@apollo-annotation/shared 0.3.7 → 0.3.8

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.
Files changed (45) hide show
  1. package/dist/Changes/AddAssemblyAndFeaturesFromFileChange.js +1 -1
  2. package/dist/Changes/AddAssemblyAndFeaturesFromFileChange.js.map +1 -1
  3. package/dist/Changes/AddAssemblyFromFileChange.js +1 -1
  4. package/dist/Changes/AddAssemblyFromFileChange.js.map +1 -1
  5. package/dist/Changes/AddRefSeqAliasesChange.js +2 -4
  6. package/dist/Changes/AddRefSeqAliasesChange.js.map +1 -1
  7. package/dist/Changes/ImportJBrowseConfigChange.js +1 -1
  8. package/dist/Changes/ImportJBrowseConfigChange.js.map +1 -1
  9. package/dist/Changes/MergeExonsChange.d.ts +0 -1
  10. package/dist/Changes/MergeExonsChange.js +14 -30
  11. package/dist/Changes/MergeExonsChange.js.map +1 -1
  12. package/dist/Changes/MergeTranscriptsChange.d.ts +1 -3
  13. package/dist/Changes/MergeTranscriptsChange.js +55 -56
  14. package/dist/Changes/MergeTranscriptsChange.js.map +1 -1
  15. package/dist/Checks/CDSCheck.d.ts +1 -1
  16. package/dist/Checks/CDSCheck.js +8 -9
  17. package/dist/Checks/CDSCheck.js.map +1 -1
  18. package/dist/Checks/TranscriptCheck.d.ts +9 -0
  19. package/dist/Checks/TranscriptCheck.js +109 -0
  20. package/dist/Checks/TranscriptCheck.js.map +1 -0
  21. package/dist/Checks/index.d.ts +1 -0
  22. package/dist/Checks/index.js +1 -0
  23. package/dist/Checks/index.js.map +1 -1
  24. package/dist/GFF3/gff3ToAnnotationFeature.test.js +1 -1
  25. package/dist/GFF3/gff3ToAnnotationFeature.test.js.map +1 -1
  26. package/dist/tsconfig.tsbuildinfo +1 -1
  27. package/dist/util.d.ts +3 -0
  28. package/dist/util.js +33 -0
  29. package/dist/util.js.map +1 -1
  30. package/package.json +7 -7
  31. package/src/Changes/AddAssemblyAndFeaturesFromFileChange.ts +2 -1
  32. package/src/Changes/AddAssemblyFromFileChange.ts +1 -1
  33. package/src/Changes/AddRefSeqAliasesChange.ts +2 -4
  34. package/src/Changes/ImportJBrowseConfigChange.ts +1 -1
  35. package/src/Changes/MergeExonsChange.ts +52 -36
  36. package/src/Changes/MergeTranscriptsChange.ts +82 -67
  37. package/src/Checks/CDSCheck.ts +10 -10
  38. package/src/Checks/TranscriptCheck.ts +139 -0
  39. package/src/Checks/index.ts +1 -0
  40. package/src/GFF3/gff3ToAnnotationFeature.test.ts +1 -1
  41. package/src/util.ts +37 -0
  42. package/test_data/example01.json +20 -20
  43. package/test_data/example02.json +38 -38
  44. package/test_data/example04.json +57 -57
  45. package/test_data/gene_representations.gff3 +1054 -276
@@ -0,0 +1,139 @@
1
+ import { Check } from '@apollo-annotation/common'
2
+ import {
3
+ type AnnotationFeatureSnapshot,
4
+ type CheckResultSnapshot,
5
+ } from '@apollo-annotation/mst'
6
+ import { revcom } from '@jbrowse/core/util'
7
+ import ObjectID from 'bson-objectid'
8
+
9
+ interface SpliceSequence {
10
+ fivePrimeSeq: string
11
+ fivePrimeMin: number
12
+ threePrimeSeq: string
13
+ threePrimeMin: number
14
+ }
15
+
16
+ enum CAUSES {
17
