SCT#
In this notebook, we will use SCT (Staked Clumping and Thresholding) to calculate the Polygenic Risk Score (PRS).
Note: SCT needs to be installed using R.
Install SCT#
Install SCT using the following commands:
Activate the conda Environment.
Type R
Run the following commands:
install.packages("remotes")
library(remotes)
remotes::install_github("https://github.com/privefl/bigsnpr.git")
The content in this notebook has been taken from the https://privefl.github.io/bigsnpr/articles/SCT.html
Thanks to Florian Privé for creating one of the best documentations explaining each aspect of the calculation.
The following SCR.R file is required for execution.
args <- commandArgs(trailingOnly = TRUE)
print(args)
# Argument Descriptions
#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`
if (args[5]=="1"){
cran_mirror_url <- "https://cran.r-project.org"
install.packages("remotes", repos = cran_mirror_url)
library(remotes)
#remotes::install_github("https://github.com/privefl/bigsnpr.git")
library(bigsnpr)
options(bigstatsr.check.parallel.blas = FALSE)
options(default.nproc.blas = NULL)
library(data.table)
library(magrittr)
info <- readRDS(runonce::download_file(
"https://ndownloader.figshare.com/files/25503788",
fname = "map_hm3_ldpred2.rds"))
library(bigsnpr)
options(bigstatsr.check.parallel.blas = FALSE)
options(default.nproc.blas = NULL)
library(data.table)
library(magrittr)
help(snp_cor)
}
if (args[5]=="2"){
library(bigsnpr)
options(bigstatsr.check.parallel.blas = FALSE)
options(default.nproc.blas = NULL)
library(data.table)
library(magrittr)
result <-paste(".",args[2],paste(args[4],toString(".rds"), sep = ""),sep="//")
if (file.exists(result)) {
file.remove(result)
print(paste("File", result, "deleted."))
}
result <-paste(".",args[2],paste(args[4],toString(".bk"), sep = ""),sep="//")
if (file.exists(result)) {
file.remove(result)
print(paste("File", result, "deleted."))
}
result <-paste(".",args[2],paste(args[4],toString(".bed"), sep = ""),sep="//")
snp_readBed(result)
# now attach the genotype object
result <-paste(".",args[2],paste(args[4],toString(".rds"), sep = ""),sep="//")
obj.bigSNP <- snp_attach(result)
str(obj.bigSNP, max.level = 2, strict.width = "cut")
G <- obj.bigSNP$genotypes
CHR <- obj.bigSNP$map$chromosome
POS <- obj.bigSNP$map$physical.pos
y <- obj.bigSNP$fam$affection - 1
NCORES <- nb_cores()
# Check some counts for the 10 first variants
big_counts(G, ind.col = 1:10)
result <-paste(".",args[1],paste(args[1],toString("SCT.txt"), sep = ""),sep="//")
sumstats <- bigreadr::fread2(result)
set.seed(1)
ind.train <- sample(nrow(G) )
names(sumstats) <- c("chr", "rsid", "pos", "a0", "a1", "beta", "p")
#sumstats$pos <- as.character(sumstats$pos)
#map$pos <- as.character(map$pos)
map <- obj.bigSNP$map[,-(2:3)]
names(map) <- c("chr", "pos", "a0", "a1")
info_snp <- snp_match(sumstats, map)
info_snp <- snp_match(sumstats, map, strand_flip = FALSE)
# beta and lpval need to have the same length as ncol(G), CHR and POS
# -> one solution is to use missing values and use the 'exclude' parameter
beta <- rep(NA, ncol(G))
beta[info_snp$`_NUM_ID_`] <- info_snp$beta
lpval <- rep(NA, ncol(G))
lpval[info_snp$`_NUM_ID_`] <- -log10(info_snp$p)
lpval[is.na(lpval)] <- 0
beta[is.na(beta)] <- 0
# The clumping step might take some time to complete
all_keep <- snp_grid_clumping(G, CHR, POS, ind.row = ind.train,
lpS = lpval, exclude = which(is.na(lpval)),
ncores = NCORES)
attr(all_keep, "grid")
result <-paste(".",args[2],"public-data-scores.bk",sep="//")
print(result)
if (file.exists(result)) {
file.remove(result)
print(paste("File", result, "deleted."))
