jkbiolib 1.0.0__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.
Files changed (56) hide show
  1. jkbiolib-1.0.0/PKG-INFO +7 -0
  2. jkbiolib-1.0.0/README.md +0 -0
  3. jkbiolib-1.0.0/doc/bcftools.md +17 -0
  4. jkbiolib-1.0.0/doc/bedtools.md +8 -0
  5. jkbiolib-1.0.0/doc/environments/star_fusion.yml +235 -0
  6. jkbiolib-1.0.0/doc/fastq.md +12 -0
  7. jkbiolib-1.0.0/doc/star-fusion.qmd +17 -0
  8. jkbiolib-1.0.0/doc/thousg.md +15 -0
  9. jkbiolib-1.0.0/jkbiolib/.gitignore +1 -0
  10. jkbiolib-1.0.0/jkbiolib/__init__.py +0 -0
  11. jkbiolib-1.0.0/jkbiolib/data/gencode.v19.annotation.gtf.exons.bed.sorted.gz +0 -0
  12. jkbiolib-1.0.0/jkbiolib/data/gencode.v19.annotation.gtf.gene.bed.sorted.gz +0 -0
  13. jkbiolib-1.0.0/jkbiolib/data/thousg-rna-long_read-samples.tsv +61 -0
  14. jkbiolib-1.0.0/jkbiolib/data/thousg-rna-short_read-samples.tsv +1559 -0
  15. jkbiolib-1.0.0/jkbiolib/data/thousg-short_read-high_cov.index.tsv +2528 -0
  16. jkbiolib-1.0.0/jkbiolib/datasets/.gitignore +1 -0
  17. jkbiolib-1.0.0/jkbiolib/datasets/__init__.py +0 -0
  18. jkbiolib-1.0.0/jkbiolib/datasets/loaders.py +57 -0
  19. jkbiolib-1.0.0/jkbiolib/download.py +55 -0
  20. jkbiolib-1.0.0/jkbiolib/variant/.gitignore +1 -0
  21. jkbiolib-1.0.0/jkbiolib/variant/__init__.py +0 -0
  22. jkbiolib-1.0.0/jkbiolib/variant/convert.py +84 -0
  23. jkbiolib-1.0.0/jkbiolib/variant/vcf.py +79 -0
  24. jkbiolib-1.0.0/pyproject.toml +42 -0
  25. jkbiolib-1.0.0/pyproject.toml.cp +25 -0
  26. jkbiolib-1.0.0/tests/.gitignore +1 -0
  27. jkbiolib-1.0.0/tests/README.md +6 -0
  28. jkbiolib-1.0.0/tests/data/.gitignore +4 -0
  29. jkbiolib-1.0.0/tests/data/.gitkeep +0 -0
  30. jkbiolib-1.0.0/tests/data/ALL.wgs.mergedSV.v8.20130502.svs.genotypes.vcf.gz.tbi +0 -0
  31. jkbiolib-1.0.0/tests/data/download_data.sh +10 -0
  32. jkbiolib-1.0.0/tests/data/genotypes.vcf.gz +0 -0
  33. jkbiolib-1.0.0/tests/data/genotypes.vcf.gz.tbi +0 -0
  34. jkbiolib-1.0.0/tests/data/split/0---DUP_gs_CNV_22_16050654_16063474---22_16050654_16063474_CNV.vcf +72 -0
  35. jkbiolib-1.0.0/tests/data/split/1---SI_BD_17525---22_16533236_16536204_DEL.vcf +72 -0
  36. jkbiolib-1.0.0/tests/data/split/2---YL_CN_CEU_5170---22_16577743_16613100_DEL.vcf +72 -0
  37. jkbiolib-1.0.0/tests/data/split/3---SI_BD_17528---22_16589908_16605656_DEL.vcf +72 -0
  38. jkbiolib-1.0.0/tests/data/split/4---YL_CN_STU_4360---22_16633635_16655786_DEL.vcf +72 -0
  39. jkbiolib-1.0.0/tests/data/split/5---DUP_gs_CNV_22_16877183_16965103---22_16877183_16965103_CNV.vcf +72 -0
  40. jkbiolib-1.0.0/tests/data/split/6---SVA_umary_SVA_814---22_16918023__SVA.vcf +72 -0
