[med-svn] [tophat] 02/05: Imported Upstream version 2.0.11

Andreas Tille tille at debian.org
Tue Mar 18 13:17:01 UTC 2014


This is an automated email from the git hooks/post-receive script.

tille pushed a commit to branch master
in repository tophat.

commit 2770873f365405e551fcaddbd831c4bb53476ea6
Author: Andreas Tille <tille at debian.org>
Date:   Tue Mar 18 13:58:17 2014 +0100

    Imported Upstream version 2.0.11
---
 configure              | 24 +++++++++++-----------
 configure.ac           |  2 +-
 src/tophat-fusion-post | 55 ++++++++++++++++++++++++++------------------------
 src/tophat.py          |  2 +-
 4 files changed, 43 insertions(+), 40 deletions(-)

diff --git a/configure b/configure
index 932984f..115b8dc 100755
--- a/configure
+++ b/configure
@@ -1,6 +1,6 @@
 #! /bin/sh
 # Guess values for system-dependent variables and create Makefiles.
-# Generated by GNU Autoconf 2.59 for tophat 2.0.10.
+# Generated by GNU Autoconf 2.59 for tophat 2.0.11.
 #
 # Report bugs to <tophat.cufflinks at gmail.com>.
 #
@@ -269,8 +269,8 @@ SHELL=${CONFIG_SHELL-/bin/sh}
 # Identity of this package.
 PACKAGE_NAME='tophat'
 PACKAGE_TARNAME='tophat'
-PACKAGE_VERSION='2.0.10'
-PACKAGE_STRING='tophat 2.0.10'
+PACKAGE_VERSION='2.0.11'
+PACKAGE_STRING='tophat 2.0.11'
 PACKAGE_BUGREPORT='tophat.cufflinks at gmail.com'
 
 ac_unique_file="config.h.in"
@@ -792,7 +792,7 @@ if test "$ac_init_help" = "long"; then
   # Omit some internal or obsolete options to make the list less imposing.
   # This message is too long to be a string in the A/UX 3.1 sh.
   cat <<_ACEOF
-\`configure' configures tophat 2.0.10 to adapt to many kinds of systems.
+\`configure' configures tophat 2.0.11 to adapt to many kinds of systems.
 
 Usage: $0 [OPTION]... [VAR=VALUE]...
 
@@ -858,7 +858,7 @@ fi
 
 if test -n "$ac_init_help"; then
   case $ac_init_help in
-     short | recursive ) echo "Configuration of tophat 2.0.10:";;
+     short | recursive ) echo "Configuration of tophat 2.0.11:";;
    esac
   cat <<\_ACEOF
 
@@ -1009,7 +1009,7 @@ fi
 test -n "$ac_init_help" && exit 0
 if $ac_init_version; then
   cat <<\_ACEOF
-tophat configure 2.0.10
+tophat configure 2.0.11
 generated by GNU Autoconf 2.59
 
 Copyright (C) 2003 Free Software Foundation, Inc.
@@ -1023,7 +1023,7 @@ cat >&5 <<_ACEOF
 This file contains any messages produced by compilers while
 running configure, to aid debugging if configure makes a mistake.
 
-It was created by tophat $as_me 2.0.10, which was
+It was created by tophat $as_me 2.0.11, which was
 generated by GNU Autoconf 2.59.  Invocation command line was
 
   $ $0 $@
@@ -1361,7 +1361,7 @@ ac_compiler_gnu=$ac_cv_c_compiler_gnu
 
 
 cat >>confdefs.h <<\_ACEOF
-#define SVN_REVISION "4167"
+#define SVN_REVISION "4203"
 _ACEOF
 
 
@@ -1675,7 +1675,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='tophat'
- VERSION='2.0.10'
+ VERSION='2.0.11'
 
 
 cat >>confdefs.h <<_ACEOF
@@ -7134,7 +7134,7 @@ fi
 
 # Define the identity of the package.
  PACKAGE='tophat'
- VERSION='2.0.10'
+ VERSION='2.0.11'
 
 
 cat >>confdefs.h <<_ACEOF
@@ -7966,7 +7966,7 @@ _ASBOX
 } >&5
 cat >&5 <<_CSEOF
 
-This file was extended by tophat $as_me 2.0.10, which was
+This file was extended by tophat $as_me 2.0.11, which was
 generated by GNU Autoconf 2.59.  Invocation command line was
 
   CONFIG_FILES    = $CONFIG_FILES
@@ -8029,7 +8029,7 @@ _ACEOF
 
 cat >>$CONFIG_STATUS <<_ACEOF
 ac_cs_version="\\
-tophat config.status 2.0.10
+tophat config.status 2.0.11
 configured by $0, generated by GNU Autoconf 2.59,
   with options \\"`echo "$ac_configure_args" | sed 's/[\\""\`\$]/\\\\&/g'`\\"
 
diff --git a/configure.ac b/configure.ac
index 7fc65ab..936d4ec 100644
--- a/configure.ac
+++ b/configure.ac
@@ -4,7 +4,7 @@ m4_include([ax_bam.m4])
 #m4_include([ax_check_zlib.m4])
 
 define([svnversion], esyscmd([sh -c "svnversion|tr -d '\n'"]))dnl
-AC_INIT([tophat],[2.0.10],[tophat.cufflinks at gmail.com])
+AC_INIT([tophat],[2.0.11],[tophat.cufflinks at gmail.com])
 AC_DEFINE(SVN_REVISION, "svnversion", [SVN Revision])
 
 AC_CONFIG_SRCDIR([config.h.in])
diff --git a/src/tophat-fusion-post b/src/tophat-fusion-post
index 20a8f44..c4be6bc 100755
--- a/src/tophat-fusion-post
+++ b/src/tophat-fusion-post
@@ -35,6 +35,8 @@ Options:
 
     -p/--num-threads               <int>       [ default: 1                  ]
 
+    --no-filter-by-annotation
+
     --skip-fusion-kmer
     --skip-filter-fusion
     --skip-blast
@@ -69,6 +71,8 @@ class TopHatFusionParams:
         self.is_human = True
 
         self.num_threads = 1
+
+        self.filter_by_annotation = True
         
         self.skip_fusion_kmer = False
         self.skip_filter_fusion = False
@@ -95,6 +99,7 @@ class TopHatFusionParams:
                                          "fusion-multireads=",
                                          "non-human",
                                          "num-threads=",
+                                         "no-filter-by-annotation",
                                          "skip-fusion-kmer",
                                          "skip-filter-fusion",
                                          "skip-blast",
@@ -129,6 +134,8 @@ class TopHatFusionParams:
                 output_dir = value + "/"
                 logging_dir = output_dir + "logs/"
                 tmp_dir = output_dir + "tmp/"
+            if option == "--no-filter-by-annotation":
+                self.filter_by_annotation = False
             if option == "--skip-fusion-kmer":
                 self.skip_fusion_kmer = True
             if option == "--skip-filter-fusion":
@@ -435,8 +442,9 @@ def filter_fusion(bwt_idx_prefix, params):
         fusion_file.readline()
         for line in fusion_file:
             info, sim, left_seq_org, right_seq_org, left_dist, right_dist, pair_list = line[:-1].split('\t@\t')[:7]
-
             info = info.split('\t')
+            if sim.strip() == "":
+                continue
             sim = sim.split(' ')
             left_seq = left_seq_org.replace(' ', '')
             right_seq = right_seq_org.replace(' ', '')
@@ -460,17 +468,8 @@ def filter_fusion(bwt_idx_prefix, params):
             else:
                 single = False
 
-            if string.find(data, "maher") != -1:
-                extent = min(10, num_reads)
-                if single:
-                    if left_ext < 25 + extent * 2 or right_ext < 25 + extent * 2:
-                        continue
-                else:
-                    if left_ext < 14 + extent or right_ext < 14 + extent:
-                        continue
-            else:
-                if left_ext < 16 or right_ext < 16:
-                    continue
+            if left_ext < 16 or right_ext < 16:
+                continue
 
             both = num_reads + num_pair_ends_both
             all = both
@@ -483,9 +482,11 @@ def filter_fusion(bwt_idx_prefix, params):
                     both < params.num_fusion_both:
                 continue
 
+            """
             if (chr1 != chr2 and num_unsupport_reads > num_reads) or \
                     (chr1 == chr2 and num_unsupport_reads > all + num_pair_ends + 5):
                 continue
+            """
 
             pairs = []
             if num_pair_ends >= 1:
@@ -500,7 +501,6 @@ def filter_fusion(bwt_idx_prefix, params):
             # are the sequences around the breakpoint different enough?
             if int(sim[0]) < 8:
                 continue
-           
 
