gwaslab 3.4.37__py3-none-any.whl → 3.4.39__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of gwaslab might be problematic. Click here for more details.

Files changed (57) hide show
  1. gwaslab/bd_common_data.py +6 -3
  2. gwaslab/bd_download.py +9 -9
  3. gwaslab/bd_get_hapmap3.py +43 -9
  4. gwaslab/data/formatbook.json +722 -721
  5. gwaslab/g_Log.py +22 -5
  6. gwaslab/g_Sumstats.py +110 -163
  7. gwaslab/g_SumstatsPair.py +76 -25
  8. gwaslab/g_SumstatsT.py +2 -2
  9. gwaslab/g_Sumstats_summary.py +3 -3
  10. gwaslab/g_version.py +10 -10
  11. gwaslab/hm_casting.py +36 -17
  12. gwaslab/hm_harmonize_sumstats.py +354 -221
  13. gwaslab/hm_rsid_to_chrpos.py +1 -1
  14. gwaslab/io_preformat_input.py +49 -43
  15. gwaslab/io_read_ldsc.py +49 -1
  16. gwaslab/io_to_formats.py +428 -295
  17. gwaslab/ldsc_irwls.py +198 -0
  18. gwaslab/ldsc_jackknife.py +514 -0
  19. gwaslab/ldsc_ldscore.py +417 -0
  20. gwaslab/ldsc_parse.py +294 -0
  21. gwaslab/ldsc_regressions.py +747 -0
  22. gwaslab/ldsc_sumstats.py +629 -0
  23. gwaslab/qc_check_datatype.py +3 -3
  24. gwaslab/qc_fix_sumstats.py +891 -778
  25. gwaslab/util_ex_calculate_ldmatrix.py +31 -13
  26. gwaslab/util_ex_gwascatalog.py +25 -25
  27. gwaslab/util_ex_ldproxyfinder.py +10 -10
  28. gwaslab/util_ex_ldsc.py +189 -0
  29. gwaslab/util_ex_process_ref.py +3 -3
  30. gwaslab/util_ex_run_coloc.py +26 -4
  31. gwaslab/util_in_calculate_gc.py +6 -6
  32. gwaslab/util_in_calculate_power.py +42 -43
  33. gwaslab/util_in_convert_h2.py +8 -8
  34. gwaslab/util_in_fill_data.py +30 -30
  35. gwaslab/util_in_filter_value.py +201 -74
  36. gwaslab/util_in_get_density.py +10 -10
  37. gwaslab/util_in_get_sig.py +445 -71
  38. gwaslab/viz_aux_annotate_plot.py +12 -12
  39. gwaslab/viz_aux_quickfix.py +42 -37
  40. gwaslab/viz_aux_reposition_text.py +10 -7
  41. gwaslab/viz_aux_save_figure.py +18 -8
  42. gwaslab/viz_plot_compare_af.py +32 -33
  43. gwaslab/viz_plot_compare_effect.py +63 -71
  44. gwaslab/viz_plot_miamiplot2.py +34 -26
  45. gwaslab/viz_plot_mqqplot.py +126 -75
  46. gwaslab/viz_plot_qqplot.py +11 -8
  47. gwaslab/viz_plot_regionalplot.py +36 -33
  48. gwaslab/viz_plot_rg_heatmap.py +28 -26
  49. gwaslab/viz_plot_stackedregional.py +40 -21
  50. gwaslab/viz_plot_trumpetplot.py +65 -61
  51. gwaslab-3.4.39.dist-info/LICENSE +674 -0
  52. {gwaslab-3.4.37.dist-info → gwaslab-3.4.39.dist-info}/METADATA +5 -4
  53. gwaslab-3.4.39.dist-info/RECORD +80 -0
  54. gwaslab-3.4.37.dist-info/RECORD +0 -72
  55. /gwaslab-3.4.37.dist-info/LICENSE → /gwaslab-3.4.39.dist-info/LICENSE_before_v3.4.39 +0 -0
  56. {gwaslab-3.4.37.dist-info → gwaslab-3.4.39.dist-info}/WHEEL +0 -0
  57. {gwaslab-3.4.37.dist-info → gwaslab-3.4.39.dist-info}/top_level.txt +0 -0
gwaslab/data/formatbook.json CHANGED
@@ -1,98 +1,4 @@
1
1
  {
2
- "metal": {
3
- "meta_data": {
4
- "format_name": "metal",
5
- "format_source": "https://genome.sph.umich.edu/wiki/METAL_Documentation",
6
- "format_version": "20220726"
7
- },
8
- "format_dict": {
9
- "MarkerName": "SNPID",
10
- "Allele1": "EA",
11
- "Allele2": "NEA",
12
- "Freq1": "EAF",
13
- "Effect": "BETA",
14
- "StdErr": "SE",
15
- "P-value": "P",
16
- "Direction": "DIRECTION"
17
- }
18
- },
19
- "gwascatalog_hm": {
20
- "meta_data": {
21
- "format_name": "gwascatalog_hm",
22
- "format_source": "https://www.ebi.ac.uk/gwas/docs/methods/summary-statistics",
23
- "format_version": 20220806
24
- },
25
- "format_dict": {
26
- "hm_variant_id": "SNPID",
27
- "chromosome": "CHR",
28
- "base_pair_location": "POS",
29
- "hm_other_allele": "NEA",
30
- "hm_effect_allele": "EA",
31
- "hm_beta": "BETA",
32
- "hm_effect_allele_frequency": "EAF",
33
- "standard_error": "SE",
34
- "p-value": "P",
35
- "hm_odds_ratio": "OR",
36
- "hm_ci_lower": "OR_95L",
37
- "hm_ci_upper": "OR_95U"
38
- }
39
- },
40
- "gwascatalog": {
41
- "meta_data": {
42
- "format_name": "gwascatalog",
43
- "format_source": "https://www.ebi.ac.uk/gwas/docs/methods/summary-statistics",
44
- "format_version": "20220726"
45
- },
46
- "format_dict": {
47
- "variant_id": "SNPID",
48
- "chromosome": "CHR",
49
- "base_pair_location": "POS",
50
- "other_allele": "NEA",
51
- "effect_allele": "EA",
52
- "beta": "BETA",
53
- "effect_allele_frequency": "EAF",
54
- "standard_error": "SE",
55
- "p-value": "P",
56
- "odds_ratio": "OR",
57
- "ci_lower": "OR_95L",
58
- "ci_upper": "OR_95U"
59
- }
60
- },
61
- "plink_pvar": {
62
- "meta_data": {
63
- "format_name": "plink_pvar",
64
- "format_source_1": "https://www.cog-genomics.org/plink/2.0/formats#pvar",
65
- "format_version": "20231124",
66
- "format_cite_name": "pvar",
67
- "format_separator": "\t",
68
- "format_na": ".",
69
- "format_comment": "#",
70
- "format_header": true,
71
- "format_col_order": [
72
- "POS",
73
- "SNPID",
74
- "NEA",
75
- "EA",
76
- "QUAL",
77
- "FILTER",
78
- "INFO",
79
- "FORMAT",
80
- "CM"
81
- ],
82
- "last_check_date": "20231124"
83
- },
84
- "format_dict": {
85
- "POS": "POS",
86
- "ID": "SNPID",
87
- "REF": "NEA",
88
- "ALT": "EA",
89
- "QUAL": "QUAL",
90
- "FILTER": "FILTER",
91
- "INFO": "INFO",
92
- "FORMAT": "FORMAT",
93
- "CM": "CM"
94
- }
95
- },
96
2
  "plink": {
97
3
  "meta_data": {
98
4
  "format_name": ".assoc, .assoc.fisher, .assoc.linear, .assoc.logistic, .assoc.dosage",
@@ -116,109 +22,6 @@
116
22
  "NMISS": "N"
117
23
  }
118
24
  },
119
- "plink_logistic": {
120
- "meta_data": {
121
- "format_name": ".assoc.logistic",
122
- "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
123
- "format_version": "Stable (beta 6.26, 2 Apr)",
124
- "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
125
- },
126
- "format_dict": {
127
- "SNP": "SNPID",
128
- "CHR": "CHR",
129
- "BP": "POS",
130
- "A2": "NEA",
131
- "A1": "EA",
132
- "OR": "OR",
133
- "L95": "OR_95L",
134
- "H95": "OR_95U",
135
- "SE": "SE",
136
- "P": "P",
137
- "STAT": "T",
138