  41. jkbiolib-1.0.0/tests/data/split/7---BI_GS_DEL1_B2_P2862_55---22_16940402_16944607_DEL.vcf +72 -0
  42. jkbiolib-1.0.0/tests/data/split/8---UW_VH_15403---22_16942602_16945851_DEL.vcf +72 -0
  43. jkbiolib-1.0.0/tests/data/split/BI_GS_DEL1_B2_P2862_55---22_16940402_16944607_DEL.vcf +72 -0
  44. jkbiolib-1.0.0/tests/data/split/DUP_gs_CNV_22_16050654_16063474---22_16050654_16063474_CNV.vcf +72 -0
  45. jkbiolib-1.0.0/tests/data/split/DUP_gs_CNV_22_16877183_16965103---22_16877183_16965103_CNV.vcf +72 -0
  46. jkbiolib-1.0.0/tests/data/split/SI_BD_17525---22_16533236_16536204_DEL.vcf +72 -0
  47. jkbiolib-1.0.0/tests/data/split/SI_BD_17528---22_16589908_16605656_DEL.vcf +72 -0
  48. jkbiolib-1.0.0/tests/data/split/SVA_umary_SVA_814.vcf +72 -0
  49. jkbiolib-1.0.0/tests/data/split/UW_VH_15403---22_16942602_16945851_DEL.vcf +72 -0
  50. jkbiolib-1.0.0/tests/data/split/YL_CN_CEU_5170---22_16577743_16613100_DEL.vcf +72 -0
  51. jkbiolib-1.0.0/tests/data/split/YL_CN_STU_4360---22_16633635_16655786_DEL.vcf +72 -0
  52. jkbiolib-1.0.0/tests/data/stix_queries.txt +7 -0
  53. jkbiolib-1.0.0/tests/data/variants.bed +10 -0
  54. jkbiolib-1.0.0/tests/test_dataset_loaders.py +14 -0
  55. jkbiolib-1.0.0/tests/test_variant.py +40 -0
  56. jkbiolib-1.0.0/uv.lock +775 -0
jkbiolib-1.0.0/PKG-INFO ADDED
@@ -0,0 +1,7 @@
1
+ Metadata-Version: 2.5
2
+ Name: jkbiolib
3
+ Version: 1.0.0
4
+ Summary: Bioinformatics library
5
+ Requires-Python: >=3.11
6
+ Requires-Dist: cyvcf2>=0.30
7
+ Requires-Dist: pandas>=3.0.3
jkbiolib-1.0.0/README.md ADDED
File without changes
jkbiolib-1.0.0/doc/bcftools.md ADDED
@@ -0,0 +1,17 @@
1
+ # bcftools
2
+
3
+ intersect two vcf files. exact position matching, unlike bedtools intersect.
4
+ ```
5
+ # --nfiles=2: variant must be both files
6
+ # --write 1: write the variants only in the first file
7
+ # --collapse all: compare genomic position only; genotypes do not matter
8
+ # --output-type z: compressed vcf
9
+ # --output: outfile
10
+ bcftools isec \
11
+ --nfiles=2 \
12
+ --write 1 \
13
+ --collapse all \
14
+ --output-type z \
15
+ --output $vcf_out \
16
+ $vcf_a $vcf_b
17
+ ```
jkbiolib-1.0.0/doc/bedtools.md ADDED
@@ -0,0 +1,8 @@
1
+ # bedtools
2
+
3
+
4
+ report records overlapping A and B. include the info from both A and B (wa,wb)
5
+ ```
6
+ bedtools intersect \
7
+ -a A.bed -b B.bed -u
8
+ ```
jkbiolib-1.0.0/doc/environments/star_fusion.yml ADDED
@@ -0,0 +1,235 @@
1
+ name: star_fusion_test
2
+ channels:
3
+ - ggd-genomics
4
+ - bioconda
5
+ - conda-forge
6
+ - defaults
7
+ dependencies:
8
