Merge pull request #226 from AlexandrovLab/cosmic_v3.4

COSMIC V3.4 Update

.gitignore

@@ -136,10 +136,7 @@ test_matobj_output/
 test_segCNV_output/
 test_text_output/
 test_vcf_output/
-test_matrix_48_output/
-test_matrix_78_output/
-test_matrix_83_output/
-test_matrix_96_output/
+test_matrix_*_output/
 SigProfilerExtractor/data/VCFInput/logs/
 SigProfilerExtractor/data/VCFInput/input/
 SigProfilerExtractor/data/VCFInput/output/

README.md

@@ -124,7 +124,7 @@ sigProfilerExtractor(input_type, out_put, input_data, reference_genome="GRCh37",
 |  | **combined_stability** | Float | Default is 1.0. The cutoff thresh-hold of the combined stability (sum of average and minimum stability). Solutions with combined stabilities below this thresh-hold will not be considered. | 
 |  | **allow_stability_drop** | Boolean | Default is False. Defines if solutions with a drop in stability with respect to the highest stable number of signatures will be considered. | 
 | **Decomposition** |  |  |  | 
-|  | **cosmic_version** | Float | Takes a positive float among 1, 2, 3, 3.1, 3.2 and 3.3. Default is 3.3. Defines the version of the COSMIC reference signatures. | 
+|  | **cosmic_version** | Float | Takes a positive float among 1, 2, 3, 3.1, 3.2, 3.3, and 3.4. Default is 3.4. Defines the version of the COSMIC reference signatures. | 
 |  | **make_decomposition_plots** | Boolean | Defualt is True. If True, Denovo to Cosmic sigantures decompostion plots will be created as a part the results. | 
 |  | **collapse_to_SBS96** | Boolean | Defualt is True. If True, SBS288 and SBS1536 Denovo signatures will be mapped to SBS96 reference signatures. If False, those will be mapped to reference signatures of the same context. 
 | **Others** |  |  |  | 

SigProfilerExtractor/data/TextInput/Samples_SV.txt

@@ -0,0 +1,33 @@
+Mutation Types	PD8969a	PD18031a	PD4103a	PD14472a	PD9572a
+clustered_del_1-10Kb	0	0	5	0	0
+clustered_del_10-100Kb	0	1	4	0	0
+clustered_del_100Kb-1Mb	0	2	9	0	0
+clustered_del_1Mb-10Mb	0	2	16	0	1
+clustered_del_>10Mb	0	0	13	0	0
+clustered_tds_1-10Kb	0	0	1	0	0
+clustered_tds_10-100Kb	0	0	3	0	1
+clustered_tds_100Kb-1Mb	0	4	5	0	0
+clustered_tds_1Mb-10Mb	0	1	11	0	0
+clustered_tds_>10Mb	0	2	8	0	0
+clustered_inv_1-10Kb	0	7	7	0	0
+clustered_inv_10-100Kb	0	7	7	0	0
+clustered_inv_100Kb-1Mb	0	7	14	0	3
+clustered_inv_1Mb-10Mb	0	3	33	0	0
+clustered_inv_>10Mb	0	3	19	0	1
+clustered_trans	0	11	186	0	1
+non-clustered_del_1-10Kb	14	2	14	0	1
+non-clustered_del_10-100Kb	10	8	11	0	0
+non-clustered_del_100Kb-1Mb	4	2	23	0	0
+non-clustered_del_1Mb-10Mb	2	1	18	1	0
+non-clustered_del_>10Mb	3	0	11	1	0
+non-clustered_tds_1-10Kb	1	0	1	0	0
+non-clustered_tds_10-100Kb	2	3	1	0	0
+non-clustered_tds_100Kb-1Mb	4	1	7	0	1
+non-clustered_tds_1Mb-10Mb	2	2	11	0	0
+non-clustered_tds_>10Mb	4	0	10	1	0
+non-clustered_inv_1-10Kb	5	6	13	0	1
+non-clustered_inv_10-100Kb	2	3	5	0	0
+non-clustered_inv_100Kb-1Mb	4	1	18	0	1
+non-clustered_inv_1Mb-10Mb	7	2	19	0	0
+non-clustered_inv_>10Mb	11	1	27	1	0
+non-clustered_trans	51	11	83	3	6

