Implements #9, #13

Makefile

@@ -8,15 +8,17 @@ deltamp := $(patsubst src/%,bin/%,$(patsubst %.main,%,$(wildcard $(addsuffix *.m
 batch_spec := $(addprefix bin/,$(notdir $(shell ls lib/$(batch)/deltamp.*)))
 steps := $(patsubst src/%,bin/%,$(patsubst %.step,%.sh,$(wildcard $(addsuffix *.step,src/))))
 highmems := $(patsubst %.head,%_highmem.head,$(shell ls lib/$(batch)/*.head | grep -v "_"))
+test_config := $(patsubst src/%,test/%,$(patsubst %.config,%.tsv,$(wildcard $(addsuffix *.config,src/))))
 
 # search paths
 vpath %.main src
 vpath %.step src
 vpath %.head lib/$(batch)
+vpath %.config src
 
 # main rule
 .PHONY: all clean
-all: $(deltamp) $(module) $(steps) $(batch_spec)
+all: $(deltamp) $(module) $(steps) $(batch_spec) $(test_config)
 
 # rule to build deltamp and pipeline_master
 $(deltamp): bin/% : %.main | lib/$(batch)/option_variables
@@ -61,6 +63,10 @@ endif
 $(batch_spec): bin/deltamp.% : lib/$(batch)/deltamp.%
 	cp $^ $@ && chmod +x $@
 
+# rule to build test configuration file
+$(test_config): test/%.tsv : %.config
+	sed "s#USER#$$USER#;s#CURDIR#$(CURDIR)#" $< > $@
+
 # clean rule
 clean :
-	rm -r $(deltamp) modulefiles $(steps) $(highmems) $(batch_spec)
+	rm -r $(deltamp) modulefiles $(steps) $(highmems) $(batch_spec) $(test_config)

bin/variables_definition.tsv

@@ -1,6 +1,5 @@
 PROJECT	#	Project name	.+
 OWNER	$USER	User name	.+
-EMAIL	$USER@example.com	Email address	.+@.+
 OUT_PATH	/home/$USER	Path to output location	^/.+(/.+)*$
 EXEC_PATH	/work/$USER	Path to execution location	^/.+(/.+)*$
 TECH	Illumina	Sequencing technology	454 Illumina
@@ -24,7 +23,9 @@ CLUST	mcl	Clustering algorithm	mcl sumaclust cd-hit-est vsearch swarm
 TRESH	97	Clustering similarity threshold	^[0-9]+(.[0-9]+)?$
 PREV_PATH	no	Cluster with previous subproject reference sequences	no ^/.+(/.+)*$
 DEL_SING	no	Remove singletons before chimera re-check	no yes
-REF_DB	UNITE	Reference database	UNITE SILVA PR2 NCBI NCBI_16ranks GBOL GBOL_16ranks
+DBFOLD	/home/$USER	Directory path to database	^/.+(/.+)*$
+REF_DB	no	Database prefix name	^[^ \t]+$
+CUT_DB	no	Reduce database to amplified fragment	no yes
 ASSIGN_ALL	no	Assign all reads	no yes
 MIN_SAMP	1	Minimum number of sample for abundant OTUs	^[0-9]+$
 MIN_DOM	4	Minimum number of reads for abundant OTUs	^[0-9]+$

src/configuration_PRJEB5170_Cercozoa.config

@@ -0,0 +1,52 @@
+PROJECT
+Project name	MultiBarSoilEuk
+User name	USER
+Path to output location	CURDIR/test
+Path to execution location	CURDIR/test
+
+LIBRAIRIES
+Sequencing technology	454
+Directory path to archives or libraries OR BioProject accession	PRJEB5170
+
+TARGET
+Target organisms	Cercozoa
+Target region	18S
+Forward primer name	Cer2f
+Forward primer sequence (5' to 3')	ATTTCTGCCCTATCAGCT
+Reverse primer name	Cer1r
+Reverse primer sequence (5' to 3')	ATACTAGCACCCCCAACT
+Sequencing direction	forward
+
+TRIMMING
+Number of mismatches allowed on the barcode sequence	1
+Number of mismatches allowed on the primer sequence	4
+Maximum number of ambiguities allowed in the sequence	0
+Maximum homopolymer length allowed	8
+Minimum sequence length	300
+Maximum sequence length	700
+Minimum average quality on the trimmed sequence length	25
+Denoising	yes
+
+PIPELINE
+Minimum number of trimmed reads per sample	700
+Clustering algorithm		vsearch
+Clustering similarity threshold	96
+Directory path to database	CURDIR/test
+Reference database	pr2_test.gb203
+Minimum number of sample for abundant OTUs	1
+Minimum number of reads for abundant OTUs	2
+
+BARCODES
+Barcode sequence (454 only)	Sample name	[Forward] library name OR URL	Reverse library name OR URL (Illumina only)
+ACGAGTGCGT	cerso01a	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso01a.sff
+ACGCTCGACA	cerso01b	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso01b.sff
+AGACGCACTC	cerso01c	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso01c.sff
+AGCACTGTAG	cerso06a	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso06a.sff
+ATCAGACACG	cerso06b	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso06b.sff
+ATATCGCGAG	cerso06c	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso06c.sff
+CGTGTCTCTA	cerso13a	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso13a.sff
+CTCGCGTGTC	cerso13b	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso13b.sff
+TAGTATCAGC	cerso13c	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso13c.sff
+TCTCTATGCG	cerso18a	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso18a.sff
+TGATACGTCT	cerso18b	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso18b.sff
+TACTGAGCTA	cerso18c	ftp.sra.ebi.ac.uk/vol1/ERA279/ERA279305/sff/AMP12_HV6G38L03-04_cerso18c.sff

