Skip to content

Commit c56e773

Browse files
alexandriai168alexandriai168
committed
more namechange
1 parent 8125391 commit c56e773

11 files changed

Lines changed: 38 additions & 38 deletions

‎build/build_dataset.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -47,7 +47,7 @@ def process_docker(dataset,validate):
4747
'sarcpdo': ['sarcpdo'],
4848
'genes': ['genes'],
4949
'upload': ['upload'],
50-
'crcPDO': ['crcPDO'],
50+
'crcpdo': ['crcpdo'],
5151
'bladderpdo': ['bladderpdo']
5252
}
5353

@@ -131,7 +131,7 @@ def process_omics(executor, dataset, should_continue):
131131
'sarcpdo': ['mutations', 'transcriptomics'],
132132
'pancpdo': ['transcriptomics'],
133133
'bladderpdo': ['copy_number', 'mutations', 'transcriptomics'],
134-
'crcPDO':['copy_number', 'mutations', 'transcriptomics']
134+
'crcpdo':['copy_number', 'mutations', 'transcriptomics']
135135
}
136136

137137
expected_omics = dataset_omics_files.get(dataset, [])

‎build/crcPDO/01-samples-crcPDO.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -180,6 +180,6 @@ def generate_sample_file(sequencing_data_path:str = None, prev_samples_path:str
180180
else:
181181
print("Previous sample sheet {} detected. Running sample file generation and checking for duplicate IDs.".format(args.prevSamples))
182182
sample_sheet = generate_sample_file(sequencing_data_path = sequencing_download_path, prev_samples_path= args.prevSamples)
183-
sample_sheet.to_csv("/tmp/crcPDO_samples.csv", index=False)
183+
sample_sheet.to_csv("/tmp/crcpdo_samples.csv", index=False)
184184

185185

‎build/crcPDO/02-omics-crcPDO.py‎

Lines changed: 9 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -82,7 +82,7 @@ def map_mutations(mutation_data, improve_id_data, entrez_data):
8282
mapped_mutation_data = mapped_mutation_data.rename(columns={'Entrez_Gene_Id':'entrez_id','Genome_Change':'mutation','Variant_Classification':'variant_classification'})
8383
mapped_mutation_data = mapped_mutation_data.drop(columns=['Hugo_Symbol','Tumor_Sample_Barcode','other_id'])
8484
mapped_mutation_data['source'] = "vandeWetering_2015"
85-
mapped_mutation_data['study'] = "crcPDO"
85+
mapped_mutation_data['study'] = "crcpdo"
8686
mapped_mutation_data = mapped_mutation_data.astype({'entrez_id':'int'})
8787

8888
return(mapped_mutation_data)
@@ -136,7 +136,7 @@ def map_transcriptomics(transciptomics_data, improve_id_data, entrez_data):
136136
# clean up column names and data types
137137
mapped_transcriptomics_df = mapped_transcriptomics_df.drop(columns=['stable_id','patient','other_id'])
138138
mapped_transcriptomics_df['source'] = "vandeWetering_2015"
139-
mapped_transcriptomics_df['study'] = "crcPDO"
139+
mapped_transcriptomics_df['study'] = "crcpdo"
140140
mapped_transcriptomics_df = mapped_transcriptomics_df.astype({'entrez_id':'int','improve_sample_id':'int'})
141141
mapped_transcriptomics_df = mapped_transcriptomics_df[['entrez_id','transcriptomics','improve_sample_id','source','study']]
142142