+ 'NonCanonicalSpliceSiteAtFivePrime',
18
+ 'NonCanonicalSpliceSiteAtThreePrime',
19
+ }
20
+ const CHECK_NAME = 'TranscriptCheck'
21
+
22
+ async function getSpliceSequences(
23
+ transcript: AnnotationFeatureSnapshot,
24
+ getSequence: (start: number, end: number) => Promise<string>,
25
+ ): Promise<SpliceSequence[]> {
26
+ if (!transcript.children) {
27
+ return []
28
+ }
29
+ const exons: AnnotationFeatureSnapshot[] = []
30
+ for (const [, child] of Object.entries(transcript.children)) {
31
+ if (child.type === 'exon') {
32
+ exons.push(child)
33
+ }
34
+ }
35
+ if (exons.length < 2) {
36
+ return []
37
+ }
38
+
39
+ const spliceSeq: SpliceSequence[] = []
40
+ for (let i = 0; i < exons.length - 1; i++) {
41
+ let fivePrimeMin = exons[i].max
42
+ let threePrimeMin = exons[i + 1].min - 2
43
+ if (transcript.strand === -1) {
44
+ const _fivePrimeMin = fivePrimeMin
45
+ fivePrimeMin = threePrimeMin
46
+ threePrimeMin = _fivePrimeMin
47
+ }
48
+
49
+ let fivePrimeSeq = await getSequence(fivePrimeMin, fivePrimeMin + 2)
50
+ let threePrimeSeq = await getSequence(threePrimeMin, threePrimeMin + 2)
51
+ if (transcript.strand === -1) {
52
+ threePrimeSeq = revcom(threePrimeSeq)
53
+ fivePrimeSeq = revcom(fivePrimeSeq)
54
+ }
55
+
56
+ spliceSeq.push({
57
+ fivePrimeSeq,
58
+ fivePrimeMin,
59
+ threePrimeSeq,
60
+ threePrimeMin,
61
+ })
62
+ }
63
+ return spliceSeq
64
+ }
65
+
66
+ async function checkTranscript(
67
+ feature: AnnotationFeatureSnapshot,
68
+ getSequence: (start: number, end: number) => Promise<string>,
69
+ ): Promise<CheckResultSnapshot[]> {
70
+ const checkResults: CheckResultSnapshot[] = []
71
+
72
+ const VALID_FIVE_PRIME_SEQ = new Set(['GT'])
73
+ const VALID_THREE_PRIME_SEQ = new Set(['AG'])
74
+ const spliceSequences = await getSpliceSequences(feature, getSequence)
75
+ for (const spliceSequence of spliceSequences) {
76
+ if (!VALID_FIVE_PRIME_SEQ.has(spliceSequence.fivePrimeSeq.toUpperCase())) {
77
+ checkResults.push({
78
+ _id: new ObjectID().toHexString(),
79
+ name: CHECK_NAME,
80
+ cause: CAUSES[CAUSES.NonCanonicalSpliceSiteAtFivePrime],
81
+ ids: [feature._id],
82
+ refSeq: feature.refSeq.toString(),
83
+ start: spliceSequence.fivePrimeMin,
84
+ end: spliceSequence.fivePrimeMin + 2,
85
+ message: `Unexpected 5' splice site in "${feature._id}". Expected: ${[...VALID_FIVE_PRIME_SEQ].join('|')}, got: ${spliceSequence.fivePrimeSeq}`,
86
+ })
87
+ }
88
+ if (
89
+ !VALID_THREE_PRIME_SEQ.has(spliceSequence.threePrimeSeq.toUpperCase())
90
+ ) {
91
+ checkResults.push({
92
+ _id: new ObjectID().toHexString(),
93
+ name: CHECK_NAME,
94
+ cause: CAUSES[CAUSES.NonCanonicalSpliceSiteAtThreePrime],
95
+ ids: [feature._id],
96
+ refSeq: feature.refSeq.toString(),
97
+ start: spliceSequence.threePrimeMin,
98
+ end: spliceSequence.threePrimeMin + 2,
99
+ message: `Unexpected 3' splice site in "${feature._id}". Expected: ${[...VALID_THREE_PRIME_SEQ].join('|')}, got: ${spliceSequence.threePrimeSeq}`,
100
+ })
101
+ }
102
+ }
103
+ return checkResults
104
+ }
105
+