}
result <-paste(".",args[2],"public-data-scores",sep="//")
multi_PRS <- snp_grid_PRS(G, all_keep, beta, lpval, ind.row = ind.train,
backingfile = result,
n_thr_lpS = 1, ncores = NCORES)
dim(multi_PRS) ## 4200 C+T scores for 400 individuals''
final_mod <- snp_grid_stacking(multi_PRS, y[ind.train], ncores = NCORES, K = 4)
new_beta <- final_mod$beta.G
ind <- which(new_beta != 0)
info_snp$newbeta <-new_beta
print(head(new_beta))
result <-paste(".",args[2],paste(args[3],toString(".sct"), sep = ""),sep="//")
write.table(info_snp, file = result, row.names = FALSE,sep="\t", quote = FALSE)
}
GWAS file processing for SCT.#
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
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, # LDpred-2 requires betas for calculation
# 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_converted = pd.DataFrame({
'chromosome': df['CHR'].astype(int), # Convert 'CHR' to integer
'marker.ID': df['SNP'].astype(str), # Convert 'SNP' to string
'physical.pos': df['BP'].astype(int), # Convert 'BP' to integer
'allele1': df['A1'].astype(str), # Convert 'A1' to string
'allele2': df['A2'].astype(str), # Convert 'A2' to string
'beta': df['BETA'].astype(float), # Convert 'BETA' to float
'p': df['P'].astype(float) # Convert 'P' to float
})
print("Length of DataFrame!",len(df_converted))
df_converted.dropna(inplace=True)
df_converted.to_csv(filedirec + os.sep +filedirec+"SCT.txt",sep="\t",index=False)
print(df_converted.head().to_markdown())
print("Length of DataFrame!",len(df_converted))
Length of DataFrame! 499617
| | chromosome | marker.ID | physical.pos | allele1 | allele2 | beta | p |
|---:|-------------:|:------------|---------------:|:----------|:----------|------------:|---------:|
| 0 | 1 | rs3131962 | 756604 | A | G | -0.00211532 | 0.483171 |
| 1 | 1 | rs12562034 | 768448 | A | G | 0.00068708 | 0.834808 |
| 2 | 1 | rs4040617 | 779322 | G | A | -0.00239932 | 0.42897 |
| 3 | 1 | rs79373928 | 801536 | G | T | 0.00203363 | 0.808999 |
| 4 | 1 | rs11240779 | 808631 | G | A | 0.00130747 | 0.590265 |
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 = "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","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
prs_result = pd.DataFrame()
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):
# The geno tag is specific to SCT.
command = [
"./plink",
"--geno",str(0.00000000000001),
"--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):
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),
"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):
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),
"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 SCT#
def transform_sct_data(traindirec, newtrainfilename,p, 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)
#raise
# 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")
import glob
def delete_files_with_prefix(directory, filename_prefix,prefix):
"""
Deletes all files in the specified directory that start with the given filename prefix.
Parameters:
directory (str): The directory where the files are located.
filename_prefix (str): The prefix of the filenames to be deleted.
"""
# Construct the full file prefix
file_prefix = os.path.join(directory, filename_prefix + prefix)
# Find all files that match the prefix
files_to_delete = glob.glob(file_prefix + "*")
# Delete each file
for file in files_to_delete:
try:
os.remove(file)
print(f"Deleted: {file}")
except Exception as e:
print(f"Failed to delete {file}: {e}")
# Delete the files generated in the previous iteration.
delete_files_with_prefix(traindirec, "","train_data.sctgwas")
delete_files_with_prefix(traindirec, "","train_data.sct")
# 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)
os.system("Rscript SCT.R "+os.path.join(filedirec)+" "+traindirec+" "+trainfilename+" "+newtrainfilename+".clumped.pruned"+ " "+"2"+" ")
temp = pd.read_csv(traindirec+os.sep+"train_data.sct",sep="\s+" )
