add exon/intron index information

YangLab · Jan 22, 2016 · 31857ea · 31857ea
1 parent 11d4cff
commit 31857ea
Show file tree

Hide file tree

Showing 5 changed files with 40 additions and 19 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,3 +1,9 @@
+## 1.1.6 (2016-1-22)
+
+Improvements:
+
+* add exon/intron index information
+
 ## 1.1.5 (2016-1-20)
 
 Improvements:

diff --git a/README.md b/README.md
@@ -4,9 +4,9 @@
 
 CIRCexplorer is a combined strategy to identify junction reads from back spliced exons and intron lariats.
 
-Version: 1.1.5
+Version: 1.1.6
 
-Last Modified: 2016-1-20
+Last Modified: 2016-1-22
 
 Authors: Xiao-Ou Zhang ([email protected]), Li Yang ([email protected])
 
@@ -82,7 +82,7 @@ To detect fusion junctions with STAR, `--chimSegmentMin` should be set to a posi
 ##Usage
 
 ```bash
-CIRCexplorer.py 1.1.5 -- circular RNA analysis toolkits.
+CIRCexplorer.py 1.1.6 -- circular RNA analysis toolkits.
 
 Usage: CIRCexplorer.py [options]
 
@@ -174,6 +174,7 @@ See details in [the example file](https://github.com/YangLab/CIRCexplorer/blob/m
 | circType    | 'Yes' for ciRNA, and 'No' for circRNA (before 1.1.0); 'circRNA' or 'ciRNA' (after 1.1.1)|
 | geneName    | Name of gene                          |
 | isoformName | Name of isoform                       |
+| exonIndex/intronIndex | Index (start from 1) of exon (for circRNA) or intron (for ciRNA) in given isoform (newly added in 1.1.6) |
 | flankIntron | Left intron/Right intron              |
 
 ***Note: The first 12 columns are in [BED12 format](http://genome.ucsc.edu/FAQ/FAQformat.html#format1).***

diff --git a/circ/CIRCexplorer.py b/circ/CIRCexplorer.py
@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 
 """
-CIRCexplorer.py 1.1.5 -- circular RNA analysis toolkit.
+CIRCexplorer.py 1.1.6 -- circular RNA analysis toolkit.
 
 Usage: CIRCexplorer.py [options]
 
@@ -22,7 +22,7 @@
 """
 
 __author__ = 'Xiao-Ou Zhang ([email protected])'
-__version__ = '1.1.5'
+__version__ = '1.1.6'
 
 from docopt import docopt
 import sys
@@ -134,8 +134,16 @@ def fix_fusion(ref_f, genome_fa, input_f, output_f, no_fix):
             name = 'circular_RNA/' + reads
             gene, iso, chrom, strand, index = fus.split()
             starts, ends = ref['\t'.join([gene, iso, chrom, strand])]
+            exon_num = len(starts)
+            intron_num = exon_num - 1
             if ',' in index:  # back spliced exons
                 s, e = [int(x) for x in index.split(',')]
+                if strand == '+':
+                    index_info = ','.join(str(x + 1)
+                                          for x in xrange(s, e + 1))
+                else:
+                    index_info = ','.join(str(exon_num - x)
+                                          for x in xrange(s, e + 1))
                 start = str(starts[s])
                 end = str(ends[e])
                 length = str(e - s + 1)
@@ -152,15 +160,21 @@ def fix_fusion(ref_f, genome_fa, input_f, output_f, no_fix):
                 intron = '|'.join([left_intron, right_intron])
                 bed = '\t'.join([chrom, start, end, name, fixed, strand, start,
                                  start, '0,0,0', length, sizes, offsets,
-                                 reads, 'circRNA', gene, iso, intron])
+                                 reads, 'circRNA', gene, iso, index_info,
+                                 intron])
             else:  # ciRNAs
                 index, start, end = index.split('|')
-                size = str(int(end) - int(start))
                 index = int(index)
+                if strand == '+':
+                    index_info = str(index + 1)
+                else:
+                    index_info = str(intron_num - index)
+                size = str(int(end) - int(start))
                 intron = '%s:%d-%d' % (chrom, ends[index], starts[index + 1])
                 bed = '\t'.join([chrom, start, end, name, fixed, strand, start,
