Mercurial > repos > jjohnson > cummerbund
changeset 8:fbbbc9fd8fb9
Use fasta_indexes tool_data_table
| author | Jim Johnson <jj@umn.edu> |
|---|---|
| date | Mon, 13 Oct 2014 09:29:20 -0500 |
| parents | b5562b9a55c7 |
| children | 532a336a14c1 |
| files | cuffdiff_wrapper.xml tool-data/all_fasta.loc.sample tool-data/fasta_indexes.loc.sample tool-data/sam_fa_indices.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 5 files changed, 32 insertions(+), 55 deletions(-) [+] |
line wrap: on
line diff
--- a/cuffdiff_wrapper.xml Mon Oct 13 09:12:47 2014 -0500 +++ b/cuffdiff_wrapper.xml Mon Oct 13 09:29:20 2014 -0500 @@ -66,7 +66,7 @@ && echo 'cuff<-readCufflinks( dbFile = "cuffdata.db", gtfFile = "$gtf_link", genome = "$bias_correction.seq_source.ref_file", rebuild = T)' >> cuffData.r #else: ## Built-in genome. - && echo 'cuff<-readCufflinks( dbFile = "cuffdata.db", gtfFile = "$gtf_link", genome = "${__get_data_table_entry__('sam_fa_indexes', 'value', $gtf_input.dbkey, 'path')}", rebuild = T)' >> cuffData.r + && echo 'cuff<-readCufflinks( dbFile = "cuffdata.db", gtfFile = "$gtf_link", genome = "${__get_data_table_entry__('fasta_indexes', 'value', $gtf_input.dbkey, 'path')}", rebuild = T)' >> cuffData.r #end if #else && echo 'cuff<-readCufflinks( dbFile = "cuffdata.db", rebuild = T)' >> cuffData.r
--- a/tool-data/all_fasta.loc.sample Mon Oct 13 09:12:47 2014 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,18 +0,0 @@ -#This file lists the locations and dbkeys of all the fasta files -#under the "genome" directory (a directory that contains a directory -#for each build). The script extract_fasta.py will generate the file -#all_fasta.loc. This file has the format (white space characters are -#TAB characters): -# -#<unique_build_id> <dbkey> <display_name> <file_path> -# -#So, all_fasta.loc could look something like this: -# -#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa -#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa -#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa -# -#Your all_fasta.loc file should contain an entry for each individual -#fasta file. So there will be multiple fasta files for each build, -#such as with hg19 above. -#
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/fasta_indexes.loc.sample Mon Oct 13 09:29:20 2014 -0500 @@ -0,0 +1,29 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Samtools indexed sequences data files. You will need +#to create these data files and then create a fasta_indexes.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The fasta_indexes.loc +#file has this format (white space characters are TAB characters): +# +# <unique_build_id> <dbkey> <display_name> <file_base_path> +# +#So, for example, if you had hg19 Canonical indexed stored in +# +# /depot/data2/galaxy/hg19/sam/, +# +#then the fasta_indexes.loc entry would look like this: +# +#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /depot/data2/galaxy/hg19/sam/hg19canon.fa +# +#and your /depot/data2/galaxy/hg19/sam/ directory +#would contain hg19canon.fa and hg19canon.fa.fai files. +# +#Your fasta_indexes.loc file should include an entry per line for +#each index set you have stored. The file in the path does actually +#exist, but it should never be directly used. Instead, the name serves +#as a prefix for the index file. For example: +# +#hg18canon hg18 Human (Homo sapiens): hg18 Canonical /depot/data2/galaxy/hg18/sam/hg18canon.fa +#hg18full hg18 Human (Homo sapiens): hg18 Full /depot/data2/galaxy/hg18/sam/hg18full.fa +#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /depot/data2/galaxy/hg19/sam/hg19canon.fa +#hg19full hg19 Human (Homo sapiens): hg19 Full /depot/data2/galaxy/hg19/sam/hg19full.fa
--- a/tool-data/sam_fa_indices.loc.sample Mon Oct 13 09:12:47 2014 -0500 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,28 +0,0 @@ -#This is a sample file distributed with Galaxy that enables tools -#to use a directory of Samtools indexed sequences data files. You will need -#to create these data files and then create a sam_fa_indices.loc file -#similar to this one (store it in this directory) that points to -#the directories in which those files are stored. The sam_fa_indices.loc -#file has this format (white space characters are TAB characters): -# -#index <seq> <location> -# -#So, for example, if you had hg18 indexed stored in -#/depot/data2/galaxy/sam/, -#then the sam_fa_indices.loc entry would look like this: -# -#index hg18 /depot/data2/galaxy/sam/hg18.fa -# -#and your /depot/data2/galaxy/sam/ directory -#would contain hg18.fa and hg18.fa.fai files: -# -#-rw-r--r-- 1 james universe 830134 2005-09-13 10:12 hg18.fa -#-rw-r--r-- 1 james universe 527388 2005-09-13 10:12 hg18.fa.fai -# -#Your sam_fa_indices.loc file should include an entry per line for -#each index set you have stored. The file in the path does actually -#exist, but it should never be directly used. Instead, the name serves -#as a prefix for the index file. For example: -# -#index hg18 /depot/data2/galaxy/sam/hg18.fa -#index hg19 /depot/data2/galaxy/sam/hg19.fa
--- a/tool_data_table_conf.xml.sample Mon Oct 13 09:12:47 2014 -0500 +++ b/tool_data_table_conf.xml.sample Mon Oct 13 09:29:20 2014 -0500 @@ -1,12 +1,6 @@ <tables> - <!-- Locations of all fasta files under genome directory --> - <table name="all_fasta" comment_char="#"> + <table name="fasta_indexes" comment_char="#"> <columns>value, dbkey, name, path</columns> - <file path="tool-data/all_fasta.loc" /> - </table> - <!-- Location of SAMTools indexes and other files --> - <table name="sam_fa_indexes" comment_char="#"> - <columns>line_type, value, path</columns> - <file path="tool-data/sam_fa_indices.loc" /> + <file path="tool-data/fasta_indexes.loc" /> </table> </tables>