def parse_methylation(project_id, bucket_name, filename, outfilename,
metadata):
"""Download and convert blob into dataframe
Transform the file: includes data cleaning
Add Metadata information
"""
# setup logging
configure_logging('mirna.isoform',
"logs/" + metadata['AliquotBarcode'] + '.log')
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
#main steps: download, convert to df, cleanup, transform, add metadata
data_df = gcutils.convert_blob_to_dataframe(gcs,
project_id,
bucket_name,
filename,
skiprows=1)
data_df.columns = [
'Probe_Id', "Beta_Value", "Gene_Symbol", "Chromosome",
"Genomic_Coordinate"
]
data_df = add_metadata(data_df, metadata)
data_df = additional_changes(data_df)
# upload the contents of the dataframe in njson format
df_string = data_df.to_csv(index=False, header=False, float_format='%.2f')
status = gcs.upload_blob_from_string(outfilename, df_string)
return status
def parse_methylation(project_id, bucket_name, filename, outfilename, metadata):
"""Download and convert blob into dataframe
Transform the file: includes data cleaning
Add Metadata information
"""
# setup logging
configure_logging('mirna.isoform', "logs/" + metadata['AliquotBarcode'] + '.log')
# connect to the cloud bucket
gcs = GcsConnector(project_id, bucket_name)
#main steps: download, convert to df, cleanup, transform, add metadata
data_df = gcutils.convert_blob_to_dataframe(gcs, project_id, bucket_name, filename, skiprows=1)
data_df.columns = ['Probe_Id', "Beta_Value", "Gene_Symbol", "Chromosome", "Genomic_Coordinate"]
data_df = add_metadata(data_df, metadata)
data_df = additional_changes(data_df)
# upload the contents of the dataframe in njson format
df_string = data_df.to_csv(index=False, header=False, float_format='%.2f')
status = gcs.upload_blob_from_string(outfilename, df_string)
return status
def generate_oncotator_inputfiles(project_id, bucket_name, filename,
outputfilename, oncotator_columns):
print(filename)
# NEW connection
gcs = GcsConnector(project_id, bucket_name)
filebuffer = gcs.download_blob_to_file(filename)
# convert blob into dataframe
try:
maf_df = convert_file_to_dataframe(filebuffer)
except:
print 'problem converting %s to a dataframe' % (filename)
raise
# clean-up dataframe
maf_df = cleanup_dataframe(maf_df)
print maf_df.columns
# lowercase the column names (WHY?)
maf_df.columns = map(lambda x: x.lower(), maf_df.columns)
#--------------------------------------------
# data - manipulation
#--------------------------------------------
maf_df["ncbi_build"] = maf_df["ncbi_build"].replace({
'hg19': '37',
'GRCh37': '37',
'GRCh37-lite': '37'
})
#---------------------------------------------
## Filters
## remember all the column names are lowercase
#---------------------------------------------
filters = {
"chromosome": map(str, range(1, 23)) + ['X', 'Y'],
"mutation_status": ['somatic', 'Somatic'],
"sequencer": ['Illumina HiSeq', 'Illumina GAIIx', 'Illumina MiSeq'],
"ncbi_build": ['37']
}
filter_checklist_df = maf_df.isin(filters)
filter_string = ((filter_checklist_df["chromosome"] == True)
& (filter_checklist_df["mutation_status"] == True)
& (filter_checklist_df["sequencer"] == True)
& (filter_checklist_df["ncbi_build"] == True))
maf_df = maf_df[filter_string]
#---------------------
#Oncotator part: generate intermediate files for Oncotator
#---------------------
# oncotator needs these columns
replace_column_names = {
"ncbi_build": 'build',
'chromosome': 'chr',
'start_position': 'start',
'end_position': 'end',
'reference_allele': 'ref_allele',
'tumor_seq_allele1': 'tum_allele1',
'tumor_seq_allele2': 'tum_allele2',
'tumor_sample_barcode': 'tumor_barcode',
'matched_norm_sample_barcode': 'normal_barcode'
}
# replace columns with new headings; just name change
for rcol in replace_column_names:
maf_df.columns = [
replace_column_names[x] if x == rcol else x for x in maf_df.columns
]
oncotator_columns = [
replace_column_names[y] if y == rcol else y
for y in oncotator_columns
]
# remove/mangle any duplicate columns ( we are naming line a, a.1, a.2 etc)
maf_df.columns = mangle_dupe_cols(maf_df.columns.values)
#---------------------
#Oncotator part: generate intermediate files for Oncotator
#---------------------
oncotator_df = maf_df[oncotator_columns]
print "df_columns", len(oncotator_df.columns)
df_stringIO = oncotator_df.to_csv(sep='\t',
index=False,
columns=oncotator_columns)
# upload the file
gcs.upload_blob_from_string(outputfilename, df_stringIO)
return True
def generate_oncotator_inputfiles(project_id, bucket_name, filename, outputfilename, oncotator_columns):
print (filename)
# NEW connection
gcs = GcsConnector(project_id, bucket_name)
filebuffer = gcs.download_blob_to_file(filename)
# convert blob into dataframe
maf_df = convert_file_to_dataframe(filebuffer)
# clean-up dataframe
maf_df = cleanup_dataframe(maf_df)
