def main():
parser = argparse.ArgumentParser()
parser.add_argument('--cancerType', dest='type',\
help='Cancer type to be collected')
parser.add_argument('--getData',dest='get', action='store_true',\
default=False,help='Set flag to get all data')
opts = parser.parse_args()
if opts.get:
for ds in ['brca', 'ccrcc', 'colon', 'ovarian', 'endometrial', 'luad']:
cptac.download(dataset=ds)
if opts.type.lower() == 'brca':
dat = cptac.Brca()
elif opts.type.lower() == 'ccrcc':
dat = cptac.Ccrcc()
elif opts.type.lower() == 'coad':
dat = cptac.Colon()
elif opts.type.lower() == 'ovca':
dat = cptac.Ovarian()
elif opts.type.lower() == 'luad':
dat = cptac.Luad()
elif opts.type.lower() == 'endometrial':
dat = cptac.Endometrial()
else:
exit()
df = dat.get_phosphoproteomics()
pdf = dat.get_proteomics()
# df.columns = [' '.join(col).strip() for col in df.columns.values]
df.to_csv(path_or_buf="phos_file.tsv", sep='\t')
pdf.to_csv(path_or_buf='prot_file.tsv', sep='\t')
def download(dataset, version="latest", redownload=False):
dataset = dataset.lower()
if dataset.startswith("pdc"):
return _pdc_download(dataset, version=version, redownload=redownload)
elif dataset.startswith("pancan") or dataset == "all":
box_token = get_box_token()
if dataset == "pancanbrca":
sources = BRCA_SOURCES
elif dataset == "pancanccrcc":
sources = CCRCC_SOURCES
elif dataset == "pancancoad":
sources = COAD_SOURCES
elif dataset == "pancangbm":
sources = GBM_SOURCES
elif dataset == "pancanhnscc":
sources = HNSCC_SOURCES
elif dataset == "pancanlscc":
sources = LSCC_SOURCES
elif dataset == "pancanluad":
sources = LUAD_SOURCES
elif dataset == "pancanov":
sources = OV_SOURCES
elif dataset == "pancanucec":
sources = UCEC_SOURCES
elif dataset == "all":
sources = BRCA_SOURCES + CCRCC_SOURCES + COAD_SOURCES + GBM_SOURCES + HNSCC_SOURCES + LSCC_SOURCES + LUAD_SOURCES + OV_SOURCES + UCEC_SOURCES
else:
raise InvalidParameterError(f"{dataset} is not a valid dataset.")
overall_success = True
for source in sources:
if source.startswith("pdc"):
single_success = download(source,
version=version,
redownload=redownload)
else:
single_success = cptac.download(source,
version=version,
redownload=redownload,
box_auth=True,
box_token=box_token)
if not single_success:
overall_success = False
return overall_success
else:
return cptac.download(dataset,
version=version,
redownload=redownload,
box_auth=True)
def download_datasets(get_datasets_lists):
# Download public datasets
for cancer in get_datasets_lists["public"]:
try:
print(f"Downloading {cancer}...", end='\r')
cptac.download(cancer, redownload=True)
except:
pytest.fail(f"Unable to download data for {cancer} dataset.")
# TODO: Download restricted datasets
return True
def downloadCptac():
