Python Bed.read方法代码示例

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
 def setUpClass(self):
     self.currentFolder = os.path.dirname(os.path.realpath(__file__))
     #TODO: get data set with NANs!
     snpreader = Bed(self.currentFolder + "/examples/toydata",count_A1=False)
     self.pheno_fn = self.currentFolder + "/examples/toydata.phe"
     self.snpdata = snpreader.read(order='F',force_python_only=True)
     self.snps = self.snpdata.val

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
    def setUpClass(self):
        currentFolder = os.path.dirname(os.path.realpath(__file__))
        self.snp_fn = currentFolder + "/../../tests/datasets/mouse/alldata"
        self.pheno_fn = currentFolder + "/../../tests/datasets/mouse/pheno_10_causals.txt"
        #self.cov_fn = currentFolder + "/examples/toydata.cov"

        # load data
        ###################################################################
        snp_reader = Bed(self.snp_fn)
        pheno = pstpheno.loadOnePhen(self.pheno_fn)
        #cov = pstpheno.loadPhen(self.cov_fn)
        
        # intersect sample ids
        snp_reader, pheno = pysnptools.util.intersect_apply([snp_reader, pheno])
        
        self.G = snp_reader.read(order='C').val
        self.G = stdizer.Unit().standardize(self.G)
        self.G.flags.writeable = False
        self.y = pheno['vals'][:,0]
        self.y.flags.writeable = False

        # load pcs
        #self.G_cov = cov['vals']
        self.G_cov = np.ones((len(self.y), 1))
        self.G_cov.flags.writeable = False

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
 def read_plink(self, fn_plink = None):
     """
     plink reader
     """
     PL = Bed(fn_plink)
     PLOB = PL.read()
     self.GT = PLOB.val
     self.POS = PLOB.pos[:,[0,1]]
     self.SID = PLOB.iid[:,1]
     self.isNormalised = False

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
    def factory(snpreader, num_snps_in_memory, standardizer, blocksize):
        if isinstance(snpreader, str):
            snpreader = Bed(snpreader)

        if num_snps_in_memory >= snpreader.sid_count:
            in_memory = InMemory(snpreader.read(order='C').standardize(standardizer), standardizer, blocksize)
            in_memory._snpreader.val.flags.writeable = False
            in_memory._val = in_memory._snpreader.val
            return in_memory
        else:
            return FromDisk(snpreader, num_snps_in_memory, standardizer, blocksize, None)

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
def process_data(input_path, output_path, name):
    snpreader = Bed(os.path.join(input_path, name))
    data = snpreader.read()
    values = data.val
    preproc_vals = pysnp_genpreproc(values)
    assert(np.any(np.isnan(preproc_vals)) == False)
    saved = os.path.join(output_path, name + ".h5py")
    path, keys = h5_save(path=saved, data_obj={name:preproc_vals}, dt='f')
    return {'n_subjects':data.iid_count, 'subject_ids':data.iid,
            'n_snps':data.sid_count, 'snp_ids':data.sid,
            'data_preprocessed_location': {'path':path, 'key':keys}}

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
 def test_write_x_x_cpp(self):
     snpreader = Bed(self.currentFolder + "/examples/toydata")
     for order in ['C','F']:
         for dtype in [np.float32,np.float64]:
             snpdata = snpreader.read(order=order,dtype=dtype)
             snpdata.val[-1,0] = float("NAN")
             output = "tempdir/toydata.{0}{1}.cpp".format(order,"32" if dtype==np.float32 else "64")
             create_directory_if_necessary(output)
             Bed.write(snpdata, output)
             snpdata2 = Bed(output).read()
             assert TestLoader.is_same(snpdata, snpdata2) #!!!define an equality method on snpdata?

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
 def test_write_x_x_cpp(self):
     snpreader = Bed(self.currentFolder + "/examples/toydata")
     for order in ['C','F']:
         for dtype in [np.float32,np.float64]:
             snpdata = snpreader.read(order=order,dtype=dtype)
             snpdata.val[-1,0] = float("NAN")
             output = "tempdir/toydata.{0}{1}.cpp".format(order,"32" if dtype==np.float32 else "64")
             create_directory_if_necessary(output)
             Bed.write(output, snpdata)
             snpdata2 = Bed(output).read()
             np.testing.assert_array_almost_equal(snpdata.val, snpdata2.val, decimal=10)

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
 def test_subset_view(self):
     snpreader2 = Bed(self.currentFolder + "/examples/toydata",count_A1=False)[:,:]
     result = snpreader2.read(view_ok=True)
     self.assertFalse(snpreader2 is result)
     result2 = result[:,:].read()
     self.assertFalse(sp.may_share_memory(result2.val,result.val))
     result3 = result[:,:].read(view_ok=True)
     self.assertTrue(sp.may_share_memory(result3.val,result.val))
     result4 = result3.read()
     self.assertFalse(sp.may_share_memory(result4.val,result3.val))
     result5 = result4.read(view_ok=True)
     self.assertTrue(sp.may_share_memory(result4.val,result5.val))

