gffkit 0.3__tar.gz → 0.3.1__tar.gz
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.
- {gffkit-0.3/src/gffkit.egg-info → gffkit-0.3.1}/PKG-INFO +39 -4
- {gffkit-0.3 → gffkit-0.3.1}/README.md +38 -3
- {gffkit-0.3 → gffkit-0.3.1}/pyproject.toml +1 -1
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit/__init__.py +1 -1
- {gffkit-0.3 → gffkit-0.3.1/src/gffkit.egg-info}/PKG-INFO +39 -4
- {gffkit-0.3 → gffkit-0.3.1}/LICENSE +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/MANIFEST.in +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/setup.cfg +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit/__main__.py +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit/add_utr.py +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit/complement_annotations.py +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit/detect_bridge_merged_genes.py +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit/main.py +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit.egg-info/SOURCES.txt +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit.egg-info/dependency_links.txt +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit.egg-info/entry_points.txt +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/src/gffkit.egg-info/top_level.txt +0 -0
- {gffkit-0.3 → gffkit-0.3.1}/tests/test_complement_sources.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: gffkit
|
|
3
|
-
Version: 0.3
|
|
3
|
+
Version: 0.3.1
|
|
4
4
|
Summary: Region-aware GFF annotation integration toolkit
|
|
5
5
|
Author: Qunjie Zhang
|
|
6
6
|
License: MIT
|
|
@@ -48,7 +48,8 @@ gffkit integrate \
|
|
|
48
48
|
--annotation-a EviAnn.gff3 \
|
|
49
49
|
--annotation-b ANNEVO.gff3 \
|
|
50
50
|
--outdir gffkit_out \
|
|
51
|
-
--prefix sample
|
|
51
|
+
--prefix sample \
|
|
52
|
+
-t 8
|
|
52
53
|
```
|
|
53
54
|
|
|
54
55
|
Outputs:
|
|
@@ -61,7 +62,7 @@ Outputs:
|
|
|
61
62
|
|
|
62
63
|
```bash
|
|
63
64
|
# 1. Detect suspicious merged genes in Annotation A
|
|
64
|
-
gffkit detect-bridge -i EviAnn.gff3 -o suspicious.tsv
|
|
65
|
+
gffkit detect-bridge -i EviAnn.gff3 -o suspicious.tsv -t 8
|
|
65
66
|
|
|
66
67
|
# 2. Use A as the global reference, but switch to B in suspicious regions
|
|
67
68
|
gffkit complement \
|
|
@@ -69,12 +70,27 @@ gffkit complement \
|
|
|
69
70
|
--add ANNEVO.gff3 \
|
|
70
71
|
--swap_region_tsv suspicious.tsv \
|
|
71
72
|
--swap_region_flank 100 \
|
|
72
|
-
--output merged.gff3
|
|
73
|
+
--output merged.gff3 \
|
|
74
|
+
-t 8
|
|
73
75
|
|
|
74
76
|
# 3. Add UTR features
|
|
75
77
|
gffkit add-utr -i merged.gff3 -o final.annotation.withUTR.gff3
|
|
76
78
|
```
|
|
77
79
|
|
|
80
|
+
### Merge three or more annotations
|
|
81
|
+
|
|
82
|
+
Use repeated `--add` arguments. Files are merged in the order provided.
|
|
83
|
+
|
|
84
|
+
```bash
|
|
85
|
+
gffkit complement \
|
|
86
|
+
--ref EviAnn.gff3 \
|
|
87
|
+
--add ANNEVO.gff3 \
|
|
88
|
+
--add Helixer.gff3 \
|
|
89
|
+
--add PASA.gff3 \
|
|
90
|
+
--output merged.multi.gff3 \
|
|
91
|
+
-t 8
|
|
92
|
+
```
|
|
93
|
+
|
|
78
94
|
## Command overview
|
|
79
95
|
|
|
80
96
|
```bash
|
|
@@ -85,11 +101,30 @@ gffkit add-utr --help
|
|
|
85
101
|
gffkit integrate --help
|
|
86
102
|
```
|
|
87
103
|
|
|
104
|
+
## Threads
|
|
105
|
+
|
|
106
|
+
Version 0.3 and later add `-t/--threads`.
|
|
107
|
+
|
|
108
|
+
- `detect-bridge` analyzes genes in parallel.
|
|
109
|
+
- `complement` pre-parses multiple `--add` files in parallel, then merges them in the original command-line order.
|
|
110
|
+
- `integrate` passes the thread count to the detect and complement steps.
|
|
111
|
+
|
|
112
|
+
Example:
|
|
113
|
+
|
|
114
|
+
```bash
|
|
115
|
+
gffkit integrate --annotation-a EviAnn.gff3 --annotation-b ANNEVO.gff3 -t 16
|
|
116
|
+
```
|
|
117
|
+
|
|
88
118
|
## Annotation integration strategy
|
|
89
119
|
|
|
90
120
|
- Annotation A, for example EviAnn/RNA-seq-supported GFF, is used as the global primary reference.