SigProfilerExtractor/sigpro.py

@@ -101,6 +101,8 @@ def importdata(datatype="matrix"):
         data = paths+"/data/CSVInput/csv_example.csv"
     elif datatype=="seg:BATTENBERG":
         data = paths+"/data/CNVInput/Battenberg_test.tsv"
+    elif datatype=="matrix_SV":
+        data = paths+"/data/TextInput/Samples_SV.txt"
     elif datatype=="vcf":
         data = paths+"/data/VCFInput/"
     return data
@@ -165,7 +167,7 @@ def sigProfilerExtractor(input_type,
                          input_data, 
                          reference_genome="GRCh37", 
                          opportunity_genome = "GRCh37", 
-                         cosmic_version=3.3,
+                         cosmic_version=3.4,
                          context_type = "default", 
                          exome = False, 
                          minimum_signatures=1,

SigProfilerExtractor/subroutines.py

@@ -1099,9 +1099,9 @@ def export_information(loopResults, mutation_type, output, index, colnames, sequ
     elif m=="ID83":
         plot.plotID(signature_subdirectory+"/"+mutation_type+"_S"+str(i)+"_Signatures"+".txt", signature_subdirectory+"/Signature_plot/" , "S"+str(i), "83", True, custom_text_upper=stability_list, custom_text_middle=total_mutation_list)
     elif m=="CNV48":
-         plot.plotCNV(signature_subdirectory+"/"+mutation_type+"_S"+str(i)+"_Signatures"+".txt", signature_subdirectory+"/Signature_plot/"  , "S"+str(i), "pdf", percentage=True, aggregate=False)
+         plot.plotCNV(signature_subdirectory+"/"+mutation_type+"_S"+str(i)+"_Signatures"+".txt", signature_subdirectory+"/Signature_plot/"  , "S"+str(i), percentage=True, aggregate=False)
     elif m=="SV32":
-         plot.plotSV(signature_subdirectory+"/"+mutation_type+"_S"+str(i)+"_Signatures"+".txt", signature_subdirectory+"/Signature_plot/"  , "S"+str(i), "pdf", percentage=True, aggregate=False)
+         plot.plotSV(signature_subdirectory+"/"+mutation_type+"_S"+str(i)+"_Signatures"+".txt", signature_subdirectory+"/Signature_plot/"  , "S"+str(i), percentage=True, aggregate=False)
     elif m=="SBS96" or m=="SBS288" or m=="SBS384" or m=="SBS1536" or m=="SBS4608":
         # parse 'm' to be accepted by the plotSBS function
         tmp_m = m

setup.py

@@ -8,7 +8,7 @@
 if os.path.exists("dist"):
     shutil.rmtree("dist")
 
-VERSION = '1.1.22'
+VERSION = '1.1.23'
 
 
 with open('README.md') as f:
@@ -20,7 +20,7 @@ def write_version_py(filename='SigProfilerExtractor/version.py'):
 # THIS FILE IS GENERATED FROM SIGPROFILEREXTRACTOR SETUP.PY
 short_version = '%(version)s'
 version = '%(version)s'
-Update = 'Upgrade v1.1.22: Resolve issue with 4608 plotting as custom'
+Update = 'Upgrade v1.1.23: Update to use the latest SigProfilerAssignment with COSMIC v3.4 signatures.'
     
     """
     fh = open(filename, 'w')
@@ -34,7 +34,7 @@ def write_version_py(filename='SigProfilerExtractor/version.py'):
           'nimfa>=1.1.0', 
           'SigProfilerMatrixGenerator>=1.2.17',
           'sigProfilerPlotting>=1.3.16',
-          'SigProfilerAssignment>=0.0.32',
+          'SigProfilerAssignment>=0.1.0',
           'pillow',
           'statsmodels>=0.9.0',
           'scikit-learn>=0.24.2',

test.py

@@ -45,6 +45,12 @@ def run_seg_48():
             minimum_signatures=3, maximum_signatures=3, nmf_replicates=5,
             min_nmf_iterations=100, max_nmf_iterations=1000, nmf_test_conv=100)
 
+def run_matrix_32():
+    data = sig.importdata("matrix_SV")
+    sig.sigProfilerExtractor("matrix", "test_matrix_32_output", data,
+            minimum_signatures=3, maximum_signatures=3, nmf_replicates=5,
+            min_nmf_iterations=100, max_nmf_iterations=1000, nmf_test_conv=100)
+
 def run_matobj():
     data = sig.importdata("matobj")
     sig.sigProfilerExtractor("matobj", "test_matobj_output", data,
@@ -63,6 +69,7 @@ def run_csv():
     run_matrix_78()
     run_matrix_83()
     run_matrix_48()
+    run_matrix_32()
     run_seg_48()
     run_vcf()
     # run_matobj()