant.
247090 more top variant IDs missing; see log file.
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/train_data.QC.clumped.pruned.log.
Options in effect:
--bfile SampleData1/Fold_0/train_data.QC
--extract SampleData1/Fold_0/train_data.valid.snp
--indep-pairwise 200 50 0.25
--make-bed
--out SampleData1/Fold_0/train_data.QC.clumped.pruned
63761 MB RAM detected; reserving 31880 MB for main workspace.
491952 variants loaded from .bim file.
380 people (183 males, 197 females) loaded from .fam.
380 phenotype values loaded from .fam.
--extract: 172878 variants remaining.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 380 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is 0.999891.
172878 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--make-bed to SampleData1/Fold_0/train_data.QC.clumped.pruned.bed +
SampleData1/Fold_0/train_data.QC.clumped.pruned.bim +
SampleData1/Fold_0/train_data.QC.clumped.pruned.fam ... 101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899done.
Pruned 2 variants from chromosome 1, leaving 14011.
Pruned 2 variants from chromosome 2, leaving 13811.
Pruned 2 variants from chromosome 3, leaving 11783.
Pruned 0 variants from chromosome 4, leaving 11041.
Pruned 1 variant from chromosome 5, leaving 10631.
Pruned 50 variants from chromosome 6, leaving 10018.
Pruned 0 variants from chromosome 7, leaving 9496.
Pruned 4 variants from chromosome 8, leaving 8863.
Pruned 0 variants from chromosome 9, leaving 7768.
Pruned 5 variants from chromosome 10, leaving 8819.
Pruned 10 variants from chromosome 11, leaving 8410.
Pruned 0 variants from chromosome 12, leaving 8198.
Pruned 0 variants from chromosome 13, leaving 6350.
Pruned 1 variant from chromosome 14, leaving 5741.
Pruned 0 variants from chromosome 15, leaving 5569.
Pruned 2 variants from chromosome 16, leaving 6067.
Pruned 1 variant from chromosome 17, leaving 5722.
Pruned 0 variants from chromosome 18, leaving 5578.
Pruned 0 variants from chromosome 19, leaving 4364.
Pruned 0 variants from chromosome 20, leaving 4916.
Pruned 0 variants from chromosome 21, leaving 2811.
Pruned 0 variants from chromosome 22, leaving 2831.
Pruning complete. 80 of 172878 variants removed.
Marker lists written to
SampleData1/Fold_0/train_data.QC.clumped.pruned.prune.in and
SampleData1/Fold_0/train_data.QC.clumped.pruned.prune.out .
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/test_data.clumped.pruned.log.
Options in effect:
--bfile SampleData1/Fold_0/test_data
--extract SampleData1/Fold_0/train_data.valid.snp
--indep-pairwise 200 50 0.25
--make-bed
--out SampleData1/Fold_0/test_data.clumped.pruned
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (44 males, 51 females) loaded from .fam.
95 phenotype values loaded from .fam.
--extract: 172878 variants remaining.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 95 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is 0.999891.
172878 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--make-bed to SampleData1/Fold_0/test_data.clumped.pruned.bed +
SampleData1/Fold_0/test_data.clumped.pruned.bim +
SampleData1/Fold_0/test_data.clumped.pruned.fam ... 101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899done.
Pruned 1829 variants from chromosome 1, leaving 12184.
Pruned 1861 variants from chromosome 2, leaving 11952.
Pruned 1567 variants from chromosome 3, leaving 10218.
Pruned 1415 variants from chromosome 4, leaving 9626.
Pruned 1347 variants from chromosome 5, leaving 9285.
Pruned 1291 variants from chromosome 6, leaving 8777.
Pruned 1238 variants from chromosome 7, leaving 8258.
Pruned 1144 variants from chromosome 8, leaving 7723.
Pruned 902 variants from chromosome 9, leaving 6866.
Pruned 1090 variants from chromosome 10, leaving 7734.
Pruned 1036 variants from chromosome 11, leaving 7384.
Pruned 1061 variants from chromosome 12, leaving 7137.
Pruned 771 variants from chromosome 13, leaving 5579.
Pruned 683 variants from chromosome 14, leaving 5059.
Pruned 603 variants from chromosome 15, leaving 4966.
Pruned 710 variants from chromosome 16, leaving 5359.
Pruned 605 variants from chromosome 17, leaving 5118.
Pruned 648 variants from chromosome 18, leaving 4930.
Pruned 384 variants from chromosome 19, leaving 3980.
Pruned 559 variants from chromosome 20, leaving 4357.
Pruned 297 variants from chromosome 21, leaving 2514.
Pruned 276 variants from chromosome 22, leaving 2555.
Pruning complete. 21317 of 172878 variants removed.
Marker lists written to SampleData1/Fold_0/test_data.clumped.pruned.prune.in
and SampleData1/Fold_0/test_data.clumped.pruned.prune.out .
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/test_data.log.
Options in effect:
--bfile SampleData1/Fold_0/test_data.clumped.pruned
--extract SampleData1/Fold_0/train_data.valid.snp
--out SampleData1/Fold_0/test_data
--pca 6
63761 MB RAM detected; reserving 31880 MB for main workspace.
172878 variants loaded from .bim file.
95 people (44 males, 51 females) loaded from .fam.
95 phenotype values loaded from .fam.
--extract: 172878 variants remaining.
Using up to 8 threads (change this with --threads).
Before main variant filters, 95 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is 0.999891.
172878 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
Relationship matrix calculation complete.
--pca: Results saved to SampleData1/Fold_0/test_data.eigenval and
SampleData1/Fold_0/test_data.eigenvec .
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/train_data.log.
