Esempio n. 1
0
                                                   index_col=None)
            print 'Exclude:'
            print mapper.exclude.head()
            if 'ID' not in mapper.exclude.columns and (
                    'CHR' not in mapper.exclude.columns
                    or 'bp' not in mapper.exclude.columns):
                raise ValueError(
                    '{} table does not have ID or CHR,bp columns'.format(
                        args.snp_id_exc))
        mapper.load(args.mapper)  # Load the mapper files
        mapper.load_flip(args.mapper,
                         encode=args.encoded)  # often args.encoded is is null
        mapper.cluster = args.cluster  # Is n by default
        mapper.node = args.node

        Analyser = HaseAnalyser()

        pard = []

        with Timer() as t:
            for i, j in enumerate(args.derivatives):
                pard.append(Reader('partial'))
                pard[i].start(j, study_name=args.study_name[i])
                pard[i].folder.load()

        print "time to set PD is {}s".format(t.secs)

        PD = [
            False if isinstance(i.folder._data.b4, type(None)) else True
            for i in pard
        ]
Esempio n. 2
0
		#ARG_CHECKER.check(args,mode='meta-stage')

		##### Init data readers #####
		if args.derivatives is None:
			raise ValueError('For meta-stage analysis partial derivatives data are required!')
		mapper=Mapper()
		mapper.chunk_size=MAPPER_CHUNK_SIZE
		mapper.genotype_names=args.study_name
		mapper.reference_name=args.ref_name
		mapper.load(args.mapper)
		mapper.load_flip(args.mapper)
		mapper.cluster=args.cluster
		mapper.node=args.node

		Analyser=HaseAnalyser()

		pard=[]


		for i,j in enumerate(args.derivatives):
			pard.append(Reader('partial') )
			pard[i].start(j, study_name=args.study_name[i])
			pard[i].folder.load()


		PD=[False if isinstance(i.folder._data.b4, type(None) ) else True for i in pard]

		if np.sum(PD)!=len(pard) and np.sum(PD)!=0:
			raise ValueError('All study should have b4 data for partial derivatives!')
Esempio n. 3
0
                        "--out",
                        type=str,
                        required=True,
                        help="path to save result folder")
    parser.add_argument(
        "-df",
        type=float,
        default=None,
        help="degree of freedom = ( #subjects in study  - #covariates - 1 )")
    parser.add_argument("-N",
                        type=int,
                        default=None,
                        help="file number to read")
    #TODO (low) add reference panel
    args = parser.parse_args()
    Analyser = HaseAnalyser()
    print args

    Analyser.DF = args.df
    Analyser.result_path = args.r
    Analyser.file_number = args.N

    results = OrderedDict()
    results['RSID'] = np.array([])
    results['p_value'] = np.array([])
    results['t-stat'] = np.array([])
    results['phenotype'] = np.array([])
    results['SE'] = np.array([])
    results['MAF'] = np.array([])
    results['BETA'] = np.array([])
Esempio n. 4
0
from hdgwas.tools import Timer,HaseAnalyser, Reference
import argparse
import pandas as pd
import numpy as np


if __name__=="__main__":

	os.environ['HASEDIR']=os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
	parser = argparse.ArgumentParser(description='Script analyse results of HASE')
	parser.add_argument("-r", required=True,help="path to hase results")
	parser.add_argument("-o", "--out", type=str, required=True,help="path to save result folder")
	parser.add_argument("-df", type=float,default=None, help="degree of freedom = ( #subjects in study  - #covariates - 1 )")
	#TODO (low) add reference panel
	args = parser.parse_args()
	Analyser=HaseAnalyser()
	print args

	Analyser.DF=args.df
	Analyser.result_path=args.r

	results={}
	results['RSID']=np.array([])
	results['p_value']=np.array([])
	results['t-stat']=np.array([])
	results['phenotype']=np.array([])
	results['SE']=np.array([])
	results['MAF']=np.array([])
	results['BETA'] = np.array([])

	while True: