def optParse(errorflag):
#This function handles the command line options.
parser = argparse.ArgumentParser(description="Unique substitution counting.");
parser.add_argument("-i", dest="input", help="Input directory containing a single run_codeml output directory or codeml_combined directory.");
parser.add_argument("-t", dest="target_specs", help="A list contained in quotes. Spaces separate groups, commas separate species within groups. E.g: \"triMan1 lepWed1,odoRosDiv1 orcOrc1,turTru2\"");
parser.add_argument("-o", dest="output_suffix", help="The SUFFIX of the directory name to be created by the script. Something descriptive for your run.", default="");
args = parser.parse_args();
if errorflag == 0:
if args.input == None:
gwctcore.errorOut(1, "-i must be defined");
optParse(1);
if args.target_specs == None:
gwctcore.errorOut(2, "-t must be defined");
optParse(1);
return args.input, args.target_specs, args.output_suffix;
elif errorflag == 1:
parser.print_help();
sys.exit();
def optParse():
# This function handles the command line options and does some error checking.
parser = argparse.ArgumentParser(description="Runs codeml on a directory full of .fa files. Files MUST have .fa extension. Dependencies: PAML, newickutils (if you want to prune your tree with --prune)");
parser.add_argument("-i", dest="input", help="Input. A directory containing many FASTA (.fa) files.");
parser.add_argument("-p", dest="paml_path", help="You must specify the full path to your PAML DIRECTORY here.");
parser.add_argument("-t", dest="tree_file", help="A user specified tree for codeml to use. If not specified, codeml will infer the tree.", default="");
parser.add_argument("--prune", dest="prune_opt", help="If not all species present in the tree will be present in each alignment, set this flag to prune the tree for each file.", action="store_true");
# parser.add_argument("-seqtype", dest="paml_seqtype", help="Enter either 'codon' or 'aa'. Default value is 'codon'.", default='codon');
parser.add_argument("-v", dest="verbosity", help="An option to control the output printed to the screen. 1: print all codeml output, 0: print only a progress bar. Default: 1", type=int, default=1);
parser.add_argument("-o", dest="output", help="Desired output directory. If none is entered, will be determined automatically.", default=False);
args = parser.parse_args();
if args.input == None or args.paml_path == None:
sys.exit(gc.errorOut(1, "Both -i must be set."));
if not os.path.isdir(args.input) or not os.path.isdir(args.paml_path):
sys.exit(gc.errorOut(2, "Both -i must be valid directory paths!"));
else:
args.input = os.path.abspath(args.input);
args.paml_path = os.path.abspath(args.paml_path);
if not os.path.isfile(args.tree_file):
sys.exit(gc.errorOut(3, "-t must be a valid file name."));
try:
td, tree, r = gt.treeParse(open(args.tree_file, "r").read().replace("\n",""));
except:
sys.exit(gc.errorOut(4, "-t does not contain a valid Newick string!"));
if args.verbosity not in [0,1]:
sys.exit(gc.errorOut(6, "-v must take values of either 1 or 0"));
return args.input, args.paml_path, args.tree_file, args.prune_opt, args.verbosity, args.output;
def optParse(errorflag):
#This function handles the command line options.
parser = argparse.ArgumentParser(
description="Unique substitution counting.")
parser.add_argument(
"-i",
dest="input",
help=
"Input directory containing a single run_codeml output directory or codeml_combined directory."
