Major upgrade

Added example output Parsing all data from fusion detection tools Working installation Added some basic testing Added new databases: COSMIC and Mitelman
Clinical-Genomics · Mar 15, 2019 · ffcf5ea · ffcf5ea
1 parent 69c3570
commit ffcf5ea
Show file tree

Hide file tree

Showing 36 changed files with 22,409 additions and 108 deletions.
diff --git a/.gitignore b/.gitignore
@@ -1,5 +1,5 @@
 .vscode
-db/
+*.db
 build/
 dist/
 *.egg-info

diff --git a/.travis.yml b/.travis.yml
@@ -3,8 +3,11 @@ python:
   - "3.6"
 
 install:
+  - pip install pylint
+  - pip install Sphinx sphinxcontrib-napoleon
   - pip install -r requirements.txt
   - python setup.py install
 
 script:
-  - fusion_report --help
+  - pylint fusion_report/
+  - pytest
diff --git a/bin/fusion_report b/bin/fusion_report
@@ -9,10 +9,13 @@ from fusion_report.lib.section import Section
 from fusion_report.lib.graph import Graph
 from fusion_report.helpers.tool_parser import ToolParser
 from fusion_report.helpers.core import tool_detection_chart, known_vs_unknown_chart, \
-    distribution_chart, create_fusions_table, create_ppi_graph, print_progress_bar
+    distribution_chart, create_fusions_table, create_ppi_graph, print_progress_bar, \
+    get_db_fusions
 
 # Minimum number of tools that have to detect a fusion, used as a filter in Dashboard
 TOOL_DETECTION_CUTOFF = 2
+SUPPORTED_TOOLS = ['ericscript', 'starfusion', 'fusioncatcher', 'pizzly', 'squid']
+DEFAULT_TOOL_WEIGHT = float(100/len(SUPPORTED_TOOLS))
 
 def parse(params):
     """
@@ -22,34 +25,28 @@ def parse(params):
         params (ArgumentParser):
     """
     tools = ToolParser()
-    tools.parse('ericscript', params.ericscript)
-    tools.parse('starfusion', params.starfusion)
-    tools.parse('fusioncatcher', params.fusioncatcher)
-    tools.parse('pizzly', params.pizzly)
-    tools.parse('squid', params.squid)
+    for tool in SUPPORTED_TOOLS:
+        tools.parse(tool, params.__dict__[tool])
 
     return tools
 
-def generate_index(params, parser, known_fusions, unknown_fusions):
+def generate_index(params, parser):
     """
     Helper function for generating index.html page.
 
     Args:
         params (ArgumentParser)
         parser (ToolParser)
-        known_fusions (list): List of known fusions
-        unknown_fusions (list): List of unknown fusions
     Returns:
         Page: Returns final Page object for index.html page.
     """
-    known_sum = len(known_fusions)
-    unknown_sum = len(unknown_fusions)
+    known_fusions, unknown_fusions = parser.get_db_counts()
     index_page = Page(
         title='index',
         page_variables={
             'sample': params.sample,
-            'fusions_sum': int(unknown_sum + known_sum),
-            'known_fusion_sum': known_sum,
+            'fusions_sum': int(unknown_fusions + known_fusions),
+            'known_fusion_sum': known_fusions,
             'fusion_tools': parser.get_tools()
         },
         partial_template='index'
@@ -72,7 +69,7 @@ def generate_index(params, parser, known_fusions, unknown_fusions):
             'known_vs_unknown_chart',
             'Known Vs Unknown',
             'Shows the ration between found and unknown missing fusions in the local database.',
-            known_vs_unknown_chart(known_sum, unknown_sum)
+            known_vs_unknown_chart(known_fusions, unknown_fusions)
         )
     )
     dashboard_section.add_graph(
@@ -91,13 +88,13 @@ def generate_index(params, parser, known_fusions, unknown_fusions):
         content='''
             Filters fusions found by at least {tool} tools. If number of chosen tools is less 
             than {tool} the filter is disabled. The whole list can be found in 
-            <code>results/Report-{sample}/fusions.txt</code>.
+            <code>./Report-{sample}/fusions.json</code>.
             '''.format(tool=str(params.tool_num), sample=str(params.sample))
     )
     fusion_list_section.data = create_fusions_table(
         parser.get_fusions(),
         parser.get_tools(),
-        known_fusions, params.tool_num
+        params
     )
     index_page.add_section(fusion_list_section)
 