# After obtaining betas from the LDpred-2
# Append the new betas.
if check_phenotype_is_binary_or_continous(filedirec)=="Binary":
temp["newbeta"] = np.exp(temp["newbeta"])
else:
pass
temp.iloc[:,[4,2,9]].to_csv(traindirec+os.sep+"train_data.sctgwas",sep="\t",index=False)
print(temp.iloc[:,[4,2,9]].head())
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.sctgwas", "1", "2", "3", "header",
"--q-score-range", traindirec+os.sep+"range_list",traindirec+os.sep+"SNP_SBLUP.pvalue",
#"--extract", traindirec+os.sep+trainfilename+".valid.snp",
"--out", traindirec+os.sep+Name+os.sep+trainfilename
]
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.sctgwas", "1", "2", "3", "header",
"--q-score-range", traindirec+os.sep+"range_list",traindirec+os.sep+"SNP_SBLUP.pvalue",
"--out", folddirec+os.sep+Name+os.sep+testfilename
]
subprocess.run(command)
heritability = ""
numberofvariants = ""
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)
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)
result_directory = "sct"
# 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:
transform_sct_data(folddirec, newtrainfilename, p, 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
--geno 1e-14
--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.
4954 variants removed due to missing genotype data (--geno).
486998 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
Pruned 18583 variants from chromosome 1, leaving 20253.
Pruned 19369 variants from chromosome 2, leaving 19966.
Pruned 16190 variants from chromosome 3, leaving 16952.
Pruned 15208 variants from chromosome 4, leaving 15930.
Pruned 13989 variants from chromosome 5, leaving 15272.
Pruned 19069 variants from chromosome 6, leaving 14712.
Pruned 12921 variants from chromosome 7, leaving 13911.
Pruned 12240 variants from chromosome 8, leaving 12900.
Pruned 9814 variants from chromosome 9, leaving 11422.
Pruned 11815 variants from chromosome 10, leaving 12785.
Pruned 11985 variants from chromosome 11, leaving 12152.
Pruned 10809 variants from chromosome 12, leaving 11974.
Pruned 7806 variants from chromosome 13, leaving 9208.
Pruned 7517 variants from chromosome 14, leaving 8381.
Pruned 7274 variants from chromosome 15, leaving 8103.
Pruned 7941 variants from chromosome 16, leaving 8895.
Pruned 7360 variants from chromosome 17, leaving 8310.
Pruned 6656 variants from chromosome 18, leaving 8218.
Pruned 6331 variants from chromosome 19, leaving 6407.
Pruned 5876 variants from chromosome 20, leaving 7170.
Pruned 3389 variants from chromosome 21, leaving 4075.
Pruned 3744 variants from chromosome 22, leaving 4116.
Pruning complete. 235886 of 486998 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: 251112 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.
251112 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--clump: 172070 clumps formed from 251112 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.
248502 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: 172070 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.
172070 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 3 variants from chromosome 1, leaving 13939.
Pruned 3 variants from chromosome 2, leaving 13765.
Pruned 2 variants from chromosome 3, leaving 11711.
Pruned 1 variant from chromosome 4, leaving 11001.
Pruned 1 variant from chromosome 5, leaving 10592.
Pruned 47 variants from chromosome 6, leaving 9996.
Pruned 2 variants from chromosome 7, leaving 9457.
Pruned 3 variants from chromosome 8, leaving 8806.
Pruned 0 variants from chromosome 9, leaving 7757.
Pruned 2 variants from chromosome 10, leaving 8773.
Pruned 13 variants from chromosome 11, leaving 8364.
Pruned 2 variants from chromosome 12, leaving 8131.
Pruned 0 variants from chromosome 13, leaving 6312.
Pruned 1 variant from chromosome 14, leaving 5709.
Pruned 0 variants from chromosome 15, leaving 5545.
Pruned 0 variants from chromosome 16, leaving 6032.