Options in effect:
--bfile SampleData1/Fold_0/train_data.QC.clumped.pruned
--extract SampleData1/Fold_0/train_data.valid.snp
--out SampleData1/Fold_0/train_data
--pca 6
63761 MB RAM detected; reserving 31880 MB for main workspace.
172878 variants loaded from .bim file.
380 people (183 males, 197 females) loaded from .fam.
380 phenotype values loaded from .fam.
--extract: 172878 variants remaining.
Using up to 8 threads (change this with --threads).
Before main variant filters, 380 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is 0.999891.
172878 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
Relationship matrix calculation complete.
--pca: Results saved to SampleData1/Fold_0/train_data.eigenval and
SampleData1/Fold_0/train_data.eigenvec .
File or directory does not exist: SampleData1/Fold_0/CTPR.beta
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Note: --recodeA flag deprecated. Use "--recode A ...".
Logging to SampleData1/Fold_0/train_data.QC.clumped.pruned_CTPR.log.
Options in effect:
--bfile SampleData1/Fold_0/train_data.QC.clumped.pruned
--keep SampleData1/Fold_0/train_data.QC.clumped.pruned.fam
--out SampleData1/Fold_0/train_data.QC.clumped.pruned_CTPR
--recode A
63761 MB RAM detected; reserving 31880 MB for main workspace.
172878 variants loaded from .bim file.
380 people (183 males, 197 females) loaded from .fam.
380 phenotype values loaded from .fam.
--keep: 380 people remaining.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 380 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is 0.999891.
172878 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--recode A to SampleData1/Fold_0/train_data.QC.clumped.pruned_CTPR.raw ...
101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899done.
172878
markername maf beta1 se1
3 1:801536_G_T 0.483212 0.002034 0.008396
8 1:840753_C_T 0.498936 -0.002658 0.002079
9 1:849998_A_G 0.435377 0.003237 0.002638
11 1:851390_T_G 0.432960 0.013190 0.005034
14 1:862772_G_A 0.417471 -0.011314 0.005959
**************************************************************
* CTPR v1.1 January 29 2019
* Cross-Trait Penalized Regression
* Cross-eThnic Penalized Regression
* Developed by Wonil Chung
**************************************************************
Visit https://github.com/wonilchung/CTPR for latest updates
Copyright (C) 2017-2019 Wonil Chung
For Help, Type ./ctpr -h or ./ctprmpi -h
**************************************************************
* CTPR v1.1 January 29 2019
* Cross-Trait Penalized Regression
* Cross-eThnic Penalized Regression
* Developed by Wonil Chung
**************************************************************
Visit https://github.com/wonilchung/CTPR for latest updates
Copyright (C) 2017-2019 Wonil Chung
For Help, Type ./ctpr -h or ./ctprmpi -h
CTPR Software is freely available to only academic users.
**************************************************************
PARAMETER ASSIGNMENT
**************************************************************
Command Line Options:
Output File: SampleData1/Fold_0/CTPR
Genotype File for Training: SampleData1/Fold_0/train_data.QC.clumped.pruned_CTPR.dose
Number of Folds: 5
Lambda2 for cross-trait penalty: 0 0.9423 1.6028 3.37931
Phenotype File: SampleData1/Fold_0/train_data_CTPR.phe
Number of Phenotypes to be Analyzed: 1
Penalty Terms: Lasso+CTPR
Current Time: 2024-09-14 22:27:27.000, CPU time used: 0 hours, 0 minutes, 0 seconds
**************************************************************
PRELIMINARY PHENOTYPE/GENOTYPE/SUMMARY FILE CHECK
**************************************************************
Performing basic file check on training genotype data : SampleData1/Fold_0/train_data.QC.clumped.pruned_CTPR.dose
Checking file...
380 samples and 172878 markers found in the file...
Performing basic file check on training phenotype data : SampleData1/Fold_0/train_data_CTPR.phe
Checking file...
380 samples and 1 phenotypes found in the file...
Maximum Number of Non-zero beta: 43219
Initial basic file check on phenotype/genoytype/summary data successful !!!
Current Time: 2024-09-14 22:27:27.000, CPU time used: 0 hours, 0 minutes, 0 seconds
**************************************************************
PARAMETER COMBINATION CHECK
**************************************************************
Current Time: 2024-09-14 22:27:27.000, CPU time used: 0 hours, 0 minutes, 0 seconds
**************************************************************
READING PHENOTYPE FILES
**************************************************************
Examples: Ys(0,0) = 171.256, Ys(0,1) = 171.534
Reading phenotype data successful !!!
**************************************************************
READING GENOTYPE FILES
**************************************************************
Examples: i = 0, Xs(i)(0,0) = 0, Xs(i)(0,1) = 2
Reading genotype data successful !!!
Current Time: 2024-09-14 22:27:38.000, CPU time used: 0 hours, 0 minutes, 11 seconds
**************************************************************
COORDINATE DECENT ALGORITHM
**************************************************************
Current Time: 2024-09-14 22:27:38.000, CPU time used: 0 hours, 0 minutes, 11 seconds
Lasso and CTPR penalties are used...
Determining maximum lambda1...
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Finished!
Current Time: 2024-09-14 22:55:25.000, CPU time used: 0 hours, 27 minutes, 27 seconds
Coordinate decent algorithm process [0] has been finished...
Conduct CV...
Maximum length of lambda1 and lambda2: 101, 4
Current Time: 2024-09-14 22:55:27.000, CPU time used: 0 hours, 27 minutes, 29 seconds
Lasso and CTPR penalties are used...
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Finished!
Current Time: 2024-09-14 23:18:18.000, CPU time used: 0 hours, -21 minutes, -46 seconds
Coordinate decent algorithm process [1] has been finished...
Current Time: 2024-09-14 23:18:54.000, CPU time used: 0 hours, -21 minutes, -9 seconds
Lasso and CTPR penalties are used...