@@ -115,6 +112,7 @@ def generate_fusion_page(params, parser, fusion, db):
     Returns:
         Page: Returns final Page object for <fusion>.html page.
     """
+    db.connect('fusiongdb')
     fusion_page = Page(
         title=fusion,
         page_variables={
@@ -128,7 +126,7 @@ def generate_fusion_page(params, parser, fusion, db):
         title='Detail results from fusion detection tools',
         content='Some description for each tool?'
     )
-    detail_section.data = parser.get_fusion(fusion)
+    detail_section.data = parser.get_fusion(fusion).__dict__
     fusion_page.add_section(detail_section)
     # Variations section
     variations_section = Section(
@@ -232,102 +230,127 @@ def generate_report(params):
     Args:
         params (ArgumentParser)
     """
+    i = 0
     parser = parse(params)
-    db = Db(params.database)
-    known_fusions = []
-    unknown_fusions = []
-    report = Report(params.config, params.output)
-
-    # Get all fusions from DB
-    db.connect('fusiongdb')
-    db_fusions = db.select('''
-        SELECT DISTINCT (h_gene || "--" || t_gene) as fusion_pair 
-        FROM TCGA_ChiTaRS_combined_fusion_information_on_hg19
-        ''')
-    db_fusions = [x['fusion_pair'] for x in db_fusions]
-
+    db = Db(params.db_path)
     fusions = parser.get_fusions()
+    db_fusions = get_db_fusions(db)
+
+    report = Report(params.config, params.output)
     print_progress_bar(0, len(fusions), 50)
-    for i, fusion in enumerate(fusions):
 
-        if fusion not in db_fusions:
-            unknown_fusions.append(fusion)
-            # progress bar
-            sleep(0.1)
-            print_progress_bar(i + 1, len(fusions), 50)
-            continue # go to next fusion
+    for fusion, detail in fusions:
+        i += 1
+        for db_name, db_list in db_fusions.items():
+            if fusion in db_list:
+                detail.add_db(db_name)
+
+        if 'FusionGDB' in detail.dbs:
+            fusion_page = generate_fusion_page(params, parser, fusion, db)
+            report.add_page(fusion_page)
 
-        known_fusions.append(fusion)
-        fusion_page = generate_fusion_page(params, parser, fusion, db)
-        report.add_page(fusion_page)
         # progress bar
         sleep(0.1)
-        print_progress_bar(i + 1, len(fusions), 50)
+        print_progress_bar(i, len(fusions), 50)
 
-    index_page = generate_index(params, parser, known_fusions, unknown_fusions)
+    index_page = generate_index(params, parser)
     report.add_page(index_page)
+    parser.save(params.output, 'fusions')
     print(f'The report for `sample` {params.sample} was generated in {params.output}.')
 
 def main():
     """Main function for processing command line arguments"""
     parser = argparse.ArgumentParser(
-        description='Tool for generating friendly UI custom report'
+        description='''
+            Tool for generating friendly UI custom report. 
+            Supported tools are: {0} and {1}.
+        '''.format(', '.join(SUPPORTED_TOOLS[:-1]), SUPPORTED_TOOLS[-1])
+    )
+    mandatory = parser.add_argument_group('Mandatory arguments', 'Required arguments to run app.')
+    mandatory.add_argument(
+        'sample',
+        help='Sample name',
+        type=str
+    )
+    mandatory.add_argument(
+        'output',
+        help='Output directory',
+        type=str
     )
-    parser.add_argument(
+    mandatory.add_argument(
+        'db_path',
+        help='Path to folder where all databases are stored.',
+        type=str
+    )
+    tools = parser.add_argument_group('Tools', 'List of all supported tools with their weights.')
+    tools.add_argument(
         '--ericscript',
         help='EricScript output file',
         type=str
     )
-    parser.add_argument(
+    tools.add_argument(
+        '--ericscript_weight',
+        help='EricScript weight',
+        type=float,
+        default=DEFAULT_TOOL_WEIGHT
+    )
+    tools.add_argument(
         '--fusioncatcher',
         help='FusionCatcher output file',
         type=str
     )
-    parser.add_argument(
+    tools.add_argument(
+        '--fusioncatcher_weight',
+        help='FusionCatcher weight',
+        type=float,
+        default=DEFAULT_TOOL_WEIGHT
+    )
+    tools.add_argument(
         '--starfusion',
         help='STAR-Fusion output file',
         type=str
     )
-    parser.add_argument(
+    tools.add_argument(
+        '--starfusion_weight',
+        help='STAR-Fusion weight',
+        type=float,
+        default=DEFAULT_TOOL_WEIGHT
+    )
+    tools.add_argument(
         '--pizzly',
         help='Pizzly output file',
         type=str
     )
-    parser.add_argument(
+    tools.add_argument(
+        '--pizzly_weight',
+        help='Pizzly weight',
+        type=float,
+        default=DEFAULT_TOOL_WEIGHT
+    )
+    tools.add_argument(
         '--squid',
         help='Squid output file',
         type=str
     )
-    parser.add_argument(
-        '-s', '--sample',
-        help='Sample name',
-        type=str,
-        required=True
-    )
-    parser.add_argument(
-        '-o', '--output',
-        help='Output directory',
-        type=str,
-        required=True
+    tools.add_argument(
+        '--squid_weight',
+        help='Squid weight',
+        type=float,
+        default=DEFAULT_TOOL_WEIGHT
     )
-    parser.add_argument(
+    optional = parser.add_argument_group('Optional', 'List of additional configuration parameters.')
+    optional.add_argument(
         '-c', '--config',
         help='Input config file',
         type=str,
         required=False
     )
-    parser.add_argument(
+    optional.add_argument(
         '-t', '--tool_num',
         help='Number of tools required to detect a fusion',
         type=int,
         default=TOOL_DETECTION_CUTOFF
     )
-    parser.add_argument(
-        '-db', '--database',
-        help='Path to database file fusions.db (for local development)',
-        type=str,
-        required=False
-    )
     generate_report(parser.parse_args())
 