- "CHISQ": "CHISQ",
139
- "NMISS": "N"
140
- }
141
- },
142
- "regenie": {
143
- "meta_data": {
144
- "format_name": "regenie",
145
- "format_source_1": "https://rgcgithub.github.io/regenie/",
146
- "format_source_2": "https://github.com/rgcgithub/regenie/blob/master/example/test_bin_out_firth_Y1.regenie",
147
- "format_version": "20220726",
148
- "format_cite_name": "REGENIE",
149
- "format_separator": " ",
150
- "format_na": "NA",
151
- "format_comment": null,
152
- "format_col_order": [
153
- "CHROM",
154
- "GENPOS",
155
- "ID",
156
- "ALLELE0",
157
- "ALLELE1",
158
- "A1FREQ",
159
- "N",
160
- "TEST",
161
- "BETA",
162
- "SE",
163
- "CHISQ",
164
- "LOG10P"
165
- ],
166
- "last_check_date": 20230501
167
- },
168
- "format_dict": {
169
- "ID": "SNPID",
170
- "CHROM": "CHR",
171
- "GENPOS": "POS",
172
- "ALLELE0": "NEA",
173
- "ALLELE1": "EA",
174
- "A1FREQ": "EAF",
175
- "N": "N",
176
- "INFO": "INFO",
177
- "BETA": "BETA",
178
- "SE": "SE",
179
- "CHISQ": "CHISQ",
180
- "LOG10P": "MLOG10P"
181
- }
182
- },
183
- "mtag": {
184
- "meta_data": {
185
- "format_name": "mtag",
186
- "format_source": "https://github.com/JonJala/mtag/wiki/Tutorial-1:-The-Basics",
187
- "format_version": "v1.0.8",
188
- "format_separator": "\t",
189
- "format_cite_name": "MTAG v1.0.8",
190
- "format_comment": null,
191
- "format_na": null,
192
- "format_col_order": [
193
- "snpid",
194
- "chr",
195
- "bpos",
196
- "a1",
197
- "beta",
198
- "a2",
199
- "freq",
200
- "beta",
201
- "se",
202
- "z",
203
- "pval",
204
- "p_value",
205
- "n"
206
- ]
207
- },
208
- "format_dict": {
209
- "snpid": "rsID",
210
- "chr": "CHR",
211
- "bpos": "POS",
212
- "a2": "NEA",
213
- "a1": "EA",
214
- "freq": "EAF",
215
- "n": "N",
216
- "beta": "BETA",
217
- "se": "SE",
218
- "pval": "P",
219
- "z": "Z"
220
- }
221
- },
222
25
  "vcf": {
223
26
  "meta_data": {
224
27
  "format_name": "vcf",
@@ -264,53 +67,26 @@
264
67
  "EZ": "Z"
265
68
  }
266
69
  },
267
- "plink_assoc": {
70
+ "bolt_lmm": {
268
71
  "meta_data": {
269
- "format_name": ".assoc, .assoc.fisher",
270
- "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
271
- "format_version": "Stable (beta 6.26, 2 Apr)",
272
- "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
72
+ "format_name": ".stats",
73
+ "format_source": "https://alkesgroup.broadinstitute.org/BOLT-LMM/BOLT-LMM_manual.html",
74
+ "format_version": "v2.4 (July 22, 2022)",
75
+ "software_license": "BOLT-LMM is free software under the GNU General Public License v3.0 (GPLv3).",
76
+ "format_citation": "Loh, P. R., Tucker, G., Bulik-Sullivan, B. K., Vilhjalmsson, B. J., Finucane, H. K., Salem, R. M., ... & Price, A. L. (2015). Efficient Bayesian mixed-model analysis increases association power in large cohorts. Nature genetics, 47(3), 284-290."
273
77
  },
274
78
  "format_dict": {
275
79
  "SNP": "SNPID",
276
80
  "CHR": "CHR",
277
81
  "BP": "POS",
278
- "A2": "NEA",
279
- "A1": "EA",
280
- "OR": "OR",
281
- "L95": "OR_95L",
282
- "H95": "OR_95U",
283
- "SE": "SE",
284
- "P": "P",
285
- "CHISQ": "CHISQ"
286
- }
287
- },
288
- "plink2_logistic": {
289
- "meta_data": {
290
- "format_name": "PLINK2 .glm.firth, .glm.logistic[.hybrid]",
291
- "format_source": "https://www.cog-genomics.org/plink/2.0/formats",
292
- "format_version": "Alpha 3.3 final (3 Jun)",
293
- "last_check_date": 20220806
294
- },
295
- "format_dict": {
296
- "ID": "SNPID",
297
- "#CHROM": "CHR",
298
- "POS": "POS",
299
- "REF": "REF",
300
- "ALT": "ALT",
301
- "A1": "EA",
302
- "OBS_CT": "N",
303
- "A1_FREQ": "EAF",
82
+ "ALLELE0": "NEA",
83
+ "ALLELE1": "EA",
84
+ "A1FREQ": "EAF",
304
85
  "BETA": "BETA",
305
- "LOG(OR)_SE": "SE",
306
86
  "SE": "SE",
307
- "Z_STAT": "Z",
308
- "P": "P",
309
- "LOG10_P": "MLOG10P",
310
- "MACH_R2": "INFO",
311
- "OR": "OR",
312
- "L95": "OR_95L",
313
- "U95": "OR_95U"
87
+ "P_BOLT_LMM": "P",
88
+ "INFO": "INFO",
89
+ "CHISQ_BOLT_LMM": "CHISQ"
314
90
  }
315
91
  },
316
92
  "cojo": {
@@ -340,132 +116,178 @@
340
116
  "N": "N"
341
117
  }
342
118
  },
343
- "plink_linear": {
119
+ "mrmega": {
344
120
  "meta_data": {
345
- "format_name": ".assoc.linear",
346
- "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
347
- "format_version": "Stable (beta 6.26, 2 Apr)",
348
- "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
349
- },
350
- "format_dict": {
351
- "SNP": "SNPID",
352
- "CHR": "CHR",
353
- "BP": "POS",
354
- "A2": "NEA",
355
- "A1": "EA",
356
- "BETA": "BETA",
357
- "L95": "BETA_95L",
358
- "H95": "BETA_95U",
359
- "SE": "SE",
360
- "P": "P",
361
- "STAT": "T",
362
- "CHISQ": "CHISQ",
363
- "NMISS": "N"
364
- }
365
- },
366
- "plink2_firth": {
367
- "meta_data": {
368
- "format_name": "PLINK2 .glm.firth, .glm.logistic[.hybrid]",
369
- "format_source": "https://www.cog-genomics.org/plink/2.0/formats",
370
- "format_version": "Alpha 3.3 final (3 Jun)",
121
+ "format_name": "mrmega",
122
+ "format_source": "https://genomics.ut.ee/en/tools",
123
+ "format_version": "ver0.2",
371
124
  "last_check_date": 20220806
372
125
  },
373
126
  "format_dict": {
374
- "ID": "SNPID",
375
- "#CHROM": "CHR",
376
- "POS": "POS",
377
- "REF": "REF",
378
- "ALT": "ALT",
379
- "A1": "EA",
380
- "OBS_CT": "N",
381
- "A1_FREQ": "EAF",
382
- "BETA": "BETA",
383
- "LOG(OR)_SE": "SE",
384
- "SE": "SE",
385
- "Z_STAT": "Z",
386
- "P": "P",
387
- "LOG10_P": "MLOG10P",
388
- "MACH_R2": "INFO",
389
- "OR": "OR",
390
- "L95": "OR_95L",
391
- "U95": "OR_95U"
392
- }
393
- },
394
- "pheweb": {
395
- "meta_data": {
396
- "format_name": "pheweb",
397
- "format_source": "https://github.com/statgen/pheweb",
398
- "format_version": "20220928"
399
- },
400
- "format_dict": {
401
- "rsids": "rsID",
402
- "chrom": "CHR",
403
- "pos": "POS",
404
- "ref": "NEA",
405
- "alt": "EA",
406
- "beta": "BETA",
407
- "af": "EAF",
408
- "sebeta": "SE",
409
- "pval": "P",
410
- "or": "OR",
411
- "r2": "INFO",