src/deltamp.main

@@ -390,79 +390,31 @@ fi
 SAMP_SIZE=`sed -n '$=' config/lib4.list`
 
 # Databases
-DBFOLD=/data/ecogen/databases/mothur
-if [ $REF_DB == "UNITE" ] && [ $TARG == "ITS" ]
+if [ $TARG == "ITS" ]
 then
-	VERSION[DB]=v7_2
-	DB=unite.${VERSION[DB]}
-	CITATION[DB]="Kõljalg et al., 2013"
-	FULLCITATION[DB]="Kõljalg U, Nilsson RH, Abarenkov K et al. (2013) Towards a unified paradigm for sequence-based identification of fungi. Molecular Ecology, 22, 5271–5277."
+	if [ $CUT_DB == "yes" ]
+	then
+		echo "Database can only be reduced to amplified fragment for SSU fragments."
+		show_doc | fmt -s -w $(tput cols) >&2
+		exit 1
+	fi
 	CITATION[FUN]="Nguyen et al., 2016"
 	FULLCITATION[FUN]="Nguyen, N. H., Song, Z., Bates, S. T., Branco, S., Tedersoo, L., Menke, J., … Kennedy, P. G. (2016). FUNGuild: An open annotation tool for parsing fungal community datasets by ecological guild. Fungal Ecology, 20, 241–248."
 	VERSION[FUN]=1.1
-elif [ $REF_DB == "SILVA" ]
-then
-	VERSION[DB]=128
-	CITATION[DB]="Quast et al., 2013"
-	FULLCITATION[DB]="Quast C, Pruesse E, Yilmaz P et al. (2013) The SILVA ribosomal RNA gene database project: improved data processing and web-based tools. Nucleic Acids Research, 41, D590–D596."
-	if [ $TARG == "16S" ]
-	then
-		DB=silva.${VERSION[DB]}.Nr99.prok
-	elif [ $TARG == "18S" ]
-	then
-		DB=silva.${VERSION[DB]}.Nr99.euk
-	fi
-elif [ $REF_DB == "PR2" ] && [ $TARG == "18S" ]
-then
-	VERSION[DB]=gb203
-	DB=PR2_${VERSION[DB]}
-	CITATION[DB]="Guillou et al., 2012"
-	FULLCITATION[DB]="Guillou L, Bachar D, Audic S et al. (2012) The Protist Ribosomal Reference database (PR2): a catalog of unicellular eukaryote Small Sub-Unit rRNA sequences with curated taxonomy. Nucleic Acids Research, 41, D597–D604."
-elif [ $REF_DB == "NCBI" ] && [ $TARG == "COI" ]
-then
-	VERSION[DB]=gb211
-	DB=ncbi_COI
-	CITATION[DB]="Benson et al., 2013"
-	FULLCITATION[DB]="Benson DA, Cavanaugh M, Clark K et al. (2013) GenBank. Nucleic Acids Research, 41, D36–42."
-elif [ $REF_DB == "NCBI_16ranks" ] && [ $TARG == "COI" ]
-then
-	VERSION[DB]=gb211
-	DB=ncbi_COI_16ranks
-	CITATION[DB]="Benson et al., 2013"
-	FULLCITATION[DB]="Benson DA, Cavanaugh M, Clark K et al. (2013) GenBank. Nucleic Acids Research, 41, D36–42."
-elif [ $REF_DB == "GBOL" ] && [ $TARG == "COI" ]
-then
-	DB=ncbi_GBOL_COI
-	CITATION[DB]="GBOL: http://www.bolgermany.de"
-elif [ $REF_DB == "GBOL_16ranks" ] && [ $TARG == "COI" ]
-then
-	DB=ncbi_GBOL_COI_16ranks
-	CITATION[DB]="GBOL: http://www.bolgermany.de"
-else
-	echo "# The reference database does not match with the target gene."
-	show_doc | fmt -s -w $(tput cols) >&2
-	cd .. && rm -r $SUBPROJECT
-	if [ ! "$(ls -A)" ] ; then cd .. && rmdir $PROJECT ; fi
-	exit 1
 fi
 
-if [[ $DB == "silva"* ]]
+if ( [ $TARG == "18S" ] || [ $TARG == "16S" ] ) && [ $CUT_DB == "yes" ]
 then
-	DBALIGN=$(echo $DB | sed 's/^\(.*\)\.\([^\.]*\)$/\1\.align\.\2/')
-	if [ $TECH == "454" ]
+	if [ $TECH == "454" ] && [ $FLIP == "true" ]
 	then
-		if [ $FLIP == "true" ]
-		then
-			DBCHOP=$RVS_NAME.$FWD_NAME.$DBALIGN
-			DBCUT=$RVS_NAME.$FWD_NAME.$DB
-		else
-			DBCHOP=$FWD_NAME.$RVS_NAME.$DBALIGN
-			DBCUT=$FWD_NAME.$RVS_NAME.$DB
-		fi
-	else	
-		DBCHOP=$FWD_NAME.$RVS_NAME.$DBALIGN
+		DBCUT=$RVS_NAME.$FWD_NAME.$DB
+	else
 		DBCUT=$FWD_NAME.$RVS_NAME.$DB
 	fi
+	if [ ! -z $DBALIGN ] || [ $DBALIGN != "no" ]
+	then
+		DBCHOP=`echo $DBCUT | sed "s/$DB$/$DBALIGN/"`
+	fi
 fi
 
 # Save newly set variables to file (avoiding lowercase variables from loops):