Skip to content

Commit ec365f0

Browse files
jeromekellehermergify[bot]
authored andcommitted
Remove all-missing fields from example VCF
Closes #1197
1 parent 636d744 commit ec365f0

File tree

3 files changed

+54
-54
lines changed

3 files changed

+54
-54
lines changed

sgkit/tests/io/vcf/data/all_fields.vcf

Lines changed: 47 additions & 47 deletions
Original file line numberDiff line numberDiff line change
@@ -49,20 +49,20 @@
4949
#CHROM POS ID REF ALT QUAL FILTER INFO FORMAT s1 s2
5050
1 1 . G A,C . PASS IB0 . . .
5151
1 2 . A G,G . PASS II1=126 . . .
52-
1 3 . A G,G . PASS II1=. . . .
52+
1 3 . A G,G . PASS . . . .
5353
1 4 . T A,C . PASS II2=459,-140 . . .
5454
1 5 . T A,C . PASS II2=.,-140 . . .
5555
1 6 . T A,C . PASS II2=459,. . . .
56-
1 7 . T A,C . PASS II2=.,. . . .
56+
1 7 . T A,C . PASS . . . .
5757
1 8 . A A,G . PASS IIA=294,130 . . .
5858
1 9 . A A,G . PASS IIA=.,130 . . .
5959
1 10 . A A,G . PASS IIA=294,. . . .
60-
1 11 . A A,G . PASS IIA=.,. . . .
60+
1 11 . A A,G . PASS . . . .
6161
1 12 . A A,G . PASS IIR=95,724,44 . . .
6262
1 13 . A A,G . PASS IIR=.,724,44 . . .
6363
1 14 . A A,G . PASS IIR=95,.,44 . . .
6464
1 15 . A A,G . PASS IIR=95,724,. . . .
65-
1 16 . A A,G . PASS IIR=.,.,. . . .
65+
1 16 . A A,G . PASS . . . .
6666
1 17 . G A,G . PASS IID=-879,-534,238,-670,482,-913,396 . . .
6767
1 18 . G A,G . PASS IID=.,-534,238,-670,482,-913,396 . . .
6868
1 19 . G A,G . PASS IID=-879,.,238,-670,482,-913,396 . . .
@@ -71,28 +71,28 @@
7171
1 22 . G A,G . PASS IID=-879,-534,238,-670,.,-913,396 . . .
7272
1 23 . G A,G . PASS IID=-879,-534,238,-670,482,.,396 . . .
7373
1 24 . G A,G . PASS IID=-879,-534,238,-670,482,-913,. . . .
74-
1 25 . G A,G . PASS IID=.,.,.,.,.,.,. . . .
74+
1 25 . G A,G . PASS . . . .
7575
1 26 . G A,G . PASS IID=-129,687,-870,685 . . .
7676
1 27 . G A,G . PASS IID=.,687,-870,685 . . .
7777
1 28 . G A,G . PASS IID=-129,.,-870,685 . . .
7878
1 29 . G A,G . PASS IID=-129,687,.,685 . . .
7979
1 30 . G A,G . PASS IID=-129,687,-870,. . . .
80-
1 31 . G A,G . PASS IID=.,.,.,. . . .
80+
1 31 . G A,G . PASS . . . .
8181
1 32 . T A,T . PASS IF1=-887.177 . . .
82-
1 33 . T A,T . PASS IF1=. . . .
82+
1 33 . T A,T . PASS . . . .
8383
1 34 . G C,A . PASS IF2=443.998,877.105 . . .
8484
1 35 . G C,A . PASS IF2=.,877.105 . . .
8585
1 36 . G C,A . PASS IF2=443.998,. . . .
86-
1 37 . G C,A . PASS IF2=.,. . . .
86+
1 37 . G C,A . PASS . . . .
8787
1 38 . T C,A . PASS IFA=-998.442,984.423 . . .
8888
1 39 . T C,A . PASS IFA=.,984.423 . . .
8989
1 40 . T C,A . PASS IFA=-998.442,. . . .
90-
1 41 . T C,A . PASS IFA=.,. . . .
90+
1 41 . T C,A . PASS . . . .
9191
1 42 . A T,G . PASS IFR=234.963,223.306,-985.867 . . .
9292
1 43 . A T,G . PASS IFR=.,223.306,-985.867 . . .
9393
1 44 . A T,G . PASS IFR=234.963,.,-985.867 . . .
9494
