Merge pull request #7 from 4dn-dcic/dev

Dev

README.md

@@ -65,6 +65,10 @@ optional arguments:
   -s SAMPLE_NAME, --sample_name SAMPLE_NAME
                         sample name to be used as the file prefix and in the
                         report (do not include space)
+  -M MAX_LOGDISTANCE, --max_logdistance MAX_LOGDISTANCE
+                        Maximum log distance. This number should not be larger
+                        than all chromosomes. Choose 8.2 for mouse. Default
+                        8.4 (human).
 ```
 2) plot.r
 ```
@@ -86,6 +90,8 @@ python pairsqc.py -p test_samples/merged_nodup.tab.chrblock_sorted.txt.gz -c tes
 Rscript plot.r 4
 zip report.zip report # if you want to create a zip file for the report.
 ```
+* Note : The default max logdistance is set to be 8.4, which works for human. For non-human species, use -M option to reset the max logdistance. (e.g. -M 8.2 for mouse)
+
 
  
 ### QC metrics and plots

VERSION_HISTORY.md

@@ -5,3 +5,12 @@
 * The report can now contain information about multiple samples.
   * `pairsqc.py` now takes sample name as an option (-s). The output files in the output report directory will have the sample name as file prefix.
   * `plot.r` also assumes sample names as prefix in the report directory (auto-detect).
+  * Now d3 interactive plots are integrated with the Nozzle report. (https://github.com/SooLee/d3forNozzleR)
+
+### 0.2.1
+  * 'Sample' is used as a sample name place holder (instead of an empty string), when sample name is not specified.
+
+### 0.2.2
+  * `-M` option is introduced to work for non-human species (e.g. -M 8.2 for mouse)
+
+

pairsqc.py

@@ -328,6 +328,7 @@ def distance_histogram (pairs_file, chromsize_file, outfilename, cols=cols_pairs
     parser.add_argument('-t','--input_type', help = "input file type (P:pairs, M:merged_nodups, OM:old_merged_nodups)")
     parser.add_argument('-O','--outdir_prefix', help = "prefix of output directory (output directory name will be <outdir_prefix>_report")
     parser.add_argument('-s','--sample_name', help = "sample name to be used as the file prefix and in the report (do not include space)")
+    parser.add_argument('-M','--max_logdistance', help = "Maximum log distance. This number should not be larger than all chromosomes. Choose 8.2 for mouse. Default 8.4 (human).")
     args = parser.parse_args()
 
     if args.outdir_prefix:
@@ -359,7 +360,14 @@ def distance_histogram (pairs_file, chromsize_file, outfilename, cols=cols_pairs
     CIS_TRANS_OUT_FILE_PATH = outdir + '/' + sample_name + '.' + CIS_TRANS_OUT_FILE_SUFFIX
     PLOT_TABLE_OUT_FILE_PATH = outdir + '/' + sample_name + '.' + PLOT_TABLE_OUT_FILE_SUFFIX
 
+
+    # max_logdistance
+    if args.max_logdistance:
+        max_logdist = float(args.max_logdistance)
+    else:
+        max_logdist = 8.4
+
     # get the stats
     cis_trans_ratio (args.pairs, outfilename=CIS_TRANS_OUT_FILE_PATH, cols = cols)
-    distance_histogram (args.pairs, args.chrsize, outfilename=PLOT_TABLE_OUT_FILE_PATH, cols = cols, orientation_list = orientation_list)
+    distance_histogram (args.pairs, args.chrsize, outfilename=PLOT_TABLE_OUT_FILE_PATH, cols = cols, orientation_list = orientation_list, max_logdistance = max_logdist)