Skip to content

Sumstats parsers

COJOSSParser

Bases: SumstatsParser

A specialized class for parsing GWAS summary statistics files generated by the COJO software.

See Also

Attributes:

Name Type Description
col_name_converter

A dictionary mapping column names in the original table to magenpy's column names.
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv.
Source code in magenpy/parsers/sumstats_parsers.py 
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
class COJOSSParser(SumstatsParser):
    """
    A specialized class for parsing GWAS summary statistics files generated by the `COJO` software.

    !!! seealso "See Also"
        * [Plink2SSParser][magenpy.parsers.sumstats_parsers.Plink2SSParser]
        * [Plink1SSParser][magenpy.parsers.sumstats_parsers.Plink1SSParser]
        * [FastGWASSParser][magenpy.parsers.sumstats_parsers.FastGWASSParser]
        * [SSFParser][magenpy.parsers.sumstats_parsers.SSFParser]
        * [SaigeSSParser][magenpy.parsers.sumstats_parsers.SaigeSSParser]

    :ivar col_name_converter: A dictionary mapping column names in the original table to magenpy's column names.
    :ivar read_csv_kwargs: Keyword arguments to pass to pandas' `read_csv`.
    """

    format_name = "cojo"
    aliases = ("cojo",)
    standard_cols = ("SNP", "A1", "A2", "MAF", "BETA", "SE", "PVAL", "N")
    output_col_name_converter = {"MAF": "freq", "BETA": "b", "SE": "se", "PVAL": "p"}

    def __init__(self, col_name_converter=None, **read_csv_kwargs):
        """

        Initialize the COJO summary statistics parser.

        :param col_name_converter: A dictionary/string mapping column names
        in the original table to magenpy's column names for the various
        summary statistics. If a string, it should be a comma-separated list of
        key-value pairs (e.g. 'rsid=SNP,pos=POS').
        :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
        """
        super().__init__(col_name_converter, **read_csv_kwargs)

        self.col_name_converter = self.col_name_converter or {}

        self.col_name_converter.update(
            {"freq": "MAF", "b": "BETA", "se": "SE", "p": "PVAL"}
        )

__init__(col_name_converter=None, **read_csv_kwargs)

Initialize the COJO summary statistics parser.

Parameters:

Name Type Description Default
col_name_converter

A dictionary/string mapping column names in the original table to magenpy's column names for the various summary statistics. If a string, it should be a comma-separated list of key-value pairs (e.g. 'rsid=SNP,pos=POS').

 None
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv

 {}
Source code in magenpy/parsers/sumstats_parsers.py 
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
def __init__(self, col_name_converter=None, **read_csv_kwargs):
    """

    Initialize the COJO summary statistics parser.

    :param col_name_converter: A dictionary/string mapping column names
    in the original table to magenpy's column names for the various
    summary statistics. If a string, it should be a comma-separated list of
    key-value pairs (e.g. 'rsid=SNP,pos=POS').
    :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
    """
    super().__init__(col_name_converter, **read_csv_kwargs)

    self.col_name_converter = self.col_name_converter or {}

    self.col_name_converter.update(
        {"freq": "MAF", "b": "BETA", "se": "SE", "p": "PVAL"}
    )

FastGWASSParser

Bases: SumstatsParser

A specialized class for parsing GWAS summary statistics files generated by the FastGWA software.

See Also

Attributes:

Name Type Description
col_name_converter

A dictionary mapping column names in the original table to magenpy's column names.
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv.
Source code in magenpy/parsers/sumstats_parsers.py 
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
class FastGWASSParser(SumstatsParser):
    """
    A specialized class for parsing GWAS summary statistics files generated by the `FastGWA` software.

    !!! seealso "See Also"
        * [Plink2SSParser][magenpy.parsers.sumstats_parsers.Plink2SSParser]
        * [Plink1SSParser][magenpy.parsers.sumstats_parsers.Plink1SSParser]
        * [COJOSSParser][magenpy.parsers.sumstats_parsers.COJOSSParser]
        * [SSFParser][magenpy.parsers.sumstats_parsers.SSFParser]
        * [SaigeSSParser][magenpy.parsers.sumstats_parsers.SaigeSSParser]

    :ivar col_name_converter: A dictionary mapping column names in the original table to magenpy's column names.
    :ivar read_csv_kwargs: Keyword arguments to pass to pandas' `read_csv`.