1 45 . A T,G . PASS IFR=234.963,223.306,. . . .
95-
1 46 . A T,G . PASS IFR=.,.,. . . .
95+
1 46 . A T,G . PASS . . . .
9696
1 47 . T G,G . PASS IFD=-417.542,223.706,-721.012,-415.711,-267.276,-87.86,570.352,-600.652,28.4689 . . .
9797
1 48 . T G,G . PASS IFD=.,223.706,-721.012,-415.711,-267.276,-87.86,570.352,-600.652,28.4689 . . .
9898
1 49 . T G,G . PASS IFD=-417.542,.,-721.012,-415.711,-267.276,-87.86,570.352,-600.652,28.4689 . . .
@@ -103,7 +103,7 @@
103103
1 54 . T G,G . PASS IFD=-417.542,223.706,-721.012,-415.711,-267.276,-87.86,.,-600.652,28.4689 . . .
104104
1 55 . T G,G . PASS IFD=-417.542,223.706,-721.012,-415.711,-267.276,-87.86,570.352,.,28.4689 . . .
105105
1 56 . T G,G . PASS IFD=-417.542,223.706,-721.012,-415.711,-267.276,-87.86,570.352,-600.652,. . . .
106-
1 57 . T G,G . PASS IFD=.,.,.,.,.,.,.,.,. . . .
106+
1 57 . T G,G . PASS . . . .
107107
1 58 . T G,G . PASS IFD=-907.099,215.09,-658.952,-869.897,897.771,931.264,616.795,-390.772,-804.656 . . .
108108
1 59 . T G,G . PASS IFD=.,215.09,-658.952,-869.897,897.771,931.264,616.795,-390.772,-804.656 . . .
109109
1 60 . T G,G . PASS IFD=-907.099,.,-658.952,-869.897,897.771,931.264,616.795,-390.772,-804.656 . . .
@@ -114,28 +114,28 @@
114114
1 65 . T G,G . PASS IFD=-907.099,215.09,-658.952,-869.897,897.771,931.264,.,-390.772,-804.656 . . .
115115
1 66 . T G,G . PASS IFD=-907.099,215.09,-658.952,-869.897,897.771,931.264,616.795,.,-804.656 . . .
116116
1 67 . T G,G . PASS IFD=-907.099,215.09,-658.952,-869.897,897.771,931.264,616.795,-390.772,. . . .
117-
1 68 . T G,G . PASS IFD=.,.,.,.,.,.,.,.,. . . .
117+
1 68 . T G,G . PASS . . . .
118118
1 69 . T C,G . PASS IC1=f . . .
119-
1 70 . T C,G . PASS IC1=. . . .
119+
1 70 . T C,G . PASS . . . .
120120
1 71 . G T,G . PASS IC2=e,a . . .
121121
1 72 . G T,G . PASS IC2=.,a . . .
122122
1 73 . G T,G . PASS IC2=e,. . . .
123-
1 74 . G T,G . PASS IC2=.,. . . .
123+
1 74 . G T,G . PASS . . . .
124124
1 75 . A C,A . PASS ICA=b,a . . .
125125
1 76 . A C,A . PASS ICA=.,a . . .
126126
1 77 . A C,A . PASS ICA=b,. . . .
127-
1 78 . A C,A . PASS ICA=.,. . . .
127+
1 78 . A C,A . PASS . . . .
128128
1 79 . C G,C . PASS ICR=c,b,b . . .
129129
1 80 . C G,C . PASS ICR=.,b,b . . .
130130
1 81 . C G,C . PASS ICR=c,.,b . . .
131131
1 82 . C G,C . PASS ICR=c,b,. . . .
132-
1 83 . C G,C . PASS ICR=.,.,. . . .
132+
1 83 . C G,C . PASS . . . .
133133
1 84 . T G,G . PASS ICD=b,f,b,c . . .
134134
1 85 . T G,G . PASS ICD=.,f,b,c . . .
135135
1 86 . T G,G . PASS ICD=b,.,b,c . . .
136136
1 87 . T G,G . PASS ICD=b,f,.,c . . .
137137
1 88 . T G,G . PASS ICD=b,f,b,. . . .
138-
1 89 . T G,G . PASS ICD=.,.,.,. . . .
138+
1 89 . T G,G . PASS . . . .
139139
1 90 . T G,G . PASS ICD=g,e,d,e,f,f,b . . .
140140
1 91 . T G,G . PASS ICD=.,e,d,e,f,f,b . . .
141141
1 92 . T G,G . PASS ICD=g,.,d,e,f,f,b . . .