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Finished!
Current Time: 2024-09-14 23:36:40.000, CPU time used: 0 hours, -3 minutes, -28 seconds
Coordinate decent algorithm process [2] has been finished...
Current Time: 2024-09-14 23:37:16.000, CPU time used: 0 hours, -2 minutes, -53 seconds
Lasso and CTPR penalties are used...
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Finished!
Current Time: 2024-09-14 23:56:21.000, CPU time used: 0 hours, 16 minutes, 7 seconds
Coordinate decent algorithm process [3] has been finished...
Current Time: 2024-09-14 23:56:54.000, CPU time used: 0 hours, 16 minutes, 40 seconds
Lasso and CTPR penalties are used...
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Finished!
Current Time: 2024-09-15 00:16:36.000, CPU time used: 0 hours, -35 minutes, -17 seconds
Coordinate decent algorithm process [4] has been finished...
Current Time: 2024-09-15 00:17:12.000, CPU time used: 0 hours, -34 minutes, -41 seconds
Lasso and CTPR penalties are used...
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*101~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Finished!
Current Time: 2024-09-15 00:34:53.000, CPU time used: 0 hours, -17 minutes, -3 seconds
Coordinate decent algorithm process [5] has been finished...
Save all coefficients...
Current Time: 2024-09-15 00:35:29.000, CPU time used: 0 hours, -16 minutes, -28 seconds
0 1:756604_A_G
1 1:768448_A_G
2 1:779322_G_A
3 1:801536_G_T
4 1:808631_G_A
...
499612 22:51174939_T_C
499613 22:51175626_G_A
499614 22:51183255_A_G
499615 22:51185848_G_A
499616 22:51193629_G_A
Name: marker, Length: 499617, dtype: object
0 1:801536_G_T
1 1:840753_C_T
2 1:849998_A_G
3 1:851390_T_G
4 1:862772_G_A
...
172873 22:51156666_T_C
172874 22:51163138_T_C
172875 22:51171497_A_G
172876 22:51174939_T_C
172877 22:51175626_G_A
Name: 0, Length: 172878, dtype: object
CHR BP SNP A1 A2 N SE P OR \
3 1 801536 rs79373928 G T 388028 0.008413 0.808999 1.002036
8 1 840753 rs4970382 C T 388028 0.002074 0.199967 0.997346
9 1 849998 rs13303222 A G 388028 0.002646 0.221234 1.003243
11 1 851390 rs72631889 T G 388028 0.005101 0.009708 1.013278
14 1 862772 rs192998324 G A 388028 0.005892 0.054822 0.988750
INFO MAF newbeta
3 0.908963 0.483212 0.0
8 0.914603 0.498936 0.0
9 0.913359 0.435377 0.0
11 0.897499 0.432960 0.0
14 0.898013 0.417471 0.0
SNP A1 newbeta
3 rs79373928 G 0.0
8 rs4970382 C 0.0
9 rs13303222 A 0.0
11 rs72631889 T 0.0
14 rs192998324 G 0.0
... ... .. ...
499602 rs9628187 T 0.0
499607 rs715586 T 0.0
499610 rs2301584 A 0.0
499612 rs73174435 T 0.0
499613 rs3810648 G 0.0
[172878 rows x 3 columns]
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/ctpr/train_data.log.
Options in effect:
--bfile SampleData1/Fold_0/train_data.QC.clumped.pruned
--extract SampleData1/Fold_0/train_data.valid.snp
--out SampleData1/Fold_0/ctpr/train_data
--q-score-range SampleData1/Fold_0/range_list SampleData1/Fold_0/SNP.pvalue
--score SampleData1/Fold_0/.finalctpr 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
36624 variants loaded from .bim file.
380 people (183 males, 197 females) loaded from .fam.
380 phenotype values loaded from .fam.
--extract: 36624 variants remaining.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 380 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is exactly 1.
36624 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
Warning: 144112 lines skipped in --score file (144112 due to variant ID
mismatch, 0 due to allele code mismatch); see
SampleData1/Fold_0/ctpr/train_data.nopred for details.
Warning: 470852 lines skipped in --q-score-range data file.
--score: 28766 valid predictors loaded.
--score: 20 ranges processed.
Results written to SampleData1/Fold_0/ctpr/train_data.*.profile.
PLINK v1.90b7.2 64-bit (11 Dec 2023) www.cog-genomics.org/plink/1.9/
(C) 2005-2023 Shaun Purcell, Christopher Chang GNU General Public License v3
Logging to SampleData1/Fold_0/ctpr/test_data.log.
Options in effect:
--bfile SampleData1/Fold_0/test_data.clumped.pruned
--extract SampleData1/Fold_0/train_data.valid.snp
--out SampleData1/Fold_0/ctpr/test_data
--q-score-range SampleData1/Fold_0/range_list SampleData1/Fold_0/SNP.pvalue
--score SampleData1/Fold_0/.finalctpr 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
38646 variants loaded from .bim file.
95 people (44 males, 51 females) loaded from .fam.
95 phenotype values loaded from .fam.
--extract: 38646 variants remaining.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 95 founders and 0 nonfounders present.
Calculating allele frequencies... 10111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989 done.
Total genotyping rate is exactly 1.
38646 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
Warning: 142540 lines skipped in --score file (142540 due to variant ID
mismatch, 0 due to allele code mismatch); see
SampleData1/Fold_0/ctpr/test_data.nopred for details.
Warning: 469280 lines skipped in --q-score-range data file.
--score: 30338 valid predictors loaded.
--score: 20 ranges processed.
Results written to SampleData1/Fold_0/ctpr/test_data.*.profile.
Continous Phenotype!
Repeat the process for each fold.#
Change the foldnumber variable.
