tlpSum#
tlpSum is similar to lassosum jpattee/penRegSum and requires almost similar arguments. To install tlpSum, install R, devtools, lassosum, and then penRegSum, which contains tlpSum.
Install tlpSum#
install.packages(c("devtools", "RcppArmadillo", "data.table", "Matrix"), dependencies=TRUE)
library(devtools)
install_github("tshmak/lassosum")
devtools::install_github("jpattee/penRegSum")
install.packages('pROC')
It is recommended to use the common SNPs between the test and training data to speed up the process.
tlpSum requires ldBlock and we can use the LD block from lassosum for tlpSum.
Install lassosum#
install.packages(c("devtools", "RcppArmadillo", "data.table", "Matrix"), dependencies=TRUE)
library(devtools)
install_github("tshmak/lassosum")
Type R in the command line, then:
library("lassosum")
data("package:lassosum")
system.file(package = "lassosum")
Output
"/data/ascher01/uqmmune1/miniconda3/envs/genetics/lib/R/library/lassosum"
q()
Go to the Lassosum data files, and based on genotype population and genomic build, choose the appropriate LD file.
cd /data/ascher01/uqmmune1/miniconda3/envs/genetics/lib/R/library/lassosum
ls
Output
data DESCRIPTION help html include INDEX lassosum lassosum.R libs Meta NAMESPACE R
cd data/
ls
Berisa.AFR.hg19.bed Berisa.ASN.hg38.bed Berisa.R refpanel.bed summarystats.txt testsample.covar.txt
Berisa.AFR.hg38.bed Berisa.EUR.hg19.bed Berisa.README refpanel.bim testsample.bed testsample.fam
Berisa.ASN.hg19.bed Berisa.EUR.hg38.bed GenerateData.R refpanel.fam testsample.bim testsample.pheno.txt
Copy EUR.hg19 and save it in the working directory where this notebook is placed. Depending on the genomic build, you can change the reference file.
We copied Berisa.EUR.hg19.bed to EUR.hg19 in the current directory:
cp Berisa.EUR.hg19.bed /data/ascher01/uqmmune1/BenchmarkingPGSTools/EUR.hg19.bed
Use tlpSum#
Use tlpSum with the following parameters:
tlpSum(
cors,
bfile,
lambdas,
taus,
s = 0.5,
thr = 1e-04,
init = NULL,
maxIter = 1000,
extract = NULL,
ldBlocks = NULL,
corBim = NULL
)
tlpSum Hyperparameters specified in R file.#
Define the parameters in tlpSum.R file.
lambdas <- c(0.001, 0.01)
taus <- c(0.01, 0.1)
s <- c(0.5)
library(lassosum)
library(penRegSum)
library(data.table)
library(pROC)
package_directory <- system.file(package = "lassosum")
args <- commandArgs(trailingOnly = TRUE)
print(args)
help(tlpSum)
#1. Argument one is the directory. Example: `SampleData1`
#2. Argument two is the file name. Example: `SampleData1\\Fold_0`
#3. Argument three is the output file name. Example: `train_data`
#4. Argument four is the specific function to be called. Example: `train_data.QC.clumped.pruned`
#5. Argument five is the GWAS. Example: `EBPRSGWAS.txt`
# Argument Descriptions:
# 1. Directory
# 2. File name
# 3. Output file name
# 4. Specific function to be called
# 5. Number of PCA
# 6. convergence
# 7. iteration
#args <- c(
# "SampleData1",
# "SampleData1\\Fold_0",
# "train_data",
# "train_data.QC.clumped.pruned",
# "6",
# "convergence",
# "iteration"
#)
#args <- c("SampleData1","SampleData1\\Fold_0","train_data","train_data.QC.clumped.pruned","EBPRSGWAS.txt" )
ld.file <- "EUR.hg19.bed"
result <- paste(".", args[1], paste(args[1], toString(".txt"), sep = ""), sep = "//")
bimfile <- paste(".", args[2], paste(args[4], toString(".bim"), sep = ""), sep = "//")
bimfile <-fread(bimfile)
result <- paste(".", args[1], paste(args[1], toString(".txt"), sep = ""), sep = "//")
ss <- fread(result)