+ - _openmp_mutex=4.5=20_gnu
9
+ - _r-mutex=1.0.1=anacondar_1
10
+ - binutils_impl_linux-64=2.45.1=default_hfdba357_102
11
+ - bwidget=1.10.1=ha770c72_1
12
+ - bzip2=1.0.8=hda65f42_9
13
+ - c-ares=1.34.6=hb03c661_0
14
+ - ca-certificates=2026.4.22=hbd8a1cb_0
15
+ - cairo=1.18.4=he90730b_1
16
+ - curl=8.20.0=hcf29cc6_0
17
+ - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
18
+ - font-ttf-inconsolata=3.000=h77eed37_0
19
+ - font-ttf-source-code-pro=2.038=h77eed37_0
20
+ - font-ttf-ubuntu=0.83=h77eed37_3
21
+ - fontconfig=2.17.1=h27c8c51_0
22
+ - fonts-conda-ecosystem=1=0
23
+ - fonts-conda-forge=1=hc364b38_1
24
+ - fribidi=1.0.16=hb03c661_0
25
+ - gcc_impl_linux-64=15.2.0=he0086c7_19
26
+ - gfortran_impl_linux-64=15.2.0=h281d09f_19
27
+ - graphite2=1.3.14=hecca717_2
28
+ - gsl=2.7=he838d99_0
29
+ - gxx_impl_linux-64=15.2.0=hda75c37_19
30
+ - harfbuzz=14.2.0=h6083320_0
31
+ - htslib=1.23.1=h633afcb_0
32
+ - icu=78.3=h33c6efd_0
33
+ - kernel-headers_linux-64=5.14.0=he073ed8_3
34
+ - keyutils=1.6.3=hb9d3cd8_0
35
+ - krb5=1.22.2=ha1258a1_0
36
+ - ld_impl_linux-64=2.45.1=default_hbd61a6d_102
37
+ - lerc=4.1.0=hdb68285_0
38
+ - libblas=3.11.0=7_h4a7cf45_openblas
39
+ - libcblas=3.11.0=7_h0358290_openblas
40
+ - libcurl=8.20.0=hcf29cc6_0
41
+ - libdb=6.2.32=h9c3ff4c_0
42
+ - libdeflate=1.25=h17f619e_0
43
+ - libedit=3.1.20250104=pl5321h7949ede_0
44
+ - libev=4.33=hd590300_2
45
+ - libexpat=2.8.0=hecca717_0
46
+ - libffi=3.5.2=h3435931_0
47
+ - libfreetype=2.14.3=ha770c72_0
48
+ - libfreetype6=2.14.3=h73754d4_0
49
+ - libgcc=15.2.0=he0feb66_19
50
+ - libgcc-devel_linux-64=15.2.0=hcc6f6b0_119
51
+ - libgcc-ng=15.2.0=h69a702a_19
52
+ - libgfortran=15.2.0=h69a702a_19
53
+ - libgfortran-ng=15.2.0=h69a702a_19
54
+ - libgfortran5=15.2.0=h68bc16d_19
55
+ - libglib=2.88.1=h0d30a3d_2
56
+ - libgomp=15.2.0=he0feb66_19
57
+ - libiconv=1.18=h3b78370_2
58
+ - libjpeg-turbo=3.1.4.1=hb03c661_0
59
+ - liblapack=3.11.0=7_h47877c9_openblas
60
+ - liblzma=5.8.3=hb03c661_0
61
+ - libnghttp2=1.68.1=h877daf1_0
62
+ - libopenblas=0.3.33=pthreads_h94d23a6_0
63
+ - libpng=1.6.58=h421ea60_0
64
+ - libsanitizer=15.2.0=h90f66d4_19
65
+ - libssh2=1.11.1=hcf80075_0
66
+ - libstdcxx=15.2.0=h934c35e_19
67
+ - libstdcxx-devel_linux-64=15.2.0=hd446a21_119
68
+ - libstdcxx-ng=15.2.0=hdf11a46_19
69
+ - libtiff=4.7.1=h9d88235_1
70
+ - libuuid=2.42.1=h5347b49_0
71
+ - libuv=1.51.0=hb03c661_1
72
+ - libwebp-base=1.6.0=hd42ef1d_0
73
+ - libxcb=1.17.0=h8a09558_0
74
+ - libxcrypt=4.4.36=hd590300_1
75
+ - libxml2=2.15.3=h49c6c72_0
76
+ - libxml2-16=2.15.3=hca6bf5a_0
77
+ - libzlib=1.3.2=h25fd6f3_2
