Mercurial > repos > iuc > umi_tools_dedup

changeset 1:c0691d1977dd draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 8da5246c32d60a49e6b6b9027c9adc0a31d4bc5a
author iuc
date Sun, 25 Feb 2018 13:07:44 -0500
parents a6477bafd522
children 2ee290d6c24d
files test-data/out_wl_paired.html test-data/out_wl_paired.log test-data/out_wl_paired.tresh.tab test-data/out_wl_paired.txt test-data/out_wl_single.html test-data/out_wl_single.tresh.tab test-data/out_wl_single.txt
diffstat 7 files changed, 97 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out_wl_paired.html	Sun Feb 25 13:07:44 2018 -0500
@@ -0,0 +1,1 @@
+<html> <head></head><body> <h1>Cell and Count Metrics</h1> <img src="OUT_cell_barcode_count_density.png" ><br /> <img src="OUT_cell_barcode_knee.png" ><br /> <img src="OUT_cell_barcode_counts.png" ><br /> </body></html>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out_wl_paired.log	Sun Feb 25 13:07:44 2018 -0500
@@ -0,0 +1,40 @@
+# output generated by whitelist --bc-pattern=CCCNNNNNNNNXXXXX --subset-reads=0 --stdin=/tmp/tmpibtvD6/files/000/dataset_5.dat --read2-in=/tmp/tmpibtvD6/files/000/dataset_6.dat --expect-cells=5 --error-correct-threshold=3 --method=reads --plot-prefix=OUT --log=/tmp/tmpibtvD6/files/000/dataset_8.dat
+# job started at Sun Feb 25 10:50:16 2018 on bag -- e78e4e5b-e99e-426a-8a92-c8b3beeadf18
+# pid: 2385, system: Linux 4.13.0-32-generic #35-Ubuntu SMP Thu Jan 25 09:13:46 UTC 2018 x86_64
+# blacklist_tsv                           : None
+# cell_number                             : False
+# compresslevel                           : 6
+# error_correct_threshold                 : 3
+# expect_cells                            : 5
+# extract_method                          : string
+# filter_cell_barcodes                    : False
+# log2stderr                              : False
+# loglevel                                : 1
+# method                                  : reads
+# pattern                                 : CCCNNNNNNNNXXXXX
+# pattern2                                : None
+# plot_prefix                             : OUT
+# prime3                                  : None
+# random_seed                             : None
+# read2_in                                : /tmp/tmpibtvD6/files/000/dataset_6.dat
+# short_help                              : None
+# stderr                                  : <_io.TextIOWrapper name='<stderr>' mode='w' encoding='UTF-8'>
+# stdin                                   : <_io.TextIOWrapper name='/tmp/tmpibtvD6/files/000/dataset_5.dat' mode='r' encoding='UTF-8'>
+# stdlog                                  : <_io.TextIOWrapper name='/tmp/tmpibtvD6/files/000/dataset_8.dat' mode='a' encoding='UTF-8'>
+# stdout                                  : <_io.TextIOWrapper name='<stdout>' mode='w' encoding='UTF-8'>
+# subset_reads                            : 0
+# timeit_file                             : None
+# timeit_header                           : None
+# timeit_name                             : all
+# whitelist_tsv                           : None
+2018-02-25 10:50:16,016 INFO Starting barcode extraction
+2018-02-25 10:50:16,017 INFO Parsed 0 reads
+2018-02-25 10:50:16,019 INFO Starting - whitelist determination
+2018-02-25 10:50:17,208 INFO Finished - whitelist determination
+2018-02-25 10:50:17,208 INFO Starting - finding putative error cell barcodes
+2018-02-25 10:50:17,208 INFO Finished - finding putative error cell barcodes
+2018-02-25 10:50:17,208 INFO Writing out whitelist
+2018-02-25 10:50:17,208 INFO Parsed 100 reads
+2018-02-25 10:50:17,208 INFO 100 reads matched the barcode pattern
+2018-02-25 10:50:17,208 INFO Found 23 unique cell barcodes
+# job finished in 1 seconds at Sun Feb 25 10:50:17 2018 --  2.35  0.08  0.00  0.00 -- e78e4e5b-e99e-426a-8a92-c8b3beeadf18