|
|
91
121
|
- Annotation B, for example ANNEVO/deep-learning GFF, is used as the local primary reference only in suspicious merged-gene regions.
|
|
92
122
|
- UTR features are reconstructed after merging using an exon-minus-CDS strategy.
|
|
123
|
+
- When multiple tools annotate the same gene locus, the GFF source column is combined with `|`, for example `EviAnn|ANNEVO`.
|
|
124
|
+
|
|
125
|
+
## Maintainer notes
|
|
126
|
+
|
|
127
|
+
When command-line options or behavior changes, update this `README.md` in the versioned package directory before building and uploading to PyPI.
|
|
93
128
|
|
|
94
129
|
## License
|
|
95
130
|
|
|
@@ -23,7 +23,8 @@ gffkit integrate \
|
|
|
23
23
|
--annotation-a EviAnn.gff3 \
|
|
24
24
|
--annotation-b ANNEVO.gff3 \
|
|
25
25
|
--outdir gffkit_out \
|
|
26
|
-
--prefix sample
|
|
26
|
+
--prefix sample \
|
|
27
|
+
-t 8
|
|
27
28
|
```
|
|
28
29
|
|
|
29
30
|
Outputs:
|
|
@@ -36,7 +37,7 @@ Outputs:
|
|
|
36
37
|
|
|
37
38
|
```bash
|
|
38
39
|
# 1. Detect suspicious merged genes in Annotation A
|
|
39
|
-
gffkit detect-bridge -i EviAnn.gff3 -o suspicious.tsv
|
|
40
|
+
gffkit detect-bridge -i EviAnn.gff3 -o suspicious.tsv -t 8
|
|
40
41
|
|
|
41
42
|
# 2. Use A as the global reference, but switch to B in suspicious regions
|
|
42
43
|
gffkit complement \
|
|
@@ -44,12 +45,27 @@ gffkit complement \
|
|
|
44
45
|
--add ANNEVO.gff3 \
|
|
45
46
|
--swap_region_tsv suspicious.tsv \
|
|
46
47
|
--swap_region_flank 100 \
|
|
47
|
-
--output merged.gff3
|
|
48
|
+
--output merged.gff3 \
|
|
49
|
+
-t 8
|
|
48
50
|
|
|
49
51
|
# 3. Add UTR features
|
|
50
52
|
gffkit add-utr -i merged.gff3 -o final.annotation.withUTR.gff3
|
|
51
53
|
```
|
|
52
54
|
|
|
55
|
+
### Merge three or more annotations
|
|
56
|
+
|
|
57
|
+
Use repeated `--add` arguments. Files are merged in the order provided.
|
|
58
|
+
|
|
59
|
+
```bash
|
|
60
|
+
gffkit complement \
|
|
61
|
+
--ref EviAnn.gff3 \
|
|
62
|
+
--add ANNEVO.gff3 \
|
|
63
|
+
--add Helixer.gff3 \
|
|
64
|
+
--add PASA.gff3 \
|
|
65
|
+
--output merged.multi.gff3 \
|
|
66
|
+
-t 8
|
|
67
|
+
```
|
|
68
|
+
|
|
53
69
|
## Command overview
|
|
54
70
|
|
|
55
71
|
```bash
|
|
@@ -60,11 +76,30 @@ gffkit add-utr --help
|
|
|
60
76
|
gffkit integrate --help
|
|
61
77
|
```
|
|
62
78
|
|
|
79
|
+
## Threads
|
|
80
|
+
|
|
81
|
+
Version 0.3 and later add `-t/--threads`.
|
|
82
|
+
|
|
83
|
+
- `detect-bridge` analyzes genes in parallel.
|
|
84
|
+
- `complement` pre-parses multiple `--add` files in parallel, then merges them in the original command-line order.
|
|
85
|
+
- `integrate` passes the thread count to the detect and complement steps.
|
|
86
|
+
|
|
87
|
+
Example:
|
|
88
|
+
|
|
89
|
+
```bash
|
|
90
|
+
gffkit integrate --annotation-a EviAnn.gff3 --annotation-b ANNEVO.gff3 -t 16
|
|
91
|
+
```
|
|
92
|
+
|
|
63
93
|
## Annotation integration strategy
|
|
64
94
|
|
|
65
95
|
- Annotation A, for example EviAnn/RNA-seq-supported GFF, is used as the global primary reference.
|
|
66
96
|
- Annotation B, for example ANNEVO/deep-learning GFF, is used as the local primary reference only in suspicious merged-gene regions.
|
|
67
97
|
- UTR features are reconstructed after merging using an exon-minus-CDS strategy.
|
|
98
|
+
- When multiple tools annotate the same gene locus, the GFF source column is combined with `|`, for example `EviAnn|ANNEVO`.