412
- "num_samples": "n"
127
+ "MarkerName ": "SNPID",
128
+ "Chromosome": "CHR",
129
+ "Position": "POS",
130
+ "NEA": "NEA",
131
+ "EA": "EA",
132
+ "EAF": "EAF",
133
+ "Nsample": "N",
134
+ "Effects": "DIRECTION",
135
+ "chisq_association": "CHISQ",
136
+ "ndf_association": "ndf_association",
137
+ "P-value_association": "P"
413
138
  }
414
139
  },
415
- "ssf": {
140
+ "auto": {
416
141
  "meta_data": {
417
- "format_name": "ssf",
418
- "format_source": "https://www.biorxiv.org/content/10.1101/2022.07.15.500230v1.full",
419
- "format_cite_name": "GWAS-SSF v0.1",
142
+ "format_name": "auto",
420
143
  "format_separator": "\t",
421
144
  "format_na": "#NA",
422
145
  "format_comment": null,
423
- "format_col_order": [
424
- "chromosome",
425
- "base_pair_location",
426
- "effect_allele",
427
- "other_allele",
428
- "beta",
429
- "odds_ratio",
430
- "hazard_ratio",
431
- "standard_error",
432
- "effect_allele_frequency",
433
- "p_value",
434
- "neg_log_10_p_value",
435
- "ci_upper",
436
- "ci_lower",
437
- "rsid",
438
- "variant_id",
439
- "info",
440
- "ref_allele",
441
- "n"
442
- ],
443
146
  "format_version": 20230328
444
147
  },
445
148
  "format_dict": {
446
149
  "variant_id": "SNPID",
150
+ "SNP": "SNPID",
151
+ "snp": "SNPID",
152
+ "SNPID": "SNPID",
153
+ "snpid": "SNPID",
154
+ "MARKERNAME": "SNPID",
155
+ "MARKER": "SNPID",
156
+ "markername": "SNPID",
157
+ "marker": "SNPID",
158
+ "RSID": "rsID",
447
159
  "rsid": "rsID",
160
+ "hm_rsID": "rsID",
161
+ "rsID": "SNPID",
448
162
  "chromosome": "CHR",
163
+ "Chromosome": "CHR",
164
+ "CHROMOSOME": "CHR",
165
+ "CHR": "CHR",
166
+ "chr": "CHR",
167
+ "Chr": "CHR",
168
+ "CHROM": "CHR",
169
+ "Chrom": "CHR",
170
+ "chrom": "CHR",
449
171
  "base_pair_location": "POS",
450
- "other_allele": "NEA",
172
+ "POS": "POS",
173
+ "Pos": "POS",
174
+ "pos": "POS",
175
+ "BP": "POS",
176
+ "bp": "POS",
177
+ "bpos": "POS",
178
+ "REF": "NEA",
179
+ "Ref": "NEA",
180
+ "reference_allele": "NEA",
181
+ "reference": "NEA",
182
+ "NEA": "NEA",
183
+ "nea": "NEA",
184
+ "non_effect_allele": "NEA",
185
+ "NON_EFFECT_ALLELE": "NEA",
186
+ "A0": "NEA",
187
+ "a0": "NEA",
188
+ "ALLELE0": "NEA",
189
+ "Allele0": "NEA",
190
+ "allele0": "NEA",
191
+ "ALLELE_0": "NEA",
192
+ "Allele_0": "NEA",
193
+ "allele_0": "NEA",
194
+ "A2": "NEA",
195
+ "a2": "NEA",
196
+ "ALLELE2": "NEA",
197
+ "Allele2": "NEA",
198
+ "allele2": "NEA",
199
+ "ALLELE_2": "NEA",
200
+ "Allele_2": "NEA",
201
+ "allele_2": "NEA",
202
+ "alternative_allele": "EA",
203
+ "alternative": "EA",
204
+ "Alt": "EA",
205
+ "ALT": "EA",
206
+ "A1": "EA",
207
+ "a1": "EA",
451
208
  "effect_allele": "EA",
209
+ "EA": "EA",
210
+ "ea": "EA",
211
+ "ALLELE1": "EA",
212
+ "Allele1": "EA",
213
+ "allele1": "EA",
214
+ "ALLELE_1": "EA",
215
+ "Allele_1": "EA",
216
+ "allele_1": "EA",
217
+ "Frq": "EAF",
218
+ "FRQ": "EAF",
219
+ "frq": "EAF",
220
+ "Frequency": "EAF",
221
+ "FREQ": "EAF",
222
+ "Freq": "EAF",
223
+ "Freq1": "EAF",
224
+ "freq": "EAF",
225
+ "A1FREQ": "EAF",
452
226
  "effect_allele_frequency": "EAF",
227
+ "allelefrequency_effect": "EAF",
228
+ "eaf": "EAF",
229
+ "EAF": "EAF",
230
+ "AF1": "EAF",
231
+ "maf": "MAF",
232
+ "Maf": "MAF",
233
+ "MAF": "MAF",
453
234
  "n": "N",
235
+ "N": "N",
236
+ "sample_size": "N",
237
+ "TotalSampleSize": "N",
238
+ "Nsample": "N",
239
+ "num_samples": "N",
454
240
  "beta": "BETA",
241
+ "BETA": "BETA",
242
+ "Beta": "BETA",
243
+ "Effect": "BETA",
244
+ "B": "BETA",
245
+ "b": "BETA",
246
+ "effect_weight": "BETA",
247
+ "betase": "SE",
248
+ "sebeta": "SE",
249
+ "se": "SE",
250
+ "SE": "SE",
455
251
  "standard_error": "SE",
252
+ "StdErr": "SE",
456
253
  "p_value": "P",
254
+ "PVAL": "P",
255
+ "Pval": "P",
256
+ "p": "P",
257
+ "P": "P",
258
+ "P.value": "P",
259
+ "p.value": "P",
260
+ "P_BOLT_LMM": "P",
457
261
  "neg_log_10_p_value": "MLOG10P",
262
+ "MLOG10P": "MLOG10P",
263
+ "LOG10_P": "MLOG10P",
264
+ "chisq": "CHISQ",
265
+ "chisq_association": "CHISQ",
266
+ "CHISQ_BOLT_LMM": "CHISQ",
267
+ "Z": "Z",
268
+ "z": "Z",
269
+ "Direction": "DIRECTION",
270
+ "DIRECTION": "DIRECTION",
458
271
  "info": "INFO",
272
+ "INFO": "INFO",
273
+ "Rsq": "INFO",
274
+ "R2": "INFO",
275
+ "r2": "INFO",
276
+ "imputationInfo": "INFO",
459
277
  "odds_ratio": "OR",
278
+ "OR": "OR",
460
279
  "hazard_ratio": "HR",
461
280
  "ci_lower": "OR_95L",
462
- "ci_upper": "OR_95U"
281
+ "OR_95L": "OR_95L",
282
+ "ci_upper": "OR_95U",
283
+ "OR_95U": "OR_95U",
284
+ "STATUS": "STATUS"
463
285
  }
464
286
  },
465
- "plink_fisher": {
287
+ "plink_dosage": {
466
288
  "meta_data": {
467
- "format_name": ".assoc, .assoc.fisher",
468
- "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
289
+ "format_name": ".assoc.dosage",
290
+ "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc_dosage",
469
291
  "format_version": "Stable (beta 6.26, 2 Apr)",
470
292
  "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
471
293
  },
@@ -475,148 +297,109 @@
475
297
  "BP": "POS",
476
298
  "A2": "NEA",
477
299
  "A1": "EA",
300
+ "FRQ": "EAF",
478
301
  "OR": "OR",
479
- "L95": "OR_95L",
480
- "H95": "OR_95U",
481
- "SE": "SE",
482
- "P": "P",
483
- "CHISQ": "CHISQ"
484
- }
485
- },
486
- "fastgwa": {
487
- "meta_data": {
488
- "format_name": "fastgwa",
489
- "format_source": "https://yanglab.westlake.edu.cn/software/gcta/#fastGWA",
490
- "format_source2": "https://yanglab.westlake.edu.cn/software/gcta/#fastGWA-GLMM",
491
- "format_version": "20220726"
492
- },
493
- "format_dict": {
494
- "SNP": "SNPID",
495
- "CHR": "CHR",
496
- "POS": "POS",
497
- "A2": "NEA",
498
- "A1": "EA",
499
- "AF1": "EAF",
500
302
  "BETA": "BETA",
303
+ "INFO": "INFO",
501
304
  "SE": "SE",
502
305
  "P": "P"
503
306
  }
504
307
  },
505
- "template": {
308
+ "gwascatalog_hm": {
506
309
  "meta_data": {
507
- "format_name": "",