@@ -144,22 +144,22 @@
144144
1 95 . T G,G . PASS ICD=g,e,d,e,.,f,b . . .
145145
1 96 . T G,G . PASS ICD=g,e,d,e,f,.,b . . .
146146
1 97 . T G,G . PASS ICD=g,e,d,e,f,f,. . . .
147-
1 98 . T G,G . PASS ICD=.,.,.,.,.,.,. . . .
147+
1 98 . T G,G . PASS . . . .
148148
1 99 . A C,C . PASS IS1=bc . . .
149-
1 100 . A C,C . PASS IS1=. . . .
149+
1 100 . A C,C . PASS . . . .
150150
1 101 . T T,C . PASS IS2=hij,d . . .
151151
1 102 . T T,C . PASS IS2=.,d . . .
152152
1 103 . T T,C . PASS IS2=hij,. . . .
153-
1 104 . T T,C . PASS IS2=.,. . . .
153+
1 104 . T T,C . PASS . . . .
154154
1 105 . T C,C . PASS ISA=bc,efg . . .
155155
1 106 . T C,C . PASS ISA=.,efg . . .
156156
1 107 . T C,C . PASS ISA=bc,. . . .
157-
1 108 . T C,C . PASS ISA=.,. . . .
157+
1 108 . T C,C . PASS . . . .
158158
1 109 . C G,T . PASS ISR=d,bc,op . . .
159159
1 110 . C G,T . PASS ISR=.,bc,op . . .
160160
1 111 . C G,T . PASS ISR=d,.,op . . .
161161
1 112 . C G,T . PASS ISR=d,bc,. . . .
162-
1 113 . C G,T . PASS ISR=.,.,. . . .
162+
1 113 . C G,T . PASS . . . .
163163
1 114 . G A,A . PASS ISD=ab,hij,klmn,d,ab,d,op,efg . . .
164164
1 115 . G A,A . PASS ISD=.,hij,klmn,d,ab,d,op,efg . . .
165165
1 116 . G A,A . PASS ISD=ab,.,klmn,d,ab,d,op,efg . . .
@@ -169,89 +169,89 @@
169169
1 120 . G A,A . PASS ISD=ab,hij,klmn,d,ab,.,op,efg . . .
170170
1 121 . G A,A . PASS ISD=ab,hij,klmn,d,ab,d,.,efg . . .
171171
1 122 . G A,A . PASS ISD=ab,hij,klmn,d,ab,d,op,. . . .
172-
1 123 . G A,A . PASS ISD=.,.,.,.,.,.,.,. . . .
172+
1 123 . G A,A . PASS . . . .
173173
1 124 . G A,A . PASS ISD=op,op,ab . . .
174174
1 125 . G A,A . PASS ISD=.,op,ab . . .
175175
1 126 . G A,A . PASS ISD=op,.,ab . . .
176176
1 127 . G A,A . PASS ISD=op,op,. . . .
177-
1 128 . G A,A . PASS ISD=.,.,. . . .
177+
1 128 . G A,A . PASS . . . .
178178
2 129 . G G,G . PASS . FI1 -795 .
179179
2 130 . C G,A . PASS . FI2 104,955 .,955
180-
2 131 . C G,A . PASS . FI2 104,. .,.
180+
2 131 . C G,A . PASS . FI2 104,. .
181181
2 132 . C C,T . PASS . FIA 585,895 .,895
182-
2 133 . C C,T . PASS . FIA 585,. .,.
182+
2 133 . C C,T . PASS . FIA 585,. .
183183
2 134 . T C,G . PASS . FIR 411,25,21 .,25,21
184184
2 135 . T C,G . PASS . FIR 411,.,21 411,25,.
185-
2 136 . T C,G . PASS . FIR .,.,. .,.,.
185+
2 136 . T C,G . PASS . FIR . .
186186
2 137 . A T,T . PASS . FIG 413,-435,129,795,845,500 .,-435,129,795,845,500
187187
2 138 . A T,T . PASS . FIG 413,.,129,795,845,500 413,-435,.,795,845,500
188188
2 139 . A T,T . PASS . FIG 413,-435,129,.,845,500 413,-435,129,795,.,500
189-
2 140 . A T,T . PASS . FIG 413,-435,129,795,845,. .,.,.,.,.,.
189+
2 140 . A T,T . PASS . FIG 413,-435,129,795,845,. .
190190
2 141 . C G,G . PASS . FID -271,579 .,579
191-
2 142 . C G,G . PASS . FID -271,. .,.
191+
2 142 . C G,G . PASS . FID -271,. .
192192