|
|
99
|
+
|
|
100
|
+
## Maintainer notes
|
|
101
|
+
|
|
102
|
+
When command-line options or behavior changes, update this `README.md` in the versioned package directory before building and uploading to PyPI.
|
|
68
103
|
|
|
69
104
|
## License
|
|
70
105
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: gffkit
|
|
3
|
-
Version: 0.3
|
|
3
|
+
Version: 0.3.1
|
|
4
4
|
Summary: Region-aware GFF annotation integration toolkit
|
|
5
5
|
Author: Qunjie Zhang
|
|
6
6
|
License: MIT
|
|
@@ -48,7 +48,8 @@ gffkit integrate \
|
|
|
48
48
|
--annotation-a EviAnn.gff3 \
|
|
49
49
|
--annotation-b ANNEVO.gff3 \
|
|
50
50
|
--outdir gffkit_out \
|
|
51
|
-
--prefix sample
|
|
51
|
+
--prefix sample \
|
|
52
|
+
-t 8
|
|
52
53
|
```
|
|
53
54
|
|
|
54
55
|
Outputs:
|
|
@@ -61,7 +62,7 @@ Outputs:
|
|
|
61
62
|
|
|
62
63
|
```bash
|
|
63
64
|
# 1. Detect suspicious merged genes in Annotation A
|
|
64
|
-
gffkit detect-bridge -i EviAnn.gff3 -o suspicious.tsv
|
|
65
|
+
gffkit detect-bridge -i EviAnn.gff3 -o suspicious.tsv -t 8
|
|
65
66
|
|
|
66
67
|
# 2. Use A as the global reference, but switch to B in suspicious regions
|
|
67
68
|
gffkit complement \
|
|
@@ -69,12 +70,27 @@ gffkit complement \
|
|
|
69
70
|
--add ANNEVO.gff3 \
|
|
70
71
|
--swap_region_tsv suspicious.tsv \
|
|
71
72
|
--swap_region_flank 100 \
|
|
72
|
-
--output merged.gff3
|
|
73
|
+
--output merged.gff3 \
|
|
74
|
+
-t 8
|
|
73
75
|
|
|
74
76
|
# 3. Add UTR features
|
|
75
77
|
gffkit add-utr -i merged.gff3 -o final.annotation.withUTR.gff3
|
|
76
78
|
```
|
|
77
79
|
|
|
80
|
+
### Merge three or more annotations
|
|
81
|
+
|
|
82
|
+
Use repeated `--add` arguments. Files are merged in the order provided.
|
|
83
|
+
|
|
84
|
+
```bash
|
|
85
|
+
gffkit complement \
|
|
86
|
+
--ref EviAnn.gff3 \
|
|
87
|
+
--add ANNEVO.gff3 \
|
|
88
|
+
--add Helixer.gff3 \
|
|
89
|
+
--add PASA.gff3 \
|
|
90
|
+
--output merged.multi.gff3 \
|
|
91
|
+
-t 8
|
|
92
|
+
```
|
|
93
|
+
|
|
78
94
|
## Command overview
|
|
79
95
|
|
|
80
96
|
```bash
|
|
@@ -85,11 +101,30 @@ gffkit add-utr --help
|
|
|
85
101
|
gffkit integrate --help
|
|
86
102
|
```
|
|
87
103
|
|
|
104
|
+
## Threads
|
|
105
|
+
|
|
106
|
+
Version 0.3 and later add `-t/--threads`.
|
|
107
|
+
|
|
108
|
+
- `detect-bridge` analyzes genes in parallel.
|
|
109
|
+
- `complement` pre-parses multiple `--add` files in parallel, then merges them in the original command-line order.
|
|
110
|
+
- `integrate` passes the thread count to the detect and complement steps.
|
|
111
|
+
|
|
112
|
+
Example:
|
|
113
|
+
|
|
114
|
+
```bash
|
|
115
|
+
gffkit integrate --annotation-a EviAnn.gff3 --annotation-b ANNEVO.gff3 -t 16
|
|
116
|
+
```
|
|
117
|
+
|
|
88
118
|
## Annotation integration strategy
|
|
89
119
|
|
|
90
120
|
- Annotation A, for example EviAnn/RNA-seq-supported GFF, is used as the global primary reference.
|
|
91
121
|
- Annotation B, for example ANNEVO/deep-learning GFF, is used as the local primary reference only in suspicious merged-gene regions.
|
|
92
122
|
- UTR features are reconstructed after merging using an exon-minus-CDS strategy.
|
|
123
|
+
- When multiple tools annotate the same gene locus, the GFF source column is combined with `|`, for example `EviAnn|ANNEVO`.
|
|
124
|
+
|
|
125
|
+
## Maintainer notes
|
|
126
|
+
|
|
127
|
+
When command-line options or behavior changes, update this `README.md` in the versioned package directory before building and uploading to PyPI.
|
|
93
128
|
|
|
94
129
|
## License
|
|
95
130
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|