diff --git a/scripts_of/config.json b/scripts_of/config.json index 754af28e..4c84d1c7 100644 --- a/scripts_of/config.json +++ b/scripts_of/config.json @@ -7,18 +7,30 @@ "__comment": "BASEOUTNAME : Just the filename without the directory path (of the output filename)", "__comment": "IDENTIFIER : A name generated by OrthoFinder to uniquely identify the orthogroup (a number of methods use this to name the output file automatically, see RAxML command for an example). Not applicable for program_type search.", "__comment": "DATABASE : For the search program_type, for use in the search_cmd. The full path of the database to search against", - + + "mafft":{ + "program_type": "msa", + "cmd_line": "mafft --localpair --maxiterate 1000 --anysymbol INPUT > OUTPUT 2> /dev/null", + "cmd_line_fast": "mafft --anysymbol INPUT > OUTPUT 2> /dev/null", + "n_seqs_use_fast" : "500" + }, + "muscle":{ "program_type": "msa", "cmd_line": "muscle -in INPUT -out OUTPUT" }, - + + "fasttree":{ + "program_type": "tree", + "cmd_line": "FastTree INPUT > OUTPUT 2> /dev/null" + }, + "raxml":{ "program_type": "tree", "cmd_line": "raxmlHPC-AVX -m PROTGAMMALG -p 12345 -s INPUT -n IDENTIFIER -w PATH > /dev/null", "ouput_filename": "PATH/RAxML_bestTree.IDENTIFIER" }, - + "raxml-ng":{ "program_type": "tree", "cmd_line": "raxml-ng --msa INPUT --model LG+G4 --seed 12345 --threads 1", @@ -36,13 +48,13 @@ "db_cmd": "diamond makedb --in INPUT -d OUTPUT", "search_cmd": "diamond blastp -d DATABASE -q INPUT -o OUTPUT --more-sensitive -p 1 --quiet -e 0.001 --compress 1" }, - + "blast_gz":{ "program_type": "search", "db_cmd": "makeblastdb -dbtype prot -in INPUT -out OUTPUT", "search_cmd": "blastp -outfmt 6 -evalue 0.001 -query INPUT -db DATABASE | gzip > OUTPUT.gz" }, - + "mmseqs":{ "program_type": "search", "db_cmd": "mmseqs createdb INPUT OUTPUT.fa ; mmseqs createindex OUTPUT.fa /tmp", diff --git a/scripts_of/program_caller.py b/scripts_of/program_caller.py index a81d5bf0..fc473892 100644 --- a/scripts_of/program_caller.py +++ b/scripts_of/program_caller.py @@ -63,9 +63,6 @@ def __init__(self, configure_file): self.tree = dict() self.search_db = dict() self.search_search = dict() - # Add default methods - self.msa['mafft'] = Method('mafft', {"cmd_line": "mafft --localpair --maxiterate 1000 --anysymbol INPUT > OUTPUT 2> /dev/null", "cmd_line_fast": "mafft --anysymbol INPUT > OUTPUT 2> /dev/null", "n_seqs_use_fast" : "500"}) - self.tree['fasttree'] = Method('fasttree', {"cmd_line": "FastTree INPUT > OUTPUT 2> /dev/null"}) if configure_file == None: return if not os.path.exists(configure_file): @@ -86,7 +83,7 @@ def __init__(self, configure_file): continue if 'program_type' not in v: - print(("WARNING: Incorrecty formatted configuration file entry: %s" % name)) + print(("WARNING: Incorrectly formatted configuration file entry: %s" % name)) print("'program_type' entry is missing") try: if v['program_type'] == 'msa': @@ -101,7 +98,7 @@ def __init__(self, configure_file): self.tree[name] = Method(name, v) elif v['program_type'] == 'search': if ('db_cmd' not in v) or ('search_cmd' not in v): - print(("WARNING: Incorrecty formatted configuration file entry: %s" % name)) + print(("WARNING: Incorrectly formatted configuration file entry: %s" % name)) print("'cmd_line' entry is missing") raise InvalidEntryException if name in self.search_db: @@ -110,10 +107,10 @@ def __init__(self, configure_file): self.search_db[name] = Method(name, {'cmd_line':v['db_cmd']}) self.search_search[name] = Method(name, {'cmd_line':v['search_cmd']}) if 'ouput_filename' in v: - print(("WARNING: Incorrecty formatted configuration file entry: %s" % name)) + print(("WARNING: Incorrectly formatted configuration file entry: %s" % name)) print("'ouput_filename' option is not supported for 'program_type' 'search'") else: - print(("WARNING: Incorrecty formatted configuration file entry: %s" % name)) + print(("WARNING: Incorrectly formatted configuration file entry: %s" % name)) print(("'program_type' should be 'msa' or 'tree', got '%s'" % v['program_type'])) except InvalidEntryException: pass