)
parser.add_argument(
"-t",
dest="target_specs",
help=
"A list contained in quotes. Spaces separate groups, commas separate species within groups. E.g: \"triMan1 lepWed1,odoRosDiv1 orcOrc1,turTru2\""
)
parser.add_argument(
"-o",
dest="output_suffix",
help=
"The SUFFIX of the directory name to be created by the script. Something descriptive for your run.",
default="")
args = parser.parse_args()
if errorflag == 0:
if args.input == None:
gwctcore.errorOut(1, "-i must be defined")
optParse(1)
if args.target_specs == None:
gwctcore.errorOut(2, "-t must be defined")
optParse(1)
return args.input, args.target_specs, args.output_suffix
elif errorflag == 1:
parser.print_help()
sys.exit()
def optParse(errorflag):
#This function handles the command line options.
parser = argparse.ArgumentParser(description="Runs codeml on a single .fa file or a directory full of .fa files. Dependencies: PAML, newickutils (if you want to prune your tree)");
parser.add_argument("-i", dest="input", help="Input. Either a directory containing many FASTA files or a single FASTA file.");
parser.add_argument("-c", dest="paml_path", help="You must specify the full path to your PAML DIRECTORY here.");
parser.add_argument("-t", dest="tree_file", help="A user specified tree for codeml to use. If not specified, codeml will infer the tree.", default="");
parser.add_argument("-p", dest="prune_opt", help="If not all species present in the tree will be present in each alignment, set this to 1 to prune the tree for each file. Default: 0", type=int, default=0);
parser.add_argument("-s", dest="paml_seqtype", help="The seqtype for codeml to use. 1 (default): Codons; 2: Amino Acids", type=int, default=1);
parser.add_argument("-b", dest="branch_site", help="Specifies the type of run for PAML's branch site test. 0 (default): Do not do branch site test; 1: Do the null model of the branch site test (model=2, NSsite=2, fix_omega=1, omega=1); 2: Do the alternate model of the branch site test (model=2, NSsite=2, fix_omega=0, omega=1). A branch must be specified in your tree file.", type=int, default=0);
parser.add_argument("-a", dest="anc_opt", help="Option to tell PAML to do ancestral reconstruction (1) or not (0). Default: 0.", type=int, default=0);
parser.add_argument("-v", dest="verbosity", help="An option to control the output printed to the screen. 1: print all codeml output, 0: print only a progress bar. Default: 1", type=int, default=1);
parser.add_argument("-l", dest="log_opt", help="A boolean option to tell the script whether to create a logfile (1) or not (0). Default: 1", type=int, default=1);
parser.add_argument("-x", dest="logdir_suffix", help="A string to add on to the end of the output directory.");
args = parser.parse_args();
if errorflag == 0:
if args.input == None or args.paml_path == None:
gwctcore.errorOut(1, "Both -i and -c must be set");
optParse(1);
if not os.path.isfile(args.tree_file):
gwctcore.errorOut(2, "-t must be a valid tree file name");
optParse(1);
if args.prune_opt not in [0,1]:
gwctcore.errorOut(3, "-p must take values of either 1 or 0");
optParse(1);
if args.prune_opt == 1 and args.tree_file == "":
gwctcore.errorOut(4, "With -p set to 1 a tree file must be specified");
optParse(1);
if args.paml_seqtype not in [1,2]:
gwctcore.errorOut(5, "-s must taked values of either 1 or 2");
optParse(1);
if args.branch_site not in [0,1,2]:
gwctcore.errorOut(6, "-b must take values of 0, 1, or 2");
optParse(1);
if args.anc_opt not in [0,1]:
gwctcore.errorOut(7, "-a must take values of 1 or 0");
optParse(1);
if args.verbosity not in [0,1]:
gwctcore.errorOut(8, "-v must take values of either 1 or 0");
optParse(1);
if args.log_opt not in [0,1]:
gwctcore.errorOut(9, "-l must take values of either 1 or 0");
optParse(1);
if args.logdir_suffix == None:
args.logdir_suffix = "";
return args.input, args.paml_path, args.tree_file, args.prune_opt, args.paml_seqtype, args.branch_site, args.anc_opt, args.verbosity, args.log_opt, args.logdir_suffix;
elif errorflag == 1:
parser.print_help();
sys.exit();
#def core.logCheck(lopt, lfilename, outline): # if lopt == 1: # core.printWrite(lfilename, outline); # else: # print outline; ############################################ #Main Block ############################################ ins, ppath, treefile, prune, seqtype, bsopt, aopt, v, l, outdir_suffix = optParse(0); starttime = gwctcore.getLogTime(); if not os.path.isdir(ppath): gwctcore.errorOut(10, "-c must be a valid directory path"); optParse(1); if os.path.isfile(ins): fileflag = 1; indir = os.path.dirname(os.path.realpath(ins)); indir, script_outdir = gwctcore.getOutdir(indir, "run_codeml", starttime, outdir_suffix); outdir = os.path.join(script_outdir, "codeml_out"); if aopt == 1: ancdir = os.path.join(script_outdir, "anc_seqs_fa"); filelist = [ins]; else: fileflag = 0; indir, script_outdir = gwctcore.getOutdir(ins, "run_codeml", starttime, outdir_suffix); outdir = os.path.join(script_outdir, "codeml_out");
def optParse():
#This function handles the command line options.
