# HG changeset patch
# User trinity_ctat
# Date 1531842433 14400
# Node ID f92fcdde48fc11e9b4a17e34e388fe8e568765c3
Upload ctat tools.
diff -r 000000000000 -r f92fcdde48fc ctat_metagenomics.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/ctat_metagenomics.xml Tue Jul 17 11:47:13 2018 -0400
@@ -0,0 +1,109 @@
+
+
+ Centrifuge classifier for metagenomic sequences (RNA-Seq)
+
+ centrifuge
+ ctat-metagenomics
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+.. class:: infomark
+
+ctat_metagenomics is a component of the Trinity Cancer Transcriptome Analysis Toolkit (CTAT). CTAT's metagenomics is a classifier for metagenomic sequences (RNA-Seq) for foreign transcript detection. It leverages Centrifuge, a novel microbial classification engine that enables rapid, accurate, and sensitive labeling of reads and quantification of species, and Kraken. As well, we are leveraging RNA-Seq reads and Trinity-reconstructed transcripts. Our efforts here are being carried out in collaboration with the group of Steven Salzberg at JHU.
+
+For more information:
+
+https://ccb.jhu.edu/software/centrifuge/manual.shtml#what-is-centrifuge
+
+
+
+ 10.1101/gr.210641.116
+
+
+
diff -r 000000000000 -r f92fcdde48fc test-data/centrifuge/SRR2219890_1_20k_reads.classification.report.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/centrifuge/SRR2219890_1_20k_reads.classification.report.txt Tue Jul 17 11:47:13 2018 -0400
@@ -0,0 +1,8 @@
+name taxID taxRank genomeSize numReads numUniqueReads abundance
+root 1 no rank 0 370 370 0.0
+Bacillus 1386 genus 5402033 31 31 0.0
+Homo sapiens 9606 species 3238442024 4384 4384 0.00519472
+synthetic construct 32630 species 26537524 8 8 0.000787552
+Methanocaldococcus 196118 genus 1584277 1 1 0.0
+Methanocaldococcus jannaschii DSM 2661 243232 leaf 1739927 50 50 0.994018
+Leptotrichia buccalis C-1013-b 523794 leaf 2465610 1 1 0.0
diff -r 000000000000 -r f92fcdde48fc test-data/centrifuge/SRR2219890_1_20k_reads.kraken_style_report.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/centrifuge/SRR2219890_1_20k_reads.kraken_style_report.txt Tue Jul 17 11:47:13 2018 -0400
@@ -0,0 +1,58 @@
+ 2.67 133 133 U 0 unclassified
+ 97.33 4845 370 - 1 root
+ 89.73 4467 0 - 131567 cellular organisms
+ 88.07 4384 0 D 2759 Eukaryota
+ 88.07 4384 0 - 33154 Opisthokonta
+ 88.07 4384 0 K 33208 Metazoa
+ 88.07 4384 0 - 6072 Eumetazoa
+ 88.07 4384 0 - 33213 Bilateria
+ 88.07 4384 0 - 33511 Deuterostomia
+ 88.07 4384 0 P 7711 Chordata
+ 88.07 4384 0 - 89593 Craniata
+ 88.07 4384 0 - 7742 Vertebrata
+ 88.07 4384 0 - 7776 Gnathostomata
+ 88.07 4384 0 - 117570 Teleostomi
+ 88.07 4384 0 - 117571 Euteleostomi
+ 88.07 4384 0 - 8287 Sarcopterygii
+ 88.07 4384 0 - 1338369 Dipnotetrapodomorpha
+ 88.07 4384 0 - 32523 Tetrapoda
+ 88.07 4384 0 - 32524 Amniota
+ 88.07 4384 0 C 40674 Mammalia
+ 88.07 4384 0 - 32525 Theria
+ 88.07 4384 0 - 9347 Eutheria
+ 88.07 4384 0 - 1437010 Boreoeutheria
+ 88.07 4384 0 - 314146 Euarchontoglires
+ 88.07 4384 0 O 9443 Primates
+ 88.07 4384 0 - 376913 Haplorrhini
+ 88.07 4384 0 - 314293 Simiiformes
+ 88.07 4384 0 - 9526 Catarrhini
+ 88.07 4384 0 - 314295 Hominoidea
+ 88.07 4384 0 F 9604 Hominidae
+ 88.07 4384 0 - 207598 Homininae
+ 88.07 4384 0 G 9605 Homo
+ 88.07 4384 4384 S 9606 Homo sapiens
+ 1.02 51 0 D 2157 Archaea
+ 1.02 51 0 P 28890 Euryarchaeota
+ 1.02 51 0 C 183939 Methanococci
+ 1.02 51 0 O 2182 Methanococcales
+ 1.02 51 0 F 196117 Methanocaldococcaceae
+ 1.02 51 1 G 196118 Methanocaldococcus
+ 1.00 50 0 S 2190 Methanocaldococcus jannaschii
+ 1.00 50 50 - 243232 Methanocaldococcus jannaschii DSM 2661
+ 0.64 32 0 D 2 Bacteria
+ 0.62 31 0 - 1783272 Terrabacteria group
+ 0.62 31 0 P 1239 Firmicutes
+ 0.62 31 0 C 91061 Bacilli
+ 0.62 31 0 O 1385 Bacillales
+ 0.62 31 0 F 186817 Bacillaceae
+ 0.62 31 31 G 1386 Bacillus
+ 0.02 1 0 P 32066 Fusobacteria
+ 0.02 1 0 C 203490 Fusobacteriia
+ 0.02 1 0 O 203491 Fusobacteriales
+ 0.02 1 0 F 1129771 Leptotrichiaceae
+ 0.02 1 0 G 32067 Leptotrichia
+ 0.02 1 0 S 40542 Leptotrichia buccalis
+ 0.02 1 1 - 523794 Leptotrichia buccalis C-1013-b
+ 0.16 8 0 - 28384 other sequences
+ 0.16 8 0 - 81077 artificial sequences
+ 0.16 8 8 S 32630 synthetic construct
diff -r 000000000000 -r f92fcdde48fc test-data/centrifuge/SRR2219890_1_adj_20k_reads.fastq
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/centrifuge/SRR2219890_1_adj_20k_reads.fastq Tue Jul 17 11:47:13 2018 -0400
@@ -0,0 +1,20000 @@
+@HWI-D00361:29:H8HM6ADXX:1:1101:1238:2179/1
+CGCTCCCCTGACACGTAGGCNNNCATACTGATGCGGTATTGTGCCAGCAT
++SRR2219890.1 HWI-D00361:29:H8HM6ADXX:1:1101:1238:2179
+<<
+# value is a unique id
+# name is the display name
+# path is the directory where the index files are stored
+#
+#ctat_centrifuge_indexes.loc could look like:
+#
+#p_compressed+h+v CTAT_CentrifugeIndex_p_compressed+h+v /path/to/centrifuge/index/p_compressed+h+v
+#
diff -r 000000000000 -r f92fcdde48fc tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Tue Jul 17 11:47:13 2018 -0400
@@ -0,0 +1,14 @@
+
+
+
+
+