ss <- ss[ss$SNP %in% bimfile$V2, ]
ss <- ss[!P == 0]
cor <- p2cor(p = ss$P,
n = ss$N,
sign = ss$BETA)
lambdas <- c(0.001,0.01)
taus <- c(0.01,0.1)
s <- c(0.5)
bfile <- paste(".", args[2], args[4], sep = "//")
out <-tlpSum(
cors= cor,
bfile = bfile,
lambdas = lambdas,
taus = taus,
s = s,
#s = 0.5,
thr = as.numeric(args[6]),
#init = NULL,
maxIter = as.numeric(args[7]),
#extract = NULL,
ldBlocks = ld.file,
#corBim = NULL
)
selected_columns <- data.frame(
lambdas = out$lambdas,
taus = out$taus,
s = out$s
)
#result <-paste(".",args[2],paste(args[3],toString(".lassosum_betas"), sep = ""),sep="//")
result <-paste(".",args[2],paste(args[3],toString(".tlpSum_parameters"), sep = ""),sep="//")
write.table(selected_columns, file = result, row.names = FALSE,sep=",", quote = FALSE)
result <-paste(".",args[2],paste(args[3],toString(".tlpSum_betas"), sep = ""),sep="//")
write.table(out$beta, file = result, row.names = FALSE,sep=",", quote = FALSE)
print("IterationDOne")
tlpSum Hyperparameters specified in this code book.#
convergence: [1e-04, 1e-03]
iterations: [100]
GWAS for tlpSum#
Note: For both binary and continuous phenotype, BETAS were passed to the tlpSum pipeline. For binary phenotype, convert the OR to betas, and when tlpSum calculates the new BETAS for multiple values of lambdas and taus and s, we convert the new betas to OR using np.exp(df["BETA"]) for binary phenotype.
import os
import pandas as pd
import numpy as np
import os
import pandas as pd
import numpy as np
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"
#filedirec = sys.argv[1]
filedirec = "SampleData1"
#filedirec = "asthma_19"
#filedirec = "migraine_0"
# Read the GWAS file.
GWAS = filedirec + os.sep + filedirec+".gz"
df = pd.read_csv(GWAS,compression= "gzip",sep="\s+")
# We will save the new GWAS file containing only the betas, as Lassosum uses Betas to calculate the correlation
# which is further used to calculate the new Betas.
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 = df[['CHR', 'BP', 'SNP', 'A1', 'A2', 'N', 'SE', 'P', 'BETA', 'INFO', 'MAF']]
df.to_csv(filedirec + os.sep +filedirec+".txt",sep="\t",index=False)
print(df.head().to_markdown())
print("Length of DataFrame!",len(df))
| | CHR | BP | SNP | A1 | A2 | N | SE | P | BETA | INFO | MAF |
|---:|------:|-------:|:-----------|:-----|:-----|-------:|-----------:|---------:|------------:|---------:|---------:|
| 0 | 1 | 756604 | rs3131962 | A | G | 388028 | 0.00301666 | 0.483171 | -0.00211532 | 0.890558 | 0.36939 |
| 1 | 1 | 768448 | rs12562034 | A | G | 388028 | 0.00329472 | 0.834808 | 0.00068708 | 0.895894 | 0.336846 |
| 2 | 1 | 779322 | rs4040617 | G | A | 388028 | 0.00303344 | 0.42897 | -0.00239932 | 0.897508 | 0.377368 |
| 3 | 1 | 801536 | rs79373928 | G | T | 388028 | 0.00841324 | 0.808999 | 0.00203363 | 0.908963 | 0.483212 |
| 4 | 1 | 808631 | rs11240779 | G | A | 388028 | 0.00242821 | 0.590265 | 0.00130747 | 0.893213 | 0.45041 |
Length of DataFrame! 499617
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 = "4" # 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'
prs_result = pd.DataFrame()
# 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","model","referencepanel","lambda","delta","sparsity","p","h2","h2model","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, c,ii,p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile,tlpsum_lambda,tlpsum_tau,tlpsum_s,tlpSum_count):
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:
print("Did not work!")