Pruned 1 variant from chromosome 17, leaving 5692.
Pruned 0 variants from chromosome 18, leaving 5566.
Pruned 1 variant from chromosome 19, leaving 4344.
Pruned 0 variants from chromosome 20, leaving 4890.
Pruned 0 variants from chromosome 21, leaving 2795.
Pruned 0 variants from chromosome 22, leaving 2811.
Pruning complete. 82 of 172070 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: 172070 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.
172070 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 1807 variants from chromosome 1, leaving 12135.
Pruned 1848 variants from chromosome 2, leaving 11920.
Pruned 1548 variants from chromosome 3, leaving 10165.
Pruned 1411 variants from chromosome 4, leaving 9591.
Pruned 1353 variants from chromosome 5, leaving 9240.
Pruned 1270 variants from chromosome 6, leaving 8773.
Pruned 1224 variants from chromosome 7, leaving 8235.
Pruned 1125 variants from chromosome 8, leaving 7684.
Pruned 905 variants from chromosome 9, leaving 6852.
Pruned 1073 variants from chromosome 10, leaving 7702.
Pruned 1041 variants from chromosome 11, leaving 7336.
Pruned 1052 variants from chromosome 12, leaving 7081.
Pruned 764 variants from chromosome 13, leaving 5548.
Pruned 663 variants from chromosome 14, leaving 5047.
Pruned 597 variants from chromosome 15, leaving 4948.
Pruned 703 variants from chromosome 16, leaving 5329.
Pruned 607 variants from chromosome 17, leaving 5086.
Pruned 656 variants from chromosome 18, leaving 4910.
Pruned 399 variants from chromosome 19, leaving 3946.
Pruned 556 variants from chromosome 20, leaving 4334.
Pruned 291 variants from chromosome 21, leaving 2504.
Pruned 279 variants from chromosome 22, leaving 2532.
Pruning complete. 21172 of 172070 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.
172070 variants loaded from .bim file.
95 people (44 males, 51 females) loaded from .fam.
95 phenotype values loaded from .fam.
--extract: 172070 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 exactly 1.
172070 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.
172070 variants loaded from .bim file.
380 people (183 males, 197 females) loaded from .fam.
380 phenotype values loaded from .fam.
--extract: 172070 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 exactly 1.
172070 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 .
Deleted: SampleData1/Fold_0/train_data.sctgwas
Deleted: SampleData1/Fold_0/train_data.sct
FID IID Sex
0 HG00097 HG00097 2
1 HG00099 HG00099 2
2 HG00101 HG00101 1
3 HG00102 HG00102 2
4 HG00103 HG00103 1
380
380
[1] "SampleData1" "SampleData1/Fold_0"
[3] "train_data" "train_data.QC.clumped.pruned"
[5] "2"
Loading required package: bigstatsr
[1] "File .//SampleData1/Fold_0//train_data.QC.clumped.pruned.rds deleted."
[1] "File .//SampleData1/Fold_0//train_data.QC.clumped.pruned.bk deleted."
List of 3
$ genotypes:Reference class 'FBM.code256' [package "bigstatsr"] with 16 fields
..and 26 methods, of which 12 are possibly relevant:
.. add_columns, as.FBM, bm, bm.desc, check_dimensions,
.. check_write_permissions, copy#envRefClass, initialize, initialize#FBM,
.. save, show#envRefClass, show#FBM
$ fam :'data.frame': 380 obs. of 6 variables:
..$ family.ID : chr [1:380] "HG00097" "HG00099" "HG00101" "HG00102" ...
..$ sample.ID : chr [1:380] "HG00097" "HG00099" "HG00101" "HG00102" ...
..$ paternal.ID: int [1:380] 0 0 0 0 0 0 0 0 0 0 ...
..$ maternal.ID: int [1:380] 0 0 0 0 0 0 0 0 0 0 ...
..$ sex : int [1:380] 2 2 1 2 1 1 1 1 2 1 ...
..$ affection : num [1:380] 171 172 170 173 170 ...