 if __name__ == "__main__":

diff --git a/docs/example/AKAP9_BRAF.html b/docs/example/AKAP9_BRAF.html
diff --git a/docs/example/BRD4_NUTM1.html b/docs/example/BRD4_NUTM1.html
diff --git a/docs/example/CD74_ROS1.html b/docs/example/CD74_ROS1.html
diff --git a/docs/example/EML4_ALK.html b/docs/example/EML4_ALK.html
diff --git a/docs/example/ETV6_NTRK3.html b/docs/example/ETV6_NTRK3.html
diff --git a/docs/example/EWSR1_ATF1.html b/docs/example/EWSR1_ATF1.html
diff --git a/docs/example/EWSR1_FLI1.html b/docs/example/EWSR1_FLI1.html
diff --git a/docs/example/FGFR3_TACC3.html b/docs/example/FGFR3_TACC3.html
diff --git a/docs/example/FIP1L1_PDGFRA.html b/docs/example/FIP1L1_PDGFRA.html
diff --git a/docs/example/HOOK3_RET.html b/docs/example/HOOK3_RET.html
diff --git a/docs/example/NPM1_ALK.html b/docs/example/NPM1_ALK.html
diff --git a/docs/example/TMPRSS2_ETV1.html b/docs/example/TMPRSS2_ETV1.html
diff --git a/docs/example/fusions.json b/docs/example/fusions.json
@@ -0,0 +1 @@
+{"AKAP9--BRAF":{"score":0.0,"tools":{"ericscript":[{"position":"7:92003235:+#7:140787584:-","discordant_reads":11,"junction_reads":24,"fusion_type":"intra-chromosomal","gene_expr1":9.56,"gene_expr2":9.72,"gene_expr_fusion":37.9}],"fusioncatcher":[{"position":"7:92003235:+#7:140787584:-","common_mapping_reads":0,"spanning_pairs":10,"spanning_unique_reads":11,"longest_anchor":29,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":4,"split_count":5}],"squid":[{"position":"7:92002951-92003235:+#7:140783020-140787584:+","score":8}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"GOPC--ROS1":{"score":0.0,"tools":{"ericscript":[{"position":"6:117566854:-#6:117321394:-","discordant_reads":140,"junction_reads":73,"fusion_type":"intra-chromosomal","gene_expr1":0.0,"gene_expr2":2.11,"gene_expr_fusion":26.21}],"fusioncatcher":[{"position":"6:117566854:-#6:117321394:-","common_mapping_reads":0,"spanning_pairs":73,"spanning_unique_reads":22,"longest_anchor":30,"fusion_type":"in-frame"},{"position":"6:117566854:-#6:117320030:-","common_mapping_reads":0,"spanning_pairs":73,"spanning_unique_reads":2,"longest_anchor":26,"fusion_type":"out-of-frame"}]},"dbs":["Mitelman","COSMIC"]},"FGFR3--TACC3":{"score":0.0,"tools":{"ericscript":[{"position":"4:1806934:+#4:1727977:+","discordant_reads":978,"junction_reads":378,"fusion_type":"Read-Through","gene_expr1":0.0,"gene_expr2":1.58,"gene_expr_fusion":101.36}],"starfusion":[{"position":"4:1806934:+#4:1727977:+","junction_reads":235,"spanning_reads":637,"ffmp":69504.2245}],"fusioncatcher":[{"position":"4:1806934:+#4:1727977:+","common_mapping_reads":0,"spanning_pairs":820,"spanning_unique_reads":66,"longest_anchor":43,"fusion_type":"in-frame"},{"position":"4:1807033:+#4:1727832:+","common_mapping_reads":0,"spanning_pairs":820,"spanning_unique_reads":9,"longest_anchor":43,"fusion_type":"intronic/CDS(truncated)"}],"pizzly":[{"pair_count":487,"split_count":231}],"squid":[{"position":"4:1806048-1806934:+#4:1727976-1728733:-","score":785},{"position":"4:1806048-1807038:+#4:1727836-1728733:-","score":785}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"FIP1L1--PDGFRA":{"score":0.0,"tools":{"ericscript":[{"position":"4:53425965:+#4:54274925:+","discordant_reads":68,"junction_reads":39,"fusion_type":"intra-chromosomal","gene_expr1":0.0,"gene_expr2":0.01,"gene_expr_fusion":29.15}],"fusioncatcher":[{"position":"4:53425965:+#4:54274925:+","common_mapping_reads":0,"spanning_pairs":50,"spanning_unique_reads":42,"longest_anchor":45,"fusion_type":"in-frame"}]},"dbs":["FusionGDB","Mitelman"]},"BRD4--NUTM1":{"score":0.0,"tools":