106
+ function getCauses(): string[] {
107
+ return Object.values(CAUSES).filter((x) =>
108
+ Number.isNaN(Number(x)),
109
+ ) as string[]
110
+ }
111
+ export class TranscriptCheck extends Check {
112
+ name = 'TranscriptCheck'
113
+ causes = getCauses()
114
+ version = 1
115
+ isDefault = true
116
+
117
+ async checkFeature(
118
+ feature: AnnotationFeatureSnapshot,
119
+ getSequence: (start: number, end: number) => Promise<string>,
120
+ ): Promise<CheckResultSnapshot[]> {
121
+ if (
122
+ feature.type === 'mRNA' ||
123
+ feature.type === 'transcript' ||
124
+ feature.type === 'pseudogenic_transcript'
125
+ ) {
126
+ return checkTranscript(feature, getSequence)
127
+ }
128
+
129
+ if (!feature.children) {
130
+ return []
131
+ }
132
+
133
+ const checkResults: CheckResultSnapshot[] = []
134
+ for (const child of Object.values(feature.children)) {
135
+ checkResults.push(...(await this.checkFeature(child, getSequence)))
136
+ }
137
+ return checkResults
138
+ }
139
+ }
@@ -1 +1,2 @@
1
1
  export * from './CDSCheck'
2
+ export * from './TranscriptCheck'
@@ -127,7 +127,7 @@ export function readAnnotationFeatureSnapshot(
127
127
  return JSON.parse(lines) as AnnotationFeatureSnapshot
128
128
  }
129
129
 
130
- const [ex1, ex2, ex3, ex4] = readFeatureFile(
130
+ const [ex1, , ex2, , ex3, , ex4] = readFeatureFile(
131
131
  'test_data/gene_representations.gff3',
132
132
  )
133
133
 
package/src/util.ts CHANGED
@@ -1,5 +1,6 @@
1
1
  import { type AnnotationFeature } from '@apollo-annotation/mst'
2
2
  import { type Feature } from '@apollo-annotation/schemas'
3
+ import { type IKeyValueMap } from 'mobx'
3
4
 
4
5
  export function splitStringIntoChunks(
5
6
  input: string,
@@ -25,3 +26,39 @@ export function getPrintableId(feature: Feature): string {
25
26
  }
26
27
  return `_id: ${feature._id.toString()}`
27
28
  }
29
+
30
+ export function attributesToRecords(
31
+ attributes: IKeyValueMap<readonly string[] | undefined> | undefined,
32
+ ): Record<string, string[] | undefined> {
33
+ const records: Record<string, string[] | undefined> = {}
34
+ if (!attributes) {
35
+ return records
36
+ }
37
+ for (const [key, value] of Object.entries(attributes)) {
38
+ records[key] = value?.slice()
39
+ }
40
+ return records
41
+ }
42
+
43
+ export function stringifyAttributes(
44
+ attributes: Record<string, string[] | undefined> | undefined,
45
+ ): string {
46
+ if (!attributes) {
47
+ return ''
48
+ }
49
+ const str = []
50
+ for (const [key, value] of Object.entries(attributes)) {
51
+ let attributeName = key
52
+ if (attributeName.startsWith('gff_')) {
53
+ attributeName = attributeName.slice(4)
54
+ attributeName =
55
+ attributeName.charAt(0).toUpperCase() + attributeName.slice(1)
56
+ }
57
+ if (value) {
58
+ str.push(`${attributeName}=${value.join(',')}`)
59
+ } else {
60
+ str.push(attributeName)
61
+ }
62
+ }
63
+ return encodeURIComponent(str.join(';'))
64
+ }
@@ -14,7 +14,7 @@
14
14
  "max": 1012,
15
15
  "strand": 1,
16
16
  "attributes": {
17