508
- "format_source": "",
509
- "format_version": "20220726"
310
+ "format_name": "gwascatalog_hm",
311
+ "format_source": "https://www.ebi.ac.uk/gwas/docs/methods/summary-statistics",
312
+ "format_version": 20220806
510
313
  },
511
314
  "format_dict": {
512
- "": "OR_95U"
315
+ "hm_variant_id": "SNPID",
316
+ "chromosome": "CHR",
317
+ "base_pair_location": "POS",
318
+ "hm_other_allele": "NEA",
319
+ "hm_effect_allele": "EA",
320
+ "hm_beta": "BETA",
321
+ "hm_effect_allele_frequency": "EAF",
322
+ "standard_error": "SE",
323
+ "p-value": "P",
324
+ "hm_odds_ratio": "OR",
325
+ "hm_ci_lower": "OR_95L",
326
+ "hm_ci_upper": "OR_95U"
513
327
  }
514
328
  },
515
- "gwaslab": {
329
+ "plink_assoc": {
516
330
  "meta_data": {
517
- "format_name": "gwaslab",
518
- "format_source": "https://cloufield.github.io/gwaslab/",
519
- "format_version": "20231220_v4"
331
+ "format_name": ".assoc, .assoc.fisher",
332
+ "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
333
+ "format_version": "Stable (beta 6.26, 2 Apr)",
334
+ "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
520
335
  },
521
336
  "format_dict": {
522
- "SNPID": "SNPID",
523
- "rsID": "rsID",
337
+ "SNP": "SNPID",
524
338
  "CHR": "CHR",
525
- "POS": "POS",
526
- "NEA": "NEA",
527
- "EA": "EA",
528
- "N": "N",
529
- "BETA": "BETA",
530
- "SE": "SE",
531
- "P": "P",
532
- "MLOG10P": "MLOG10P",
533
- "INFO": "INFO",
534
- "OR": "OR",
535
- "OR_95L": "OR_95L",
536
- "OR_95U": "OR_95U",
537
- "MLOG10": "MLOG10",
538
- "CHISQ": "CHISQ",
539
- "Z": "Z",
540
- "T": "T",
541
- "F": "F",
542
- "HR": "HR",
543
- "HR_95L": "HR_95L",
544
- "HR_95U": "HR_95U",
545
- "P_HET": "P_HET",
546
- "I2": "I2",
547
- "SNPR2": "SNPR2",
548
- "DOF": "DOF",
549
- "N_CASE": "N_CASE",
550
- "N_CONTROL": "N_CONTROL",
551
- "MAF": "MAF",
552
- "DIRECTION": "DIRECTION",
553
- "STATUS": "STATUS",
554
- "REF": "REF",
555
- "ALT": "ALT"
556
- }
557
- },
558
- "plink2_linear": {
559
- "meta_data": {
560
- "format_name": "PLINK2 .glm.linear",
561
- "format_source": "https://www.cog-genomics.org/plink/2.0/formats",
562
- "format_version": "Alpha 3.3 final (3 Jun)",
563
- "last_check_date": 20220806
564
- },
565
- "format_dict": {
566
- "ID": "SNPID",
567
- "CHROM": "CHR",
568
- "POS": "POS",
569
- "REF": "REF",
570
- "ALT": "ALT",
339
+ "BP": "POS",
340
+ "A2": "NEA",
571
341
  "A1": "EA",
572
- "OBS_CT": "N",
573
- "A1_FREQ": "EAF",
574
- "BETA": "BETA",
575
- "LOG(OR)_SE": "SE",
342
+ "OR": "OR",
343
+ "L95": "OR_95L",
344
+ "H95": "OR_95U",
576
345
  "SE": "SE",
577
- "T_STAT": "T",
578
346
  "P": "P",
579
- "LOG10_P": "MLOG10P",
580
- "MACH_R2": "INFO",
581
- "L95": "BETA_95L",
582
- "U95": "BETA_95U"
347
+ "CHISQ": "CHISQ"
583
348
  }
584
349
  },
585
- "plink_bim": {
350
+ "plink_psam": {
586
351
  "meta_data": {
587
- "format_name": "plink_bim",
588
- "format_source_1": "https://www.cog-genomics.org/plink/1.9/formats#bim",
352
+ "format_name": "plink_psam",
353
+ "format_source_1": "https://www.cog-genomics.org/plink/2.0/formats#psam",
589
354
  "format_version": "20231124",
590
- "format_cite_name": "bim",
355
+ "format_cite_name": "psam",
591
356
  "format_separator": "\t",
592
357
  "format_na": null,
593
358
  "format_comment": null,
594
- "format_header": null,
359
+ "format_header": true,
595
360
  "format_datatype": {
596
- "CHR": "category",
597
- "SNPID": "string",
598
- "CM": "float",
599
- "POS": "int",
600
- "NEA": "string",
601
- "EA": "string"
361
+ "IID": "string",
362
+ "SID": "string",
363
+ "PAT": "string",
364
+ "MAT": "string",
365
+ "SEX": "category"
602
366
  },
603
367
  "format_col_order": [
604
- "CHR",
605
- "SNPID",
606
- "CM",
607
- "POS",
608
- "NEA",
609
- "EA"
368
+ "IID",
369
+ "SID",
370
+ "PAT",
371
+ "MAT",
372
+ "SEX"
610
373
  ],
611
374
  "last_check_date": "20231124"
612
375
  },
613
376
  "format_dict": {
614
- "0": "CHR",
615
- "1": "SNPID",
616
- "2": "CM",
617
- "3": "POS",
618
- "4": "NEA",
619
- "5": "EA"
377
+ "#IID": "IID",
378
+ "SID": "SID",
379
+ "PAT": "PAT",
380
+ "MAT": "MAT",
381
+ "SEX": "SEX"
382
+ }
383
+ },
384
+ "plink_fisher": {
385
+ "meta_data": {
386
+ "format_name": ".assoc, .assoc.fisher",
387
+ "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
388
+ "format_version": "Stable (beta 6.26, 2 Apr)",
389
+ "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
390
+ },
391
+ "format_dict": {
392
+ "SNP": "SNPID",
393
+ "CHR": "CHR",
394
+ "BP": "POS",
395
+ "A2": "NEA",
396
+ "A1": "EA",
397
+ "OR": "OR",
398
+ "L95": "OR_95L",
399
+ "H95": "OR_95U",
400
+ "SE": "SE",
401
+ "P": "P",
402
+ "CHISQ": "CHISQ"
620
403
  }
621
404
  },
622
405
  "regenie_gene": {
@@ -661,170 +444,110 @@
661
444
  "EXTRA": "DOF"
662
445
  }
663
446
  },
664
- "saige": {
665
- "meta_data": {
666
- "format_name": "saige",
667
- "format_source": "https://saigegit.github.io//SAIGE-doc/docs/single_step2.html",
668
- "format_version": "v1.1.3",
669
- "last_check_date": 20220806
670
- },
671
- "format_dict": {
672
- "SNPID": "SNPID",
673
- "CHR": "CHR",
674
- "POS": "POS",
675
- "Allele1": "NEA",
676
- "Allele2": "EA",
677
- "AF_Allele2": "EAF",
678
- "N": "N",
679
- "BETA": "BETA",
680
- "SE": "SE",
681
- "p.value": "P",
682
- "imputationInfo": "INFO"
683
- }
684
- },
685
- "bolt_lmm": {
447
+ "metal": {
686
448
  "meta_data": {
687
- "format_name": ".stats",
688
- "format_source": "https://alkesgroup.broadinstitute.org/BOLT-LMM/BOLT-LMM_manual.html",
689
- "format_version": "v2.4 (July 22, 2022)",
690
- "software_license": "BOLT-LMM is free software under the GNU General Public License v3.0 (GPLv3).",
691
- "format_citation": "Loh, P. R., Tucker, G., Bulik-Sullivan, B. K., Vilhjalmsson, B. J., Finucane, H. K., Salem, R. M., ... & Price, A. L. (2015). Efficient Bayesian mixed-model analysis increases association power in large cohorts. Nature genetics, 47(3), 284-290."