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
def main(args):
    print('reading seeed snps')
    seed_snps = pd.read_csv(args.seed_snps, header=None, names=['SNP'], index_col='SNP')
    seed_snps['ibs_length'] = 0
    seed_snps['ibd'] = 0

    print('reading typed snps')
    typed_snps = pd.read_csv(args.typed_snps, header=None, names=['SNP'])

    print('reading genotypes')
    data = Bed(args.bfile)
    X = data.read().val
    typed_snps_indices = np.sort(data.sid_to_index(typed_snps.SNP))
    typed_snps_bp = data.col_property[typed_snps_indices,2]

    print(len(seed_snps), 'snps in list')
    print(data.iid_count, data.sid_count, 'are dimensions of X')

    def analyze_snp(i):
        # find first typed snp after query snp
        snp_bp = data.col_property[i,2]
        v = np.where(typed_snps_bp > snp_bp)[0]
        if len(v) > 0:
            typed_i = v[0]
        else:
            typed_i = len(typed_snps_indices)-1

        n1, n2 = np.where(X[:,i] == 1)[0]
        if (X[n1,typed_snps_indices[typed_i]] - X[n2, typed_snps_indices[typed_i]])**2 == 4:
            return 0, 0

        typed_il, typed_ir = fis.find_boundaries(
                X[n1,typed_snps_indices],
                X[n2,typed_snps_indices],
                typed_i)
        typed_ir -= 1

        il = typed_snps_indices[typed_il]
        ir = typed_snps_indices[typed_ir]
        cM = data.col_property[ir, 1] - \
                data.col_property[il, 1]
        ibd = (np.mean(X[n1,il:ir] == X[n2,il:ir]) > 0.99)
        return cM, int(ibd)

    for (i, snp) in iter.show_progress(
            it.izip(data.sid_to_index(seed_snps.index), seed_snps.index),
            total=len(seed_snps)):
            # total=10):
        seed_snps.ix[snp, ['ibs_length', 'ibd']] = analyze_snp(i)

    print(seed_snps.iloc[:100])
    seed_snps.to_csv(args.outfile, sep='\t')

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
def main():
    """
    example that compares output to fastlmmc
    """


    # set up data
    phen_fn = "../feature_selection/examples/toydata.phe"
    snp_fn = "../feature_selection/examples/toydata.5chrom"
    #chrom_count = 5
    
    # load data
    ###################################################################
    snp_reader = Bed(snp_fn)
    pheno = pstpheno.loadOnePhen(phen_fn)

    cov = None
    #cov = pstpheno.loadPhen(self.cov_fn)    

    snp_reader, pheno, cov = intersect_apply([snp_reader, pheno, cov])
    
    G = snp_reader.read(order='C').val
    G = stdizer.Unit().standardize(G)
    G.flags.writeable = False
    y = pheno['vals'][:,0]
    y.flags.writeable

    # load pcs
    #G_pc = cov['vals']
    #G_pc.flags.writeable = False
    delta = 2.0
    gwas = WindowingGwas(G, y, delta=delta)
    pv = gwas.run_gwas()

    from fastlmm.association.tests.test_gwas import GwasTest
    REML = False
    snp_pos_sim = snp_reader.sid
    snp_pos_test = snp_reader.sid
    os.environ["FastLmmUseAnyMklLib"] = "1"
    gwas_c = GwasTest(snp_fn, phen_fn, snp_pos_sim, snp_pos_test, delta, REML=REML, excludeByPosition=0)
    gwas_c.run_gwas()

    import pylab
    pylab.plot(np.log(pv), np.log(gwas_c.p_values), "+")
    pylab.plot(np.arange(-18, 0), np.arange(-18,0), "-k")
    pylab.show()

    np.testing.assert_array_almost_equal(np.log(pv), np.log(gwas_c.p_values), decimal=3)
    
    simple_manhattan_plot(pv)

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
    def test_SNC(self):
        logging.info("TestSNC")
        test_snps = self.bedbase
        pheno = pstpheno.loadOnePhen(self.phen_fn,vectorize=True)
        covar = pstpheno.loadPhen(self.cov_fn)
        bed = Bed(test_snps, count_A1=False)
        snc = bed.read()
        snc.val[:,2] = [0] * snc.iid_count # make SNP #2 have constant values (aka a SNC)

        output_file_name = self.file_name("snc")

        frame = single_snp(test_snps=snc[:,:10], pheno=pheno, G0=snc, mixing=0,leave_out_one_chrom=False,
                                  covar=covar, output_file_name=output_file_name,count_A1=False
                                  )
        self.compare_files(frame,"snc")

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
def load_plink_bed_bim_fam_dataset(path_dataset, snp_ids=None,
                                   subject_ids=None, count_A1=True):
    """
    Load a Plink bed/bim/fam dataset as a SnpData instance. Optionnally a
    specific list of snps or subjects can be extracted to avoid loading
    everything in memory.