parser = argparse.ArgumentParser(
description=
"Convergent substitution counting. Dependencies: ancestral sequences from PAML formatted with gwct_codeml.py"
)
parser.add_argument(
"-i",
dest="input",
help=
"Input directory. This is the output directory of a gwct_codeml.py run and should include the folder 'anc-seqs-fa'. Will count convergent, divergent, and unique substitutions, or make pairwise comparisons if -w is set."
)
parser.add_argument(
"-t",
dest="target_specs",
help=
"A list contained in quotes. Spaces separate groups, commas separate species within groups. E.g: \"triMan1 lepWed1,odoRosDiv1 orcOrc1,turTru2\". If a target species is missing from a given alignment, it will be removed from the list of target species.",
default="")
parser.add_argument(
"-w",
dest="pairwise_opt",
help=
"Option to tell the program to simply do all pairwise comparisons of tip branches (1) or pairwise comparisons of all branches (2) and make a C/D graph. With -w set, unique substitutions will not be counted. Default: 0, do not do pairwise comparisons",
type=int,
default=0)
parser.add_argument(
"-p",
dest="prob_thresh",
help=
"A probability threshold to only retrieve convergent sites with probabilities greater than or equal to. Set to 0 for no threshold. Default: 0",
type=float,
default=0)
parser.add_argument(
"-n",
dest="number_threads",
help=
"The number of threads on which to run the job. NOTE: One thread will be reserved for the main process, so by entering '4' here, only 3 threads will be utilized on the data. Entering '2' is equivalent to running the data on 1 thread. Default: 1",
type=int,
default=1)
parser.add_argument(
"-o",
dest="output",
help=
"Desired output directory. If none is entered, will be determined automatically.",
default=False)
args = parser.parse_args()
if args.input == None or not os.path.isdir(args.input):
sys.exit(gc.errorOut(1, "-i must be a valid directory path."))
if args.pairwise_opt not in [0, 1, 2]:
sys.exit(gc.errorOut(2, "-w must take values of 0, 1, or 2."))
if args.target_specs == "" and args.pairwise_opt == 0:
sys.exit(gc.errorOut(3, "With -w set to 0, -t must be defined."))
if args.target_specs != "" and args.pairwise_opt != 0:
sys.exit(gc.errorOut(4, "Only one of -t and -w should be set."))
if args.prob_thresh < 0.0 or args.prob_thresh > 1.0:
sys.exit(gc.errorOut(5,
"-p can only take values between 0.0 and 1.0."))
if args.number_threads <= 0:
sys.exit(gc.errorOut(8, "-n must be a positive, non-zero integer."))
return args.input, args.target_specs, args.pairwise_opt, args.prob_thresh, args.number_threads, args.output
indir, orig_targets, pairwise, prob_thresh, num_threads, output = optParse()
if platform.system() == "Windows" and num_threads != 1:
print "\n** Warning! Multi-processing not currently supported on Windows. Switching to serial version (1 process).\n"
num_threads = 1
outdir = gc.defaultOut(output, indir, "-gwct")
print gc.getTime() + " | + Creating main output directory:\t" + outdir
os.system("mkdir " + outdir)
ancdir = os.path.join(indir, "anc-seqs-fa")
if not os.path.isdir(ancdir):
ancdir = os.path.join(indir, "anc_seqs_fa")
if not os.path.isdir(ancdir):
sys.exit(
gc.errorOut(
9, "Cannot find anc-seqs-fa directory within input directory."))