$ map :'data.frame': 172070 obs. of 6 variables:
..$ chromosome : int [1:172070] 1 1 1 1 1 1 1 1 1 1 ...
..$ marker.ID : chr [1:172070] "rs79373928" "rs4970382" "rs13303222" "rs7"..
..$ genetic.dist: num [1:172070] 0.587 0.621 0.621 0.621 0.621 ...
..$ physical.pos: int [1:172070] 801536 840753 849998 851390 862772 864490 8..
..$ allele1 : chr [1:172070] "G" "C" "A" "T" ...
..$ allele2 : chr [1:172070] "T" "T" "G" "G" ...
- attr(*, "class")= chr "bigSNP"
499,617 variants to be matched.
0 ambiguous SNPs have been removed.
172,070 variants have been matched; 0 were flipped and 1,641 were reversed.
499,617 variants to be matched.
172,070 variants have been matched; 0 were flipped and 1,641 were reversed.
[1] ".//SampleData1/Fold_0//public-data-scores.bk"
[1] "File .//SampleData1/Fold_0//public-data-scores.bk deleted."
[1] 0.0000000000 -0.0009204524 0.0007028182 0.0045679941 -0.0056529391
[6] -0.0008647615
Warning message:
package ‘magrittr’ was built under R version 4.1.3
rsid a0 newbeta
0 rs79373928 G 0.000000
1 rs4970382 C -0.000920
2 rs13303222 A 0.000703
3 rs72631889 T 0.004568
4 rs192998324 G -0.005653
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/sct/train_data.log.
Options in effect:
--bfile SampleData1/Fold_0/train_data.QC.clumped.pruned
--out SampleData1/Fold_0/sct/train_data
--q-score-range SampleData1/Fold_0/range_list SampleData1/Fold_0/SNP_SBLUP.pvalue
--score SampleData1/Fold_0/train_data.sctgwas 1 2 3 header
63761 MB RAM detected; reserving 31880 MB for main workspace.
172070 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... 0%1%2%3%4%5%6%7%8%9%10%11%12%13%14%15%16%17%18%19%20%21%22%23%24%25%26%27%28%29%30%31%32%33%34%35%36%37%38%39%40%41%42%43%44%45%46%47%48%49%50%51%52%53%54%55%56%57%58%59%60%61%62%63%64%65%66%67%68%69%70%71%72%73%74%75%76%77%78%79%80%81%82%83%84%85%86%87%88%89%90%91%92%93%94%95%96%97%98%99% done.
Total genotyping rate is exactly 1.
172070 variants and 380 people pass filters and QC.
Phenotype data is quantitative.
--score: 172070 valid predictors loaded.
Warning: 852 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_0/sct/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/sct/test_data.log.
Options in effect:
--bfile SampleData1/Fold_0/test_data
--out SampleData1/Fold_0/sct/test_data
--q-score-range SampleData1/Fold_0/range_list SampleData1/Fold_0/SNP_SBLUP.pvalue
--score SampleData1/Fold_0/train_data.sctgwas 1 2 3 header
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.
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: 172070 valid predictors loaded.
Warning: 852 lines skipped in --q-score-range data file.
--score: 20 ranges processed.
