Copy Number Segment#

The module copy_number_segment provides functions related to Copy Number Segment section of cBioPortal Web Public API.

pybioportal.copy_number_segment.fetch_copy_number_segments(sample_study_ids, chromosome=None, projection='SUMMARY')#

Fetch copy number segments from cBioPortal by sample ID.

Parameters:

sample_study_ids (list of dict) –
List of sample identifiers.

Each list should have the following format:

sample_study_ids = [

{“sample_ids”: [“P-0000004-T01-IM3”, “P-0000950-T01-IM3”],
“study_id”: “msk_met_2021”},

{“sample_ids”: [“TCGA-5T-A9QA-01”, “TCGA-A1-A0SB-01”],
“study_id”: “brca_tcga”}

]
chromosome (str) – Chromosome (e.g., “1”).
projection (str) –
Level of detail of the response.

Possible values:
- ”DETAILED”: Detailed information.
- ”ID”: Information with only IDs.
- ”META”: Metadata information.
- ”SUMMARY”: Summary information (default).

Returns:

A DataFrame containing the fetched copy number segments.

Return type:

pandas.DataFrame

pybioportal.copy_number_segment.get_copy_number_segments_in_sample_in_study(study_id, sample_id, chromosome=None, direction='ASC', pageNumber=0, pageSize=20000, projection='SUMMARY', sortBy='chromosome')#

Get copy number segments in a sample in a study.

Parameters:

study_id (str) – Study ID (e.g., “acc_tcga”).
sample_id (str) – Sample ID (e.g., “TCGA-OR-A5J2-01”).
chromosome (str) – Chromosome (e.g., “1”).
direction (str) –
Direction of the sort.

Possible values:
- ”ASC”: Ascending (default).
- ”DESC”: Descending.
pageNumber (int) –
Page number of the result list.
- Minimum value is 0.
pageSize (int) –
Page size of the result list.
- Minimum value is 1, maximum value is 20000.
projection (str) –
Level of detail of the response.

Possible values:
- ”DETAILED”: Detailed information.
- ”ID”: Information with only IDs.
- ”META”: Metadata information.
- ”SUMMARY”: Summary information (default).
sortBy (str) –
Name of the property that the result list is sorted by.

Possible values:
- ”chromosome”: Sort by chromosome (default).
- ”end”: Sort by end position.
- ”numberOfProbes”: Sort by the number of probes.
- ”segmentMean”: Sort by segment mean.
- ”start”: Sort by start position.

Returns:

A DataFrame containing copy number segments for the specified sample in the study.

Return type:

pandas.DataFrame

Examples#

from pybioportal import copy_number_segment as cns

df1a = cns.fetch_copy_number_segments(sample_study_ids=[
                                              {"sample_ids": ["P-0000004-T01-IM3", "P-0000950-T01-IM3"],  "study_id": "msk_met_2021"},
                                              {"sample_ids": ["TCGA-5T-A9QA-01", "TCGA-A1-A0SB-01"], "study_id": "brca_tcga"}
                                        ])
df1a

	uniqueSampleKey	uniquePatientKey	patientId	start	end	segmentMean	studyId	sampleId	chromosome	numberOfProbes
0	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	3218610	247813706	0.0034	brca_tcga	TCGA-A1-A0SB-01	1	129072
1	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	484222	174313755	0.0014	brca_tcga	TCGA-A1-A0SB-01	2	92446
2	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	174314142	174314161	-1.2680	brca_tcga	TCGA-A1-A0SB-01	2	2
3	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	174315778	194887369	0.0019	brca_tcga	TCGA-A1-A0SB-01	2	10897
4	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	194888052	194892814	-0.9361	brca_tcga	TCGA-A1-A0SB-01	2	4
...	...	...	...	...	...	...	...	...	...	...
443	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	36164670	37954722	0.3705	msk_met_2021	P-0000950-T01-IM3	21	11
444	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	39625779	45660694	0.0544	msk_met_2021	P-0000950-T01-IM3	21	48
445	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	19053406	49370834	-0.2394	msk_met_2021	P-0000950-T01-IM3	22	101
446	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	451142	1331488	-0.5502	msk_met_2021	P-0000950-T01-IM3	X	7
447	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	3085464	149924738	0.3045	msk_met_2021	P-0000950-T01-IM3	X	312