2 143 . C G,G . PASS . FID -799,981 .,981
193-
2 144 . C G,G . PASS . FID -799,. .,.
193+
2 144 . C G,G . PASS . FID -799,. .
194194
2 145 . A T,G . PASS . FF1 853.318 .
195195
2 146 . T G,A . PASS . FF2 454.544,-346.918 .,-346.918
196-
2 147 . T G,A . PASS . FF2 454.544,. .,.
196+
2 147 . T G,A . PASS . FF2 454.544,. .
197197
2 148 . C A,T . PASS . FFA 140.888,41.6685 .,41.6685
198-
2 149 . C A,T . PASS . FFA 140.888,. .,.
198+
2 149 . C A,T . PASS . FFA 140.888,. .
199199
2 150 . T T,C . PASS . FFR 922.344,689.068,494.64 .,689.068,494.64
200200
2 151 . T T,C . PASS . FFR 922.344,.,494.64 922.344,689.068,.
201-
2 152 . T T,C . PASS . FFR .,.,. .,.,.
201+
2 152 . T T,C . PASS . FFR . .
202202
2 153 . A T,T . PASS . FFG 79.3843,173.502,930.511,214.068,-448.002,-407.453 .,173.502,930.511,214.068,-448.002,-407.453
203203
2 154 . A T,T . PASS . FFG 79.3843,.,930.511,214.068,-448.002,-407.453 79.3843,173.502,.,214.068,-448.002,-407.453
204204
2 155 . A T,T . PASS . FFG 79.3843,173.502,930.511,.,-448.002,-407.453 79.3843,173.502,930.511,214.068,.,-407.453
205-
2 156 . A T,T . PASS . FFG 79.3843,173.502,930.511,214.068,-448.002,. .,.,.,.,.,.
205+
2 156 . A T,T . PASS . FFG 79.3843,173.502,930.511,214.068,-448.002,. .
206206
2 157 . A C,A . PASS . FFD -968.727 .
207207
2 158 . A C,A . PASS . FFD 544.49,-602.569,-988.956,630.923,413.715,458.014,542.541,-851.911,-283.069 .,-602.569,-988.956,630.923,413.715,458.014,542.541,-851.911,-283.069
208208
2 159 . A C,A . PASS . FFD 544.49,.,-988.956,630.923,413.715,458.014,542.541,-851.911,-283.069 544.49,-602.569,.,630.923,413.715,458.014,542.541,-851.911,-283.069
209209
2 160 . A C,A . PASS . FFD 544.49,-602.569,-988.956,.,413.715,458.014,542.541,-851.911,-283.069 544.49,-602.569,-988.956,630.923,.,458.014,542.541,-851.911,-283.069
210210
2 161 . A C,A . PASS . FFD 544.49,-602.569,-988.956,630.923,413.715,.,542.541,-851.911,-283.069 544.49,-602.569,-988.956,630.923,413.715,458.014,.,-851.911,-283.069
211211
2 162 . A C,A . PASS . FFD 544.49,-602.569,-988.956,630.923,413.715,458.014,542.541,.,-283.069 544.49,-602.569,-988.956,630.923,413.715,458.014,542.541,-851.911,.
212-
2 163 . A C,A . PASS . FFD .,.,.,.,.,.,.,.,. .,.,.,.,.,.,.,.,.
212+
2 163 . A C,A . PASS . FFD . .
213213
2 164 . T T,A . PASS . FC1 d .
214214
2 165 . G C,T . PASS . FC2 c,b .,b
215-
2 166 . G C,T . PASS . FC2 c,. .,.
215+
2 166 . G C,T . PASS . FC2 c,. .
216216
2 167 . G G,A . PASS . FCA c,g .,g
217-
2 168 . G G,A . PASS . FCA c,. .,.
217+
2 168 . G G,A . PASS . FCA c,. .
218218
2 169 . G C,G . PASS . FCR a,b,c .,b,c
219219
2 170 . G C,G . PASS . FCR a,.,c a,b,.
220-
2 171 . G C,G . PASS . FCR .,.,. .,.,.
220+
2 171 . G C,G . PASS . FCR . .
221221
2 172 . G A,A . PASS . FCG a,e,b,g,g,a .,e,b,g,g,a
222222
2 173 . G A,A . PASS . FCG a,.,b,g,g,a a,e,.,g,g,a
223223