# To view available datasets, enter 'cptac.list_data()'.
cptac.list_datasets()
cptac.download(dataset = "endometrial")
cptac.download(dataset = 'colon')
cptac.download(dataset = 'ovarian')
cptac.download(dataset = 'RenalCcrcc')
def cptacData():
'''
We need to collect and load CPTAC data
'''
print("Loading cptac datasets")
#we need to make sure all datasets are downloaded
##here are the cancers that are available without login information
allcans = ['brca', 'ccrcc', 'colon', 'ovarian', 'luad',\
#'hnscc','gbm','lscc',\
'endometrial']
print("Downloading cptac data")
for ct in allcans:
cptac.download(dataset=ct)
#then we load them into a dictionary
fdict = {'brca':cptac.Brca(), 'ccrcc':cptac.Ccrcc(),\
'colon':cptac.Colon(), 'ovarian':cptac.Ovarian(),\
#'hnscc':cptac.Hnscc(),'gbm':cptac.Gbm(), 'lscc':cptac.Lscc(),\
'endometrial':cptac.Endometrial(), 'luad':cptac.Luad()}
return fdict
def __init__(self):
cptac.download(dataset="endometrial", version='latest')
# cptac.download(dataset="brca", version='latest')
# cptac.download(dataset="gbm", version='latest')
# cptac.download(dataset="hsncc", version='latest')
# cptac.download(dataset="luad", version='latest')
cptac.download(dataset="ovarian", version='latest')
cptac.download(dataset="ccrcc", version='latest')
cptac.download(dataset="colon", version='latest')
self.en = cptac.Endometrial()
# self.brca = cptac.Brca()
# self.gbm = cptac.Gbm()
# self.hsncc = cptac.Hnscc()
# self.luad= cptac.Luad()
self.ovarian = cptac.Ovarian()
self.ccrcc = cptac.Ccrcc()
self.colon = cptac.Colon()
# self.datasets = list(self.en,self.brca,self.gbm,self.hsncc,self.luad,self.ovarian,self.ccrcc)
self.datasets = list([self.en, self.ovarian, self.ccrcc, self.colon])
#!/usr/bin/env python
# coding: utf-8
### Creation of BoxPlots for ESR1 Protien Expression ###
import cptac # import cptac to download cptac protein and clinical data
import pandas as pd # import pandas for
import matplotlib.pyplot as plt # import matplotlib for boxplot
import seaborn as sns # import seaborn for boxplot
from scipy import stats
from statannot import add_stat_annotation
cptac.download(dataset="Brca") # download breast cancer dataset
br = cptac.Brca() # save data in br variable
protein_data = br.get_proteomics() # save proteomic data
protein_data = protein_data.droplevel(1, axis=1) # remove multi index
clinical_data = br.get_clinical() # save clinical data
esr1 = protein_data["ESR1"] # save ESR1 protein expression column
clinical_data["ER.IHC.Score"] = clinical_data["ER.IHC.Score"].fillna(
"Not reported") # fill in null values
er_mask = clinical_data[
"ER.IHC.Score"] == "3+" # 3+ is ER-positive, create mask of ER-positive patients
patients = esr1[er_mask] # apply mask to protein expression data
ages = clinical_data["Age.in.Month"][er_mask] / 12 # calculate ages in years
er_positive_patients = pd.DataFrame(patients,
columns=["ESR1"]) # create new dataframe
er_positive_patients["Age"] = ages # apply ages to new column in dataframe
category = [] # set categories list
import cptac
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import scipy.stats as stats
#Alyssa's code
cptac.download(dataset="Brca")
br = cptac.Brca()
protein_data = br.get_proteomics()
#Remove the "multi" part of the dataframe (the dataframes are MultIndex pandas dataframes)
protein_data = protein_data.droplevel(1, axis=1)
rna_data = br.get_transcriptomics()
clinical_data = br.get_clinical()
clinical_data["Age_in_years"] = clinical_data["Age.in.Month"]/12
# clinical_data.to_csv("~/Desktop/qbioresearch/qbio_data_analysis_alyssa/data/clinical_data.csv")
# protein_data.to_csv("~/Desktop/qbioresearch/qbio_data_analysis_alyssa/data/protein_data.csv")
# rna_data.to_csv("~/Desktop/qbioresearch/qbio_data_analysis_alyssa/data/rna_data.csv")
# clinical_data_readin = pd.read_csv("~/Desktop/qbioresearch/qbio_data_analysis_alyssa/data/clinical_data.csv", index_col=1) #The index_col=0 creates the index (rownames) as the first column.
#Check that the patients are in the same order in rna_data and protein_data.
#We are looking at the gene expression and protein information of EACH patient, so the data needs to be in pairs.