Results written to SampleData1/Fold_0/sct/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 SCT.py 0
python SCT.py 1
python SCT.py 2
python SCT.py 3
python SCT.py 4
The following files should exist after the execution:
SampleData1/Fold_0/SCT/Results.csvSampleData1/Fold_1/SCT/Results.csvSampleData1/Fold_2/SCT/Results.csvSampleData1/Fold_3/SCT/Results.csvSampleData1/Fold_4/SCT/Results.csv
Check the results file for each fold.#
import os
# 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',
]
# 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 Train_pure_prs \
0 1.000000e-10 6.0 0.1 0.1 0.000023
1 3.359818e-10 6.0 0.1 0.1 0.000022
2 1.128838e-09 6.0 0.1 0.1 0.000024
3 3.792690e-09 6.0 0.1 0.1 0.000025
4 1.274275e-08 6.0 0.1 0.1 0.000024
5 4.281332e-08 6.0 0.1 0.1 0.000022
6 1.438450e-07 6.0 0.1 0.1 0.000020
7 4.832930e-07 6.0 0.1 0.1 0.000017
8 1.623777e-06 6.0 0.1 0.1 0.000015
9 5.455595e-06 6.0 0.1 0.1 0.000014
10 1.832981e-05 6.0 0.1 0.1 0.000012
11 6.158482e-05 6.0 0.1 0.1 0.000011
12 2.069138e-04 6.0 0.1 0.1 0.000009
13 6.951928e-04 6.0 0.1 0.1 0.000009
14 2.335721e-03 6.0 0.1 0.1 0.000008
15 7.847600e-03 6.0 0.1 0.1 0.000007
16 2.636651e-02 6.0 0.1 0.1 0.000005
17 8.858668e-02 6.0 0.1 0.1 0.000004
18 2.976351e-01 6.0 0.1 0.1 0.000003
19 1.000000e+00 6.0 0.1 0.1 0.000002
Train_null_model Train_best_model Test_pure_prs Test_null_model \
0 0.22945 0.241777 0.000011 0.12828
1 0.22945 0.242964 0.000008 0.12828
2 0.22945 0.252457 0.000014 0.12828
3 0.22945 0.257783 0.000014 0.12828
4 0.22945 0.262999 0.000015 0.12828
5 0.22945 0.265970 0.000012 0.12828
6 0.22945 0.272405 0.000012 0.12828
7 0.22945 0.273552 0.000010 0.12828
8 0.22945 0.273478 0.000009 0.12828
9 0.22945 0.279631 0.000008 0.12828
10 0.22945 0.286943 0.000007 0.12828
11 0.22945 0.294815 0.000006 0.12828
12 0.22945 0.295664 0.000005 0.12828
13 0.22945 0.313505 0.000005 0.12828
14 0.22945 0.338393 0.000005 0.12828
15 0.22945 0.357857 0.000004 0.12828
16 0.22945 0.360768 0.000003 0.12828
17 0.22945 0.366192 0.000003 0.12828
18 0.22945 0.369716 0.000002 0.12828
19 0.22945 0.371418 0.000001 0.12828
Test_best_model
0 0.138223
1 0.137800
2 0.147814
3 0.150393
4 0.160853
5 0.155081
6 0.156163
7 0.159356
8 0.163535
9 0.173988
10 0.183939
11 0.184179
12 0.179326
13 0.192260
14 0.220544
15 0.232180
16 0.242622
17 0.243304
18 0.241981
19 0.242207
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:
| | 19 |
|:-----------------|--------------:|
| clump_p1 | 1 |
| clump_r2 | 0.1 |
| clump_kb | 200 |
| p_window_size | 200 |
| p_slide_size | 50 |
| p_LD_threshold | 0.25 |
| pvalue | 1 |
| numberofpca | 6 |
| tempalpha | 0.1 |
| l1weight | 0.1 |
| Train_pure_prs | 2.17282e-06 |
| Train_null_model | 0.22945 |
| Train_best_model | 0.371418 |
| Test_pure_prs | 1.43033e-06 |
| Test_null_model | 0.12828 |
| Test_best_model | 0.242207 |
2. Reporting Generalized Performance:
| | 19 |
|:-----------------|--------------:|
| clump_p1 | 1 |
| clump_r2 | 0.1 |
| clump_kb | 200 |
| p_window_size | 200 |
| p_slide_size | 50 |
| p_LD_threshold | 0.25 |
| pvalue | 1 |
| numberofpca | 6 |
| tempalpha | 0.1 |
| l1weight | 0.1 |
| Train_pure_prs | 2.17282e-06 |
| Train_null_model | 0.22945 |
| Train_best_model | 0.371418 |
| Test_pure_prs | 1.43033e-06 |
| Test_null_model | 0.12828 |
| Test_best_model | 0.242207 |
| Difference | 0.129211 |
| Sum | 0.613625 |
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.