2 174 . G A,A . PASS . FCG a,e,b,.,g,a a,e,b,g,.,a
224-
2 175 . G A,A . PASS . FCG a,e,b,g,g,. .,.,.,.,.,.
224+
2 175 . G A,A . PASS . FCG a,e,b,g,g,. .
225225
2 176 . A G,A . PASS . FCD a,g,d,d,f,f,b,a,d .,g,d,d,f,f,b,a,d
226226
2 177 . A G,A . PASS . FCD a,.,d,d,f,f,b,a,d a,g,.,d,f,f,b,a,d
227227
2 178 . A G,A . PASS . FCD a,g,d,.,f,f,b,a,d a,g,d,d,.,f,b,a,d
228228
2 179 . A G,A . PASS . FCD a,g,d,d,f,.,b,a,d a,g,d,d,f,f,.,a,d
229229
2 180 . A G,A . PASS . FCD a,g,d,d,f,f,b,.,d a,g,d,d,f,f,b,a,.
230-
2 181 . A G,A . PASS . FCD .,.,.,.,.,.,.,.,. c,d,f,e,g,a,c
230+
2 181 . A G,A . PASS . FCD . c,d,f,e,g,a,c
231231
2 182 . A G,A . PASS . FCD .,d,f,e,g,a,c c,.,f,e,g,a,c
232232
2 183 . A G,A . PASS . FCD c,d,.,e,g,a,c c,d,f,.,g,a,c
233233
2 184 . A G,A . PASS . FCD c,d,f,e,.,a,c c,d,f,e,g,.,c
234-
2 185 . A G,A . PASS . FCD c,d,f,e,g,a,. .,.,.,.,.,.,.
234+
2 185 . A G,A . PASS . FCD c,d,f,e,g,a,. .
235235
2 186 . C T,A . PASS . FS1 bc .
236236
2 187 . C C,C . PASS . FS2 bc,op .,op
237-
2 188 . C C,C . PASS . FS2 bc,. .,.
237+
2 188 . C C,C . PASS . FS2 bc,. .
238238
2 189 . C T,G . PASS . FSA ab,op .,op
239-
2 190 . C T,G . PASS . FSA ab,. .,.
239+
2 190 . C T,G . PASS . FSA ab,. .
240240
2 191 . T T,T . PASS . FSR klmn,bc,efg .,bc,efg
241241
2 192 . T T,T . PASS . FSR klmn,.,efg klmn,bc,.
242-
2 193 . T T,T . PASS . FSR .,.,. .,.,.
242+
2 193 . T T,T . PASS . FSR . .
243243
2 194 . A C,A . PASS . FSG d,op,bc,klmn,efg,d .,op,bc,klmn,efg,d
244244
2 195 . A C,A . PASS . FSG d,.,bc,klmn,efg,d d,op,.,klmn,efg,d
245245
2 196 . A C,A . PASS . FSG d,op,bc,.,efg,d d,op,bc,klmn,.,d
246-
2 197 . A C,A . PASS . FSG d,op,bc,klmn,efg,. .,.,.,.,.,.
246+
2 197 . A C,A . PASS . FSG d,op,bc,klmn,efg,. .
247247
2 198 . T T,G . PASS . FSD klmn,bc,d,op,hij,efg,klmn,ab,hij .,bc,d,op,hij,efg,klmn,ab,hij
248248
2 199 . T T,G . PASS . FSD klmn,.,d,op,hij,efg,klmn,ab,hij klmn,bc,.,op,hij,efg,klmn,ab,hij
249249
2 200 . T T,G . PASS . FSD klmn,bc,d,.,hij,efg,klmn,ab,hij klmn,bc,d,op,.,efg,klmn,ab,hij
250250
2 201 . T T,G . PASS . FSD klmn,bc,d,op,hij,.,klmn,ab,hij klmn,bc,d,op,hij,efg,.,ab,hij
251251
2 202 . T T,G . PASS . FSD klmn,bc,d,op,hij,efg,klmn,.,hij klmn,bc,d,op,hij,efg,klmn,ab,.
252-
2 203 . T T,G . PASS . FSD .,.,.,.,.,.,.,.,. efg,klmn,bc,op,ab,bc,hij,hij
252+
2 203 . T T,G . PASS . FSD . efg,klmn,bc,op,ab,bc,hij,hij
253253
2 204 . T T,G . PASS . FSD .,klmn,bc,op,ab,bc,hij,hij efg,.,bc,op,ab,bc,hij,hij
254254
2 205 . T T,G . PASS . FSD efg,klmn,.,op,ab,bc,hij,hij efg,klmn,bc,.,ab,bc,hij,hij
255255
2 206 . T T,G . PASS . FSD efg,klmn,bc,op,.,bc,hij,hij efg,klmn,bc,op,ab,.,hij,hij
256256
2 207 . T T,G . PASS . FSD efg,klmn,bc,op,ab,bc,.,hij efg,klmn,bc,op,ab,bc,hij,.
257-
2 208 . T T,G . PASS . FSD .,.,.,.,.,.,.,. .,.,.,.,.,.,.,.
257+
2 208 . T T,G . PASS . FSD . .