print maf_df.columns
# lowercase the column names (WHY?)
maf_df.columns = map(lambda x: x.lower(), maf_df.columns)
#--------------------------------------------
# data - manipulation
#--------------------------------------------
maf_df["ncbi_build"] = maf_df["ncbi_build"].replace({ 'hg19': '37'
,'GRCh37': '37'
,'GRCh37-lite': '37'
})
#---------------------------------------------
## Filters
## remember all the column names are lowercase
#---------------------------------------------
filters = {
"chromosome" : map(str,range(1,23)) + ['X', 'Y']
,"mutation_status": ['somatic', 'Somatic']
,"sequencer": ['Illumina HiSeq', 'Illumina GAIIx', 'Illumina MiSeq']
,"ncbi_build" : ['37']
}
filter_checklist_df = maf_df.isin(filters)
filter_string = (
(filter_checklist_df["chromosome"] == True)
&
(filter_checklist_df["mutation_status"] == True)
&
(filter_checklist_df["sequencer"] == True)
&
(filter_checklist_df["ncbi_build"] == True)
)
maf_df = maf_df[filter_string]
#---------------------
#Oncotator part: generate intermediate files for Oncotator
#---------------------
# oncotator needs these columns
replace_column_names = {
"ncbi_build" : 'build'
,'chromosome' : 'chr'
,'start_position' : 'start'
,'end_position' : 'end'
,'reference_allele' : 'ref_allele'
,'tumor_seq_allele1' : 'tum_allele1'
,'tumor_seq_allele2' : 'tum_allele2'
,'tumor_sample_barcode': 'tumor_barcode'
,'matched_norm_sample_barcode': 'normal_barcode'
}
# replace columns with new headings; just name change
for rcol in replace_column_names:
maf_df.columns = [replace_column_names[x] if x==rcol else x for x in maf_df.columns]
oncotator_columns = [replace_column_names[y] if y==rcol else y for y in oncotator_columns]
# remove/mangle any duplicate columns ( we are naming line a, a.1, a.2 etc)
maf_df.columns = mangle_dupe_cols(maf_df.columns.values)
#---------------------
#Oncotator part: generate intermediate files for Oncotator
#---------------------
oncotator_df = maf_df[oncotator_columns]
print "df_columns", len(oncotator_df.columns)
df_stringIO = oncotator_df.to_csv(sep='\t', index=False, columns= oncotator_columns)
# upload the file
gcs.upload_blob_from_string(outputfilename, df_stringIO)
return True
def main():
"""Parse GCT file, merge with barcodes info, melt(tidy)
and load to Google Storage and BigQuery
"""
project_id = ''
bucket_name = ''
# example file in bucket
filename = 'ccle/mRNA-gene-exp/CCLE_Expression_Entrez_2012-09-29.gct'
outfilename = 'test'
writer = ExcelWriter('ccle.xlsx')
# connect to the google cloud bucket
gcs = GcsConnector(project_id, bucket_name)
#------------------------------
# load the GCT file
# * the file has duplicate samples (columns)
#------------------------------
# To remove duplicates, load the first few lines of the file only. Get columns, unique and select dataframe
# this is a hack, but I cant find a elegant way to remove duplciates
gct_df = pd.read_table('CCLE_Expression_Entrez_2012-09-29.gct',
sep='\t',
skiprows=2,
mangle_dupe_cols=False,
nrows=2)
unqiue_columns = np.unique(gct_df.columns)
gct_df = pd.read_table('CCLE_Expression_Entrez_2012-09-29.gct',
sep='\t',
skiprows=2,