    """

    format_name = "fastgwa"
    aliases = ("fastgwa",)
    standard_cols = ("CHR", "SNP", "POS", "A1", "A2", "MAF", "BETA", "SE", "PVAL", "N")
    output_col_name_converter = {"MAF": "AF1", "PVAL": "P"}

    def __init__(self, col_name_converter=None, **read_csv_kwargs):
        """
        :param col_name_converter: A dictionary/string mapping column names
        in the original table to magenpy's column names for the various
        summary statistics. If a string, it should be a comma-separated list of
        key-value pairs (e.g. 'rsid=SNP,pos=POS').
        :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
        """
        super().__init__(col_name_converter, **read_csv_kwargs)

        self.col_name_converter = self.col_name_converter or {}

        self.col_name_converter.update({"AF1": "MAF", "P": "PVAL"})

__init__(col_name_converter=None, **read_csv_kwargs)

Parameters:

Name Type Description Default
col_name_converter

A dictionary/string mapping column names in the original table to magenpy's column names for the various summary statistics. If a string, it should be a comma-separated list of key-value pairs (e.g. 'rsid=SNP,pos=POS').

 None
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv

 {}
Source code in magenpy/parsers/sumstats_parsers.py 
400
401
402
403
404
405
406
407
408
409
410
411
412
def __init__(self, col_name_converter=None, **read_csv_kwargs):
    """
    :param col_name_converter: A dictionary/string mapping column names
    in the original table to magenpy's column names for the various
    summary statistics. If a string, it should be a comma-separated list of
    key-value pairs (e.g. 'rsid=SNP,pos=POS').
    :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
    """
    super().__init__(col_name_converter, **read_csv_kwargs)

    self.col_name_converter = self.col_name_converter or {}

    self.col_name_converter.update({"AF1": "MAF", "P": "PVAL"})

Plink1SSParser

Bases: SumstatsParser

A specialized class for parsing GWAS summary statistics files generated by plink1.9.

See Also

Attributes:

Name Type Description
col_name_converter

A dictionary mapping column names in the original table to magenpy's column names.
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv.
Source code in magenpy/parsers/sumstats_parsers.py 
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
class Plink1SSParser(SumstatsParser):
    """
    A specialized class for parsing GWAS summary statistics files generated by `plink1.9`.

    !!! seealso "See Also"
        * [Plink2SSParser][magenpy.parsers.sumstats_parsers.Plink2SSParser]
        * [COJOSSParser][magenpy.parsers.sumstats_parsers.COJOSSParser]
        * [FastGWASSParser][magenpy.parsers.sumstats_parsers.FastGWASSParser]
        * [SSFParser][magenpy.parsers.sumstats_parsers.SSFParser]
        * [SaigeSSParser][magenpy.parsers.sumstats_parsers.SaigeSSParser]

    :ivar col_name_converter: A dictionary mapping column names in the original table to magenpy's column names.
    :ivar read_csv_kwargs: Keyword arguments to pass to pandas' `read_csv`.

    """

    format_name = "plink1.9"
    aliases = ("plink1.9",)
    standard_cols = ("CHR", "SNP", "POS", "A1", "A2", "N", "BETA", "Z", "PVAL")
    output_col_name_converter = {"POS": "BP", "N": "NMISS", "Z": "STAT", "PVAL": "P"}

    def __init__(self, col_name_converter=None, **read_csv_kwargs):
        """
        Initialize the `plink1.9` summary statistics parser.

        :param col_name_converter: A dictionary/string mapping column names
        in the original table to magenpy's column names for the various
        summary statistics. If a string, it should be a comma-separated list of
        key-value pairs (e.g. 'rsid=SNP,pos=POS').
        :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
        """

        super().__init__(col_name_converter, **read_csv_kwargs)

        self.col_name_converter = self.col_name_converter or {}

        self.col_name_converter.update(
            {"P": "PVAL", "NMISS": "N", "STAT": "Z", "BP": "POS"}
        )

__init__(col_name_converter=None, **read_csv_kwargs)

Initialize the plink1.9 summary statistics parser.

Parameters:

Name Type Description Default
col_name_converter

A dictionary/string mapping column names in the original table to magenpy's column names for the various summary statistics. If a string, it should be a comma-separated list of key-value pairs (e.g. 'rsid=SNP,pos=POS').

 None
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv

 {}
Source code in magenpy/parsers/sumstats_parsers.py 
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
def __init__(self, col_name_converter=None, **read_csv_kwargs):
    """
    Initialize the `plink1.9` summary statistics parser.

    :param col_name_converter: A dictionary/string mapping column names
    in the original table to magenpy's column names for the various
    summary statistics. If a string, it should be a comma-separated list of
    key-value pairs (e.g. 'rsid=SNP,pos=POS').
    :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
    """

    super().__init__(col_name_converter, **read_csv_kwargs)

    self.col_name_converter = self.col_name_converter or {}

    self.col_name_converter.update(
        {"P": "PVAL", "NMISS": "N", "STAT": "Z", "BP": "POS"}
    )

Plink2SSParser

Bases: SumstatsParser

A specialized class for parsing GWAS summary statistics files generated by plink2.