#foldnumber = sys.argv[1]
foldnumber = "0" # Setting 'foldnumber' to "0"
Or uncomment the following line:
# foldnumber = sys.argv[1]
python CTPR.py 0
python CTPR.py 1
python CTPR.py 2
python CTPR.py 3
python CTPR.py 4
The following files should exist after the execution:
SampleData1/Fold_0/CTPR/Results.csvSampleData1/Fold_1/CTPR/Results.csvSampleData1/Fold_2/CTPR/Results.csvSampleData1/Fold_3/CTPR/Results.csvSampleData1/Fold_4/CTPR/Results.csv
Check the results file for each fold.#
import os
result_directory = "ctpr"
# List of file names to check for existence
f = [
"./"+filedirec+"/Fold_0"+os.sep+result_directory+"Results.csv",
"./"+filedirec+"/Fold_1"+os.sep+result_directory+"Results.csv",
"./"+filedirec+"/Fold_2"+os.sep+result_directory+"Results.csv",
"./"+filedirec+"/Fold_3"+os.sep+result_directory+"Results.csv",
"./"+filedirec+"/Fold_4"+os.sep+result_directory+"Results.csv",
]
# Loop through each file name in the list
for loop in range(0,5):
# Check if the file exists in the specified directory for the given fold
if os.path.exists(filedirec+os.sep+"Fold_"+str(loop)+os.sep+result_directory+os.sep+"Results.csv"):
temp = pd.read_csv(filedirec+os.sep+"Fold_"+str(loop)+os.sep+result_directory+os.sep+"Results.csv")
print("Fold_",loop, "Yes, the file exists.")
#print(temp.head())
print("Number of P-values processed: ",len(temp))
# Print a message indicating that the file exists
else:
# Print a message indicating that the file does not exist
print("Fold_",loop, "No, the file does not exist.")
Fold_ 0 Yes, the file exists.
Number of P-values processed: 20
Fold_ 1 Yes, the file exists.
Number of P-values processed: 20
Fold_ 2 Yes, the file exists.
Number of P-values processed: 20
Fold_ 3 Yes, the file exists.
Number of P-values processed: 20
Fold_ 4 Yes, the file exists.
Number of P-values processed: 20
Sum the results for each fold.#
print("We have to ensure when we sum the entries across all Folds, the same rows are merged!")
def sum_and_average_columns(data_frames):
"""Sum and average numerical columns across multiple DataFrames, and keep non-numerical columns unchanged."""
# Initialize DataFrame to store the summed results for numerical columns
summed_df = pd.DataFrame()
non_numerical_df = pd.DataFrame()
for df in data_frames:
# Identify numerical and non-numerical columns
numerical_cols = df.select_dtypes(include=[np.number]).columns
non_numerical_cols = df.select_dtypes(exclude=[np.number]).columns
# Sum numerical columns
if summed_df.empty:
summed_df = pd.DataFrame(0, index=range(len(df)), columns=numerical_cols)
summed_df[numerical_cols] = summed_df[numerical_cols].add(df[numerical_cols], fill_value=0)
# Keep non-numerical columns (take the first non-numerical entry for each column)
if non_numerical_df.empty:
non_numerical_df = df[non_numerical_cols]
else:
non_numerical_df[non_numerical_cols] = non_numerical_df[non_numerical_cols].combine_first(df[non_numerical_cols])
# Divide the summed values by the number of dataframes to get the average
averaged_df = summed_df / len(data_frames)
# Combine numerical and non-numerical DataFrames
result_df = pd.concat([averaged_df, non_numerical_df], axis=1)
return result_df
from functools import reduce
import os
import pandas as pd
from functools import reduce
def find_common_rows(allfoldsframe):
# Define the performance columns that need to be excluded
performance_columns = [
'Train_null_model', 'Train_pure_prs', 'Train_best_model',
'Test_pure_prs', 'Test_null_model', 'Test_best_model'
]
important_columns = [
'clump_p1',
'clump_r2',
'clump_kb',
'p_window_size',
'p_slide_size',
'p_LD_threshold',
'pvalue',
'referencepanel',
'PRSice-2_Model',
'effectsizes',
'h2model',
'model',
'numberofpca',
'tempalpha',
'l1weight',
"CTPR_f",
"CTPR_lamda",
"CTPR_penalty",
"CTPR_withoutsum",
]
# Function to remove performance columns from a DataFrame
def drop_performance_columns(df):
return df.drop(columns=performance_columns, errors='ignore')
def get_important_columns(df ):
existing_columns = [col for col in important_columns if col in df.columns]
if existing_columns:
return df[existing_columns].copy()
else:
return pd.DataFrame()
# Drop performance columns from all DataFrames in the list
allfoldsframe_dropped = [drop_performance_columns(df) for df in allfoldsframe]
# Get the important columns.
allfoldsframe_dropped = [get_important_columns(df) for df in allfoldsframe_dropped]
# Iteratively find common rows and track unique and common rows
common_rows = allfoldsframe_dropped[0]
for i in range(1, len(allfoldsframe_dropped)):
# Get the next DataFrame
next_df = allfoldsframe_dropped[i]
# Count unique rows in the current DataFrame and the next DataFrame
unique_in_common = common_rows.shape[0]
unique_in_next = next_df.shape[0]
# Find common rows between the current common_rows and the next DataFrame
common_rows = pd.merge(common_rows, next_df, how='inner')
# Count the common rows after merging
common_count = common_rows.shape[0]
# Print the unique and common row counts
print(f"Iteration {i}:")
print(f"Unique rows in current common DataFrame: {unique_in_common}")
print(f"Unique rows in next DataFrame: {unique_in_next}")
print(f"Common rows after merge: {common_count}\n")
# Now that we have the common rows, extract these from the original DataFrames
extracted_common_rows_frames = []
for original_df in allfoldsframe:
# Merge the common rows with the original DataFrame, keeping only the rows that match the common rows
extracted_common_rows = pd.merge(common_rows, original_df, how='inner', on=common_rows.columns.tolist())
# Add the DataFrame with the extracted common rows to the list
extracted_common_rows_frames.append(extracted_common_rows)
# Print the number of rows in the common DataFrames
for i, df in enumerate(extracted_common_rows_frames):
print(f"DataFrame {i + 1} with extracted common rows has {df.shape[0]} rows.")