@@ -198,7 +198,7 @@ def map_copy_number(copy_number_data, improve_id_data, entrez_data):
198198
# clean up columns and data types
199199
improve_mapped_cn_df = improve_mapped_cn_df.drop(columns=['ID','score','other_id'])
200200
improve_mapped_cn_df['source'] = "vandeWetering_2015"
201-
improve_mapped_cn_df['study'] = "crcPDO"
201+
improve_mapped_cn_df['study'] = "crcpdo"
202202
improve_mapped_cn_df = improve_mapped_cn_df.rename(columns={'ENTREZID':'entrez_id'})
203203
improve_mapped_cn_df = improve_mapped_cn_df.astype({'entrez_id':'int','improve_sample_id':'int'})
204204
improve_mapped_cn_df = improve_mapped_cn_df[['entrez_id','copy_number','copy_call','study','source','improve_sample_id']]
@@ -241,8 +241,8 @@ def map_copy_number(copy_number_data, improve_id_data, entrez_data):
241241
exit()
242242
else:
243243
print("Starting transcriptomics data.")
244-
transcriptomics_df = map_transcriptomics(transciptomics_data = "/tmp/GSE65253_col_tum_org_merge.csv.gz", improve_id_data = "/tmp/crcPDO_samples.csv", entrez_data = "/tmp/genes.csv")
245-
transcriptomics_df.to_csv("/tmp/crcPDO_transcriptomics.csv", index=False)
244+
transcriptomics_df = map_transcriptomics(transciptomics_data = "/tmp/GSE65253_col_tum_org_merge.csv.gz", improve_id_data = "/tmp/crcpdo_samples.csv", entrez_data = "/tmp/genes.csv")
245+
transcriptomics_df.to_csv("/tmp/crcpdo_transcriptomics.csv", index=False)
246246

247247
if args.mutations:
248248
if args.genes is None or args.genes=='':
@@ -253,8 +253,8 @@ def map_copy_number(copy_number_data, improve_id_data, entrez_data):
253253
exit()
254254
else:
255255
print("Starting mutations data.")
256-
mutation_df = map_mutations(mutation_data = "/tmp/mutation_data.csv", improve_id_data = "/tmp/crcPDO_samples.csv", entrez_data = "/tmp/genes.csv")
257-
mutation_df.to_csv("/tmp/crcPDO_mutations.csv", index=False)
256+
mutation_df = map_mutations(mutation_data = "/tmp/mutation_data.csv", improve_id_data = "/tmp/crcpdo_samples.csv", entrez_data = "/tmp/genes.csv")
257+
mutation_df.to_csv("/tmp/crcpdo_mutations.csv", index=False)
258258

259259
if args.copy_number:
260260
if args.genes is None or args.genes=='':
@@ -265,6 +265,6 @@ def map_copy_number(copy_number_data, improve_id_data, entrez_data):
265265
exit()
266266
else:
267267
print("Starting copy number data.")
268-
mutation_df = map_copy_number(copy_number_data = "/tmp/copy_num_data.csv", improve_id_data = "/tmp/crcPDO_samples.csv", entrez_data = "/tmp/genes.csv")
269-
mutation_df.to_csv("/tmp/crcPDO_copy_number.csv", index=False)
268+
mutation_df = map_copy_number(copy_number_data = "/tmp/copy_num_data.csv", improve_id_data = "/tmp/crcpdo_samples.csv", entrez_data = "/tmp/genes.csv")
269+
mutation_df.to_csv("/tmp/crcpdo_copy_number.csv", index=False)
270270

‎build/crcPDO/03-drug-crcPDO.py‎

Lines changed: 7 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -43,18 +43,18 @@ def download_synapse_data(synID:str, save_path:str = None, synToken:str = None):
4343