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),
"convergencethreshold":c,
"iteration":ii,
"tlpsum_lambda": tlpsum_lambda ,
"tlpsum_tau":tlpsum_tau,
"tlpsum_s":tlpsum_s,
"tlpSum_count":str(tlpSum_count),
"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, c,ii,p1_val, p2_val, p3_val, c1_val, c2_val, c3_val,Name,pvaluefile,tlpsum_lambda,tlpsum_tau,tlpsum_s,tlpSum_count):
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),
"convergencethreshold":c,
"iteration":ii,
"tlpSum_count":str(tlpSum_count),
"tlpsum_lambda": tlpsum_lambda ,
"tlpsum_tau":tlpsum_tau,
"tlpsum_s":tlpsum_s,
"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 tlpSum#
def transform_tlpSum_data(traindirec, newtrainfilename,p,c,ii, 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")
# At this stage, we will merge the PCA and COV file.
tempphenotype_train = pd.read_table(traindirec+os.sep+newtrainfilename+".clumped.pruned"+".fam", sep="\s+",header=None)
phenotype = pd.DataFrame()
phenotype = tempphenotype_train[[0,1,5]]
phenotype.to_csv(traindirec+os.sep+trainfilename+".PHENO",sep="\t",header=['FID', 'IID', 'PHENO'],index=False)
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)
print(covariate_train.head())
print(len(covariate_train))
covariate_train = covariate_train[covariate_train["FID"].isin(pcs_train["FID"].values) & covariate_train["IID"].isin(pcs_train["IID"].values)]
print(len(covariate_train))
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.to_csv(traindirec+os.sep+trainfilename+".COV_PCA",sep="\t",index=False)
files_to_remove = [
traindirec+os.sep+"train_data.tlpSum_parameters",
traindirec+os.sep+"train_data.tlpSum_betas",
traindirec+os.sep+"Train_data.tlpSum",
]
# Loop through the files and remove them if they exist
for file_path in files_to_remove:
if os.path.exists(file_path):
os.remove(file_path)
print(f"Removed: {file_path}")
else:
print(f"File does not exist: {file_path}")
os.system("Rscript tlpSum.R "+os.path.join(filedirec)+" "+traindirec+" "+trainfilename+" "+newtrainfilename+".clumped.pruned"+" "+str(p)+" "+str(c)+ " "+ str(ii))
# After obtaining betas from the LDpred-2
# Append the new betas.
gridparameters = pd.read_csv(traindirec+os.sep+"train_data.tlpSum_parameters",sep=",")
allbetas = pd.read_csv(traindirec+os.sep+"train_data.tlpSum_betas",sep=",")
allbetas = allbetas.fillna(0)
count = 0
for index, row in gridparameters.iterrows():
# Accessing individual elements in the row
gwas = pd.read_csv(filedirec+os.sep+filedirec+".txt",sep="\s+")
count=count+1
lambdas = row['lambdas']
taus =row['taus']
ss =row['s']
readbimfile = pd.read_csv(traindirec+os.sep+newtrainfilename+".clumped.pruned"+".bim",sep="\s+",header=None)
gwas=gwas[gwas["SNP"].isin(readbimfile[1].values)]
gwas["newbetas"] = allbetas.iloc[:, index].values
gwas = gwas[["SNP","A1","newbetas"]]
