# HG changeset patch
# User matthias
# Date 1557074097 14400
# Node ID 39e27bd6d23015e23d4c45f7b9346ab6b4eef0f1
# Parent 4e8927c51603ba93369786db4b58ac143f046461
planemo upload for repository https://github.com/bernt-matthias/mb-galaxy-tools/tree/topic/dada2/tools/dada2 commit 990192685955e9cda0282e348c28ef6462d88a38
diff -r 4e8927c51603 -r 39e27bd6d230 README.md
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/README.md Sun May 05 12:34:57 2019 -0400
@@ -0,0 +1,39 @@
+Wrappers for the core functionality of the dada2 package https://benjjneb.github.io/dada2/index.html.
+
+- filterAndTrim
+- derep
+- learnErrors
+- dada
+- mergePairs
+- makeSequenceTable
+- removeBimeraDenovo
+
+Datatypes
+=========
+
+The dada2 Galaxy wrappers use a few extra data types to ensure that only inputs of the correct type can be used.
+
+For the outputs of derep, dada, learnErrors, and mergePairs the following datatypes are used that derive from Rdata (which contains the named list that is returned from the corresponding dada function):
+
+- dada2_derep (Rdata: named list see docs for derep-class)
+- dada2_dada (Rdata: named list, see docs for dada-class)
+- dada2_errorrates (Rdata: named list, see docs for learnErrors)
+- dada2_mergepairs (Rdata: named list, see docs for mergePairs)
+
+For the outputs of makeSequenceTable and removeBimeraDenovo the following data types are used which derive from tabular:
+
+- dada2_uniques
+-- in R a named integer vector (names are the unique sequences)
+-- in Galaxy written as a table (each row corresponding to a unique sequence, column 1: the sequence, column 2: the count)
+- dada2_sequencetable
+-- in R a named integer matrix (rows = samples, columns = unique sequences)
+-- in Galaxy written as a table (rows = unique sequences, columns = samples)
+
+Note the difference between the R and Galaxy representations! The main motivation is that the dada2_sequencetable is analogous to OTU tables as produced for instance by qiime (and it seemed natural to extend this to the uniques which are essentially a sequencetables of single samples).
+
+
+TODOs
+=====
+
+- implememt getUniques tool to view intermediate results?
+- implement tests for cached reference data
diff -r 4e8927c51603 -r 39e27bd6d230 dada2_seqCounts.xml
--- a/dada2_seqCounts.xml Mon Apr 29 09:51:56 2019 -0400
+++ b/dada2_seqCounts.xml Sun May 05 12:34:57 2019 -0400
@@ -19,11 +19,12 @@
#for $i, $rep in enumerate($inrep)
samples = list()
#for $s in $rep.input:
- #if len($rep.input) == 1
- samples <- $read_data( $s )
- #else
+ ## for collection input assume identifiers are sample names
+ #if $s.ext in ["tabular", "dada2_dada", "dada2_derep", "dada2_mergepairs"]
sample_name <- '$s.element_identifier'
samples[[sample_name]] <- $read_data( $s )
+ #else
+ samples <- $read_data( $s )
#end if
#if $s.ext == "tabular"
tabular <- T
@@ -82,6 +83,51 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ dada2_derep,dada2_dada,dada2_mergepairs
+
+
+
+
@@ -63,9 +84,9 @@
-
-
-
+
+
+