- "gff_id": ["tfbs10001"]
17
+ "gff_id": ["tfbs00001"]
18
18
  }
19
19
  },
20
20
  "66e049f17b9cedae9ad890fb": {
@@ -33,7 +33,7 @@
33
33
  "max": 1499,
34
34
  "strand": 1,
35
35
  "attributes": {
36
- "gff_id": ["exon10002"]
36
+ "gff_id": ["exon00002"]
37
37
  }
38
38
  },
39
39
  "66e049f17b9cedae9ad890f7": {
@@ -44,7 +44,7 @@
44
44
  "max": 3902,
45
45
  "strand": 1,
46
46
  "attributes": {
47
- "gff_id": ["exon10003"]
47
+ "gff_id": ["exon00003"]
48
48
  }
49
49
  },
50
50
  "66e049f17b9cedae9ad890f8": {
@@ -55,7 +55,7 @@
55
55
  "max": 5500,
56
56
  "strand": 1,
57
57
  "attributes": {
58
- "gff_id": ["exon10004"]
58
+ "gff_id": ["exon00004"]
59
59
  }
60
60
  },
61
61
  "66e049f17b9cedae9ad890f9": {
@@ -66,7 +66,7 @@
66
66
  "max": 9000,
67
67
  "strand": 1,
68
68
  "attributes": {
69
- "gff_id": ["exon10005"]
69
+ "gff_id": ["exon00005"]
70
70
  }
71
71
  },
72
72
  "66e049f17b9cedae9ad890fa": {
@@ -77,13 +77,13 @@
77
77
  "max": 7600,
78
78
  "strand": 1,
79
79
  "attributes": {
80
- "gff_id": ["cds10001"],
80
+ "gff_id": ["cds00001"],
81
81
  "gff_name": ["edenprotein.1"]
82
82
  }
83
83
  }
84
84
  },
85
85
  "attributes": {
86
- "gff_id": ["mRNA10001"],
86
+ "gff_id": ["mRNA00001"],
87
87
  "gff_name": ["EDEN.1"]
88
88
  }
89
89
  },
@@ -103,7 +103,7 @@
103
103
  "max": 1499,
104
104
  "strand": 1,
105
105
  "attributes": {
106
- "gff_id": ["exon10002"]
106
+ "gff_id": ["exon00002"]
107
107
  }
108
108
  },
109
109
  "66e049f17b9cedae9ad890fd": {
@@ -114,7 +114,7 @@
114
114
  "max": 5500,
115
115
  "strand": 1,
116
116
  "attributes": {
117
- "gff_id": ["exon10004"]
117
+ "gff_id": ["exon00004"]
118
118
  }
119
119
  },
120
120
  "66e049f17b9cedae9ad890fe": {
@@ -125,7 +125,7 @@
125
125
  "max": 9000,
126
126
  "strand": 1,
127
127
  "attributes": {
128
- "gff_id": ["exon10005"]
128
+ "gff_id": ["exon00005"]
129
129
  }
130
130
  },
131
131
  "66e049f17b9cedae9ad890ff": {
@@ -136,13 +136,13 @@
136
136
  "max": 7600,
137
137
  "strand": 1,
138
138
  "attributes": {
139
- "gff_id": ["cds10002"],
139
+ "gff_id": ["cds00002"],
140
140
  "gff_name": ["edenprotein.2"]
141
141
  }
142
142
  }
143
143
  },
144
144
  "attributes": {
145
- "gff_id": ["mRNA10002"],
145
+ "gff_id": ["mRNA00002"],
146
146
  "gff_name": ["EDEN.2"]
147
147
  }
148
148
  },
@@ -162,7 +162,7 @@
162
162
  "max": 1499,
163
163
  "strand": 1,
164
164
  "attributes": {
165
- "gff_id": ["exon10001"]
165
+ "gff_id": ["exon00001"]
166
166
  }
167
167
  },
168
168
  "66e049f17b9cedae9ad89102": {
@@ -173,7 +173,7 @@
173
173
  "max": 3902,
174
174
  "strand": 1,
175
175
  "attributes": {
176
- "gff_id": ["exon10003"]
176
+ "gff_id": ["exon00003"]
177
177
  }
178
178
  },
179
179
  "66e049f17b9cedae9ad89103": {
@@ -184,7 +184,7 @@
184
184
  "max": 5500,
185
185
  "strand": 1,
186
186
  "attributes": {
187
- "gff_id": ["exon10004"]
187
+ "gff_id": ["exon00004"]
188
188
  }
189
189
  },
190
190
  "66e049f17b9cedae9ad89104": {
@@ -195,7 +195,7 @@
195
195
  "max": 9000,
196
196
  "strand": 1,
197