See Also

Attributes:

Name Type Description
col_name_converter

A dictionary mapping column names in the original table to magenpy's column names.
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv.
Source code in magenpy/parsers/sumstats_parsers.py 
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
class Plink2SSParser(SumstatsParser):
    """
    A specialized class for parsing GWAS summary statistics files generated by `plink2`.

    !!! seealso "See Also"
        * [Plink1SSParser][magenpy.parsers.sumstats_parsers.Plink1SSParser]
        * [COJOSSParser][magenpy.parsers.sumstats_parsers.COJOSSParser]
        * [FastGWASSParser][magenpy.parsers.sumstats_parsers.FastGWASSParser]
        * [SSFParser][magenpy.parsers.sumstats_parsers.SSFParser]
        * [SaigeSSParser][magenpy.parsers.sumstats_parsers.SaigeSSParser]

    :ivar col_name_converter: A dictionary mapping column names in the original table to magenpy's column names.
    :ivar read_csv_kwargs: Keyword arguments to pass to pandas' `read_csv`.

    """

    format_name = "plink2"
    aliases = ("plink", "plink2")
    standard_cols = (
        "CHR",
        "POS",
        "SNP",
        "A1",
        "A2",
        "MAF",
        "N",
        "BETA",
        "SE",
        "Z",
        "PVAL",
    )
    output_col_name_converter = {
        "CHR": "#CHROM",
        "SNP": "ID",
        "MAF": "A1_FREQ",
        "N": "OBS_CT",
        "Z": "Z_STAT",
        "PVAL": "P",
    }

    def __init__(self, col_name_converter=None, **read_csv_kwargs):
        """

        Initialize the `plink2` summary statistics parser.

        :param col_name_converter: A dictionary/string mapping column names
        in the original table to magenpy's column names for the various
        summary statistics. If a string, it should be a comma-separated list of
        key-value pairs (e.g. 'rsid=SNP,pos=POS').
        :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
        """

        super().__init__(col_name_converter, **read_csv_kwargs)

        self.col_name_converter = self.col_name_converter or {}

        self.col_name_converter.update(
            {
                "#CHROM": "CHR",
                "ID": "SNP",
                "P": "PVAL",
                "OBS_CT": "N",
                "A1_FREQ": "MAF",
                "T_STAT": "Z",
                "Z_STAT": "Z",
            }
        )

    def parse(self, file_name, drop_na=True):
        """
        Parse a summary statistics file.
        :param file_name: The path to the summary statistics file.
        :param drop_na: Drop any entries with missing values.

        :return: A pandas DataFrame containing the parsed summary statistics.
        """

        df = super().parse(file_name, drop_na=False)

        if "A2" not in df.columns:
            try:
                if "ALT1" in df.columns:
                    df["A2"] = np.where(df["A1"] == df["ALT1"], df["REF"], df["ALT1"])
                elif "ALT" in df.columns:
                    df["A2"] = np.where(df["A1"] == df["ALT"], df["REF"], df["ALT"])
                else:
                    warnings.warn(
                        "The reference allele A2 could not be inferred "
                        "from the summary statistics file!"
                    )
            except KeyError:
                warnings.warn(
                    "The reference allele A2 could not be inferred "
                    "from the summary statistics file! Some of the columns needed to infer "
                    "the A2 allele are missing or coded differently than what we expect."
                )

        if drop_na:
            df = self.drop_na_from_essential_cols(df)

        return df

__init__(col_name_converter=None, **read_csv_kwargs)

Initialize the plink2 summary statistics parser.

Parameters:

Name Type Description Default
col_name_converter

A dictionary/string mapping column names in the original table to magenpy's column names for the various summary statistics. If a string, it should be a comma-separated list of key-value pairs (e.g. 'rsid=SNP,pos=POS').

 None
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv

 {}
Source code in magenpy/parsers/sumstats_parsers.py 
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
def __init__(self, col_name_converter=None, **read_csv_kwargs):
    """

    Initialize the `plink2` summary statistics parser.

    :param col_name_converter: A dictionary/string mapping column names
    in the original table to magenpy's column names for the various
    summary statistics. If a string, it should be a comma-separated list of
    key-value pairs (e.g. 'rsid=SNP,pos=POS').
    :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
    """

    super().__init__(col_name_converter, **read_csv_kwargs)

    self.col_name_converter = self.col_name_converter or {}

    self.col_name_converter.update(
        {
            "#CHROM": "CHR",
            "ID": "SNP",
            "P": "PVAL",
            "OBS_CT": "N",
            "A1_FREQ": "MAF",
            "T_STAT": "Z",
            "Z_STAT": "Z",
        }
    )

parse(file_name, drop_na=True)

Parse a summary statistics file.