# Return the list of DataFrames with extracted common rows
return extracted_common_rows_frames
# Example usage (assuming allfoldsframe is populated as shown earlier):
allfoldsframe = []
# Loop through each file name in the list
for loop in range(0, 5):
# Check if the file exists in the specified directory for the given fold
file_path = os.path.join(filedirec, "Fold_" + str(loop), result_directory, "Results.csv")
if os.path.exists(file_path):
allfoldsframe.append(pd.read_csv(file_path))
# Print a message indicating that the file exists
print("Fold_", loop, "Yes, the file exists.")
else:
# Print a message indicating that the file does not exist
print("Fold_", loop, "No, the file does not exist.")
# Find the common rows across all folds and return the list of extracted common rows
extracted_common_rows_list = find_common_rows(allfoldsframe)
# Sum the values column-wise
# For string values, do not sum it the values are going to be the same for each fold.
# Only sum the numeric values.
divided_result = sum_and_average_columns(extracted_common_rows_list)
print(divided_result)
We have to ensure when we sum the entries across all Folds, the same rows are merged!
Fold_ 0 Yes, the file exists.
Fold_ 1 Yes, the file exists.
Fold_ 2 Yes, the file exists.
Fold_ 3 Yes, the file exists.
Fold_ 4 Yes, the file exists.
Iteration 1:
Unique rows in current common DataFrame: 20
Unique rows in next DataFrame: 20
Common rows after merge: 20
Iteration 2:
Unique rows in current common DataFrame: 20
Unique rows in next DataFrame: 20
Common rows after merge: 20
Iteration 3:
Unique rows in current common DataFrame: 20
Unique rows in next DataFrame: 20
Common rows after merge: 20
Iteration 4:
Unique rows in current common DataFrame: 20
Unique rows in next DataFrame: 20
Common rows after merge: 20
DataFrame 1 with extracted common rows has 20 rows.
DataFrame 2 with extracted common rows has 20 rows.
DataFrame 3 with extracted common rows has 20 rows.
DataFrame 4 with extracted common rows has 20 rows.
DataFrame 5 with extracted common rows has 20 rows.
clump_p1 clump_r2 clump_kb p_window_size p_slide_size p_LD_threshold \
0 1.0 0.1 200.0 200.0 50.0 0.25
1 1.0 0.1 200.0 200.0 50.0 0.25
2 1.0 0.1 200.0 200.0 50.0 0.25
3 1.0 0.1 200.0 200.0 50.0 0.25
4 1.0 0.1 200.0 200.0 50.0 0.25
5 1.0 0.1 200.0 200.0 50.0 0.25
6 1.0 0.1 200.0 200.0 50.0 0.25
7 1.0 0.1 200.0 200.0 50.0 0.25
8 1.0 0.1 200.0 200.0 50.0 0.25
9 1.0 0.1 200.0 200.0 50.0 0.25
10 1.0 0.1 200.0 200.0 50.0 0.25
11 1.0 0.1 200.0 200.0 50.0 0.25
12 1.0 0.1 200.0 200.0 50.0 0.25
13 1.0 0.1 200.0 200.0 50.0 0.25
14 1.0 0.1 200.0 200.0 50.0 0.25
15 1.0 0.1 200.0 200.0 50.0 0.25
16 1.0 0.1 200.0 200.0 50.0 0.25
17 1.0 0.1 200.0 200.0 50.0 0.25
18 1.0 0.1 200.0 200.0 50.0 0.25
19 1.0 0.1 200.0 200.0 50.0 0.25
pvalue numberofpca tempalpha l1weight CTPR_f CTPR_lamda \
0 1.000000e-10 6.0 0.1 0.1 5.0 -1.0
1 3.359818e-10 6.0 0.1 0.1 5.0 -1.0
2 1.128838e-09 6.0 0.1 0.1 5.0 -1.0
3 3.792690e-09 6.0 0.1 0.1 5.0 -1.0
4 1.274275e-08 6.0 0.1 0.1 5.0 -1.0
5 4.281332e-08 6.0 0.1 0.1 5.0 -1.0
6 1.438450e-07 6.0 0.1 0.1 5.0 -1.0
7 4.832930e-07 6.0 0.1 0.1 5.0 -1.0
8 1.623777e-06 6.0 0.1 0.1 5.0 -1.0
9 5.455595e-06 6.0 0.1 0.1 5.0 -1.0
10 1.832981e-05 6.0 0.1 0.1 5.0 -1.0
11 6.158482e-05 6.0 0.1 0.1 5.0 -1.0
12 2.069138e-04 6.0 0.1 0.1 5.0 -1.0
13 6.951928e-04 6.0 0.1 0.1 5.0 -1.0
14 2.335721e-03 6.0 0.1 0.1 5.0 -1.0
15 7.847600e-03 6.0 0.1 0.1 5.0 -1.0
16 2.636651e-02 6.0 0.1 0.1 5.0 -1.0
17 8.858668e-02 6.0 0.1 0.1 5.0 -1.0
18 2.976351e-01 6.0 0.1 0.1 5.0 -1.0
19 1.000000e+00 6.0 0.1 0.1 5.0 -1.0
CTPR_penalty Train_pure_prs Train_null_model Train_best_model \
0 1.0 0.0 0.2339 0.2339
1 1.0 0.0 0.2339 0.2339
2 1.0 0.0 0.2339 0.2339
3 1.0 0.0 0.2339 0.2339
4 1.0 0.0 0.2339 0.2339
5 1.0 0.0 0.2339 0.2339
6 1.0 0.0 0.2339 0.2339
7 1.0 0.0 0.2339 0.2339
8 1.0 0.0 0.2339 0.2339
9 1.0 0.0 0.2339 0.2339
10 1.0 0.0 0.2339 0.2339
11 1.0 0.0 0.2339 0.2339
12 1.0 0.0 0.2339 0.2339
13 1.0 0.0 0.2339 0.2339
14 1.0 0.0 0.2339 0.2339
15 1.0 0.0 0.2339 0.2339
16 1.0 0.0 0.2339 0.2339
17 1.0 0.0 0.2339 0.2339
18 1.0 0.0 0.2339 0.2339
19 1.0 0.0 0.2339 0.2339
Test_pure_prs Test_null_model Test_best_model CTPR_withoutsum
0 0.0 0.167588 0.167588 True
1 0.0 0.167588 0.167588 True
2 0.0 0.167588 0.167588 True
3 0.0 0.167588 0.167588 True
4 0.0 0.167588 0.167588 True
5 0.0 0.167588 0.167588 True
6 0.0 0.167588 0.167588 True
7 0.0 0.167588 0.167588 True
8 0.0 0.167588 0.167588 True
9 0.0 0.167588 0.167588 True
10 0.0 0.167588 0.167588 True
11 0.0 0.167588 0.167588 True
12 0.0 0.167588 0.167588 True
13 0.0 0.167588 0.167588 True