filelist = os.listdir(ancdir)
filelist = [f for f in filelist if "ancprobs" in f]
num_files = len(filelist)
if prob_thresh == 0:
convfilename = os.path.join(outdir, "conv-sites.txt")
divfilename = os.path.join(outdir, "div-sites.txt")
elif prob_thresh != 0:
convfilename = os.path.join(outdir,
"conv-sites-" + str(prob_thresh) + ".txt")
divfilename = os.path.join(outdir,
"div-sites-" + str(prob_thresh) + ".txt")
uniqfilename = os.path.join(outdir, "unique-sites.txt")
main_header = "# GeneID\tAlignLen\tPosition\tAncAlleles\tTargetAlleles\n"
uniq_header = "# GeneID\tAlignLen\tPosition\tBackgroundAlleles\tTargetAlleles\n"
if pairwise == 0:
def optParse(errorflag):
#This function handles the command line options.
parser = argparse.ArgumentParser(description="Convergent substitution counting. Dependencies: ancestral sequences from PAML");
parser.add_argument("-i", dest="input", help="Input directory containing a single run_codeml output directory or codeml_combined directory.");
parser.add_argument("-t", dest="target_specs", help="A list contained in quotes. Spaces separate groups, commas separate species within groups. E.g: \"triMan1 lepWed1,odoRosDiv1 orcOrc1,turTru2\"", default="");
parser.add_argument("-u", dest="uniq_subs", help="A boolean to output the sites that are unique substitutions in the tip branches of interest (1) or not (0). Default: 0", type=int, default = 0);
parser.add_argument("-w", dest="pairwise_opt", help="Option to tell the program to simply do all pairwise comparisons of tip branches (1) or pairwise comparisons of all branches (2) and make a C/D graph. Default: 0, do not do pairwise comparisons", type=int, default=0);
parser.add_argument("-p", dest="prob_thresh", help="A probability threshold to only retrieve convergent sites with probabilities greater than or equal to. Set to 0 for no threshold. Default: 0", type=float, default=0);
parser.add_argument("-n", dest="number_threads", help="The number of threads on which to run the job. NOTE: One thread will be reserved for the main process, so by entering '4' here, only 3 threads will be utilized on the data. Entering '2' is equivalent to running the data on 1 thread. Default: 1", type=int, default=1);
parser.add_argument("-o", dest="output_suffix", help="The SUFFIX of the directory name to be created by the script. Something descriptive for your run.", default="");
args = parser.parse_args();
if errorflag == 0:
if args.input == None:
gwctcore.errorOut(1, "-i must be defined");
optParse(1);
if args.pairwise_opt not in [0,1,2]:
gwctcore.errorOut(2, "-w must take values of 0, 1, or 2");
optParse(1);
if args.target_specs == "" and args.pairwise_opt == 0:
gwctcore.errorOut(3, "With -w set to 0, -t must be defined");
optParse(1);
if args.target_specs != "" and args.pairwise_opt != 0:
gwctcore.errorOut(4, "Only one of -t and -w should be set");
optParse(1);
if args.prob_thresh < 0.0 or args.prob_thresh > 1.0:
gwctcore.errorOut(5, "-p can only take values between 0.0 and 1.0");
optParse(1);
if args.uniq_subs not in [0,1]:
gwctcore.errorOut(6, "-u can only take values of 0 or 1");
optParse(1);
if args.uniq_subs == 1 and args.target_specs == "":
gwctcore.errorOut(7, "-u can only be set when a set of target species is defined with -t");
optParse(1);
if args.uniq_subs == 1 and args.target_specs == None:
gwctcore.errorOut(8, "With -u set to 1, -t must also be defined and -w must be 0");
optParse(1);
if args.number_threads <= 0:
gwctcore.errorOut(9, "-n must be a positive, non-zero integer");
optParse(1);
if args.output_suffix == None:
args.output_suffix = "";
return args.input, args.target_specs, args.uniq_subs, args.pairwise_opt, args.prob_thresh, args.number_threads, args.output_suffix;
elif errorflag == 1:
parser.print_help();
sys.exit();
def optParse(errorflag):
#This function handles the command line options.