449
+ "format_name": "metal",
450
+ "format_source": "https://genome.sph.umich.edu/wiki/METAL_Documentation",
451
+ "format_version": "20220726"
692
452
  },
693
453
  "format_dict": {
694
- "SNP": "SNPID",
695
- "CHR": "CHR",
696
- "BP": "POS",
697
- "ALLELE0": "NEA",
698
- "ALLELE1": "EA",
699
- "A1FREQ": "EAF",
700
- "BETA": "BETA",
701
- "SE": "SE",
702
- "P_BOLT_LMM": "P",
703
- "INFO": "INFO",
704
- "CHISQ_BOLT_LMM": "CHISQ"
454
+ "MarkerName": "SNPID",
455
+ "Allele1": "EA",
456
+ "Allele2": "NEA",
457
+ "Freq1": "EAF",
458
+ "Effect": "BETA",
459
+ "StdErr": "SE",
460
+ "P-value": "P",
461
+ "Direction": "DIRECTION"
705
462
  }
706
463
  },
707
- "plink_psam": {
464
+ "plink_fam": {
708
465
  "meta_data": {
709
- "format_name": "plink_psam",
710
- "format_source_1": "https://www.cog-genomics.org/plink/2.0/formats#psam",
466
+ "format_name": "plink_fam",
467
+ "format_source_1": "https://www.cog-genomics.org/plink/1.9/formats#fam",
711
468
  "format_version": "20231124",
712
- "format_cite_name": "psam",
469
+ "format_cite_name": "fam",
713
470
  "format_separator": "\t",
714
471
  "format_na": null,
715
472
  "format_comment": null,
716
- "format_header": true,
473
+ "format_header": null,
717
474
  "format_datatype": {
475
+ "FID": "string",
718
476
  "IID": "string",
719
- "SID": "string",
720
477
  "PAT": "string",
721
478
  "MAT": "string",
722
- "SEX": "category"
479
+ "SEX": "category",
480
+ "PHENO1": "category"
723
481
  },
724
482
  "format_col_order": [
483
+ "FID",
725
484
  "IID",
726
- "SID",
727
485
  "PAT",
728
486
  "MAT",
729
- "SEX"
487
+ "SEX",
488
+ "PHENO1"
730
489
  ],
731
490
  "last_check_date": "20231124"
732
491
  },
733
492
  "format_dict": {
734
- "#IID": "IID",
735
- "SID": "SID",
736
- "PAT": "PAT",
737
- "MAT": "MAT",
738
- "SEX": "SEX"
739
- }
740
- },
741
- "pgscatalog_hm": {
742
- "meta_data": {
743
- "format_name": "pgscatalog_hm Harmonized File",
744
- "format_source": "https://www.pgscatalog.org/downloads/",
745
- "format_version": "20220726"
746
- },
747
- "format_dict": {
748
- "hm_rsID": "rsID",
749
- "hm_chr": "CHR",
750
- "hm_pos": "POS",
751
- "hm_inferOtherAllele": "NEA",
752
- "other_allele": "NEA",
753
- "effect_allele": "EA",
754
- "allelefrequency_effect": "EAF",
755
- "effect_weight": "BETA",
756
- "OR": "OR"
493
+ "0": "FID",
494
+ "1": "IID",
495
+ "2": "PAT",
496
+ "3": "MAT",
497
+ "4": "SEX",
498
+ "5": "PHENO1"
757
499
  }
758
500
  },
759
- "ldsc": {
501
+ "mtag": {
760
502
  "meta_data": {
761
- "format_name": "ldsc",
762
- "format_source": "https://github.com/bulik/ldsc/wiki/Summary-Statistics-File-Format",
763
- "format_source2": "https://github.com/bulik/ldsc/blob/master/munge_sumstats.py",
764
- "format_version": 20150306
765
- },
766
- "format_dict": {
767
- "SNP": "rsID",
768
- "A2": "NEA",
769
- "A1": "EA",
770
- "Frq": "EAF",
771
- "N": "N",
772
- "Beta": "BETA",
773
- "P": "P",
774
- "Z": "Z",
775
- "INFO": "INFO",
776
- "OR": "OR",
777
- "CHR": "CHR",
778
- "POS": "POS"
779
- }
780
- },
781
- "plink_fam": {
782
- "meta_data": {
783
- "format_name": "plink_fam",
784
- "format_source_1": "https://www.cog-genomics.org/plink/1.9/formats#fam",
785
- "format_version": "20231124",
786
- "format_cite_name": "fam",
503
+ "format_name": "mtag",
504
+ "format_source": "https://github.com/JonJala/mtag/wiki/Tutorial-1:-The-Basics",
505
+ "format_version": "v1.0.8",
787
506
  "format_separator": "\t",
788
- "format_na": null,
507
+ "format_cite_name": "MTAG v1.0.8",
789
508
  "format_comment": null,
790
- "format_header": null,
791
- "format_datatype": {
792
- "FID": "string",
793
- "IID": "string",
794
- "PAT": "string",
795
- "MAT": "string",
796
- "SEX": "category",
797
- "PHENO1": "category"
798
- },
509
+ "format_na": null,
799
510
  "format_col_order": [
800
- "FID",
801
- "IID",
802
- "PAT",
803
- "MAT",
804
- "SEX",
805
- "PHENO1"
806
- ],
807
- "last_check_date": "20231124"
511
+ "snpid",
512
+ "chr",
513
+ "bpos",
514
+ "a1",
515
+ "beta",
516
+ "a2",
517
+ "freq",
518
+ "beta",
519
+ "se",
520
+ "z",
521
+ "pval",
522
+ "p_value",
523
+ "n"
524
+ ]
808
525
  },
809
526
  "format_dict": {
810
- "0": "FID",
811
- "1": "IID",
812
- "2": "PAT",
813
- "3": "MAT",
814
- "4": "SEX",
815
- "5": "PHENO1"
527
+ "snpid": "rsID",
528
+ "chr": "CHR",
529
+ "bpos": "POS",
530
+ "a2": "NEA",
531
+ "a1": "EA",
532
+ "freq": "EAF",
533
+ "n": "N",
534
+ "beta": "BETA",
535
+ "se": "SE",
536
+ "pval": "P",
537
+ "z": "Z"
816
538
  }
817
539
  },
818
- "pgscatalog": {
540
+ "pgscatalog_hm": {
819
541
  "meta_data": {
820
- "format_name": "pgscatalog",
542
+ "format_name": "pgscatalog_hm Harmonized File",
821
543
  "format_source": "https://www.pgscatalog.org/downloads/",
822
544
  "format_version": "20220726"
823
545
  },
824
546
  "format_dict": {
825
- "rsID": "rsID",
826
- "chr_name": "CHR",
827
- "chr_position": "POS",
547
+ "hm_rsID": "rsID",
548
+ "hm_chr": "CHR",
549
+ "hm_pos": "POS",
550
+ "hm_inferOtherAllele": "NEA",
828
551
  "other_allele": "NEA",
829
552
  "effect_allele": "EA",
830
553
  "allelefrequency_effect": "EAF",
@@ -832,6 +555,82 @@
832
555
  "OR": "OR"
833
556
  }
834
557
  },
558
+ "regenie": {
559
+ "meta_data": {
560
+ "format_name": "regenie",
561
+ "format_source_1": "https://rgcgithub.github.io/regenie/",