Parameters:

Name Type Description Default
file_name

The path to the summary statistics file.

 required
drop_na

Drop any entries with missing values.

 True

Returns:

Type Description

A pandas DataFrame containing the parsed summary statistics.
Source code in magenpy/parsers/sumstats_parsers.py 
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
def parse(self, file_name, drop_na=True):
    """
    Parse a summary statistics file.
    :param file_name: The path to the summary statistics file.
    :param drop_na: Drop any entries with missing values.

    :return: A pandas DataFrame containing the parsed summary statistics.
    """

    df = super().parse(file_name, drop_na=False)

    if "A2" not in df.columns:
        try:
            if "ALT1" in df.columns:
                df["A2"] = np.where(df["A1"] == df["ALT1"], df["REF"], df["ALT1"])
            elif "ALT" in df.columns:
                df["A2"] = np.where(df["A1"] == df["ALT"], df["REF"], df["ALT"])
            else:
                warnings.warn(
                    "The reference allele A2 could not be inferred "
                    "from the summary statistics file!"
                )
        except KeyError:
            warnings.warn(
                "The reference allele A2 could not be inferred "
                "from the summary statistics file! Some of the columns needed to infer "
                "the A2 allele are missing or coded differently than what we expect."
            )

    if drop_na:
        df = self.drop_na_from_essential_cols(df)

    return df

SSFParser

Bases: SumstatsParser

A specialized class for parsing GWAS summary statistics that are formatted according to the standardized summary statistics format adopted by the GWAS Catalog. This format is sometimes denoted as GWAS-SSF.

Reference and details: https://github.com/EBISPOT/gwas-summary-statistics-standard

See Also

Attributes:

Name Type Description
col_name_converter

A dictionary mapping column names in the original table to magenpy's column names.
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv.
Source code in magenpy/parsers/sumstats_parsers.py 
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
class SSFParser(SumstatsParser):
    """
    A specialized class for parsing GWAS summary statistics that are formatted according
     to the standardized summary statistics format adopted by the GWAS Catalog. This format is
     sometimes denoted as `GWAS-SSF`.

    Reference and details:
    https://github.com/EBISPOT/gwas-summary-statistics-standard

    !!! seealso "See Also"
        * [Plink2SSParser][magenpy.parsers.sumstats_parsers.Plink2SSParser]
        * [Plink1SSParser][magenpy.parsers.sumstats_parsers.Plink1SSParser]
        * [COJOSSParser][magenpy.parsers.sumstats_parsers.COJOSSParser]
        * [FastGWASSParser][magenpy.parsers.sumstats_parsers.FastGWASSParser]
        * [SaigeSSParser][magenpy.parsers.sumstats_parsers.SaigeSSParser]

    :ivar col_name_converter: A dictionary mapping column names in the original table to magenpy's column names.
    :ivar read_csv_kwargs: Keyword arguments to pass to pandas' `read_csv`.

    """

    format_name = "ssf"
    aliases = ("ssf", "gwas-ssf", "gwascatalog")
    standard_cols = ("CHR", "POS", "SNP", "A1", "A2", "BETA", "SE", "MAF", "PVAL", "N")
    output_col_name_converter = {
        "CHR": "chromosome",
        "POS": "base_pair_location",
        "SNP": "rsid",
        "A1": "effect_allele",
        "A2": "other_allele",
        "BETA": "beta",
        "SE": "standard_error",
        "MAF": "effect_allele_frequency",
        "PVAL": "p_value",
        "N": "n",
    }

    def __init__(self, col_name_converter=None, **read_csv_kwargs):
        """

        Initialize the standardized summary statistics parser.

        :param col_name_converter: A dictionary/string mapping column names
        in the original table to magenpy's column names for the various
        summary statistics. If a string, it should be a comma-separated list of
        key-value pairs (e.g. 'rsid=SNP,pos=POS').
        :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
        """

        super().__init__(col_name_converter, **read_csv_kwargs)

        self.col_name_converter = self.col_name_converter or {}

        self.col_name_converter.update(
            {
                "chromosome": "CHR",
                "base_pair_location": "POS",
                "rsid": "SNP",
                "effect_allele": "A1",
                "other_allele": "A2",
                "beta": "BETA",
                "standard_error": "SE",
                "effect_allele_frequency": "MAF",
                "p_value": "PVAL",
                "n": "N",
            }
        )

__init__(col_name_converter=None, **read_csv_kwargs)

Initialize the standardized summary statistics parser.