# -*- coding: utf-8 -*-
“””bioinfoProteomicsHW4.ipynb
# Loading CPTAC Data in google colab using a Python package developed in the Payne lab at BYU.
"""
#install and import cptac and other python packages (just pandas in this case)
!pip install -q cptac
import cptac
import pandas as pd
#download endometrial data and creates a new endometrial class
cptac.download(dataset="Endometrial")
en = cptac.Endometrial()
#obtain proteomic data (enProt) and patient information (enInfo)
enProt = en.get_proteomics()
enInfo = en.get_clinical()
#i used google colab to do this, so need to mount my drive to be able to export the data
from google.colab import drive
drive.mount('drive')
#save proteome and clinical information tables to export and work on locally/in another language
enProt.to_csv("enProt.csv")
!cp enProt.csv "drive/My Drive"
enInfo.to_csv("enInfo.csv")
!cp enInfo.csv "drive/My Drive"
def setup_class(cls):
"""Download all datasets, and do any other setup."""
cptac.download(dataset="all", version="latest", redownload=False)
def _pdc_download(dataset, version, redownload, box_token):
"""Download data for the specified cancer type from the PDC."""
dataset = str.lower(dataset)
if dataset == "pdcall":
overall_result = True
for dataset in STUDY_IDS_MAP.keys():
if not _pdc_download(dataset, version, redownload):
overall_result = False
return overall_result
if not dataset.startswith("pdc"):
raise InvalidParameterError(
f"_pdc_download function can only be used for PDC datasets, which start with the prefix 'pdc'. You tried to download '{dataset}'."
)
if dataset not in STUDY_IDS_MAP.keys():
raise InvalidParameterError(
f"PDC dataset must be one of the following:\n{list(STUDY_IDS_MAP.keys())}\nYou passed '{dataset}'."
)
dataset_ids = STUDY_IDS_MAP[dataset]
# Download the file for mapping aliquots to patient IDs
if not cptac.download(dataset,
version=version,
redownload=redownload,
_box_auth=True,
_box_token=box_token):
return False
path_here = os.path.abspath(os.path.dirname(__file__))
cancer_dir = os.path.join(path_here, f"data_{dataset}")
# Check that the index file exists. If not, there was an uncaught error in the mapping file download.
index_path = os.path.join(cancer_dir, "index.txt")
if not os.path.isfile(index_path):
raise CptacDevError(
f"Index file not found at {index_path}. Mapping file download probably failed."
)
# See what data files we need to download
data_dir = os.path.join(cancer_dir, f"{dataset}_v1.0")
# If any of the files are missing, we're going to delete any remaining and redownload all, in case the missing files are a sign of a previous data problem
data_files = [f"{data_type}.tsv.gz"
for data_type in dataset_ids.keys()] + ["clinical.tsv.gz"]
for data_file in data_files:
data_file_path = os.path.join(data_dir, data_file)
if not os.path.isfile(data_file_path):
redownload = True
break
if redownload:
for data_file in data_files:
data_file_path = os.path.join(data_dir, data_file)
if os.path.isfile(data_file_path):
os.remove(data_file_path)
else:
return True # If all the files are there and the user didn't ask to redownload, we're done.
# Now download all the data files
# We'll combine all the clinical tables in case there are differences
master_clin = pd.DataFrame()
for data_type in dataset_ids.keys():
# Print an update
download_msg = f"Downloading {dataset} {data_type} files..."
print(download_msg, end="\r")
# Get the clinical and quantitative tables for the study ID
clin, quant = download_pdc_id(dataset_ids[data_type],
_download_msg=False)
# Print a new update
print(" " * len(download_msg), end="\r")
save_msg = f"Saving {dataset} {data_type} files..."
print(save_msg, end="\r")
# Append the clinical dataframe
#master_clin = master_clin.append(clin)
master_clin = pd.concat([master_clin, clin], axis=0, join='outer')
# Save the quantitative table
quant.to_csv(os.path.join(data_dir, f"{data_type}.tsv.gz"), sep="\t")
# Erase update
print(" " * len(save_msg), end="\r")
# Print an update
save_msg = f"Saving {dataset} clinical file..."
print(save_msg, end="\r")
# Drop any duplicated rows in combined clinical table, then save it too
master_clin = master_clin.drop_duplicates(keep="first")
master_clin.to_csv(os.path.join(data_dir, "clinical.tsv.gz"), sep="\t")
# Erase update
print(" " * len(save_msg), end="\r")
return True
def test_invalid_dataset(self):
with pytest.raises(InvalidParameterError) as exception_raised:
cptac.download("abc")
assert exception_raised.type == InvalidParameterError
'''
Get all cptac data
downloads data into docker image
'''
import cptac
for ds in ['brca', 'ccrcc', 'colon', 'ovarian']:
cptac.download(dataset=ds)