197
  "attributes": {
198
- "gff_id": ["exon10005"]
198
+ "gff_id": ["exon00005"]
199
199
  }
200
200
  },
201
201
  "66e049f17b9cedae9ad89105": {
@@ -206,7 +206,7 @@
206
206
  "max": 7600,
207
207
  "strand": 1,
208
208
  "attributes": {
209
- "gff_id": ["cds10003"],
209
+ "gff_id": ["cds00003"],
210
210
  "gff_name": ["edenprotein.3"]
211
211
  }
212
212
  },
@@ -218,19 +218,19 @@
218
218
  "max": 7600,
219
219
  "strand": 1,
220
220
  "attributes": {
221
- "gff_id": ["cds10004"],
221
+ "gff_id": ["cds00004"],
222
222
  "gff_name": ["edenprotein.4"]
223
223
  }
224
224
  }
225
225
  },
226
226
  "attributes": {
227
- "gff_id": ["mRNA10003"],
227
+ "gff_id": ["mRNA00003"],
228
228
  "gff_name": ["EDEN.3"]
229
229
  }
230
230
  }
231
231
  },
232
232
  "attributes": {
233
- "gff_id": ["gene10001"],
233
+ "gff_id": ["gene00001"],
234
234
  "gff_name": ["EDEN"]
235
235
  }
236
236
  }
@@ -2,24 +2,24 @@
2
2
  "_id": "66e049609048deab4117a33e",
3
3
  "refSeq": "chr1",
4
4
  "type": "gene",
5
- "min": 10999,
6
- "max": 19000,
5
+ "min": 20999,
6
+ "max": 29000,
7
7
  "strand": 1,
8
8
  "children": {
9
9
  "66e049609048deab4117a331": {
10
10
  "_id": "66e049609048deab4117a331",
11
11
  "refSeq": "chr1",
12
12
  "type": "mRNA",
13
- "min": 11049,
14
- "max": 19000,
13
+ "min": 21049,
14
+ "max": 29000,
15
15
  "strand": 1,
16
16
  "children": {
17
17
  "66e049609048deab4117a32c": {
18
18
  "_id": "66e049609048deab4117a32c",
19
19
  "refSeq": "chr1",
20
20
  "type": "exon",
21
- "min": 11049,
22
- "max": 11499,
21
+ "min": 21049,
22
+ "max": 21499,
23
23
  "strand": 1,
24
24
  "attributes": {
25
25
  "gff_id": ["exon20001"]
@@ -29,8 +29,8 @@
29
29
  "_id": "66e049609048deab4117a32d",
30
30
  "refSeq": "chr1",
31
31
  "type": "exon",
32
- "min": 12999,
33
- "max": 13902,
32
+ "min": 22999,
33
+ "max": 23902,
34
34
  "strand": 1,
35
35
  "attributes": {
36
36
  "gff_id": ["exon20004"]
@@ -40,8 +40,8 @@
40
40
  "_id": "66e049609048deab4117a32e",
41
41
  "refSeq": "chr1",
42
42
  "type": "exon",
43
- "min": 14999,
44
- "max": 15500,
43
+ "min": 24999,
44
+ "max": 25500,
45
45
  "strand": 1,
46
46
  "attributes": {
47
47
  "gff_id": ["exon20006"]
@@ -51,8 +51,8 @@
51
51
  "_id": "66e049609048deab4117a32f",
52
52
  "refSeq": "chr1",
53
53
  "type": "exon",
54
- "min": 16999,
55
- "max": 19000,
54
+ "min": 26999,
55
+ "max": 29000,
56
56
  "strand": 1,
57
57
  "attributes": {
58
58
  "gff_id": ["exon20009"]
@@ -62,8 +62,8 @@
62
62
  "_id": "66e049609048deab4117a330",
63
63
  "refSeq": "chr1",
64
64
  "type": "CDS",
65
- "min": 11200,
66
- "max": 17600,
65
+ "min": 21200,
66
+ "max": 27600,
67
67
  "strand": 1,
68
68
  "attributes": {
69
69
  "gff_id": ["cds20001"],
@@ -80,16 +80,16 @@
80
80
  "_id": "66e049609048deab4117a336",
81
81
  "refSeq": "chr1",
82
82
  "type": "mRNA",
83
- "min": 11049,
84
- "max": 19000,
83
+ "min": 21049,
84
+ "max": 29000,
85
85
  "strand": 1,
86
86
  "children": {
87
87
  "66e049609048deab4117a332": {
88
88
  "_id": "66e049609048deab4117a332",