14 0.0 0.167588 0.167588 True
15 0.0 0.167588 0.167588 True
16 0.0 0.167588 0.167588 True
17 0.0 0.167588 0.167588 True
18 0.0 0.167588 0.167588 True
19 0.0 0.167588 0.167588 True
/tmp/ipykernel_2652287/3530046141.py:24: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
non_numerical_df[non_numerical_cols] = non_numerical_df[non_numerical_cols].combine_first(df[non_numerical_cols])
/tmp/ipykernel_2652287/3530046141.py:24: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
non_numerical_df[non_numerical_cols] = non_numerical_df[non_numerical_cols].combine_first(df[non_numerical_cols])
/tmp/ipykernel_2652287/3530046141.py:24: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
non_numerical_df[non_numerical_cols] = non_numerical_df[non_numerical_cols].combine_first(df[non_numerical_cols])
/tmp/ipykernel_2652287/3530046141.py:24: SettingWithCopyWarning:
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead
See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
non_numerical_df[non_numerical_cols] = non_numerical_df[non_numerical_cols].combine_first(df[non_numerical_cols])
Results#
1. Reporting Based on Best Training Performance:#
One can report the results based on the best performance of the training data. For example, if for a specific combination of hyperparameters, the training performance is high, report the corresponding test performance.
Example code:
df = divided_result.sort_values(by='Train_best_model', ascending=False) print(df.iloc[0].to_markdown())
Binary Phenotypes Result Analysis#
You can find the performance quality for binary phenotype using the following template:
This figure shows the 8 different scenarios that can exist in the results, and the following table explains each scenario.
We classified performance based on the following table:
Performance Level |
Range |
|---|---|
Low Performance |
0 to 0.5 |
Moderate Performance |
0.6 to 0.7 |
High Performance |
0.8 to 1 |
You can match the performance based on the following scenarios:
Scenario |
What’s Happening |
Implication |
|---|---|---|
High Test, High Train |
The model performs well on both training and test datasets, effectively learning the underlying patterns. |
The model is well-tuned, generalizes well, and makes accurate predictions on both datasets. |
High Test, Moderate Train |
The model generalizes well but may not be fully optimized on training data, missing some underlying patterns. |
The model is fairly robust but may benefit from further tuning or more training to improve its learning. |
High Test, Low Train |
An unusual scenario, potentially indicating data leakage or overestimation of test performance. |
The model’s performance is likely unreliable; investigate potential data issues or random noise. |
Moderate Test, High Train |
The model fits the training data well but doesn’t generalize as effectively, capturing only some test patterns. |
The model is slightly overfitting; adjustments may be needed to improve generalization on unseen data. |
Moderate Test, Moderate Train |
The model shows balanced but moderate performance on both datasets, capturing some patterns but missing others. |
The model is moderately fitting; further improvements could be made in both training and generalization. |
Moderate Test, Low Train |
The model underperforms on training data and doesn’t generalize well, leading to moderate test performance. |
The model may need more complexity, additional features, or better training to improve on both datasets. |
Low Test, High Train |
The model overfits the training data, performing poorly on the test set. |
The model doesn’t generalize well; simplifying the model or using regularization may help reduce overfitting. |
Low Test, Low Train |
The model performs poorly on both training and test datasets, failing to learn the data patterns effectively. |
The model is underfitting; it may need more complexity, additional features, or more data to improve performance. |
Recommendations for Publishing Results#
When publishing results, scenarios with moderate train and moderate test performance can be used for complex phenotypes or diseases. However, results showing high train and moderate test, high train and high test, and moderate train and high test are recommended.
For most phenotypes, results typically fall in the moderate train and moderate test performance category.
Continuous Phenotypes Result Analysis#
You can find the performance quality for continuous phenotypes using the following template:
This figure shows the 8 different scenarios that can exist in the results, and the following table explains each scenario.