78
+ - make=4.4.1=hb9d3cd8_2
79
+ - ncurses=6.6=hdb14827_0
80
+ - openssl=3.6.2=h35e630c_0
81
+ - pandoc=3.9.0.2=ha770c72_0
82
+ - pango=1.56.4=hda50119_1
83
+ - pcre2=10.47=haa7fec5_0
84
+ - perl=5.32.1=7_hd590300_perl5
85
+ - perl-business-isbn=3.007=pl5321hd8ed1ab_0
86
+ - perl-business-isbn-data=20210112.006=pl5321hd8ed1ab_0
87
+ - perl-capture-tiny=0.48=pl5321ha770c72_1
88
+ - perl-carp=1.50=pl5321hd8ed1ab_0
89
+ - perl-carp-assert=0.21=pl5321hd8ed1ab_1
90
+ - perl-common-sense=3.75=pl5321hd8ed1ab_0
91
+ - perl-db_file=1.858=pl5321hb9d3cd8_0
92
+ - perl-exporter=5.74=pl5321hd8ed1ab_0
93
+ - perl-extutils-cppguess=0.26=pl5321h9948957_4
94
+ - perl-extutils-makemaker=7.70=pl5321hd8ed1ab_0
95
+ - perl-extutils-manifest=1.75=pl5321hdfd78af_0
96
+ - perl-inc-latest=0.500=pl5321ha770c72_0
97
+ - perl-json-xs=4.04=pl5321h9948957_0
98
+ - perl-module-build=0.4234=pl5321ha770c72_1
99
+ - perl-perlio-gzip=0.20=pl5321h577a1d6_7
100
+ - perl-set-intervaltree=0.12=pl5321h503566f_6
101
+ - perl-test-fatal=0.016=pl5321ha770c72_0
102
+ - perl-test-warnings=0.031=pl5321ha770c72_0
103
+ - perl-try-tiny=0.31=pl5321ha770c72_0
104
+ - perl-types-serialiser=1.01=pl5321hdfd78af_0
105
+ - perl-uri=5.34=pl5321ha770c72_0
106
+ - pixman=0.46.4=h54a6638_1
107
+ - pthread-stubs=0.4=hb9d3cd8_1002
108
+ - r-askpass=1.2.1=r45h54b55ab_1
109
+ - r-assertthat=0.2.1=r45hc72bb7e_6
110
+ - r-backports=1.5.1=r45h54b55ab_0
111
+ - r-base=4.5.3=h15dba0b_1
112
+ - r-base64enc=0.1_6=r45h54b55ab_0
113
+ - r-bit=4.6.0=r45h54b55ab_1
114
+ - r-bit64=4.8.0=r45h54b55ab_0
115
+ - r-blob=1.3.0=r45hc72bb7e_0
116
+ - r-broom=1.0.13=r45hc72bb7e_0
117
+ - r-bslib=0.11.0=r45hc72bb7e_0
118
+ - r-cachem=1.1.0=r45h54b55ab_2
119
+ - r-callr=3.7.6=r45hc72bb7e_2
120
+ - r-cellranger=1.1.0=r45hc72bb7e_1008
121
+ - r-cli=3.6.6=r45h3697838_0
122
+ - r-clipr=0.8.0=r45hc72bb7e_4
123
+ - r-colorspace=2.1_2=r45h54b55ab_0
124
+ - r-conflicted=1.2.0=r45h785f33e_3
125
+ - r-cpp11=0.5.5=r45h785f33e_0
126
+ - r-crayon=1.5.3=r45hc72bb7e_2
127
+ - r-curl=7.1.0=r45h10955f1_0
128
+ - r-data.table=1.17.8=r45h1c8cec4_1
129
+ - r-dbi=1.3.0=r45hc72bb7e_0
130
+ - r-dbplyr=2.5.2=r45hc72bb7e_0
131
+ - r-digest=0.6.39=r45h3697838_0
132
+ - r-dplyr=1.2.1=r45h3697838_0
133
+ - r-dtplyr=1.3.3=r45hc72bb7e_0
134
+ - r-ellipsis=0.3.3=r45h54b55ab_0
135
+ - r-evaluate=1.0.5=r45hc72bb7e_1
136
+ - r-fansi=1.0.7=r45h54b55ab_0
137
+ - r-farver=2.1.2=r45h3697838_2
138
+ - r-fastmap=1.2.0=r45h3697838_2
139
+ - r-fontawesome=0.5.3=r45hc72bb7e_1
140
+ - r-forcats=1.0.1=r45hc72bb7e_0
141
+ - r-fs=2.1.0=r45h3697838_0
142
