def main():
"""
Perform a correlation analysis of a Gene Expression Dataset and a Metabolomic Dataset.
Arguments:
:param geneDataset metDataset: Gene expression/Metabolomics wide dataset, respectively.
:type geneDataset metDataset: files
:param geneId metId: Name of the Genes/metabolites unique identifier column, respectively.
:type geneId metId: strings
:param geneAnnot metAnnot: Gene Expression/Metabolomics Annotation Datasets, respectively.
:type geneAnnot metAnnot: files
:param geneAnnotName metAnnotName: Name of the column of the Annotation file that contains
genes/metabolites names respectively.
:type geneAnnotName metAnnotName: strings
:param meth: Methodology for the correlation function. One of 'pearson', 'spearman' or
'kendall'.
:type meth: string
:param thres: PValue Threshold to cut the correlations for the output table.
:type thres: float
Returns:
:return output: Output table with the following information: Metabolite "\t" Gene "\t"
Correlation "\t" pvalue
:rtype output: file
:return corMat: Correlation Matrix
:rtype corMat: file
:return fig: Network-like output figure
:rtype fig: pdf
"""
warnings.filterwarnings("ignore", category=RRuntimeWarning)
args = getOptions()
logger = logging.getLogger()
sl.setLogger(logger)
logger.info(u"Importing data with the following parameters: "
"\n\tGene Dataset: {}"
"\n\tGene UniqueID: {}"
"\n\tMet Dataset:{}"
"\n\tMet UniqueID: {}"
"\n\tMethod: {}"
"\n\tThreshold: {}".format(
args.geneDataset,
args.geneId,
args.metDataset,
args.metId,
args.meth,
args.thres,
))
modules.checkForDuplicates(args.geneDataset, args.geneId)
modules.checkForDuplicates(args.metDataset, args.metId)
pandas2ri.activate()
with ires.path("gaitGM.data",
"all_by_all_correlation.R") as my_r_script_path:
f = open(my_r_script_path, "r")
rFile = f.read()
allByAllCorrScript = STAP(rFile, "corr_main_func")
# Prepare Gene Expression Data
geneTable = pd.read_table(args.geneDataset, sep="\t", header=0)
if args.geneAnnot:
R_gene_df = modules.Ids2Names(geneTable, args.geneId, args.geneAnnot,
args.geneName)
else:
geneTable = geneTable.set_index(args.geneId)
R_gene_df = pandas2ri.py2rpy(geneTable)
# Prepare Metabolomics Data
metTable = pd.read_table(args.metDataset, sep="\t", header=0)
if args.metAnnot:
R_met_df = modules.Ids2Names(metTable, args.metId, args.metAnnot,
args.metName)
else:
metTable = metTable.set_index(args.metId)
R_met_df = pandas2ri.py2rpy(metTable)
allByAllCorrScript.corr_main_func(
x=R_gene_df,
y=R_met_df,
meth=args.meth,
thres=args.thres,
corrMatPath=args.corMat,
outputPath=args.output,
figurePath=args.fig,
)