             # is the reads distributed symmetrically?
             if sym >= 22 + max(0, 6 - num_reads):
@@ -511,7 +511,7 @@ def filter_fusion(bwt_idx_prefix, params):
                 coord_dif = coord2 - coord1
                 if coord_dif > 0 and coord_dif < max_intron_len:
                     continue
-
+            
             if not left_seq[half_len-kmer_len:half_len] in seq_chr_dic or not right_seq[half_len:half_len+kmer_len] in seq_chr_dic:
                 continue
 
@@ -531,7 +531,7 @@ def filter_fusion(bwt_idx_prefix, params):
 
             if same:
                 continue
-
+            
             for chr_coord in right_chrs:
                 chr, coord = chr_coord.split(':')
                 coord = int(coord)
@@ -555,12 +555,12 @@ def filter_fusion(bwt_idx_prefix, params):
             dir = info[3]
             gene1, gene1_name, gene1_where, gene1_belong, gene1_sense, ens_gene1, ens_gene1_name = find_gene(chr1, coord1, dir[0], True)
             gene2, gene2_name, gene2_where, gene2_belong, gene2_sense, ens_gene2, ens_gene2_name = find_gene(chr2, coord2, dir[1], False)
+            if params.filter_by_annotation:
+                if gene1_name == gene2_name or ens_gene1_name == ens_gene2_name or ens_gene1 == ens_gene2:
+                    continue
 
-            if gene1_name == gene2_name or ens_gene1_name == ens_gene2_name or ens_gene1 == ens_gene2:
-                continue
-
-            if gene1 == "N/A" or gene2 == "N/A" or (string.find(gene1, "ENS") == 0 and string.find(gene2, "ENS") == 0):
-                continue
+                if gene1 == "N/A" or gene2 == "N/A" or (string.find(gene1, "ENS") == 0 and string.find(gene2, "ENS") == 0):
+                    continue
 
             left_diff = how_diff(left_seq[half_len - 20:half_len], right_seq[half_len - 20:half_len])
             if left_diff <= 8:
@@ -582,9 +582,9 @@ def filter_fusion(bwt_idx_prefix, params):
 
             swap = False
             if (dir == 'ff' and gene1_sense == '-' and gene2_sense == '-') or \
-               (dir == 'rr' and gene1_sense == '+' and gene2_sense == '+') or \
-               (dir == 'fr' and gene1_sense == '-' and gene2_sense == '+') or \
-               (dir == 'rf' and gene1_sense == '+' and gene2_sense == '-'):
+                   (dir == 'rr' and gene1_sense == '+' and gene2_sense == '+') or \
+                   (dir == 'fr' and gene1_sense == '-' and gene2_sense == '+') or \
+                   (dir == 'rf' and gene1_sense == '+' and gene2_sense == '-'):
                 swap = True
 
             if swap:
@@ -692,8 +692,11 @@ def filter_fusion(bwt_idx_prefix, params):
             
         return gene_list
 
-    refGene_list = read_genes("refGene.txt")
-    ensGene_list = read_genes("ensGene.txt")
+    refGene_list, ensGene_list = [], []
+    if os.path.exists("refGene.txt"):
+        refGene_list = read_genes("refGene.txt")
+    if os.path.exists("ensGene.txt"):
+        ensGene_list = read_genes("ensGene.txt")
 
     fusion_gene_list = []
     for file in sorted(os.listdir(".")):
@@ -2585,7 +2588,7 @@ def prog_path(program):
 
 
 def get_version():
-   return "2.1.0"
+   return "2.0.11"
 
 
 def main(argv=None):
diff --git a/src/tophat.py b/src/tophat.py
index 94f5848..b4677b3 100755
--- a/src/tophat.py
+++ b/src/tophat.py
@@ -1496,7 +1496,7 @@ def get_index_sam_header(params, idx_prefix, name = ""):
 def check_bowtie(params):
     bowtie_req=""
     if params.bowtie2:
-        bowtie_req="2-align"
+        bowtie_req="2"
     log_msg = "Checking for Bowtie"
     th_log(log_msg)
 

-- 
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/debian-med/tophat.git



More information about the debian-med-commit mailing list