    Parameters
    ----------
    path_dataset: str
        Path to the Plink bed/bim/fam dataset, with or without .bed extension.
    snp_ids: list/set of str, default None
        Snps that should be extracted if available in the dataset.
        By default None, all snps are loaded.
    subject_ids: list of str, default None
        Subjects that should be extracted if available in the dataset.
        By default None, all subjects are loaded.
    count_A1: bool, default True
        Genotypes are provided as allele counts, A1 if True else A2.

    Return
    ------
    snp_data: pysnptools object
        PLINK data loaded by the 'pysnptools' library.
    """

    # Load the metadata, without loading the genotypes
    snp_data = Bed(path_dataset, count_A1=count_A1)

    # If requested, filter on snp ids
    if snp_ids is not None:
        snp_ids = set(snp_ids)
        snp_bool_indexes = [(s in snp_ids) for s in snp_data.sid]
        snp_data = snp_data[:, snp_bool_indexes]

    # If requested, filter on subject ids
    if subject_ids is not None:
        subject_ids = set(subject_ids)
        subject_bool_indexes = [(s in subject_ids) for s in snp_data.iid[:, 1]]
        snp_data = snp_data[subject_bool_indexes, :]

    # Load the genotypes from the Plink dataset
    snp_data = snp_data.read()

    return snp_data

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
def cluster_data(snpreader):
    """
    compute hierarchical clustering of snp data set in bed_fn
    """

    if isinstance(snpreader,str):
        snpreader = Bed(snpreader)
    G = snpreader.read().standardize().val

    # Generate distance matrix
    from sklearn.metrics.pairwise import euclidean_distances
    D = euclidean_distances(G, G)

    # Compute and plot first dendrogram.
    fig = pylab.figure(figsize=(8,8))
    ax1 = fig.add_axes([0.09,0.1,0.2,0.6])
    Y = fc.linkage(D, method='average') #method="centroid" is cubic!
    Z1 = sch.dendrogram(Y, orientation='right')
    ax1.set_xticks([])
    ax1.set_yticks([])

    # Compute and plot second dendrogram.
    ax2 = fig.add_axes([0.3,0.71,0.6,0.2])
    #Y = sch.linkage(D, method='single')
    Z2 = sch.dendrogram(Y)
    ax2.set_xticks([])
    ax2.set_yticks([])

    # Plot distance matrix.
    axmatrix = fig.add_axes([0.3,0.1,0.6,0.6])
    idx1 = Z1['leaves']
    #dx2 = Z2['leaves']
    D = D[idx1,:]
    D = D[:,idx1]
    axmatrix.matshow(D, aspect='auto', origin='lower', cmap=pylab.cm.YlGnBu)
    axmatrix.set_xticks([])
    axmatrix.set_yticks([])

    pylab.show()

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]
def genPheno(filename="../thinFam",per=.5,savename="fakePheno.txt",c=2.0,num=5):
	sFil=Bed(filename);
	D=sFil.read().val;
	m=len(D[0]);
	n=len(D);
	print m;
	print n;
	I=[rand.randint(0,m-1) for i in range(0,num)];
	SNP=[[D[j][i] for j in range(0,n)] for i in I]
	#p0=n*peir/sum([c**i*len([j for j in SNP if j==float(i)]) for i in range(0,3)])
	print len(I);
	print len(SNP);
	print len(SNP[0]);
	print n;
	print min([len(s) for s in SNP])
	print SNP;
	
	SNP=[[max(i,0.0) for i in s] for s in SNP]
	for i in range(0,num):
		for j in range(0,n):
			if not SNP[i][j] in [1.0,0.0,2.0]:
				SNP[i][j]=0.0;
	print [list(set(s)) for s in SNP]

# 需要导入模块: from pysnptools.snpreader import Bed [as 别名]
# 或者: from pysnptools.snpreader.Bed import read [as 别名]

# Find out about iids and sids
print snpreader.iid_count
print snpreader.sid_count
print snpreader.iid[:3]
print snpreader.sid[:3]
#500
#5000
#[['cid0P0' 'cid0P0']
# ['cid1P0' 'cid1P0']
# ['cid2P0' 'cid2P0']]
#['snp625_m0_.03m1_.07' 'snp1750_m0_.02m1_.04' 'snp0_m0_.37m1_.24']

#Read all the SNP data in to memory
snpdata = snpreader.read()
#What is snpdata?
# SnpData(Bed("all.bed"))

#What do the iids and sid of snprdata look like?
print snpdata.iid_count, snpdata.sid_count
print snpdata.iid[:3]
print snpdata.sid[:3]
# The same.

# print the SNP data
print snpdata.val
#[[ 2.  2.  1. ...,  2.  1.  2.]
# [ 2.  2.  1. ...,  2.  0.  2.]
# [ 2.  2.  1. ...,  1.  1.  1.]
# ...,