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out_wl_paired.tresh.tab	Sun Feb 25 13:07:44 2018 -0500
@@ -0,0 +1,7 @@
+count	action
+1	Selected
+5	Rejected
+8	Rejected
+11	Rejected
+14	Rejected
+20	Rejected
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out_wl_paired.txt	Sun Feb 25 13:07:44 2018 -0500
@@ -0,0 +1,1 @@
+TTT	AAA,AAG,AAT,AGA,AGG,AGT,ATA,ATT,GAG,GGT,GTA,GTG,GTT,TAA,TAG,TAT,TCT,TGA,TGG,TGT,TTA,TTG	15	2,4,1,6,3,4,6,8,3,2,2,2,8,2,3,6,1,1,2,4,8,7
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out_wl_single.html	Sun Feb 25 13:07:44 2018 -0500
@@ -0,0 +1,1 @@
+<html> <head></head><body> <h1>Cell and Count Metrics</h1> <img src="OUT_cell_barcode_count_density.png" ><br /> <img src="OUT_cell_barcode_knee.png" ><br /> <img src="OUT_cell_barcode_counts.png" ><br /> </body></html>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out_wl_single.tresh.tab	Sun Feb 25 13:07:44 2018 -0500
@@ -0,0 +1,3 @@
+count	action
+1	Rejected
+4	Selected
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/out_wl_single.txt	Sun Feb 25 13:07:44 2018 -0500
@@ -0,0 +1,44 @@
+# output generated by whitelist --bc-pattern=CCCCCCCCNNNNNNNN --subset-reads=0 --stdin=/tmp/tmpibtvD6/files/000/dataset_1.dat --method=reads --plot-prefix=OUT --3prime
+# job started at Sun Feb 25 10:49:56 2018 on bag -- cb0db520-8a4e-4040-aa88-93efc0718fa8
+# pid: 2217, system: Linux 4.13.0-32-generic #35-Ubuntu SMP Thu Jan 25 09:13:46 UTC 2018 x86_64
+# blacklist_tsv                           : None
+# cell_number                             : False
+# compresslevel                           : 6
+# error_correct_threshold                 : 1
+# expect_cells                            : False
+# extract_method                          : string
+# filter_cell_barcodes                    : False
+# log2stderr                              : False
+# loglevel                                : 1
+# method                                  : reads
+# pattern                                 : CCCCCCCCNNNNNNNN
+# pattern2                                : None
+# plot_prefix                             : OUT
+# prime3                                  : True
+# random_seed                             : None
+# read2_in                                : None
+# short_help                              : None
+# stderr                                  : <_io.TextIOWrapper name='<stderr>' mode='w' encoding='UTF-8'>
+# stdin                                   : <_io.TextIOWrapper name='/tmp/tmpibtvD6/files/000/dataset_1.dat' mode='r' encoding='UTF-8'>
+# stdlog                                  : <_io.TextIOWrapper name='<stdout>' mode='w' encoding='UTF-8'>
+# stdout                                  : <_io.TextIOWrapper name='<stdout>' mode='w' encoding='UTF-8'>
+# subset_reads                            : 0
+# timeit_file                             : None
+# timeit_header                           : None
+# timeit_name                             : all
+# whitelist_tsv                           : None
+## 2018-02-25 10:49:56,061 INFO Starting barcode extraction
+## 2018-02-25 10:49:56,061 INFO Parsed 0 reads
+## 2018-02-25 10:49:56,062 INFO Starting - whitelist determination
+## 2018-02-25 10:49:57,383 INFO Finished - whitelist determination
+## 2018-02-25 10:49:57,383 INFO Starting - finding putative error cell barcodes
+## 2018-02-25 10:49:57,383 INFO Finished - finding putative error cell barcodes
+## 2018-02-25 10:49:57,383 INFO Writing out whitelist
+AAAAAAAA	AAAAAACA,AAACAAAA,AATAAAAA	3	1,1,1
+ACAAAAAC		2	
+ACAACAAA		2	
+TTACTTAA	TTACTAAA	2	1
+## 2018-02-25 10:49:57,383 INFO Parsed 100 reads
+## 2018-02-25 10:49:57,383 INFO 100 reads matched the barcode pattern
+## 2018-02-25 10:49:57,383 INFO Found 95 unique cell barcodes
+# job finished in 1 seconds at Sun Feb 25 10:49:57 2018 --  2.25  0.06  0.00  0.00 -- cb0db520-8a4e-4040-aa88-93efc0718fa8