We classified performance based on the following table:
Performance Level |
Range |
|---|---|
Low Performance |
0 to 0.2 |
Moderate Performance |
0.3 to 0.7 |
High Performance |
0.8 to 1 |
You can match the performance based on the following scenarios:
Scenario |
What’s Happening |
Implication |
|---|---|---|
High Test, High Train |
The model performs well on both training and test datasets, effectively learning the underlying patterns. |
The model is well-tuned, generalizes well, and makes accurate predictions on both datasets. |
High Test, Moderate Train |
The model generalizes well but may not be fully optimized on training data, missing some underlying patterns. |
The model is fairly robust but may benefit from further tuning or more training to improve its learning. |
High Test, Low Train |
An unusual scenario, potentially indicating data leakage or overestimation of test performance. |
The model’s performance is likely unreliable; investigate potential data issues or random noise. |
Moderate Test, High Train |
The model fits the training data well but doesn’t generalize as effectively, capturing only some test patterns. |
The model is slightly overfitting; adjustments may be needed to improve generalization on unseen data. |
Moderate Test, Moderate Train |
The model shows balanced but moderate performance on both datasets, capturing some patterns but missing others. |
The model is moderately fitting; further improvements could be made in both training and generalization. |
Moderate Test, Low Train |
The model underperforms on training data and doesn’t generalize well, leading to moderate test performance. |
The model may need more complexity, additional features, or better training to improve on both datasets. |
Low Test, High Train |
The model overfits the training data, performing poorly on the test set. |
The model doesn’t generalize well; simplifying the model or using regularization may help reduce overfitting. |
Low Test, Low Train |
The model performs poorly on both training and test datasets, failing to learn the data patterns effectively. |
The model is underfitting; it may need more complexity, additional features, or more data to improve performance. |
Recommendations for Publishing Results#
When publishing results, scenarios with moderate train and moderate test performance can be used for complex phenotypes or diseases. However, results showing high train and moderate test, high train and high test, and moderate train and high test are recommended.
For most continuous phenotypes, results typically fall in the moderate train and moderate test performance category.
2. Reporting Generalized Performance:#
One can also report the generalized performance by calculating the difference between the training and test performance, and the sum of the test and training performance. Report the result or hyperparameter combination for which the sum is high and the difference is minimal.
Example code:
df = divided_result.copy() df['Difference'] = abs(df['Train_best_model'] - df['Test_best_model']) df['Sum'] = df['Train_best_model'] + df['Test_best_model'] sorted_df = df.sort_values(by=['Sum', 'Difference'], ascending=[False, True]) print(sorted_df.iloc[0].to_markdown())
3. Reporting Hyperparameters Affecting Test and Train Performance:#
Find the hyperparameters that have more than one unique value and calculate their correlation with the following columns to understand how they are affecting the performance of train and test sets:
Train_null_modelTrain_pure_prsTrain_best_modelTest_pure_prsTest_null_modelTest_best_model
4. Other Analysis#
Once you have the results, you can find how hyperparameters affect the model performance.
Analysis, like overfitting and underfitting, can be performed as well.
The way you are going to report the results can vary.
Results can be visualized, and other patterns in the data can be explored.
import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib notebook
import matplotlib
import numpy as np
import matplotlib.pyplot as plt
df = divided_result.sort_values(by='Train_best_model', ascending=False)
print("1. Reporting Based on Best Training Performance:\n")
print(df.iloc[0].to_markdown())
df = divided_result.copy()
# Plot Train and Test best models against p-values
plt.figure(figsize=(10, 6))
plt.plot(df['pvalue'], df['Train_best_model'], label='Train_best_model', marker='o', color='royalblue')
plt.plot(df['pvalue'], df['Test_best_model'], label='Test_best_model', marker='o', color='darkorange')
# Highlight the p-value where both train and test are high
best_index = df[['Train_best_model']].sum(axis=1).idxmax()
best_pvalue = df.loc[best_index, 'pvalue']
best_train = df.loc[best_index, 'Train_best_model']
best_test = df.loc[best_index, 'Test_best_model']
# Use dark colors for the circles
plt.scatter(best_pvalue, best_train, color='darkred', s=100, label=f'Best Performance (Train)', edgecolor='black', zorder=5)
plt.scatter(best_pvalue, best_test, color='darkblue', s=100, label=f'Best Performance (Test)', edgecolor='black', zorder=5)
# Annotate the best performance with p-value, train, and test values
plt.text(best_pvalue, best_train, f'p={best_pvalue:.4g}\nTrain={best_train:.4g}', ha='right', va='bottom', fontsize=9, color='darkred')
plt.text(best_pvalue, best_test, f'p={best_pvalue:.4g}\nTest={best_test:.4g}', ha='right', va='top', fontsize=9, color='darkblue')
# Calculate Difference and Sum
df['Difference'] = abs(df['Train_best_model'] - df['Test_best_model'])
df['Sum'] = df['Train_best_model'] + df['Test_best_model']
# Sort the DataFrame
sorted_df = df.sort_values(by=['Sum', 'Difference'], ascending=[False, True])
#sorted_df = df.sort_values(by=[ 'Difference','Sum'], ascending=[ True,False])
# Highlight the general performance
general_index = sorted_df.index[0]
general_pvalue = sorted_df.loc[general_index, 'pvalue']
general_train = sorted_df.loc[general_index, 'Train_best_model']
general_test = sorted_df.loc[general_index, 'Test_best_model']
plt.scatter(general_pvalue, general_train, color='darkgreen', s=150, label='General Performance (Train)', edgecolor='black', zorder=6)
plt.scatter(general_pvalue, general_test, color='darkorange', s=150, label='General Performance (Test)', edgecolor='black', zorder=6)
# Annotate the general performance with p-value, train, and test values
plt.text(general_pvalue, general_train, f'p={general_pvalue:.4g}\nTrain={general_train:.4g}', ha='left', va='bottom', fontsize=9, color='darkgreen')
plt.text(general_pvalue, general_test, f'p={general_pvalue:.4g}\nTest={general_test:.4g}', ha='left', va='top', fontsize=9, color='darkorange')
# Add labels and legend
plt.xlabel('p-value')
plt.ylabel('Model Performance')
plt.title('Train vs Test Best Models')
plt.legend()
plt.show()
print("2. Reporting Generalized Performance:\n")
df = divided_result.copy()
df['Difference'] = abs(df['Train_best_model'] - df['Test_best_model'])
df['Sum'] = df['Train_best_model'] + df['Test_best_model']
sorted_df = df.sort_values(by=['Sum', 'Difference'], ascending=[False, True])
print(sorted_df.iloc[0].to_markdown())
print("3. Reporting the correlation of hyperparameters and the performance of 'Train_null_model', 'Train_pure_prs', 'Train_best_model', 'Test_pure_prs', 'Test_null_model', and 'Test_best_model':\n")
print("3. For string hyperparameters, we used one-hot encoding to find the correlation between string hyperparameters and 'Train_null_model', 'Train_pure_prs', 'Train_best_model', 'Test_pure_prs', 'Test_null_model', and 'Test_best_model'.")