{"ericscript":[{"position":"19:15254152:-#15:34347969:+","discordant_reads":7,"junction_reads":13,"fusion_type":"inter-chromosomal","gene_expr1":4.19,"gene_expr2":17.98,"gene_expr_fusion":83.9}],"starfusion":[{"position":"19:15254152:-#15:34347969:+","junction_reads":7,"spanning_reads":2,"ffmp":717.3602}],"fusioncatcher":[{"position":"19:15254152:-#15:34347969:+","common_mapping_reads":0,"spanning_pairs":5,"spanning_unique_reads":9,"longest_anchor":30,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":1,"split_count":6}],"squid":[{"position":"19:15254151-15254264:-#15:34347968-34348134:-","score":9}]},"dbs":["FusionGDB","Mitelman"]},"HOOK3--RET":{"score":0.0,"tools":{"ericscript":[{"position":"8:42968214:+#10:43116584:+","discordant_reads":12,"junction_reads":21,"fusion_type":"inter-chromosomal","gene_expr1":2.44,"gene_expr2":3.31,"gene_expr_fusion":31.82}],"starfusion":[{"position":"8:42968214:+#10:43116584:+","junction_reads":10,"spanning_reads":2,"ffmp":956.4802}],"fusioncatcher":[{"position":"8:42968214:+#10:43116584:+","common_mapping_reads":0,"spanning_pairs":10,"spanning_unique_reads":10,"longest_anchor":29,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":2,"split_count":8}],"squid":[{"position":"8:42968010-42968214:+#10:43116583-43116731:-","score":11}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"TMPRSS2--ETV1":{"score":0.0,"tools":{"ericscript":[{"position":"21:41494380:-#7:13935843:-","discordant_reads":9,"junction_reads":16,"fusion_type":"inter-chromosomal","gene_expr1":0.0,"gene_expr2":17.69,"gene_expr_fusion":18.49}],"starfusion":[{"position":"21:41494375:-#7:13935838:-","junction_reads":10,"spanning_reads":3,"ffmp":1036.1868}],"fusioncatcher":[{"position":"21:41494381:-#7:13935844:-","common_mapping_reads":0,"spanning_pairs":7,"spanning_unique_reads":10,"longest_anchor":38,"fusion_type":"in-frame"}],"squid":[{"position":"7:13935707-13935838:+#21:41494374-41494578:-","score":12}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"CD74--ROS1":{"score":0.0,"tools":{"ericscript":[{"position":"5:150404680:-#6:117324415:-","discordant_reads":3,"junction_reads":14,"fusion_type":"inter-chromosomal","gene_expr1":2.44,"gene_expr2":2.11,"gene_expr_fusion":19.87}],"starfusion":[{"position":"5:150404680:-#6:117324415:-","junction_reads":5,"spanning_reads":0,"ffmp":398.5334}],"fusioncatcher":[{"position":"5:150404680:-#6:117324415:-","common_mapping_reads":0,"spanning_pairs":3,"spanning_unique_reads":7,"longest_anchor":30,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":0,"split_count":2}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"EWSR1--ATF1":{"score":0.0,"tools":{"ericscript":[{"position":"22:29287134:+#12:50814280:+","discordant_reads":11,"junction_reads":25,"fusion_type":"inter-chromosomal","gene_expr1":37.0,"gene_expr2":12.27,"gene_expr_fusion":553.3}],"starfusion":[{"position":"22:29287134:+#12:50814280:+","junction_reads":8,"spanning_reads":3,"ffmp":876.7734}],"fusioncatcher":[{"position":"22:29287134:+#12:50814280:+","common_mapping_reads":0,"spanning_pairs":10,"spanning_unique_reads":10,"longest_anchor":30,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":3,"split_count":8}],"squid":[{"position":"22:29286921-29287134:+#12:50814279-50814439:-","score":10}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"EWSR1--FLI1":{"score":0.0,"tools":{"ericscript":[{"position":"22:29287134:+#11:128807180:+","discordant_reads":9,"junction_reads":12,"fusion_type":"inter-chromosomal","gene_expr1":37.0,"gene_expr2":3.29,"gene_expr_fusion":600.14}],"starfusion":[{"position":"22