# If phenotype is Binary, convert betas to OR.
if check_phenotype_is_binary_or_continous(filedirec)=="Binary":
gwas["newbetas"] = np.exp(gwas["newbetas"])
else:
pass
gwas.to_csv(traindirec+os.sep+"Train_data.tlpSum",sep="\t",index=False)
#raise
command = [
"./plink",
"--bfile", traindirec+os.sep+newtrainfilename+".clumped.pruned",
### SNP column = 1, Effect allele column 2 = 4, Effect column=4
"--score", traindirec+os.sep+"Train_data.tlpSum", "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,
### SNP column = 3, Effect allele column 1 = 4, Beta column=12
"--score", traindirec+os.sep+"Train_data.tlpSum", "1", "2", "3", "header",
"--q-score-range", traindirec+os.sep+"range_list",traindirec+os.sep+"SNP.pvalue",
"--out", folddirec+os.sep+Name+os.sep+testfilename
]
subprocess.run(command)
if check_phenotype_is_binary_or_continous(filedirec)=="Binary":
print("Binary Phenotype!")
fit_binary_phenotype_on_PRS(folddirec, newtrainfilename, p, c,ii,str(p1_val), str(p2_val), str(p3_val), str(c1_val), str(c2_val), str(c3_val), Name, pvaluefile,row['lambdas'] ,row['taus'],row['s'],count)
else:
print("Continous Phenotype!")
fit_continous_phenotype_on_PRS(folddirec, newtrainfilename,p, c,ii,str(p1_val), str(p2_val), str(p3_val), str(c1_val), str(c2_val), str(c3_val), Name, pvaluefile,row['lambdas'] ,row['taus'],row['s'],count)
convergence = [1e-04,1e-03]
iterations = [100]
result_directory = "tlpSum"
# Nested loops to iterate over different parameter values
create_directory(folddirec+os.sep+result_directory)
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 c in convergence:
for ii in iterations:
transform_tlpSum_data(folddirec, newtrainfilename, p, c,ii,str(p1_val), str(p2_val), str(p3_val), str(c1_val), str(c2_val), str(c3_val), result_directory, pvaluefile)
FID IID Sex
0 HG00096 HG00096 1
1 HG00099 HG00099 2
2 HG00101 HG00101 1
3 HG00102 HG00102 2
4 HG00103 HG00103 1
380
380
Removed: SampleData1/Fold_4/train_data.tlpSum_parameters
Removed: SampleData1/Fold_4/train_data.tlpSum_betas
Removed: SampleData1/Fold_4/Train_data.tlpSum
Type 'citation("pROC")' for a citation.
Attaching package: ‘pROC’
The following objects are masked from ‘package:stats’:
cov, smooth, var
[1] "SampleData1" "SampleData1/Fold_4"
[3] "train_data" "train_data.QC.clumped.pruned"
[5] "6" "0.0001"
[7] "100"
[1] "IterationDOne"
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
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 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/test_data.*.profile.
Continous Phenotype!
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
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 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/test_data.*.profile.
Continous Phenotype!
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
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 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/test_data.*.profile.
Continous Phenotype!
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
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 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/test_data.*.profile.
Continous Phenotype!
FID IID Sex
0 HG00096 HG00096 1
1 HG00099 HG00099 2
2 HG00101 HG00101 1
3 HG00102 HG00102 2
4 HG00103 HG00103 1
380
380
Removed: SampleData1/Fold_4/train_data.tlpSum_parameters
Removed: SampleData1/Fold_4/train_data.tlpSum_betas
Removed: SampleData1/Fold_4/Train_data.tlpSum
Type 'citation("pROC")' for a citation.
Attaching package: ‘pROC’
The following objects are masked from ‘package:stats’:
cov, smooth, var
[1] "SampleData1" "SampleData1/Fold_4"
[3] "train_data" "train_data.QC.clumped.pruned"
[5] "6" "0.001"
[7] "100"
[1] "IterationDOne"
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 95 founders and 0 nonfounders present.
Calculating allele frequencies... 101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899%
Warning: 476961 lines skipped in --q-score-range data file.
done.
Total genotyping rate is 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/test_data.*.profile.
Continous Phenotype!
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
Using 1 thread (no multithreaded calculations invoked).
Before main variant filters, 95 founders and 0 nonfounders present.
Calculating allele frequencies... 101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899%
Warning: 476961 lines skipped in --q-score-range data file.
done.
Total genotyping rate is 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/test_data.*.profile.