562
+ "format_source_2": "https://github.com/rgcgithub/regenie/blob/master/example/test_bin_out_firth_Y1.regenie",
563
+ "format_version": "20220726",
564
+ "format_cite_name": "REGENIE",
565
+ "format_separator": " ",
566
+ "format_na": "NA",
567
+ "format_comment": null,
568
+ "format_col_order": [
569
+ "CHROM",
570
+ "GENPOS",
571
+ "ID",
572
+ "ALLELE0",
573
+ "ALLELE1",
574
+ "A1FREQ",
575
+ "N",
576
+ "TEST",
577
+ "BETA",
578
+ "SE",
579
+ "CHISQ",
580
+ "LOG10P"
581
+ ],
582
+ "last_check_date": 20230501
583
+ },
584
+ "format_dict": {
585
+ "ID": "SNPID",
586
+ "CHROM": "CHR",
587
+ "GENPOS": "POS",
588
+ "ALLELE0": "NEA",
589
+ "ALLELE1": "EA",
590
+ "A1FREQ": "EAF",
591
+ "N": "N",
592
+ "INFO": "INFO",
593
+ "BETA": "BETA",
594
+ "SE": "SE",
595
+ "CHISQ": "CHISQ",
596
+ "LOG10P": "MLOG10P"
597
+ }
598
+ },
599
+ "plink_pvar": {
600
+ "meta_data": {
601
+ "format_name": "plink_pvar",
602
+ "format_source_1": "https://www.cog-genomics.org/plink/2.0/formats#pvar",
603
+ "format_version": "20231124",
604
+ "format_cite_name": "pvar",
605
+ "format_separator": "\t",
606
+ "format_na": ".",
607
+ "format_comment": "#",
608
+ "format_header": true,
609
+ "format_col_order": [
610
+ "POS",
611
+ "SNPID",
612
+ "NEA",
613
+ "EA",
614
+ "QUAL",
615
+ "FILTER",
616
+ "INFO",
617
+ "FORMAT",
618
+ "CM"
619
+ ],
620
+ "last_check_date": "20231124"
621
+ },
622
+ "format_dict": {
623
+ "POS": "POS",
624
+ "ID": "SNPID",
625
+ "REF": "NEA",
626
+ "ALT": "EA",
627
+ "QUAL": "QUAL",
628
+ "FILTER": "FILTER",
629
+ "INFO": "INFO",
630
+ "FORMAT": "FORMAT",
631
+ "CM": "CM"
632
+ }
633
+ },
835
634
  "plink2": {
836
635
  "meta_data": {
837
636
  "format_name": "PLINK2 .glm.firth, .glm.logistic,.glm.linear",
@@ -859,25 +658,48 @@
859
658
  "OR": "OR"
860
659
  }
861
660
  },
862
- "plink_dosage": {
661
+ "gwaslab": {
863
662
  "meta_data": {
864
- "format_name": ".assoc.dosage",
865
- "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc_dosage",
866
- "format_version": "Stable (beta 6.26, 2 Apr)",
867
- "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
663
+ "format_name": "gwaslab",
664
+ "format_source": "https://cloufield.github.io/gwaslab/",
665
+ "format_version": "20231220_v4"
868
666
  },
869
667
  "format_dict": {
870
- "SNP": "SNPID",
668
+ "SNPID": "SNPID",
669
+ "rsID": "rsID",
871
670
  "CHR": "CHR",
872
- "BP": "POS",
873
- "A2": "NEA",
874
- "A1": "EA",
875
- "FRQ": "EAF",
876
- "OR": "OR",
671
+ "POS": "POS",
672
+ "NEA": "NEA",
673
+ "EA": "EA",
674
+ "EAF": "EAF",
675
+ "N": "N",
877
676
  "BETA": "BETA",
878
- "INFO": "INFO",
879
677
  "SE": "SE",
880
- "P": "P"
678
+ "P": "P",
679
+ "MLOG10P": "MLOG10P",
680
+ "INFO": "INFO",
681
+ "OR": "OR",
682
+ "OR_95L": "OR_95L",
683
+ "OR_95U": "OR_95U",
684
+ "MLOG10": "MLOG10",
685
+ "CHISQ": "CHISQ",
686
+ "Z": "Z",
687
+ "T": "T",
688
+ "F": "F",
689
+ "HR": "HR",
690
+ "HR_95L": "HR_95L",
691
+ "HR_95U": "HR_95U",
692
+ "P_HET": "P_HET",
693
+ "I2": "I2",
694
+ "SNPR2": "SNPR2",
695
+ "DOF": "DOF",
696
+ "N_CASE": "N_CASE",
697
+ "N_CONTROL": "N_CONTROL",
698
+ "MAF": "MAF",
699
+ "DIRECTION": "DIRECTION",
700
+ "STATUS": "STATUS",
701
+ "REF": "REF",
702
+ "ALT": "ALT"
881
703
  }
882
704
  },
883
705
  "popcorn": {
@@ -910,172 +732,351 @@
910
732
  "OR": "OR"
911
733
  }
912
734
  },
913
- "mrmega": {
735
+ "saige": {
914
736
  "meta_data": {
915
- "format_name": "mrmega",
916
- "format_source": "https://genomics.ut.ee/en/tools",
917
- "format_version": "ver0.2",
737
+ "format_name": "saige",
738
+ "format_source": "https://saigegit.github.io//SAIGE-doc/docs/single_step2.html",
739
+ "format_version": "v1.1.3",
918
740
  "last_check_date": 20220806
919
741
  },
920
742
  "format_dict": {
921
- "MarkerName ": "SNPID",
922
- "Chromosome": "CHR",
923
- "Position": "POS",
924
- "NEA": "NEA",
925
- "EA": "EA",
926
- "EAF": "EAF",
927
- "Nsample": "N",
928
- "Effects": "DIRECTION",
929
- "chisq_association": "CHISQ",
930
- "ndf_association": "ndf_association",
931
- "P-value_association": "P"
743
+ "SNPID": "SNPID",
744
+ "CHR": "CHR",
745
+ "POS": "POS",
746
+ "Allele1": "NEA",
747
+ "Allele2": "EA",
748
+ "AF_Allele2": "EAF",
749
+ "N": "N",
750
+ "BETA": "BETA",
751
+ "SE": "SE",
752
+ "p.value": "P",
753
+ "imputationInfo": "INFO"
932
754
  }
933
755
  },
934
- "auto": {
756
+ "pheweb": {
935
757
  "meta_data": {
936
- "format_name": "auto",
937
- "format_separator": "\t",
938
- "format_na": "#NA",
939
- "format_comment": null,
940
- "format_version": 20230328
758
+ "format_name": "pheweb",
759
+ "format_source": "https://github.com/statgen/pheweb",
760
+ "format_version": "20220928"
941
761
  },
942
762
  "format_dict": {
943
- "variant_id": "SNPID",
944
- "SNP": "SNPID",
945
- "snp": "SNPID",
946
- "SNPID": "SNPID",
947
- "snpid": "SNPID",
948
- "MARKERNAME": "SNPID",
949
- "MARKER": "SNPID",
950
- "markername": "SNPID",
951
- "marker": "SNPID",
952
- "RSID": "rsID",
953
- "rsid": "rsID",
954
- "hm_rsID": "rsID",
955
- "rsID": "SNPID",
956
- "chromosome": "CHR",
957
- "Chromosome": "CHR",
958
- "CHROMOSOME": "CHR",
959
- "CHR": "CHR",
960
- "chr": "CHR",
961
- "Chr": "CHR",
962
- "CHROM": "CHR",
963
- "Chrom": "CHR",
763
+ "rsids": "rsID",
964
764
  "chrom": "CHR",
965
- "base_pair_location": "POS",
966