print("3. We performed this analysis for those hyperparameters that have more than one unique value.")
correlation_columns = [
'Train_null_model', 'Train_pure_prs', 'Train_best_model',
'Test_pure_prs', 'Test_null_model', 'Test_best_model'
]
hyperparams = [col for col in divided_result.columns if len(divided_result[col].unique()) > 1]
hyperparams = list(set(hyperparams+correlation_columns))
# Separate numeric and string columns
numeric_hyperparams = [col for col in hyperparams if pd.api.types.is_numeric_dtype(divided_result[col])]
string_hyperparams = [col for col in hyperparams if pd.api.types.is_string_dtype(divided_result[col])]
# Encode string columns using one-hot encoding
divided_result_encoded = pd.get_dummies(divided_result, columns=string_hyperparams)
# Combine numeric hyperparams with the new one-hot encoded columns
encoded_columns = [col for col in divided_result_encoded.columns if col.startswith(tuple(string_hyperparams))]
hyperparams = numeric_hyperparams + encoded_columns
# Calculate correlations
correlations = divided_result_encoded[hyperparams].corr()
# Display correlation of hyperparameters with train/test performance columns
hyperparam_correlations = correlations.loc[hyperparams, correlation_columns]
hyperparam_correlations = hyperparam_correlations.fillna(0)
# Plotting the correlation heatmap
plt.figure(figsize=(12, 8))
ax = sns.heatmap(hyperparam_correlations, annot=True, cmap='viridis', fmt='.2f', cbar=True)
ax.set_xticklabels(ax.get_xticklabels(), rotation=90, ha='right')
# Rotate y-axis labels to horizontal
#ax.set_yticklabels(ax.get_yticklabels(), rotation=0, va='center')
plt.title('Correlation of Hyperparameters with Train/Test Performance')
plt.show()
sns.set_theme(style="whitegrid") # Choose your preferred style
pairplot = sns.pairplot(divided_result_encoded[hyperparams],hue = 'Test_best_model', palette='viridis')
# Adjust the figure size
pairplot.fig.set_size_inches(15, 15) # You can adjust the size as needed
for ax in pairplot.axes.flatten():
ax.set_xlabel(ax.get_xlabel(), rotation=90, ha='right') # X-axis labels vertical
#ax.set_ylabel(ax.get_ylabel(), rotation=0, va='bottom') # Y-axis labels horizontal
# Show the plot
plt.show()
1. Reporting Based on Best Training Performance:
| | 0 |
|:-----------------|-----------:|
| clump_p1 | 1 |
| clump_r2 | 0.1 |
| clump_kb | 200 |
| p_window_size | 200 |
| p_slide_size | 50 |
| p_LD_threshold | 0.25 |
| pvalue | 1e-10 |
| numberofpca | 6 |
| tempalpha | 0.1 |
| l1weight | 0.1 |
| CTPR_f | 5 |
| CTPR_lamda | -1 |
| CTPR_penalty | 1 |
| Train_pure_prs | 0 |
| Train_null_model | 0.2339 |
| Train_best_model | 0.2339 |
| Test_pure_prs | 0 |
| Test_null_model | 0.167588 |
| Test_best_model | 0.167588 |
| CTPR_withoutsum | 1 |
2. Reporting Generalized Performance:
| | 0 |
|:-----------------|------------:|
| clump_p1 | 1 |
| clump_r2 | 0.1 |
| clump_kb | 200 |
| p_window_size | 200 |
| p_slide_size | 50 |
| p_LD_threshold | 0.25 |
| pvalue | 1e-10 |
| numberofpca | 6 |
| tempalpha | 0.1 |
| l1weight | 0.1 |
| CTPR_f | 5 |
| CTPR_lamda | -1 |
| CTPR_penalty | 1 |
| Train_pure_prs | 0 |
| Train_null_model | 0.2339 |
| Train_best_model | 0.2339 |
| Test_pure_prs | 0 |
| Test_null_model | 0.167588 |
| Test_best_model | 0.167588 |
| CTPR_withoutsum | 1 |
| Difference | 0.0663121 |
| Sum | 0.401487 |
3. Reporting the correlation of hyperparameters and the performance of 'Train_null_model', 'Train_pure_prs', 'Train_best_model', 'Test_pure_prs', 'Test_null_model', and 'Test_best_model':
3. For string hyperparameters, we used one-hot encoding to find the correlation between string hyperparameters and 'Train_null_model', 'Train_pure_prs', 'Train_best_model', 'Test_pure_prs', 'Test_null_model', and 'Test_best_model'.
3. We performed this analysis for those hyperparameters that have more than one unique value.