mangle_dupe_cols=True)
# clean-up the dataset/dataframe
gct_df = cleanup_dataframe(gct_df)
gct_df = gct_df[unqiue_columns]
# remove any gene_id starting with 'AFFX-'
gct_df[gct_df['Name'].str.startswith('AFFX-')].to_excel(
writer, sheet_name="affy_info")
gct_df = gct_df[~gct_df['Name'].str.startswith('AFFX-')]
#------------------------------
# HGNC validation
#-----------------------------
hgnc_df = hgnc_validation.get_hgnc_map()
hgnc_df.to_excel(writer, sheet_name="hgnc_info")
hgnc_dict = dict(zip(hgnc_df.entrez_id, hgnc_df.symbol))
gct_df['HGNC_gene_symbol'] = gct_df['Name'].map(
lambda gene_id: hgnc_dict.get(gene_id.replace('_at', ''), np.nan))
gct_df[['HGNC_gene_symbol', 'Name',
'Description']].to_excel(writer, sheet_name="gene_info")
gct_df['Name'] = gct_df['Name'].map(
lambda gene_id: gene_id.replace('_at', ''))
#------------------------------
# barcodes info
#------------------------------
barcodes_filename = 'ccle/mRNA-gene-exp/mRNA_names.out.tsv'
filebuffer = gcs.download_blob_to_file(barcodes_filename)
barcodes_df = pd.read_table(
filebuffer,
header=None,
names=['ParticipantBarcode', 'SampleBarcode',
'CCLE_long_name']) # convert into dataframe
barcodes_df = cleanup_dataframe(barcodes_df) # clean-up dataframe
#------------------------------
# ignore (drop) all of the columns from the gene-expression matrix
#that don't have corresponding Participant and Sample barcodes,
#------------------------------
columns_df = pd.DataFrame(unqiue_columns)
columns_df.columns = ['CCLE_long_name']
samples_map_df = pd.merge(columns_df,
barcodes_df,
on='CCLE_long_name',
how='inner')
samples_map_df.to_excel(writer, sheet_name="sample_info")
# select columns that are overlapping
overlapping_samples = samples_map_df['CCLE_long_name'].tolist()
overlapping_samples = overlapping_samples + [
'Name', 'Description', 'HGNC_gene_symbol'
]
gct_df = gct_df[overlapping_samples]
print gct_df
# melt the matrix
value_vars = [
col for col in gct_df.columns
if col not in ['Name', 'Description', 'HGNC_gene_symbol']
]
melted_df = pd.melt(gct_df,
id_vars=['Name', 'Description', 'HGNC_gene_symbol'],
value_vars=value_vars)
melted_df = melted_df.rename(
columns={
'Name': 'gene_id',
'Description': 'original_gene_symbol',
'variable': 'CCLE_long_name',
'value': 'RMA_normalized_expression'
})
# merge to get barcode information
# changed from outer join to inner join. In this case it shouldnt matter, since we already did a inner join
# while select the samples above.
data_df = pd.merge(melted_df,
samples_map_df,
on='CCLE_long_name',
how='inner')
data_df['Platform'] = "Affymetrix U133 Plus 2.0"
# reorder columns
col_order = [
"ParticipantBarcode", "SampleBarcode", "CCLE_long_name", "gene_id",
"HGNC_gene_symbol", "original_gene_symbol", "Platform",
"RMA_normalized_expression"
]
data_df = data_df[col_order]
# upload the contents of the dataframe in CSV format
print "Convert to CSV"
outfilename = "tcga/intermediary/CCLE_mrna_expr/bq_data_files/ccle_mrna_expr.csv"
df_string = data_df.to_csv(index=False, header=False)
status = gcs.upload_blob_from_string(outfilename, df_string)
print status
# save the excel file
writer.save()