- "POS": "POS",
967
- "Pos": "POS",
968
765
  "pos": "POS",
766
+ "ref": "NEA",
767
+ "alt": "EA",
768
+ "beta": "BETA",
769
+ "af": "EAF",
770
+ "sebeta": "SE",
771
+ "pval": "P",
772
+ "or": "OR",
773
+ "r2": "INFO",
774
+ "num_samples": "n"
775
+ }
776
+ },
777
+ "plink_linear": {
778
+ "meta_data": {
779
+ "format_name": ".assoc.linear",
780
+ "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
781
+ "format_version": "Stable (beta 6.26, 2 Apr)",
782
+ "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
783
+ },
784
+ "format_dict": {
785
+ "SNP": "SNPID",
786
+ "CHR": "CHR",
969
787
  "BP": "POS",
970
- "bp": "POS",
971
- "bpos": "POS",
972
- "REF": "NEA",
973
- "Ref": "NEA",
974
- "reference_allele": "NEA",
975
- "reference": "NEA",
976
- "NEA": "NEA",
977
- "nea": "NEA",
978
- "non_effect_allele": "NEA",
979
- "NON_EFFECT_ALLELE": "NEA",
980
- "A0": "NEA",
981
- "a0": "NEA",
982
- "ALLELE0": "NEA",
983
- "Allele0": "NEA",
984
- "allele0": "NEA",
985
- "ALLELE_0": "NEA",
986
- "Allele_0": "NEA",
987
- "allele_0": "NEA",
988
788
  "A2": "NEA",
989
- "a2": "NEA",
990
- "ALLELE2": "NEA",
991
- "Allele2": "NEA",
992
- "allele2": "NEA",
993
- "ALLELE_2": "NEA",
994
- "Allele_2": "NEA",
995
- "allele_2": "NEA",
996
- "alternative_allele": "EA",
997
- "alternative": "EA",
998
- "Alt": "EA",
999
- "ALT": "EA",
1000
789
  "A1": "EA",
1001
- "a1": "EA",
1002
- "effect_allele": "EA",
1003
- "EA": "EA",
1004
- "ea": "EA",
1005
- "ALLELE1": "EA",
1006
- "Allele1": "EA",
1007
- "allele1": "EA",
1008
- "ALLELE_1": "EA",
1009
- "Allele_1": "EA",
1010
- "allele_1": "EA",
790
+ "BETA": "BETA",
791
+ "L95": "BETA_95L",
792
+ "H95": "BETA_95U",
793
+ "SE": "SE",
794
+ "P": "P",
795
+ "STAT": "T",
796
+ "CHISQ": "CHISQ",
797
+ "NMISS": "N"
798
+ }
799
+ },
800
+ "plink_logistic": {
801
+ "meta_data": {
802
+ "format_name": ".assoc.logistic",
803
+ "format_source": "https://www.cog-genomics.org/plink/1.9/formats#assoc",
804
+ "format_version": "Stable (beta 6.26, 2 Apr)",
805
+ "format_citation": "Purcell, S., Neale, B., Todd-Brown, K., Thomas, L., Ferreira, M. A., Bender, D., ... & Sham, P. C. (2007). PLINK: a tool set for whole-genome association and population-based linkage analyses. The American journal of human genetics, 81(3), 559-575."
806
+ },
807
+ "format_dict": {
808
+ "SNP": "SNPID",
809
+ "CHR": "CHR",
810
+ "BP": "POS",
811
+ "A2": "NEA",
812
+ "A1": "EA",
813
+ "OR": "OR",
814
+ "L95": "OR_95L",
815
+ "H95": "OR_95U",
816
+ "SE": "SE",
817
+ "P": "P",
818
+ "STAT": "T",
819
+ "CHISQ": "CHISQ",
820
+ "NMISS": "N"
821
+ }
822
+ },
823
+ "plink2_firth": {
824
+ "meta_data": {
825
+ "format_name": "PLINK2 .glm.firth, .glm.logistic[.hybrid]",
826
+ "format_source": "https://www.cog-genomics.org/plink/2.0/formats",
827
+ "format_version": "Alpha 3.3 final (3 Jun)",
828
+ "last_check_date": 20220806
829
+ },
830
+ "format_dict": {
831
+ "ID": "SNPID",
832
+ "#CHROM": "CHR",
833
+ "POS": "POS",
834
+ "REF": "REF",
835
+ "ALT": "ALT",
836
+ "A1": "EA",
837
+ "OBS_CT": "N",
838
+ "A1_FREQ": "EAF",
839
+ "BETA": "BETA",
840
+ "LOG(OR)_SE": "SE",
841
+ "SE": "SE",
842
+ "Z_STAT": "Z",
843
+ "P": "P",
844
+ "LOG10_P": "MLOG10P",
845
+ "MACH_R2": "INFO",
846
+ "OR": "OR",
847
+ "L95": "OR_95L",
848
+ "U95": "OR_95U"
849
+ }
850
+ },
851
+ "template": {
852
+ "meta_data": {
853
+ "format_name": "",
854
+ "format_source": "",
855
+ "format_version": "20220726"
856
+ },
857
+ "format_dict": {
858
+ "": "OR_95U"
859
+ }
860
+ },
861
+ "ldsc": {
862
+ "meta_data": {
863
+ "format_name": "ldsc",
864
+ "format_source": "https://github.com/bulik/ldsc/wiki/Summary-Statistics-File-Format",
865
+ "format_source2": "https://github.com/bulik/ldsc/blob/master/munge_sumstats.py",
866
+ "format_version": 20150306
867
+ },
868
+ "format_dict": {
869
+ "SNP": "rsID",
870
+ "A2": "NEA",
871
+ "A1": "EA",
1011
872
  "Frq": "EAF",
1012
- "FRQ": "EAF",
1013
- "frq": "EAF",
1014
- "Frequency": "EAF",
1015
- "FREQ": "EAF",
1016
- "Freq": "EAF",
1017
- "Freq1": "EAF",
1018
- "freq": "EAF",
1019
- "A1FREQ": "EAF",
1020
- "effect_allele_frequency": "EAF",
1021
- "allelefrequency_effect": "EAF",
1022
- "eaf": "EAF",
1023
- "EAF": "EAF",
1024
- "AF1": "EAF",
1025
- "maf": "MAF",
1026
- "Maf": "MAF",
1027
- "MAF": "MAF",
1028
- "n": "N",
1029
873
  "N": "N",
1030
- "sample_size": "N",
1031
- "TotalSampleSize": "N",
1032
- "Nsample": "N",
1033
- "num_samples": "N",
1034
- "beta": "BETA",
1035
- "BETA": "BETA",
1036
874
  "Beta": "BETA",
1037
- "Effect": "BETA",
1038
- "B": "BETA",
1039
- "b": "BETA",
1040
- "effect_weight": "BETA",
1041
- "betase": "SE",
1042
- "sebeta": "SE",
1043
- "se": "SE",
875
+ "P": "P",
876
+ "Z": "Z",
877
+ "INFO": "INFO",
878
+ "OR": "OR",
879
+ "CHR": "CHR",
880
+ "POS": "POS"
881
+ }
882
+ },
883
+ "plink2_linear": {
884
+ "meta_data": {
885
+ "format_name": "PLINK2 .glm.linear",
886
+ "format_source": "https://www.cog-genomics.org/plink/2.0/formats",
887
+ "format_version": "Alpha 3.3 final (3 Jun)",
888
+ "last_check_date": 20220806
889
+ },
890
+ "format_dict": {
891
+ "ID": "SNPID",
892
+ "CHROM": "CHR",
893
+ "POS": "POS",
894
+ "REF": "REF",
895
+ "ALT": "ALT",
896
+ "A1": "EA",
897
+ "OBS_CT": "N",
898
+ "A1_FREQ": "EAF",
899
+ "BETA": "BETA",
900
+ "LOG(OR)_SE": "SE",
1044
901