448 rows × 10 columns

df1b = cns.fetch_copy_number_segments(sample_study_ids=[
                                              {"sample_ids": ["P-0000004-T01-IM3", "P-0000950-T01-IM3"],  "study_id": "msk_met_2021"},
                                              {"sample_ids": ["TCGA-5T-A9QA-01", "TCGA-A1-A0SB-01"], "study_id": "brca_tcga"}
                                        ], chromosome="5")
df1b.head(10)

	uniqueSampleKey	uniquePatientKey	patientId	start	end	segmentMean	studyId	sampleId	chromosome	numberOfProbes
0	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	914233	31655645	-0.0041	brca_tcga	TCGA-A1-A0SB-01	5	18310
1	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	31656726	31656768	-1.7983	brca_tcga	TCGA-A1-A0SB-01	5	2
2	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	31657098	53873836	-0.0002	brca_tcga	TCGA-A1-A0SB-01	5	9892
3	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	53873994	53874176	-1.5816	brca_tcga	TCGA-A1-A0SB-01	5	2
4	VENHQS1BMS1BMFNCLTAxOmJyY2FfdGNnYQ	VENHQS1BMS1BMFNCOmJyY2FfdGNnYQ	TCGA-A1-A0SB	53875569	180360469	0.0025	brca_tcga	TCGA-A1-A0SB-01	5	72240
5	VENHQS01VC1BOVFBLTAxOmJyY2FfdGNnYQ	VENHQS01VC1BOVFBOmJyY2FfdGNnYQ	TCGA-5T-A9QA	914233	111111798	0.0329	brca_tcga	TCGA-5T-A9QA-01	5	58513
6	VENHQS01VC1BOVFBLTAxOmJyY2FfdGNnYQ	VENHQS01VC1BOVFBOmJyY2FfdGNnYQ	TCGA-5T-A9QA	111112994	111119490	-1.0722	brca_tcga	TCGA-5T-A9QA-01	5	4
7	VENHQS01VC1BOVFBLTAxOmJyY2FfdGNnYQ	VENHQS01VC1BOVFBOmJyY2FfdGNnYQ	TCGA-5T-A9QA	111119554	112443378	0.0489	brca_tcga	TCGA-5T-A9QA-01	5	1080
8	VENHQS01VC1BOVFBLTAxOmJyY2FfdGNnYQ	VENHQS01VC1BOVFBOmJyY2FfdGNnYQ	TCGA-5T-A9QA	112450364	112450424	-1.4587	brca_tcga	TCGA-5T-A9QA-01	5	2
9	VENHQS01VC1BOVFBLTAxOmJyY2FfdGNnYQ	VENHQS01VC1BOVFBOmJyY2FfdGNnYQ	TCGA-5T-A9QA	112453010	116143516	0.0538	brca_tcga	TCGA-5T-A9QA-01	5	2225

df2 = cns.get_copy_number_segments_in_sample_in_study(study_id="msk_met_2021", sample_id="P-0000950-T01-IM3")
df2.head(10)

	uniqueSampleKey	uniquePatientKey	patientId	start	end	segmentMean	studyId	sampleId	chromosome	numberOfProbes
0	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	2488138	245977996	-0.2332	msk_met_2021	P-0000950-T01-IM3	1	545
1	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	104375092	104389868	-0.5508	msk_met_2021	P-0000950-T01-IM3	10	5
2	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	1510047	104359246	-0.2373	msk_met_2021	P-0000950-T01-IM3	10	113
3	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	105517162	134199067	-0.1375	msk_met_2021	P-0000950-T01-IM3	10	34
4	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	67198913	68758509	-0.4173	msk_met_2021	P-0000950-T01-IM3	11	12
5	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	532696	67197032	-0.0058	msk_met_2021	P-0000950-T01-IM3	11	91
6	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	69069538	133495556	0.0651	msk_met_2021	P-0000950-T01-IM3	11	235
7	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	394725	133263871	0.2584	msk_met_2021	P-0000950-T01-IM3	12	372
8	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	21004738	111119077	0.3586	msk_met_2021	P-0000950-T01-IM3	13	207
9	UC0wMDAwOTUwLVQwMS1JTTM6bXNrX21ldF8yMDIx	UC0wMDAwOTUwOm1za19tZXRfMjAyMQ	P-0000950	38055061	38068061	0.5235	msk_met_2021	P-0000950-T01-IM3	14	5