limix.io.gen.read

limix.io.gen.read(prefix, verbose=True)[source]

Read GEN files into Pandas data frames.

Parameters

prefix (str) – Path prefix to the set of GEN files.

Returns

  • sample (dask dataframe)

  • genotype (dask dataframe)

Examples

>>> from limix.io.gen import read
>>> from limix import file_example
>>>
>>> with file_example(["example.gen", "example.sample"]) as filepaths:
...     data = read(filepaths[0][:-4])
>>>
>>> print(data['sample'])
       sample_id subject_id  missing  gender  age  age_of_onset  phenotype_1
sample
1A0          1A0       W001  0.00000       2    4            -9            0
1A1          1A1       W002  0.00000       2    4            -9            0
1A2          1A2       W003  0.00000       2    4            -9            1
1A3          1A3       W004  0.09000       2    4            -9            1
1A4          1A4       W005  0.00000       2    4            -9            1
>>> print(data['genotype'].head())
          snp_id  rs_id       pos alleleA alleleB 1A0       1A1       1A2       1A3  \
                                                   AA AB BB  AA AB BB  AA AB BB  AA
candidate
SA1          SA1  rs001  10000000       A       G   0  0  1   0  0  1   0  0  1   0
SA2          SA2  rs002  10010000       A       G   0  0  1   0  1  0   1  0  0   0
SA3          SA3  rs003  10020000       C       T   1  0  0   0  1  0   0  0  1   0
SA4          SA4  rs004  10030000       G       T   1  0  0   0  1  0   0  0  1   0
SA5          SA5  rs005  10040000       C       G   0  0  1   0  1  0   1  0  0   0

                            1A4
                AB       BB  AA       AB       BB
candidate
SA1        0.42770  0.57210   0  0.02070  0.97920
SA2        1.00000  0.00000   1  0.00000  0.00000
SA3        0.99670  0.00000   0  0.00000  1.00000
SA4        1.00000  0.00000   0  0.00000  1.00000
SA5        1.00000  0.00000   1  0.00000  0.00000