sgkit/tests/io/vcf/test_vcf_roundtrip.py

Lines changed: 1 addition & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -31,9 +31,7 @@
3131
},
3232
True,
3333
),
34-
# Temporarily disabling this all_fields test while resolving missing data issue
35-
# https://github.com/pystatgen/sgkit/issues/1197
36-
# ("all_fields.vcf", None, True),
34+
("all_fields.vcf", None, True),
3735
("CEUTrio.20.21.gatk3.4.g.vcf.bgz", None, True),
3836
# don't generate header to avoid https://github.com/pydata/xarray/issues/7328
3937
("Homo_sapiens_assembly38.headerOnly.vcf.gz", None, False),

sgkit/tests/io/vcf/vcf_generator.py

Lines changed: 6 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -70,15 +70,15 @@ def generate_values(self, alt_alleles):
7070
n = generate_number(self.vcf_number, alt_alleles)
7171
data = generate_data(self.vcf_type, n)
7272
val = ",".join([str(x) for x in data])
73+
assert val != "."
7374
yield f"{val}"
7475
for i in range(n):
7576
data_str = [str(x) for x in data]
7677
data_str[i] = "." # missing
7778
val = ",".join(data_str)
78-
yield f"{val}"
79+
yield f"{val}" if val != "." else None
7980
if n > 1:
80-
val = ",".join(["."] * n) # all missing
81-
yield f"{val}"
81+
yield None # all missing
8282

8383

8484
def generate_header(info_fields, format_fields, vcf_samples):
@@ -154,7 +154,9 @@ def generate_vcf(output, seed=42):
154154
pos = pos + 1
155155
ref = alleles[0]
156156
alt = alleles[1:]
157-
info = {info_field.name: val}
157+
info = {}
158+
if val is not None:
159+
info = {info_field.name: val}
158160
samples: List[Dict[str, Any]] = [{}] * len(vcf_samples)
159161

160162
variant = VcfVariant(

0 commit comments

Comments
 (0)