parser = argparse.ArgumentParser(
description=
"Convergent substitution counting. Dependencies: ancestral sequences from PAML"
)
parser.add_argument(
"-i",
dest="input",
help=
"Input directory containing a single run_codeml output directory or codeml_combined directory."
)
parser.add_argument(
"-t",
dest="target_specs",
help=
"A list contained in quotes. Spaces separate groups, commas separate species within groups. E.g: \"triMan1 lepWed1,odoRosDiv1 orcOrc1,turTru2\"",
default="")
parser.add_argument(
"-u",
dest="uniq_subs",
help=
"A boolean to output the sites that are unique substitutions in the tip branches of interest (1) or not (0). Default: 0",
type=int,
default=0)
parser.add_argument(
"-w",
dest="pairwise_opt",
help=
"Option to tell the program to simply do all pairwise comparisons of tip branches (1) or pairwise comparisons of all branches (2) and make a C/D graph. Default: 0, do not do pairwise comparisons",
type=int,
default=0)
parser.add_argument(
"-p",
dest="prob_thresh",
help=
"A probability threshold to only retrieve convergent sites with probabilities greater than or equal to. Set to 0 for no threshold. Default: 0",
type=float,
default=0)
parser.add_argument(
"-n",
dest="number_threads",
help=
"The number of threads on which to run the job. NOTE: One thread will be reserved for the main process, so by entering '4' here, only 3 threads will be utilized on the data. Entering '2' is equivalent to running the data on 1 thread. Default: 1",
type=int,
default=1)
parser.add_argument(
"-o",
dest="output_suffix",
help=
"The SUFFIX of the directory name to be created by the script. Something descriptive for your run.",
default="")
args = parser.parse_args()
if errorflag == 0:
if args.input == None:
gwctcore.errorOut(1, "-i must be defined")
optParse(1)
if args.pairwise_opt not in [0, 1, 2]:
gwctcore.errorOut(2, "-w must take values of 0, 1, or 2")
optParse(1)
if args.target_specs == "" and args.pairwise_opt == 0:
gwctcore.errorOut(3, "With -w set to 0, -t must be defined")
optParse(1)
if args.target_specs != "" and args.pairwise_opt != 0:
gwctcore.errorOut(4, "Only one of -t and -w should be set")
optParse(1)
if args.prob_thresh < 0.0 or args.prob_thresh > 1.0:
gwctcore.errorOut(5, "-p can only take values between 0.0 and 1.0")
optParse(1)
if args.uniq_subs not in [0, 1]:
gwctcore.errorOut(6, "-u can only take values of 0 or 1")
optParse(1)
if args.uniq_subs == 1 and args.target_specs == "":
gwctcore.errorOut(
7,
"-u can only be set when a set of target species is defined with -t"
)
optParse(1)
if args.uniq_subs == 1 and args.target_specs == None:
gwctcore.errorOut(
8,
"With -u set to 1, -t must also be defined and -w must be 0")
optParse(1)
if args.number_threads <= 0:
gwctcore.errorOut(9, "-n must be a positive, non-zero integer")
optParse(1)
if args.output_suffix == None:
args.output_suffix = ""
return args.input, args.target_specs, args.uniq_subs, args.pairwise_opt, args.prob_thresh, args.number_threads, args.output_suffix
elif errorflag == 1:
parser.print_help()
sys.exit()