Parameters:

Name Type Description Default
col_name_converter

A dictionary/string mapping column names in the original table to magenpy's column names for the various summary statistics. If a string, it should be a comma-separated list of key-value pairs (e.g. 'rsid=SNP,pos=POS').

 None
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv

 {}
Source code in magenpy/parsers/sumstats_parsers.py 
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
def __init__(self, col_name_converter=None, **read_csv_kwargs):
    """

    Initialize the standardized summary statistics parser.

    :param col_name_converter: A dictionary/string mapping column names
    in the original table to magenpy's column names for the various
    summary statistics. If a string, it should be a comma-separated list of
    key-value pairs (e.g. 'rsid=SNP,pos=POS').
    :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
    """

    super().__init__(col_name_converter, **read_csv_kwargs)

    self.col_name_converter = self.col_name_converter or {}

    self.col_name_converter.update(
        {
            "chromosome": "CHR",
            "base_pair_location": "POS",
            "rsid": "SNP",
            "effect_allele": "A1",
            "other_allele": "A2",
            "beta": "BETA",
            "standard_error": "SE",
            "effect_allele_frequency": "MAF",
            "p_value": "PVAL",
            "n": "N",
        }
    )

SaigeSSParser

Bases: SumstatsParser

A specialized class for parsing GWAS summary statistics files generated by the SAIGE software. Reference and details: https://saigegit.github.io/SAIGE-doc/docs/single_step2.html

TODO: Ensure that the column names are correct across different trait types and the inference of the sample size is correct.

See Also

Attributes:

Name Type Description
col_name_converter

A dictionary mapping column names in the original table to magenpy's column names.
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv.
Source code in magenpy/parsers/sumstats_parsers.py 
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
class SaigeSSParser(SumstatsParser):
    """
    A specialized class for parsing GWAS summary statistics files generated by the `SAIGE` software.
    Reference and details:
    https://saigegit.github.io/SAIGE-doc/docs/single_step2.html

    TODO: Ensure that the column names are correct across different trait types
    and the inference of the sample size is correct.

    !!! seealso "See Also"
        * [Plink2SSParser][magenpy.parsers.sumstats_parsers.Plink2SSParser]
        * [Plink1SSParser][magenpy.parsers.sumstats_parsers.Plink1SSParser]
        * [COJOSSParser][magenpy.parsers.sumstats_parsers.COJOSSParser]
        * [FastGWASSParser][magenpy.parsers.sumstats_parsers.FastGWASSParser]
        * [SSFParser][magenpy.parsers.sumstats_parsers.SSFParser]

    :ivar col_name_converter: A dictionary mapping column names in the original table to magenpy's column names.
    :ivar read_csv_kwargs: Keyword arguments to pass to pandas' `read_csv`.

    """

    format_name = "saige"
    aliases = ("saige",)
    standard_cols = ("SNP", "A1", "A2", "MAF", "MAC", "Z", "PVAL", "N")
    output_col_name_converter = {
        "SNP": "MarkerID",
        "A2": "Allele1",
        "A1": "Allele2",
        "MAF": "AF_Allele2",
        "MAC": "AC_Allele2",
        "Z": "Tstat",
        "PVAL": "p.value",
    }

    def __init__(self, col_name_converter=None, **read_csv_kwargs):
        """
        Initialize the `SAIGE` summary statistics parser.

        :param col_name_converter: A dictionary/string mapping column names
        in the original table to magenpy's column names for the various
        summary statistics. If a string, it should be a comma-separated list of
        key-value pairs (e.g. 'rsid=SNP,pos=POS').
        :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
        """
        super().__init__(col_name_converter, **read_csv_kwargs)

        self.col_name_converter = self.col_name_converter or {}

        # NOTE: SAIGE considers Allele2 to be the effect allele, so
        # we switch their designation here:
        self.col_name_converter.update(
            {
                "MarkerID": "SNP",
                "Allele1": "A2",
                "Allele2": "A1",
                "AF_Allele2": "MAF",
                "AC_Allele2": "MAC",
                "Tstat": "Z",
                "p.value": "PVAL",
            }
        )

    def parse(self, file_name, drop_na=True):
        """
        Parse the summary statistics file.
        :param file_name: The path to the summary statistics file.
        :param drop_na: Drop any entries with missing values.

        :return: A pandas DataFrame containing the parsed summary statistics.
        """

        df = super().parse(file_name, drop_na=False)

        # Infer the sample size N
        df["N"] = df["MAC"] / (2.0 * df["MAF"])

        if drop_na:
            df = self.drop_na_from_essential_cols(df)

        return df

__init__(col_name_converter=None, **read_csv_kwargs)

Initialize the SAIGE summary statistics parser.