4444

4545
### create drug csv
46-
def create_crcPDO_drug_data(fitted_drug_data_path:str, prevDrugFilepath:str, output_drug_data_path:str):
46+
def create_crcpdo_drug_data(fitted_drug_data_path:str, prevDrugFilepath:str, output_drug_data_path:str):
4747
# import fitted drug data and get drug names from DRUG_NAME column
4848
fitted_drug_df = pd.read_csv(fitted_drug_data_path)
49-
crcPDO_drugs_df = pd.DataFrame({"DRUG_NAME":fitted_drug_df['DRUG_NAME'].unique()})
49+
crcpdo_drugs_df = pd.DataFrame({"DRUG_NAME":fitted_drug_df['DRUG_NAME'].unique()})
5050
# if there is a prev drug file, check for new drugs
5151
if prevDrugFilepath != None and prevDrugFilepath != "":
5252
prev_drug_df = pd.read_csv(prevDrugFilepath)
53-
# get drugs that are only in the crcPDO_drugs_df (aka new drugs only)
54-
new_drugs_df = crcPDO_drugs_df[~crcPDO_drugs_df.chem_name.isin(prev_drug_df.chem_name)]
53+
# get drugs that are only in the crcpdo_drugs_df (aka new drugs only)
54+
new_drugs_df = crcpdo_drugs_df[~crcpdo_drugs_df.chem_name.isin(prev_drug_df.chem_name)]
5555
else:
5656
# if there's no prev drugs, then all drugs are new
57-
new_drugs_df = crcPDO_drugs_df
57+
new_drugs_df = crcpdo_drugs_df
5858
# get new drug names
5959
new_drug_names = new_drugs_df['DRUG_NAME'].unique()
6060
# call function that gets info for these drugs
@@ -89,8 +89,8 @@ def create_crcPDO_drug_data(fitted_drug_data_path:str, prevDrugFilepath:str, out
8989
if args.Drug:
9090
if args.PrevDrugs is None or args.PrevDrugs=='':
9191
print("No previous drugs file provided. Starting improve_drug_id from SMI_1. Running drug file generation")
92-
create_crcPDO_drug_data(fitted_drug_data_path = "/tmp/fitted_data_GDSC_Org_restricted_11Mar25.csv", output_drug_data_path = "/tmp/crcPDO_drugs.tsv", prevDrugFilepath = "")
92+
create_crcpdo_drug_data(fitted_drug_data_path = "/tmp/fitted_data_GDSC_Org_restricted_11Mar25.csv", output_drug_data_path = "/tmp/crcpdo_drugs.tsv", prevDrugFilepath = "")
9393
else:
9494
print("Previous drugs file {} detected. Running drugs file generation and checking for duplicate IDs.".format(args.PrevDrugs))
95-
create_crcPDO_drug_data(fitted_drug_data_path = "/tmp/fitted_data_GDSC_Org_restricted_11Mar25.csv", prevDrugFilepath = args.PrevDrugs, output_drug_data_path = "/tmp/crcPDO_drugs.tsv")
95+
create_crcpdo_drug_data(fitted_drug_data_path = "/tmp/fitted_data_GDSC_Org_restricted_11Mar25.csv", prevDrugFilepath = args.PrevDrugs, output_drug_data_path = "/tmp/crcpdo_drugs.tsv")
9696

‎build/crcPDO/04-experiments-crcPDO.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -109,6 +109,6 @@ def create_experiments_data(experiment_data_path:str, samples_data_path:str, dru
109109
else:
110110
print("Generating experiments data.")
111111
experiments_df = create_experiments_data(experiment_data_path = "/tmp/raw_data_GDSC_Org_restricted_11Mar25_plus_viabilities.csv", samples_data_path = args.Samples, drugs_data_path = args.Drugs)
112-
output_path = "/tmp/crcPDO_experiments_for_curve_fitting.tsv"
112+
output_path = "/tmp/crcpdo_experiments_for_curve_fitting.tsv"
113113
print("Experiments data sucessfully generated. Saving tsv to {}".format(output_path))
114114
experiments_df.to_csv(output_path, sep='\t')

‎build/crcPDO/build_drugs.sh‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -5,8 +5,8 @@ echo "the variable is $1"
55
trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit 1' ERR
66

77
# running the drug python script
8-
echo "Running 03-drug-crcPDO.py with token and PrevDrugs $1."
9-
python3 03-drug-crcPDO.py --Download --Drug --Token $SYNAPSE_AUTH_TOKEN --PrevDrugs $1
8+
echo "Running 03-drug-crcpdo.py with token and PrevDrugs $1."
9+
python3 03-drug-crcpdo.py --Download --Drug --Token $SYNAPSE_AUTH_TOKEN --PrevDrugs $1
1010