:29287134:+#11:128807180:+","junction_reads":5,"spanning_reads":2,"ffmp":557.9468}],"fusioncatcher":[{"position":"22:29287134:+#11:128807180:+","common_mapping_reads":0,"spanning_pairs":9,"spanning_unique_reads":11,"longest_anchor":28,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":2,"split_count":6}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"ETV6--NTRK3":{"score":0.0,"tools":{"ericscript":[{"position":"12:11869970:+#15:87940752:-","discordant_reads":7,"junction_reads":24,"fusion_type":"inter-chromosomal","gene_expr1":9.48,"gene_expr2":0.45,"gene_expr_fusion":54.74}],"starfusion":[{"position":"12:11869969:+#15:87940753:-","junction_reads":9,"spanning_reads":4,"ffmp":1036.1868}],"fusioncatcher":[{"position":"12:11869969:+#15:87940753:-","common_mapping_reads":0,"spanning_pairs":6,"spanning_unique_reads":8,"longest_anchor":29,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":2,"split_count":8}],"squid":[{"position":"12:11869684-11869969:+#15:87940621-87940753:+","score":10}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"CIC--DUX4":{"score":0.0,"tools":{"ericscript":[{"position":"19:42295048:+#4:190174447:+","discordant_reads":6,"junction_reads":6,"fusion_type":"inter-chromosomal","gene_expr1":0.0,"gene_expr2":1.34,"gene_expr_fusion":5.54}],"fusioncatcher":[{"position":"19:42295047:+#4:190174446:+","common_mapping_reads":0,"spanning_pairs":5,"spanning_unique_reads":5,"longest_anchor":34,"fusion_type":"in-frame"}]},"dbs":["Mitelman","COSMIC"]},"EML4--ALK":{"score":0.0,"tools":{"starfusion":[{"position":"2:42301394:+#2:29223584:-","junction_reads":3,"spanning_reads":4,"ffmp":557.9467}],"fusioncatcher":[{"position":"2:42301391:+#2:29223587:-","common_mapping_reads":0,"spanning_pairs":4,"spanning_unique_reads":4,"longest_anchor":33,"fusion_type":"CDS(truncated)/UTR"}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"CD74--AL132671.2":{"score":0.0,"tools":{"starfusion":[{"position":"5:150404680:-#6:117324415:-","junction_reads":3,"spanning_reads":0,"ffmp":239.12}]},"dbs":[]},"IGH@--CRLF2":{"score":0.0,"tools":{"fusioncatcher":[{"position":"14:105863258:+#X:105799296:-","common_mapping_reads":0,"spanning_pairs":32,"spanning_unique_reads":9,"longest_anchor":94,"fusion_type":"---/intergenic"},{"position":"14:105863343:+#X:105812546:-","common_mapping_reads":0,"spanning_pairs":32,"spanning_unique_reads":6,"longest_anchor":108,"fusion_type":"---/intergenic"},{"position":"14:105863263:+#X:1228687:-","common_mapping_reads":0,"spanning_pairs":32,"spanning_unique_reads":4,"longest_anchor":33,"fusion_type":"---/intergenic"}]},"dbs":[]},"DUX4--IGH@":{"score":0.0,"tools":{"fusioncatcher":[{"position":"4:190174997:+#14:190287409:+","common_mapping_reads":0,"spanning_pairs":5,"spanning_unique_reads":5,"longest_anchor":84,"fusion_type":"CDS(truncated)/---"},{"position":"4:190175284:+#14:106638525:-","common_mapping_reads":0,"spanning_pairs":4,"spanning_unique_reads":8,"longest_anchor":38,"fusion_type":"UTR/---"}]},"dbs":[]},"MALT1--IGH@":{"score":0.0,"tools":{"fusioncatcher":[{"position":"18:58669909:+#14:105888559:+","common_mapping_reads":0,"spanning_pairs":3,"spanning_unique_reads":3,"longest_anchor":34,"fusion_type":"intergenic/---"}]},"dbs":[]},"NPM1--ALK":{"score":0.0,"tools":{"fusioncatcher":[{"position":"5:171391799:+#2:29223528:-","common_mapping_reads":0,"spanning_pairs":3,"spanning_unique_reads":3,"longest_anchor":30,"fusion_type":"in-frame"}]},"dbs":["FusionGDB","Mitelman","COSMIC"]}}
diff --git a/docs/example/index.html b/docs/example/index.html
diff --git a/fusion_report/db/Cosmic.sql b/fusion_report/db/Cosmic.sql