Parameters:

Name Type Description Default
col_name_converter

A dictionary/string mapping column names in the original table to magenpy's column names for the various summary statistics. If a string, it should be a comma-separated list of key-value pairs (e.g. 'rsid=SNP,pos=POS').

 None
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv

 {}
Source code in magenpy/parsers/sumstats_parsers.py 
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
def __init__(self, col_name_converter=None, **read_csv_kwargs):
    """
    Initialize the `SAIGE` summary statistics parser.

    :param col_name_converter: A dictionary/string mapping column names
    in the original table to magenpy's column names for the various
    summary statistics. If a string, it should be a comma-separated list of
    key-value pairs (e.g. 'rsid=SNP,pos=POS').
    :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
    """
    super().__init__(col_name_converter, **read_csv_kwargs)

    self.col_name_converter = self.col_name_converter or {}

    # NOTE: SAIGE considers Allele2 to be the effect allele, so
    # we switch their designation here:
    self.col_name_converter.update(
        {
            "MarkerID": "SNP",
            "Allele1": "A2",
            "Allele2": "A1",
            "AF_Allele2": "MAF",
            "AC_Allele2": "MAC",
            "Tstat": "Z",
            "p.value": "PVAL",
        }
    )

parse(file_name, drop_na=True)

Parse the summary statistics file.

Parameters:

Name Type Description Default
file_name

The path to the summary statistics file.

 required
drop_na

Drop any entries with missing values.

 True

Returns:

Type Description

A pandas DataFrame containing the parsed summary statistics.
Source code in magenpy/parsers/sumstats_parsers.py 
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
def parse(self, file_name, drop_na=True):
    """
    Parse the summary statistics file.
    :param file_name: The path to the summary statistics file.
    :param drop_na: Drop any entries with missing values.

    :return: A pandas DataFrame containing the parsed summary statistics.
    """

    df = super().parse(file_name, drop_na=False)

    # Infer the sample size N
    df["N"] = df["MAC"] / (2.0 * df["MAF"])

    if drop_na:
        df = self.drop_na_from_essential_cols(df)

    return df

SumstatsParser

Bases: object

A wrapper class for parsing summary statistics files that are written by statistical genetics software for Genome-wide Association testing. A common challenge is the fact that different software tools output summary statistics in different formats and with different column names. Thus, this class provides a common interface for parsing summary statistics files from different software tools and aims to make this process as seamless as possible.

The class is designed to be extensible, so that users can easily add new parsers for different software tools.

See Also

Attributes:

Name Type Description
col_name_converter

A dictionary mapping column names in the original table to magenpy's column names.
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv.
Source code in magenpy/parsers/sumstats_parsers.py 
 39
 40
 41
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
class SumstatsParser(object):
    """
    A wrapper class for parsing summary statistics files that are written by statistical genetics software
    for Genome-wide Association testing. A common challenge is the fact that different software tools
    output summary statistics in different formats and with different column names. Thus, this class
    provides a common interface for parsing summary statistics files from different software tools
    and aims to make this process as seamless as possible.

    The class is designed to be extensible, so that users can easily add new parsers for different software tools.

    !!! seealso "See Also"
        * [Plink2SSParser][magenpy.parsers.sumstats_parsers.Plink2SSParser]
        * [Plink1SSParser][magenpy.parsers.sumstats_parsers.Plink1SSParser]
        * [COJOSSParser][magenpy.parsers.sumstats_parsers.COJOSSParser]
        * [FastGWASSParser][magenpy.parsers.sumstats_parsers.FastGWASSParser]
        * [SSFParser][magenpy.parsers.sumstats_parsers.SSFParser]
        * [SaigeSSParser][magenpy.parsers.sumstats_parsers.SaigeSSParser]

    :ivar col_name_converter: A dictionary mapping column names in the original table to magenpy's column names.
    :ivar read_csv_kwargs: Keyword arguments to pass to pandas' `read_csv`.

    """

    format_name = "magenpy"
    aliases = ("magenpy",)
    standard_cols = MAGENPY_SUMSTATS_COLUMNS
    essential_col_groups = DEFAULT_ESSENTIAL_COL_GROUPS
    output_col_name_converter = {}

    def __init__(self, col_name_converter=None, **read_csv_kwargs):
        """
        Initialize the summary statistics parser.