                                  start, '0,0,0', '1', size, '0',
-                                 reads, 'ciRNA', gene, iso, intron])
+                                 reads, 'ciRNA', gene, iso, index_info,
+                                 intron])
             outf.write(bed + '\n')
     print('Fixed %d fusion junctions!' % total)
 

diff --git a/example/output_example.txt b/example/output_example.txt
@@ -1,10 +1,10 @@
-chr3	183493702	183508768	circular_RNA/1	1	+	183493702	183493702	0,0,0	4	209,159,177,184	0,1627,10210,14882	1	No	YEATS2	NM_018023	chr3:183491582-183493702|chr3:183508768-183515710
-chr2	48060102	48061850	circular_RNA/2	0	-	48060102	48060102	0,0,0	2	107,133	0,1615	2	No	FBXO11	NM_025133	chr2:48060019-48060102|chr2:48061850-48061926
-chr1	78204949	78207433	circular_RNA/1	1	-	78204949	78204949	0,0,0	4	153,63,54,132	0,1612,2111,2352	1	No	USP33	NM_015017	chr1:78201843-78204949|chr1:78207433-78211105
-chr11	118997644	118997835	circular_RNA/5	1	+	118997644	118997644	0,0,0	1	191	0	5	No	HINFP	uc010rzb.2	chr11:118992349-118997644|chr11:118997835-119001434
-chr3	69112132	69117159	circular_RNA/2	1	-	69112132	69112132	0,0,0	4	156,65,44,81	0,457,1086,4946	2	No	UBA3	NM_003968	chr3:69111330-69112132|chr3:69117159-69120685
-chr9	132841908	132854660	circular_RNA/2	1	+	132841908	132841908	0,0,0	5	140,38,57,108,134	0,3935,6790,11246,12618	2	No	GPR107	uc004bzb.2	chr9:132839653-132841908|chr9:132854660-132861735
-chr9	134381500	134381840	circular_RNA/1	1	+	134381500	134381500	0,0,0	2	107,51	0,289	1	No	POMT1	uc011mci.1	chr9:134379727-134381500|chr9:134381840-134382754
-chr9	99277930	99327765	circular_RNA/3	0	-	99277930	99277930	0,0,0	12	144,98,160,139,231,88,63,67,77,93,76,91	0,6857,7612,7938,18278,18806,23429,26177,36147,47044,49128,49744	3	No	CDC14B	uc004awl.3	chr9:99272071-99277930|chr9:99327765-99381500
-chr10	1149541	1151207	circular_RNA/3	0	+	1149541	1149541	0,0,0	2	235,142	0,1524	3	No	WDR37	uc031ptc.1	chr10:1142186-1149541|chr10:1151207-1170157
-chr9	99324974	99327765	circular_RNA/1	0	-	99324974	99324974	0,0,0	3	93,76,91	0,2084,2700	1	No	CDC14B	NM_001077181	chr9:99314154-99324974|chr9:99327765-99329049
+chrY	150833	159885	circular_RNA/2	1	+	150833	150833	0,0,0	5	148,137,129,156,184	0,4566,6481,7332,8868	2	circRNA	PLCXD1	NR_028057	3,4,5,6,7	chrY:148351-150833|chrY:159885-165763
+chrY	256250	258428	circular_RNA/1	0	-	256250	256250	0,0,0	5	157,87,75,103,104	0,658,1185,1718,2074	1	circRNA	PPP2R3B	NM_013239	7,6,5,4,3	chrY:252666-256250|chrY:258428-272139
+chrY	272139	273067	circular_RNA/2	0	-	272139	272139	0,0,0	2	186,78	0,850	2	circRNA	PPP2R3B	uc011nah.2	3,2	chrY:258428-272139|chrY:273067-297102
+chrY	1455672	1456171	circular_RNA/1	1	-	1455672	1455672	0,0,0	1	499	0	1	ciRNA	SLC25A6	NM_001636	3	chrY:1455652-1456171
+chrY	1490550	1497014	circular_RNA/1	1	-	1490550	1490550	0,0,0	3	185,163,388	0,3867,6076	1	circRNA	ASMTL	NM_001173474	8,7,6	chrY:1488007-1490550|chrY:1497014-1501161
+chrY	2111063	2111271	circular_RNA/4	0	-	2111063	2111063	0,0,0	1	208	0	4	circRNA	DHRSX	NM_145177	6	chrY:2089270-2111063|chrY:2111271-2134780
+chrY	2134780	2159644	circular_RNA/2	0	-	2134780	2134780	0,0,0	2	208,102	0,24762	2	circRNA	DHRSX	NM_145177	5,4	chrY:2111271-2134780|chrY:2159644-2276785
+chrX	299512	302131	circular_RNA/1	0	-	299512	299512	0,0,0	3	119,176,90	0,1987,2529	1	circRNA	PPP2R3B	NM_013239	11,10,9	chrX:299445-299512|chrX:302131-302617
+chrX	322139	323067	circular_RNA/1	0	-	322139	322139	0,0,0	2	186,78	0,850	1	circRNA	PPP2R3B	ENST00000445792	3,2	chrX:308428-322139|chrX:323067-347102
+chrX	1505672	1506171	circular_RNA/1	1	-	1505672	1505672	0,0,0	1	499	0	1	ciRNA	SLC25A6	NM_001636	3	chrX:1505652-1506171
diff --git a/setup.py b/setup.py
@@ -4,7 +4,7 @@
 from setuptools import setup, find_packages
 
 setup(name='CIRCexplorer',
-      version='1.1.5',
+      version='1.1.6',
       description='Circular RNA analysis toolkits',
       author='Xiao-Ou Zhang',
       author_email='[email protected]',