1111
# running the drug descriptor python script
12-
python3 build_drug_desc.py --drugtable /tmp/crcPDO_drugs.tsv --desctable /tmp/crcPDO_drug_descriptors.csv.gz
12+
python3 build_drug_desc.py --drugtable /tmp/crcpdo_drugs.tsv --desctable /tmp/crcpdo_drug_descriptors.csv.gz

‎build/crcPDO/build_exp.sh‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -4,8 +4,8 @@ set -euo pipefail
44
trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit 1' ERR
55

66
# running the drug python script
7-
echo "Running 04-experiments-crcPDO.py with token, samples file $1 and drugs file $2."
8-
python3 04-experiments-crcPDO.py --Download --Experiment --Token $SYNAPSE_AUTH_TOKEN --Samples $1 --Drugs $2
7+
echo "Running 04-experiments-crcpdo.py with token, samples file $1 and drugs file $2."
8+
python3 04-experiments-crcpdo.py --Download --Experiment --Token $SYNAPSE_AUTH_TOKEN --Samples $1 --Drugs $2
99

1010
# running the drug descriptor python script
11-
python3 fit_curve.py --input /tmp/crcPDO_experiments_for_curve_fitting.tsv --output /tmp/crcPDO_experiments.tsv
11+
python3 fit_curve.py --input /tmp/crcpdo_experiments_for_curve_fitting.tsv --output /tmp/crcpdo_experiments.tsv

‎build/crcPDO/build_omics.sh‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,5 +3,5 @@ set -euo pipefail
33

44
trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit 1' ERR
55

6-
echo "Running 02-omics-crcPDO.py with token, curSamples $2, and genes $1."
7-
python3 02-omics-crcPDO.py --parse --transcriptomics --mutations --copy_number --ids $2 --genes $1
6+
echo "Running 02-omics-crcpdo.py with token, curSamples $2, and genes $1."
7+
python3 02-omics-crcpdo.py --parse --transcriptomics --mutations --copy_number --ids $2 --genes $1

‎build/crcPDO/build_samples.sh‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -3,6 +3,6 @@ set -euo pipefail
33

44
trap 'echo "Error on or near line $LINENO while executing: $BASH_COMMAND"; exit 1' ERR
55

6-
echo "Running 01-createSamples-crcPDO.py with token and prevSamples $1."
6+
echo "Running 01-createSamples-crcpdo.py with token and prevSamples $1."
77
# download the data and then create sample sheet
8-
python3 01-samples-crcPDO.py --download --samples --token $SYNAPSE_AUTH_TOKEN --prevSamples $1
8+
python3 01-samples-crcpdo.py --download --samples --token $SYNAPSE_AUTH_TOKEN --prevSamples $1

‎build/docker/Dockerfile.crcPDO‎

Lines changed: 5 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -38,14 +38,14 @@ ENV MPLCONFIGDIR=/app/tmp/matplotlib
3838
RUN mkdir -p /app/tmp/matplotlib
3939

4040

41-
ADD build/crcPDO/requirements.R .
41+
ADD build/crcpdo/requirements.R .
4242
# installing r libraries
4343
RUN Rscript requirements.R
4444

4545

4646

4747
# installing python libraries
48-
ADD build/crcPDO/requirements.txt .
48+
ADD build/crcpdo/requirements.txt .
4949
#RUN /opt/venv/bin/pip3 install -r requirements.txt
5050
RUN pip3 install -r requirements.txt
5151

@@ -54,8 +54,8 @@ RUN which Rscript
5454

5555
#ENV PATH="/opt/venv/bin:$PATH"
5656

57-
ADD build/crcPDO/CNV-segfile-annotation.R ./
58-
ADD build/crcPDO/*py ./
59-
ADD build/crcPDO/*sh ./
57+
ADD build/crcpdo/CNV-segfile-annotation.R ./
58+
ADD build/crcpdo/*py ./
59+
ADD build/crcpdo/*sh ./
6060

6161
ADD build/utils/* ./

0 commit comments

Comments
 (0)