        :param col_name_converter: A dictionary/string mapping column names
        in the original table to magenpy's column names for the various
        summary statistics. If a string, it should be a comma-separated list of
        key-value pairs (e.g. 'rsid=SNP,pos=POS').
        :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
        """

        if isinstance(col_name_converter, str):
            self.col_name_converter = {
                k: v
                for entry in col_name_converter.split(",")
                for k, v in [entry.strip().split("=")]
                if len(entry.strip()) > 0
            }
        else:
            self.col_name_converter = col_name_converter

        self.read_csv_kwargs = read_csv_kwargs

        # If the delimiter is not specified, assume whitespace by default:
        if (
            "sep" not in self.read_csv_kwargs
            and "delimiter" not in self.read_csv_kwargs
        ):
            self.read_csv_kwargs["sep"] = r"\s+"

    @classmethod
    def get_standard_cols(cls):
        """
        :return: The standard magenpy columns for this summary statistics format.
        """
        return list(cls.standard_cols)

    @classmethod
    def get_essential_col_groups(cls):
        """
        Essential columns are encoded as groups of alternatives. Each group must
        be satisfied by at least one of its alternatives.

        :return: A tuple of essential column alternative groups.
        """
        return cls.essential_col_groups

    @classmethod
    def get_essential_cols(cls, columns):
        """
        Resolve the essential column groups against a concrete set of columns.

        :param columns: The available columns in a summary statistics table.

        :return: A list of essential columns present in the table.
        """
        columns = set(columns)
        essential_cols = []

        for alternatives in cls.essential_col_groups:
            for col_set in alternatives:
                if set(col_set).issubset(columns):
                    essential_cols.extend(
                        [c for c in col_set if c not in essential_cols]
                    )
                    break

        return essential_cols

    @classmethod
    def drop_na_from_essential_cols(cls, df):
        """
        Drop rows with missing values in columns that are essential for variant
        identity and effect-size interpretation.

        :param df: A pandas DataFrame containing summary statistics.

        :return: A DataFrame with missing essential values removed.
        """
        essential_cols = cls.get_essential_cols(df.columns)

        if len(essential_cols) > 0:
            return df.dropna(subset=essential_cols)

        warnings.warn(
            "Could not identify any essential summary statistics columns; "
            "no rows were dropped for missing values."
        )
        return df

    @classmethod
    def format_table(cls, df):
        """
        Format a magenpy summary statistics table for output.

        :param df: A pandas DataFrame with magenpy-standard column names.

        :return: A DataFrame with format-specific column names.
        """
        return df.rename(columns=cls.output_col_name_converter)

    def parse(self, file_name, drop_na=True):
        """
        Parse a summary statistics file.
        :param file_name: The path to the summary statistics file.
        :param drop_na: If True, drop any entries with missing values.

        :return: A pandas DataFrame containing the parsed summary statistics.
        """

        df = pd.read_csv(file_name, **self.read_csv_kwargs)

        if self.col_name_converter is not None:
            df.rename(columns=self.col_name_converter, inplace=True)

        try:
            df["POS"] = df["POS"].astype(np.int32)
        except KeyError:
            pass

        if drop_na:
            df = self.drop_na_from_essential_cols(df)

        return df

__init__(col_name_converter=None, **read_csv_kwargs)

Initialize the summary statistics parser.

Parameters:

Name Type Description Default
col_name_converter

A dictionary/string mapping column names in the original table to magenpy's column names for the various summary statistics. If a string, it should be a comma-separated list of key-value pairs (e.g. 'rsid=SNP,pos=POS').

 None
read_csv_kwargs

Keyword arguments to pass to pandas' read_csv

 {}
Source code in magenpy/parsers/sumstats_parsers.py 
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
def __init__(self, col_name_converter=None, **read_csv_kwargs):
    """
    Initialize the summary statistics parser.

    :param col_name_converter: A dictionary/string mapping column names
    in the original table to magenpy's column names for the various
    summary statistics. If a string, it should be a comma-separated list of
    key-value pairs (e.g. 'rsid=SNP,pos=POS').
    :param read_csv_kwargs: Keyword arguments to pass to pandas' read_csv
    """

    if isinstance(col_name_converter, str):
        self.col_name_converter = {
            k: v
            for entry in col_name_converter.split(",")
            for k, v in [entry.strip().split("=")]
            if len(entry.strip()) > 0
        }
    else:
        self.col_name_converter = col_name_converter

    self.read_csv_kwargs = read_csv_kwargs

    # If the delimiter is not specified, assume whitespace by default:
    if (
        "sep" not in self.read_csv_kwargs
        and "delimiter" not in self.read_csv_kwargs
    ):
        self.read_csv_kwargs["sep"] = r"\s+"

drop_na_from_essential_cols(df) classmethod

Drop rows with missing values in columns that are essential for variant identity and effect-size interpretation.

Parameters:

Name Type Description Default
df

A pandas DataFrame containing summary statistics.

 required

Returns:

Type Description

A DataFrame with missing essential values removed.
Source code in magenpy/parsers/sumstats_parsers.py 
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
@classmethod
def drop_na_from_essential_cols(cls, df):
    """
    Drop rows with missing values in columns that are essential for variant
    identity and effect-size interpretation.