@@ -0,0 +1,20 @@
+CREATE TABLE "CosmicFusionExport" (
+	"sample_id" integer NOT NULL,
+	"sample_name" varchar(50) NOT NULL DEFAULT '',
+	"primary_site" varchar(50) NOT NULL DEFAULT '',
+	"site_subtype_1" varchar(50) NOT NULL DEFAULT '',
+	"site_subtype_2" varchar(50) NOT NULL DEFAULT '',
+    "site_subtype_3" varchar(50) NOT NULL DEFAULT '',
+	"primary_histology" varchar(50) NOT NULL DEFAULT '',
+    "histology_subtype_1" varchar(50) NOT NULL DEFAULT '',
+    "histology_subtype_2" varchar(50) NOT NULL DEFAULT '',
+    "histology_subtype_3" varchar(50) NOT NULL DEFAULT '',
+    "fusion_id" integer NOT NULL,
+    "translocation_name" varchar(50) NOT NULL DEFAULT '',
+    "translocation_type" varchar(50) NOT NULL DEFAULT '',
+    "pubmed" integer NOT NULL,
+    "id_study" integer NOT NULL
+);
+
+.separator "\t"
+.import CosmicFusionExport_stripped.tsv CosmicFusionExport
-Original file line number
+Diff line change
@@ -1,5 +1,5 @@
     .vscode
-    db/
+    *.db
     build/
     dist/
     *.egg-info
@@ Expand Down @@
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		{"AKAP9--BRAF":{"score":0.0,"tools":{"ericscript":[{"position":"7:92003235:+#7:140787584:-","discordant_reads":11,"junction_reads":24,"fusion_type":"intra-chromosomal","gene_expr1":9.56,"gene_expr2":9.72,"gene_expr_fusion":37.9}],"fusioncatcher":[{"position":"7:92003235:+#7:140787584:-","common_mapping_reads":0,"spanning_pairs":10,"spanning_unique_reads":11,"longest_anchor":29,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":4,"split_count":5}],"squid":[{"position":"7:92002951-92003235:+#7:140783020-140787584:+","score":8}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"GOPC--ROS1":{"score":0.0,"tools":{"ericscript":[{"position":"6:117566854:-#6:117321394:-","discordant_reads":140,"junction_reads":73,"fusion_type":"intra-chromosomal","gene_expr1":0.0,"gene_expr2":2.11,"gene_expr_fusion":26.21}],"fusioncatcher":[{"position":"6:117566854:-#6:117321394:-","common_mapping_reads":0,"spanning_pairs":73,"spanning_unique_reads":22,"longest_anchor":30,"fusion_type":"in-frame"},{"position":"6:117566854:-#6:117320030:-","common_mapping_reads":0,"spanning_pairs":73,"spanning_unique_reads":2,"longest_anchor":26,"fusion_type":"out-of-frame"}]},"dbs":["Mitelman","COSMIC"]},"FGFR3--TACC3":{"score":0.0,"tools":{"ericscript":[{"position":"4:1806934:+#4:1727977:+","discordant_reads":978,"junction_reads":378,"fusion_type":"Read-Through","gene_expr1":0.0,"gene_expr2":1.58,"gene_expr_fusion":101.36}],"starfusion":[{"position":"4:1806934:+#4:1727977:+","junction_reads":235,"spanning_reads":637,"ffmp":69504.2245}],"fusioncatcher":[{"position":"4:1806934:+#4:1727977:+","common_mapping_reads":0,"spanning_pairs":820,"spanning_unique_reads":66,"longest_anchor":43,"fusion_type":"in-frame"},{"position":"4:1807033:+#4:1727832:+","common_mapping_reads":0,"spanning_pairs":820,"spanning_unique_reads":9,"longest_anchor":43,"fusion_type":"intronic/CDS(truncated)"}],"pizzly":[{"pair_count":487,"split_count":231}],"squid":[{"position":"4:1806048-1806934:+#4:1727976-1728733:-","score":785},{"position":"4:1806048-1807038:+#4:1727836-1728733:-","score":785}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"FIP1L1--PDGFRA":{"score":0.0,"tools":{"ericscript":[{"position":"4:53425965:+#4:54274925:+","discordant_reads":68,"junction_reads":39,"fusion_type":"intra-chromosomal","gene_expr1":0.0,"gene_expr2":0.01,"gene_expr_fusion":29.15}],"fusioncatcher":[{"position":"4:53425965:+#4:54274925:+","common_mapping_reads":0,"spanning_pairs":50,"spanning_unique_reads":42,"longest_anchor":45,"fusion_type":"in-frame"}]},"dbs":["FusionGDB","Mitelman"]},"BRD4--NUTM1":{"score":0.0,"tools":{"ericscript":[{"position":"19:15254152:-#15:34347969:+","discordant_reads":7,"junction_reads":13,"fusion_type":"inter-chromosomal","gene_expr1":4.19,"gene_expr2":17.98,"gene_expr_fusion":83.9}],"starfusion":[{"position":"19:15254152:-#15:34347969:+","junction_reads":7,"spanning_reads":2,"ffmp":717.3602}],"fusioncatcher":[{"position":"19:15254152:-#15:34347969:+","common_mapping_reads":0,"spanning_pairs":5,"spanning_unique_reads":9,"longest_anchor":30,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":1,"split_count":6}],"squid":[{"position":"19:15254151-15254264:-#15:34347968-34348134:-","score":9}]},"dbs":["FusionGDB","Mitelman"]},"HOOK3--RET":{"score":0.0,"tools":{"ericscript":[{"position":"8:42968214:+#10:43116584:+","discordant_reads":12,"junction_reads":21,"fusion_type":"inter-chromosomal","gene_expr1":2.44,"gene_expr2":3.31,"gene_expr_fusion":31.82}],"starfusion":[{"position":"8:42968214:+#10:43116584:+","junction_reads":10,"spanning_reads":2,"ffmp":956.4802}],"fusioncatcher":[{"position":"8:42968214:+#10:43116584:+","common_mapping_reads":0,"spanning_pairs":10,"spanning_unique_reads":10,"longest_anchor":29,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":2,"split_count":8}],"squid":[{"position":"8:42968010-42968214:+#10:43116583-43116731:-","score":11}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"TMPRSS2--ETV1":{"score":0.0,"tools":{"ericscript":[{"position":"21:41494380:-#7:13935843:-","discordant_reads":9,"junction_reads":16,"fusion_type":"inter-chromosomal","gene_expr1":0.0,"gene_expr2":17.69,"gene_expr_fusion":18.49}],"starfusion":[{"position":"21:41494375:-#7:13935838:-","junction_reads":10,"spanning_reads":3,"ffmp":1036.1868}],"fusioncatcher":[{"position":"21:41494381:-#7:13935844:-","common_mapping_reads":0,"spanning_pairs":7,"spanning_unique_reads":10,"longest_anchor":38,"fusion_type":"in-frame"}],"squid":[{"position":"7:13935707-13935838:+#21:41494374-41494578:-","score":12}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"CD74--ROS1":{"score":0.0,"tools":{"ericscript":[{"position":"5:150404680:-#6:117324415:-","discordant_reads":3,"junction_reads":14,"fusion_type":"inter-chromosomal","gene_expr1":2.44,"gene_expr2":2.11,"gene_expr_fusion":19.87}],"starfusion":[{"position":"5:150404680:-#6:117324415:-","junction_reads":5,"spanning_reads":0,"ffmp":398.5334}],"fusioncatcher":[{"position":"5:150404680:-#6:117324415:-","common_mapping_reads":0,"spanning_pairs":3,"spanning_unique_reads":7,"longest_anchor":30,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":0,"split_count":2}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"EWSR1--ATF1":{"score":0.0,"tools":{"ericscript":[{"position":"22:29287134:+#12:50814280:+","discordant_reads":11,"junction_reads":25,"fusion_type":"inter-chromosomal","gene_expr1":37.0,"gene_expr2":12.27,"gene_expr_fusion":553.3}],"starfusion":[{"position":"22:29287134:+#12:50814280:+","junction_reads":8,"spanning_reads":3,"ffmp":876.7734}],"fusioncatcher":[{"position":"22:29287134:+#12:50814280:+","common_mapping_reads":0,"spanning_pairs":10,"spanning_unique_reads":10,"longest_anchor":30,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":3,"split_count":8}],"squid":[{"position":"22:29286921-29287134:+#12:50814279-50814439:-","score":10}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"EWSR1--FLI1":{"score":0.0,"tools":{"ericscript":[{"position":"22:29287134:+#11:128807180:+","discordant_reads":9,"junction_reads":12,"fusion_type":"inter-chromosomal","gene_expr1":37.0,"gene_expr2":3.29,"gene_expr_fusion":600.14}],"starfusion":[{"position":"22:29287134:+#11:128807180:+","junction_reads":5,"spanning_reads":2,"ffmp":557.9468}],"fusioncatcher":[{"position":"22:29287134:+#11:128807180:+","common_mapping_reads":0,"spanning_pairs":9,"spanning_unique_reads":11,"longest_anchor":28,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":2,"split_count":6}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"ETV6--NTRK3":{"score":0.0,"tools":{"ericscript":[{"position":"12:11869970:+#15:87940752:-","discordant_reads":7,"junction_reads":24,"fusion_type":"inter-chromosomal","gene_expr1":9.48,"gene_expr2":0.45,"gene_expr_fusion":54.74}],"starfusion":[{"position":"12:11869969:+#15:87940753:-","junction_reads":9,"spanning_reads":4,"ffmp":1036.1868}],"fusioncatcher":[{"position":"12:11869969:+#15:87940753:-","common_mapping_reads":0,"spanning_pairs":6,"spanning_unique_reads":8,"longest_anchor":29,"fusion_type":"in-frame"}],"pizzly":[{"pair_count":2,"split_count":8}],"squid":[{"position":"12:11869684-11869969:+#15:87940621-87940753:+","score":10}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"CIC--DUX4":{"score":0.0,"tools":{"ericscript":[{"position":"19:42295048:+#4:190174447:+","discordant_reads":6,"junction_reads":6,"fusion_type":"inter-chromosomal","gene_expr1":0.0,"gene_expr2":1.34,"gene_expr_fusion":5.54}],"fusioncatcher":[{"position":"19:42295047:+#4:190174446:+","common_mapping_reads":0,"spanning_pairs":5,"spanning_unique_reads":5,"longest_anchor":34,"fusion_type":"in-frame"}]},"dbs":["Mitelman","COSMIC"]},"EML4--ALK":{"score":0.0,"tools":{"starfusion":[{"position":"2:42301394:+#2:29223584:-","junction_reads":3,"spanning_reads":4,"ffmp":557.9467}],"fusioncatcher":[{"position":"2:42301391:+#2:29223587:-","common_mapping_reads":0,"spanning_pairs":4,"spanning_unique_reads":4,"longest_anchor":33,"fusion_type":"CDS(truncated)/UTR"}]},"dbs":["FusionGDB","Mitelman","COSMIC"]},"CD74--AL132671.2":{"score":0.0,"tools":{"starfusion":[{"position":"5:150404680:-#6:117324415:-","junction_reads":3,"spanning_reads":0,"ffmp":239.12}]},"dbs":[]},"IGH@--CRLF2":{"score":0.0,"tools":{"fusioncatcher":[{"position":"14:105863258:+#X:105799296:-","common_mapping_reads":0,"spanning_pairs":32,"spanning_unique_reads":9,"longest_anchor":94,"fusion_type":"---/intergenic"},{"position":"14:105863343:+#X:105812546:-","common_mapping_reads":0,"spanning_pairs":32,"spanning_unique_reads":6,"longest_anchor":108,"fusion_type":"---/intergenic"},{"position":"14:105863263:+#X:1228687:-","common_mapping_reads":0,"spanning_pairs":32,"spanning_unique_reads":4,"longest_anchor":33,"fusion_type":"---/intergenic"}]},"dbs":[]},"DUX4--IGH@":{"score":0.0,"tools":{"fusioncatcher":[{"position":"4:190174997:+#14:190287409:+","common_mapping_reads":0,"spanning_pairs":5,"spanning_unique_reads":5,"longest_anchor":84,"fusion_type":"CDS(truncated)/---"},{"position":"4:190175284:+#14:106638525:-","common_mapping_reads":0,"spanning_pairs":4,"spanning_unique_reads":8,"longest_anchor":38,"fusion_type":"UTR/---"}]},"dbs":[]},"MALT1--IGH@":{"score":0.0,"tools":{"fusioncatcher":[{"position":"18:58669909:+#14:105888559:+","common_mapping_reads":0,"spanning_pairs":3,"spanning_unique_reads":3,"longest_anchor":34,"fusion_type":"intergenic/---"}]},"dbs":[]},"NPM1--ALK":{"score":0.0,"tools":{"fusioncatcher":[{"position":"5:171391799:+#2:29223528:-","common_mapping_reads":0,"spanning_pairs":3,"spanning_unique_reads":3,"longest_anchor":30,"fusion_type":"in-frame"}]},"dbs":["FusionGDB","Mitelman","COSMIC"]}}