Continous Phenotype!
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
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 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/test_data.*.profile.
Continous Phenotype!
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_4/tlpSum/train_data.log.
Options in effect:
--bfile SampleData1/Fold_4/train_data.QC.clumped.pruned
--out SampleData1/Fold_4/tlpSum/train_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
22657 variants loaded from .bim file.
380 people (186 males, 194 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 exactly 1.
22657 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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_4/tlpSum/test_data.log.
Options in effect:
--bfile SampleData1/Fold_4/test_data
--out SampleData1/Fold_4/tlpSum/test_data
--q-score-range SampleData1/Fold_4/range_list SampleData1/Fold_4/SNP.pvalue
--score SampleData1/Fold_4/Train_data.tlpSum 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
551892 variants loaded from .bim file.
95 people (41 males, 54 females) loaded from .fam.
95 phenotype values loaded from .fam.
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 0.999896.
551892 variants and 95 people pass filters and QC.
Phenotype data is quantitative.
--score: 22657 valid predictors loaded.
Warning: 476961 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_4/tlpSum/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 tlpSum.py 0
python tlpSum.py 1
python tlpSum.py 2
python tlpSum.py 3
python tlpSum.py 4
The following files should exist after the execution:
SampleData1/Fold_0/tlpSum/Results.csvSampleData1/Fold_1/tlpSum/Results.csvSampleData1/Fold_2/tlpSum/Results.csvSampleData1/Fold_3/tlpSum/Results.csvSampleData1/Fold_4/tlpSum/Results.csv
Check the results file for each fold.#
import os
result_directory = "tlpSum"
# 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: 160
Fold_ 1 Yes, the file exists.
Number of P-values processed: 160
Fold_ 2 Yes, the file exists.
Number of P-values processed: 160
Fold_ 3 Yes, the file exists.
Number of P-values processed: 160
Fold_ 4 Yes, the file exists.
Number of P-values processed: 160
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',
"tlpsum_lambda" ,
"tlpsum_tau" ,
"tlpsum_s" ,
"convergencethreshold",
"iteration",
]
# 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]
#print(common_rows)
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: 160
Unique rows in next DataFrame: 160
Common rows after merge: 160
Iteration 2:
Unique rows in current common DataFrame: 160
Unique rows in next DataFrame: 160
Common rows after merge: 160
Iteration 3:
Unique rows in current common DataFrame: 160
Unique rows in next DataFrame: 160
Common rows after merge: 160
Iteration 4:
Unique rows in current common DataFrame: 160
Unique rows in next DataFrame: 160
Common rows after merge: 160
DataFrame 1 with extracted common rows has 160 rows.
DataFrame 2 with extracted common rows has 160 rows.
DataFrame 3 with extracted common rows has 160 rows.
DataFrame 4 with extracted common rows has 160 rows.
DataFrame 5 with extracted common rows has 160 rows.
clump_p1 clump_r2 clump_kb p_window_size p_slide_size \
0 1.0 0.1 200.0 200.0 50.0
1 1.0 0.1 200.0 200.0 50.0
2 1.0 0.1 200.0 200.0 50.0
3 1.0 0.1 200.0 200.0 50.0
4 1.0 0.1 200.0 200.0 50.0
.. ... ... ... ... ...
155 1.0 0.1 200.0 200.0 50.0
156 1.0 0.1 200.0 200.0 50.0
157 1.0 0.1 200.0 200.0 50.0
158 1.0 0.1 200.0 200.0 50.0
159 1.0 0.1 200.0 200.0 50.0
p_LD_threshold pvalue numberofpca tempalpha l1weight ... \
0 0.25 1.000000e-10 6.0 0.1 0.1 ...
1 0.25 3.359818e-10 6.0 0.1 0.1 ...
2 0.25 1.128838e-09 6.0 0.1 0.1 ...
3 0.25 3.792690e-09 6.0 0.1 0.1 ...
4 0.25 1.274275e-08 6.0 0.1 0.1 ...
.. ... ... ... ... ... ...