  "SE": "SE",
902
+ "T_STAT": "T",
903
+ "P": "P",
904
+ "LOG10_P": "MLOG10P",
905
+ "MACH_R2": "INFO",
906
+ "L95": "BETA_95L",
907
+ "U95": "BETA_95U"
908
+ }
909
+ },
910
+ "plink_bim": {
911
+ "meta_data": {
912
+ "format_name": "plink_bim",
913
+ "format_source_1": "https://www.cog-genomics.org/plink/1.9/formats#bim",
914
+ "format_version": "20231124",
915
+ "format_cite_name": "bim",
916
+ "format_separator": "\t",
917
+ "format_na": null,
918
+ "format_comment": null,
919
+ "format_header": null,
920
+ "format_datatype": {
921
+ "CHR": "category",
922
+ "SNPID": "string",
923
+ "CM": "float",
924
+ "POS": "int",
925
+ "NEA": "string",
926
+ "EA": "string"
927
+ },
928
+ "format_col_order": [
929
+ "CHR",
930
+ "SNPID",
931
+ "CM",
932
+ "POS",
933
+ "NEA",
934
+ "EA"
935
+ ],
936
+ "last_check_date": "20231124"
937
+ },
938
+ "format_dict": {
939
+ "0": "CHR",
940
+ "1": "SNPID",
941
+ "2": "CM",
942
+ "3": "POS",
943
+ "4": "NEA",
944
+ "5": "EA"
945
+ }
946
+ },
947
+ "pgscatalog": {
948
+ "meta_data": {
949
+ "format_name": "pgscatalog",
950
+ "format_source": "https://www.pgscatalog.org/downloads/",
951
+ "format_version": "20220726"
952
+ },
953
+ "format_dict": {
954
+ "rsID": "rsID",
955
+ "chr_name": "CHR",
956
+ "chr_position": "POS",
957
+ "other_allele": "NEA",
958
+ "effect_allele": "EA",
959
+ "allelefrequency_effect": "EAF",
960
+ "effect_weight": "BETA",
961
+ "OR": "OR"
962
+ }
963
+ },
964
+ "gwascatalog": {
965
+ "meta_data": {
966
+ "format_name": "gwascatalog",
967
+ "format_source": "https://www.ebi.ac.uk/gwas/docs/methods/summary-statistics",
968
+ "format_version": "20220726"
969
+ },
970
+ "format_dict": {
971
+ "variant_id": "SNPID",
972
+ "chromosome": "CHR",
973
+ "base_pair_location": "POS",
974
+ "other_allele": "NEA",
975
+ "effect_allele": "EA",
976
+ "beta": "BETA",
977
+ "effect_allele_frequency": "EAF",
978
+ "standard_error": "SE",
979
+ "p-value": "P",
980
+ "odds_ratio": "OR",
981
+ "ci_lower": "OR_95L",
982
+ "ci_upper": "OR_95U"
983
+ }
984
+ },
985
+ "ssf": {
986
+ "meta_data": {
987
+ "format_name": "ssf",
988
+ "format_source": "https://www.biorxiv.org/content/10.1101/2022.07.15.500230v1.full",
989
+ "format_cite_name": "GWAS-SSF v0.1",
990
+ "format_separator": "\t",
991
+ "format_na": "#NA",
992
+ "format_comment": null,
993
+ "format_col_order": [
994
+ "chromosome",
995
+ "base_pair_location",
996
+ "effect_allele",
997
+ "other_allele",
998
+ "beta",
999
+ "odds_ratio",
1000
+ "hazard_ratio",
1001
+ "standard_error",
1002
+ "effect_allele_frequency",
1003
+ "p_value",
1004
+ "neg_log_10_p_value",
1005
+ "ci_upper",
1006
+ "ci_lower",
1007
+ "rsid",
1008
+ "variant_id",
1009
+ "info",
1010
+ "ref_allele",
1011
+ "n"
1012
+ ],
1013
+ "format_version": 20230328
1014
+ },
1015
+ "format_dict": {
1016
+ "variant_id": "SNPID",
1017
+ "rsid": "rsID",
1018
+ "chromosome": "CHR",
1019
+ "base_pair_location": "POS",
1020
+ "other_allele": "NEA",
1021
+ "effect_allele": "EA",
1022
+ "effect_allele_frequency": "EAF",
1023
+ "n": "N",
1024
+ "beta": "BETA",
1045
1025
  "standard_error": "SE",
1046
- "StdErr": "SE",
1047
1026
  "p_value": "P",
1048
- "PVAL": "P",
1049
- "Pval": "P",
1050
- "p": "P",
1051
- "P": "P",
1052
- "P.value": "P",
1053
- "p.value": "P",
1054
- "P_BOLT_LMM": "P",
1055
1027
  "neg_log_10_p_value": "MLOG10P",
1056
- "MLOG10P": "MLOG10P",
1057
- "LOG10_P": "MLOG10P",
1058
- "chisq": "CHISQ",
1059
- "chisq_association": "CHISQ",
1060
- "CHISQ_BOLT_LMM": "CHISQ",
1061
- "Z": "Z",
1062
- "z": "Z",
1063
- "Direction": "DIRECTION",
1064
- "DIRECTION": "DIRECTION",
1065
1028
  "info": "INFO",
1066
- "INFO": "INFO",
1067
- "Rsq": "INFO",
1068
- "R2": "INFO",
1069
- "r2": "INFO",
1070
- "imputationInfo": "INFO",
1071
1029
  "odds_ratio": "OR",
1072
- "OR": "OR",
1073
1030
  "hazard_ratio": "HR",
1074
1031
  "ci_lower": "OR_95L",
1075
- "OR_95L": "OR_95L",
1076
- "ci_upper": "OR_95U",
1077
- "OR_95U": "OR_95U",
1078
- "STATUS": "STATUS"
1032
+ "ci_upper": "OR_95U"
1033
+ }
1034
+ },
1035
+ "fastgwa": {
1036
+ "meta_data": {
1037
+ "format_name": "fastgwa",
1038
+ "format_source": "https://yanglab.westlake.edu.cn/software/gcta/#fastGWA",
1039
+ "format_source2": "https://yanglab.westlake.edu.cn/software/gcta/#fastGWA-GLMM",
1040
+ "format_version": "20220726"
1041
+ },
1042
+ "format_dict": {
1043
+ "SNP": "SNPID",
1044
+ "CHR": "CHR",
1045
+ "POS": "POS",
1046
+ "A2": "NEA",
1047
+ "A1": "EA",
1048
+ "AF1": "EAF",
1049
+ "BETA": "BETA",
1050
+ "SE": "SE",
1051
+ "P": "P"
1052
+ }
1053
+ },
1054
+ "plink2_logistic": {
1055
+ "meta_data": {
1056
+ "format_name": "PLINK2 .glm.firth, .glm.logistic[.hybrid]",
1057
+ "format_source": "https://www.cog-genomics.org/plink/2.0/formats",
1058
+ "format_version": "Alpha 3.3 final (3 Jun)",
1059
+ "last_check_date": 20220806
1060
+ },
1061
+ "format_dict": {
1062
+ "ID": "SNPID",
1063
+ "#CHROM": "CHR",
1064
+ "POS": "POS",
1065
+ "REF": "REF",
1066
+ "ALT": "ALT",
1067
+ "A1": "EA",
1068
+ "OBS_CT": "N",
1069
+ "A1_FREQ": "EAF",
1070
+ "BETA": "BETA",
1071
+ "LOG(OR)_SE": "SE",
1072
+ "SE": "SE",
1073
+ "Z_STAT": "Z",
1074
+ "P": "P",
1075
+ "LOG10_P": "MLOG10P",
1076
+ "MACH_R2": "INFO",
1077
+ "OR": "OR",
1078
+ "L95": "OR_95L",
1079
+ "U95": "OR_95U"
1079
1080
  }
1080
1081
  }
1081
1082
  }