+ - r-gargle=1.6.1=r45h785f33e_0
143
+ - r-generics=0.1.4=r45hc72bb7e_1
144
+ - r-ggplot2=4.0.3=r45h785f33e_0
145
+ - r-glue=1.8.1=r45h54b55ab_0
146
+ - r-googledrive=2.1.2=r45hc72bb7e_1
147
+ - r-googlesheets4=1.1.2=r45h785f33e_1
148
+ - r-gtable=0.3.6=r45hc72bb7e_1
149
+ - r-haven=2.5.5=r45h6d565e7_1
150
+ - r-highr=0.12=r45hc72bb7e_0
151
+ - r-hms=1.1.4=r45hc72bb7e_0
152
+ - r-htmltools=0.5.9=r45h3697838_0
153
+ - r-httr=1.4.8=r45hc72bb7e_0
154
+ - r-ids=1.0.1=r45hc72bb7e_5
155
+ - r-isoband=0.3.0=r45h3697838_0
156
+ - r-jquerylib=0.1.4=r45hc72bb7e_4
157
+ - r-jsonlite=2.0.0=r45h54b55ab_1
158
+ - r-knitr=1.51=r45hc72bb7e_0
159
+ - r-labeling=0.4.3=r45hc72bb7e_2
160
+ - r-lattice=0.22_9=r45h54b55ab_0
161
+ - r-lifecycle=1.0.5=r45hc72bb7e_0
162
+ - r-lubridate=1.9.5=r45h54b55ab_0
163
+ - r-magrittr=2.0.5=r45h54b55ab_0
164
+ - r-matrix=1.7_5=r45h0e4624f_0
165
+ - r-memoise=2.0.1=r45hc72bb7e_4
166
+ - r-mime=0.13=r45h54b55ab_1
167
+ - r-modelr=0.1.11=r45hc72bb7e_3
168
+ - r-munsell=0.5.1=r45hc72bb7e_2
169
+ - r-openssl=2.4.1=r45h68c19f5_0
170
+ - r-pillar=1.11.1=r45hc72bb7e_0
171
+ - r-pkgconfig=2.0.3=r45hc72bb7e_5
172
+ - r-prettyunits=1.2.0=r45hc72bb7e_2
173
+ - r-processx=3.9.0=r45h54b55ab_0
174
+ - r-progress=1.2.3=r45hc72bb7e_2
175
+ - r-ps=1.9.3=r45h54b55ab_0
176
+ - r-purrr=1.2.2=r45h54b55ab_0
177
+ - r-r6=2.6.1=r45hc72bb7e_1
178
+ - r-ragg=1.5.2=r45h9f1dc4d_0
179
+ - r-ranger=0.18.0=r45h3697838_0
180
+ - r-rappdirs=0.3.4=r45h54b55ab_0
181
+ - r-rcolorbrewer=1.1_3=r45h785f33e_4
182
+ - r-rcpp=1.1.1_1.1=r45h3697838_0
183
+ - r-rcppeigen=0.3.4.0.2=r45h3704496_1
184
+ - r-readr=2.2.0=r45h3697838_0
185
+ - r-readxl=1.5.0=r45h10e25cc_0
186
+ - r-rematch=2.0.0=r45hc72bb7e_2
187
+ - r-rematch2=2.1.2=r45hc72bb7e_5
188
+ - r-reprex=2.1.1=r45hc72bb7e_2
189
+ - r-rlang=1.2.0=r45h3697838_0
190
+ - r-rmarkdown=2.31=r45hc72bb7e_0
191
+ - r-rstudioapi=0.18.0=r45hc72bb7e_0
192
+ - r-rvest=1.0.5=r45hc72bb7e_1
193
+ - r-s7=0.2.2=r45h54b55ab_0
194
+ - r-sass=0.4.10=r45h3697838_1
195
+ - r-scales=1.4.0=r45hc72bb7e_1
196
+ - r-selectr=0.5_1=r45hc72bb7e_0
197
+ - r-stringi=1.8.7=r45h3d52c89_2
198
+ - r-stringr=1.6.0=r45h785f33e_0
199
+ - r-sys=3.4.3=r45h54b55ab_1
200
+ - r-systemfonts=1.3.2=r45h74f4acd_0
201
+ - r-textshaping=1.0.5=r45h74f4acd_0
202
+ - r-tibble=3.3.1=r45h54b55ab_0
203
+ - r-tidyr=1.3.2=r45h3697838_0
204
+ - r-tidyselect=1.2.1=r45hc72bb7e_2
205
+ - r-tidyverse=2.0.0=r45h785f33e_3
206
+ - r-timechange=0.4.0=r45h3697838_0
207
+ - r-tinytex=0.59=r45hc72bb7e_0
208
+ - r-tzdb=0.5.0=r45h3697838_2
209
+ - r-utf8=1.2.6=r45h54b55ab_1
210
