Merge pull request #75 from CGATOxford/{TS}-addSubsetToGroup

Add subset to group command and correct output
CGATOxford · Feb 1, 2017 · e1b9c4a · e1b9c4a
2 parents 70b5ce3 + 09e30a4
commit e1b9c4a
Show file tree

Hide file tree

Showing 11 changed files with 25,651 additions and 3,638 deletions.
diff --git a/tests/group_cluster.tsv b/tests/group_cluster.tsv
diff --git a/tests/group_cluster_py3.tsv b/tests/group_cluster_py3.tsv
diff --git a/tests/group_dir.tsv b/tests/group_dir.tsv
diff --git a/tests/group_dir_py3.tsv b/tests/group_dir_py3.tsv
diff --git a/tests/group_dir_subset.sam b/tests/group_dir_subset.sam
diff --git a/tests/group_dir_subset.tsv b/tests/group_dir_subset.tsv
diff --git a/tests/group_dir_subset_py3.sam b/tests/group_dir_subset_py3.sam
diff --git a/tests/group_dir_subset_py3.tsv b/tests/group_dir_subset_py3.tsv
diff --git a/tests/tests.yaml b/tests/tests.yaml
@@ -82,20 +82,27 @@ dedup_single_sep:
       references: [single_sep.sam]
       options: "dedup -L test.log --out-sam --random-seed=123456789 --method=directional --umi-separator=:" 
 
-group unique:
+group_unique:
       skip_python: 3
       stdin: chr19.bam
       outputs: [stdout, group_uniq.tsv]
       references: [group_uniq.sam, group_uniq.tsv]
       options: group -L test.log --out-sam --random-seed=123456789 --method=unique --output-bam --out-sam --group-out=group_uniq.tsv
 
-group cluster:
+group_cluster:
       skip_python: 3
       stdin: chr19.bam
       outputs: [stdout, group_cluster.tsv]
       references: [group_cluster.sam, group_cluster.tsv]
       options: group -L test.log --out-sam --random-seed=123456789 --method=cluster --output-bam --out-sam --group-out=group_cluster.tsv
 
+group_directional_subset:
+      skip_python: 3
+      stdin: chr19.bam
+      outputs: [stdout, group_dir_subset.tsv]
+      references: [group_dir_subset.sam, group_dir_subset.tsv]
+      options: group -L test.log --out-sam --random-seed=123456789 --method=directional --output-bam --out-sam --group-out=group_dir_subset.tsv --subset=0.1
+
 # ## End of python 2 tests ##
 
 
@@ -172,34 +179,43 @@ dedup_single_sep_py3:
       references: [single_sep_py3.sam]
       options: "dedup -L test.log --out-sam --random-seed=123456789 --method=directional --umi-separator=:" 
 
-group unique_py3:
+group_unique_py3:
       skip_python: 2
       stdin: chr19.bam
       outputs: [stdout, group_uniq.tsv]
       references: [group_uniq_py3.sam, group_uniq_py3.tsv]
       options: group -L test.log --out-sam --random-seed=123456789 --method=unique --output-bam --out-sam --group-out=group_uniq.tsv
 
-group cluster_py3:
+group_cluster_py3:
       skip_python: 2
       stdin: chr19.bam
       outputs: [stdout, group_cluster.tsv]
       references: [group_cluster_py3.sam, group_cluster_py3.tsv]
       options: group -L test.log --out-sam --random-seed=123456789 --method=cluster --output-bam --out-sam --group-out=group_cluster.tsv
 
-# group adjacency_py3:
+# group_adjacency_py3:
 #       skip_python: 2
 #       stdin: chr19.bam
 #       outputs: [stdout, group_adj.tsv]
 #       references: [group_adj_py3.sam, group_adj_py3.tsv]
 #       options: group -L test.log --out-sam --random-seed=123456789 --method=adjacency --output-bam --out-sam --group-out=group_adj.tsv
 
-group directional_py3:
+group_directional_py3:
       skip_python: 2
       stdin: chr19.bam
       outputs: [stdout, group_dir.tsv]
       references: [group_dir_py3.sam, group_dir_py3.tsv]
       options: group -L test.log --out-sam --random-seed=123456789 --method=directional --output-bam --out-sam --group-out=group_dir.tsv
 
+
+group_directional_subset_py3:
+      skip_python: 2
+      stdin: chr19.bam
+      outputs: [stdout, group_dir_subset.tsv]
+      references: [group_dir_subset_py3.sam, group_dir_subset_py3.tsv]
+      options: group -L test.log --out-sam --random-seed=123456789 --method=directional --output-bam --out-sam --group-out=group_dir_subset.tsv --subset=0.1
+
+
 ## End of python 3 tests ##
 
 

diff --git a/umi_tools/group.py b/umi_tools/group.py
@@ -249,6 +249,9 @@ def main(argv=None):
     parser.add_option("--umi-separator", dest="umi_sep",
                       type="string", help="separator between read id and UMI",
                       default="_")
+    parser.add_option("--subset", dest="subset", type="float",
+                      help="Use only a fraction of reads, specified by subset",
+                      default=None)
     parser.add_option("--spliced-is-unique", dest="spliced",
                       action="store_true",
                       help="Treat a spliced read as different to an unspliced"
@@ -353,7 +356,7 @@ def main(argv=None):
             infile,
             read_events,
             ignore_umi=False,
-            subset=False,
+            subset=options.subset,
             quality_threshold=options.mapping_quality,
             paired=options.paired,
             chrom=options.chrom,
@@ -407,8 +410,8 @@ def main(argv=None):
                         mapping_outfile.write("%s\n" % "\t".join(map(str, (
                             read.query_name, read.reference_name,
                             umi_methods.get_read_position(read, options.soft)[1],
-                            umi_methods.get_umi(read, options.umi_sep).decode(),
-                            counts[top_umi],
+                            umi.decode(),
+                            counts[umi],
                             top_umi.decode(),
                             group_count,
                             unique_id))))

diff --git a/umi_tools/version.py b/umi_tools/version.py
@@ -1 +1 @@
-__version__ = "0.3.5"
+__version__ = "0.3.6"