    :param df: A pandas DataFrame containing summary statistics.

    :return: A DataFrame with missing essential values removed.
    """
    essential_cols = cls.get_essential_cols(df.columns)

    if len(essential_cols) > 0:
        return df.dropna(subset=essential_cols)

    warnings.warn(
        "Could not identify any essential summary statistics columns; "
        "no rows were dropped for missing values."
    )
    return df

format_table(df) classmethod

Format a magenpy summary statistics table for output.

Parameters:

Name Type Description Default
df

A pandas DataFrame with magenpy-standard column names.

 required

Returns:

Type Description

A DataFrame with format-specific column names.
Source code in magenpy/parsers/sumstats_parsers.py 
158
159
160
161
162
163
164
165
166
167
@classmethod
def format_table(cls, df):
    """
    Format a magenpy summary statistics table for output.

    :param df: A pandas DataFrame with magenpy-standard column names.

    :return: A DataFrame with format-specific column names.
    """
    return df.rename(columns=cls.output_col_name_converter)

get_essential_col_groups() classmethod

Essential columns are encoded as groups of alternatives. Each group must be satisfied by at least one of its alternatives.

Returns:

Type Description

A tuple of essential column alternative groups.
Source code in magenpy/parsers/sumstats_parsers.py 
105
106
107
108
109
110
111
112
113
@classmethod
def get_essential_col_groups(cls):
    """
    Essential columns are encoded as groups of alternatives. Each group must
    be satisfied by at least one of its alternatives.

    :return: A tuple of essential column alternative groups.
    """
    return cls.essential_col_groups

get_essential_cols(columns) classmethod

Resolve the essential column groups against a concrete set of columns.

Parameters:

Name Type Description Default
columns

The available columns in a summary statistics table.

 required

Returns:

Type Description

A list of essential columns present in the table.
Source code in magenpy/parsers/sumstats_parsers.py 
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
@classmethod
def get_essential_cols(cls, columns):
    """
    Resolve the essential column groups against a concrete set of columns.

    :param columns: The available columns in a summary statistics table.

    :return: A list of essential columns present in the table.
    """
    columns = set(columns)
    essential_cols = []

    for alternatives in cls.essential_col_groups:
        for col_set in alternatives:
            if set(col_set).issubset(columns):
                essential_cols.extend(
                    [c for c in col_set if c not in essential_cols]
                )
                break

    return essential_cols

get_standard_cols() classmethod

Returns:

Type Description

The standard magenpy columns for this summary statistics format.
Source code in magenpy/parsers/sumstats_parsers.py 
 98
 99
100
101
102
103
@classmethod
def get_standard_cols(cls):
    """
    :return: The standard magenpy columns for this summary statistics format.
    """
    return list(cls.standard_cols)

parse(file_name, drop_na=True)

Parse a summary statistics file.

Parameters:

Name Type Description Default
file_name

The path to the summary statistics file.

 required
drop_na

If True, drop any entries with missing values.

 True

Returns:

Type Description

A pandas DataFrame containing the parsed summary statistics.
Source code in magenpy/parsers/sumstats_parsers.py 
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
def parse(self, file_name, drop_na=True):
    """
    Parse a summary statistics file.
    :param file_name: The path to the summary statistics file.
    :param drop_na: If True, drop any entries with missing values.

    :return: A pandas DataFrame containing the parsed summary statistics.
    """

    df = pd.read_csv(file_name, **self.read_csv_kwargs)

    if self.col_name_converter is not None:
        df.rename(columns=self.col_name_converter, inplace=True)

    try:
        df["POS"] = df["POS"].astype(np.int32)
    except KeyError:
        pass

    if drop_na:
        df = self.drop_na_from_essential_cols(df)

    return df

get_sumstats_parser(sumstats_format)

Get the parser class for a supported summary statistics format.

Parameters:

Name Type Description Default
sumstats_format

The summary statistics format name or alias.

 required

Returns:

Type Description

A SumstatsParser subclass.
Source code in magenpy/parsers/sumstats_parsers.py 
583
584
585
586
587
588
589
590
591
592
593
594
595
596
def get_sumstats_parser(sumstats_format):
    """
    Get the parser class for a supported summary statistics format.

    :param sumstats_format: The summary statistics format name or alias.

    :return: A SumstatsParser subclass.
    """
    try:
        return SUMSTATS_PARSER_REGISTRY[sumstats_format.lower()]
    except KeyError:
        raise KeyError(
            f"Parsers for summary statistics format {sumstats_format} are not implemented!"
        )