155 0.25 7.847600e-03 6.0 0.1 0.1 ...
156 0.25 2.636651e-02 6.0 0.1 0.1 ...
157 0.25 8.858668e-02 6.0 0.1 0.1 ...
158 0.25 2.976351e-01 6.0 0.1 0.1 ...
159 0.25 1.000000e+00 6.0 0.1 0.1 ...
tlpsum_s convergencethreshold iteration tlpSum_count Train_pure_prs \
0 0.5 0.0001 100.0 1.0 6.211779e-05
1 0.5 0.0001 100.0 1.0 5.962893e-05
2 0.5 0.0001 100.0 1.0 6.135016e-05
3 0.5 0.0001 100.0 1.0 5.881835e-05
4 0.5 0.0001 100.0 1.0 5.338668e-05
.. ... ... ... ... ...
155 0.5 0.0010 100.0 4.0 5.419154e-07
156 0.5 0.0010 100.0 4.0 3.487532e-07
157 0.5 0.0010 100.0 4.0 2.158063e-07
158 0.5 0.0010 100.0 4.0 1.271082e-07
159 0.5 0.0010 100.0 4.0 7.122637e-08
Train_null_model Train_best_model Test_pure_prs Test_null_model \
0 0.23001 0.237424 5.728271e-05 0.118692
1 0.23001 0.238657 5.544787e-05 0.118692
2 0.23001 0.242130 6.118321e-05 0.118692
3 0.23001 0.244765 5.890476e-05 0.118692
4 0.23001 0.247383 5.383525e-05 0.118692
.. ... ... ... ...
155 0.23001 0.237176 4.783806e-07 0.118692
156 0.23001 0.237173 3.069725e-07 0.118692
157 0.23001 0.237191 1.900140e-07 0.118692
158 0.23001 0.237197 1.119822e-07 0.118692
159 0.23001 0.237197 6.273614e-08 0.118692
Test_best_model
0 0.117234
1 0.118535
2 0.125606
3 0.128001
4 0.135118
.. ...
155 0.104503
156 0.104487
157 0.104594
158 0.104558
159 0.104558
[160 rows x 22 columns]
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:
| | 118 |
|:---------------------|--------------:|
| clump_p1 | 1 |
| clump_r2 | 0.1 |
| clump_kb | 200 |
| p_window_size | 200 |
| p_slide_size | 50 |
| p_LD_threshold | 0.25 |
| pvalue | 0.297635 |
| numberofpca | 6 |
| tempalpha | 0.1 |
| l1weight | 0.1 |
| tlpsum_lambda | 0.001 |
| tlpsum_tau | 0.1 |
| tlpsum_s | 0.5 |
| convergencethreshold | 0.001 |
| iteration | 100 |
| tlpSum_count | 2 |
| Train_pure_prs | 2.64545e-06 |
| Train_null_model | 0.23001 |
| Train_best_model | 0.381661 |
| Test_pure_prs | 2.83249e-06 |
| Test_null_model | 0.118692 |
| Test_best_model | 0.320262 |
2. Reporting Generalized Performance:
| | 118 |
|:---------------------|--------------:|
| clump_p1 | 1 |
| clump_r2 | 0.1 |
| clump_kb | 200 |
| p_window_size | 200 |
| p_slide_size | 50 |
| p_LD_threshold | 0.25 |
| pvalue | 0.297635 |
| numberofpca | 6 |
| tempalpha | 0.1 |
| l1weight | 0.1 |
| tlpsum_lambda | 0.001 |
| tlpsum_tau | 0.1 |
| tlpsum_s | 0.5 |
| convergencethreshold | 0.001 |
| iteration | 100 |
| tlpSum_count | 2 |
| Train_pure_prs | 2.64545e-06 |
| Train_null_model | 0.23001 |
| Train_best_model | 0.381661 |
| Test_pure_prs | 2.83249e-06 |
| Test_null_model | 0.118692 |
| Test_best_model | 0.320262 |
| Difference | 0.0613987 |
| Sum | 0.701923 |
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.