89
89
  "refSeq": "chr1",
90
90
  "type": "exon",
91
- "min": 11049,
92
- "max": 11499,
91
+ "min": 21049,
92
+ "max": 21499,
93
93
  "strand": 1,
94
94
  "attributes": {
95
95
  "gff_id": ["exon20002"]
@@ -99,8 +99,8 @@
99
99
  "_id": "66e049609048deab4117a333",
100
100
  "refSeq": "chr1",
101
101
  "type": "exon",
102
- "min": 14999,
103
- "max": 15500,
102
+ "min": 24999,
103
+ "max": 25500,
104
104
  "strand": 1,
105
105
  "attributes": {
106
106
  "gff_id": ["exon20007"]
@@ -110,8 +110,8 @@
110
110
  "_id": "66e049609048deab4117a334",
111
111
  "refSeq": "chr1",
112
112
  "type": "exon",
113
- "min": 16999,
114
- "max": 19000,
113
+ "min": 26999,
114
+ "max": 29000,
115
115
  "strand": 1,
116
116
  "attributes": {
117
117
  "gff_id": ["exon20010"]
@@ -121,8 +121,8 @@
121
121
  "_id": "66e049609048deab4117a335",
122
122
  "refSeq": "chr1",
123
123
  "type": "CDS",
124
- "min": 11200,
125
- "max": 17600,
124
+ "min": 21200,
125
+ "max": 27600,
126
126
  "strand": 1,
127
127
  "attributes": {
128
128
  "gff_id": ["cds20002"],
@@ -139,16 +139,16 @@
139
139
  "_id": "66e049609048deab4117a33d",
140
140
  "refSeq": "chr1",
141
141
  "type": "mRNA",
142
- "min": 11299,
143
- "max": 19000,
142
+ "min": 21299,
143
+ "max": 29000,
144
144
  "strand": 1,
145
145
  "children": {
146
146
  "66e049609048deab4117a337": {
147
147
  "_id": "66e049609048deab4117a337",
148
148
  "refSeq": "chr1",
149
149
  "type": "exon",
150
- "min": 11299,
151
- "max": 11499,
150
+ "min": 21299,
151
+ "max": 21499,
152
152
  "strand": 1,
153
153
  "attributes": {
154
154
  "gff_id": ["exon20003"]
@@ -158,8 +158,8 @@
158
158
  "_id": "66e049609048deab4117a338",
159
159
  "refSeq": "chr1",
160
160
  "type": "exon",
161
- "min": 12999,
162
- "max": 13902,
161
+ "min": 22999,
162
+ "max": 23902,
163
163
  "strand": 1,
164
164
  "attributes": {
165
165
  "gff_id": ["exon20005"]
@@ -169,8 +169,8 @@
169
169
  "_id": "66e049609048deab4117a339",
170
170
  "refSeq": "chr1",
171
171
  "type": "exon",
172
- "min": 14999,
173
- "max": 15500,
172
+ "min": 24999,
173
+ "max": 25500,
174
174
  "strand": 1,
175
175
  "attributes": {
176
176
  "gff_id": ["exon20008"]
@@ -180,8 +180,8 @@
180
180
  "_id": "66e049609048deab4117a33a",
181
181
  "refSeq": "chr1",
182
182
  "type": "exon",
183
- "min": 16999,
184
- "max": 19000,
183
+ "min": 26999,
184
+ "max": 29000,
185
185
  "strand": 1,
186
186
  "attributes": {
187
187
  "gff_id": ["exon20011"]
@@ -191,8 +191,8 @@
191
191
  "_id": "66e049609048deab4117a33b",
192
192
  "refSeq": "chr1",
193
193
  "type": "CDS",
194
- "min": 13300,
195
- "max": 17600,
194
+ "min": 23300,
195
+ "max": 27600,
196
196
  "strand": 1,
197
197
  "attributes": {
198
198
  "gff_id": ["cds20003"],
@@ -203,8 +203,8 @@
203
203
  "_id": "66e049609048deab4117a33c",
204
204
  "refSeq": "chr1",
205
205
  "type": "CDS",
206
- "min": 13390,
207
- "max": 17600,
206
+ "min": 23390,
207
+ "max": 27600,
208
208
  "strand": 1,
209
209
  "attributes": {
210
210
  "gff_id": ["cds20004"],