+ - r-uuid=1.2_2=r45h54b55ab_0
211
+ - r-vctrs=0.7.3=r45h3697838_0
212
+ - r-viridislite=0.4.3=r45hc72bb7e_0
213
+ - r-vroom=1.7.1=r45h3697838_0
214
+ - r-withr=3.0.2=r45hc72bb7e_1
215
+ - r-xfun=0.57=r45h3697838_0
216
+ - r-xml2=1.5.2=r45he78afff_0
217
+ - r-yaml=2.3.12=r45h54b55ab_0
218
+ - readline=8.3=h853b02a_0
219
+ - samtools=1.23.1=ha83d96e_0
220
+ - sed=4.10=h19d0853_0
221
+ - star=2.7.11b=h5ca1c30_8
222
+ - sysroot_linux-64=2.34=h087de78_3
223
+ - tk=8.6.13=noxft_h366c992_103
224
+ - tktable=2.10=h5a7a40f_8
225
+ - tzdata=2025c=hc9c84f9_1
226
+ - xorg-libice=1.1.2=hb9d3cd8_0
227
+ - xorg-libsm=1.2.6=he73a12e_0
228
+ - xorg-libx11=1.8.13=he1eb515_0
229
+ - xorg-libxau=1.0.12=hb03c661_1
230
+ - xorg-libxdmcp=1.1.5=hb03c661_1
231
+ - xorg-libxext=1.3.7=hb03c661_0
232
+ - xorg-libxrender=0.9.12=hb9d3cd8_0
233
+ - xorg-libxt=1.3.1=hb9d3cd8_0
234
+ - zlib=1.3.2=h25fd6f3_2
235
+ - zstd=1.5.7=hb78ec9c_6
jkbiolib-1.0.0/doc/fastq.md ADDED
@@ -0,0 +1,12 @@
1
+ # fastq examples
2
+
3
+
4
+ Downsample fastq to 100k reads
5
+ ```
6
+ # https://onestopdataanalysis.com/subsample-paired-fastq-fasta/
7
+ # FASTQ R1
8
+ seqtk sample -s 123 read1.fq 100000 > sub_read1.fq
9
+
10
+ # FASTQ R2
11
+ seqtk sample -s 123 read2.fq 100000 > sub_read2.fq
12
+ ```
jkbiolib-1.0.0/doc/star-fusion.qmd ADDED
@@ -0,0 +1,17 @@
1
+ # star-fusion
2
+
3
+ Example cancer cell line data from Cancer Cell Line Encyclopedia
4
+
5
+ K562 cell line
6
+ - https://zenodo.org/records/13363154/files/SRR521460_1.fastq.20M.fq.gz?download=1
7
+ - https://zenodo.org/records/13363154/files/SRR521460_2.fastq.20M.fq.gz?download=1
8
+
9
+ Do not use -J mode. Instead, call fusions on fastq directly
10
+ ```
11
+ # download the genome lib dir (33GB)
12
+ # url: https://data.broadinstitute.org/Trinity/CTAT_RESOURCE_LIB/GRCh37_gencode_v19_CTAT_lib_Mar012021.STAR_v2.7.11a.plug-n-play.tar.gz
13
+ GENOME_LIB_DIR="<path_to_genome_lib_dir>"
14
+ STAR-Fusion --genome_lib_dir $GENOME_LIB_DIR \
15
+ --left_fq read_1.fastq \
16
+ --right_fq read_2.fastq \
17
+ --output_dir star_fusion_outdir
jkbiolib-1.0.0/doc/thousg.md ADDED
@@ -0,0 +1,15 @@
1
+ # 1000 Genomes
2
+
3
+
4
+ ## RNA-seq
5
+
6
+ hg00100 mage rna-seq, paired-end
7
+
8
+ ``` python
9
+ host='ftp.sra.ebi.ac.uk'
10
+ remote_file='/vol1/fastq/SRR197/065/SRR19762765/SRR19762765_2.fastq.gz'
11
+ local_file='hg00100.mage.rna.fastq2.gz'
12
+ start_byte=0
13
+ bytes_to_get=int(1e6)
14
+ download_ftp_chunk(host,remote_file, local_file,start_byte,bytes_to_get)
15
+ ```
jkbiolib-1.0.0/jkbiolib/.gitignore ADDED
@@ -0,0 +1 @@
1
+ __pycache__/*
jkbiolib-1.0.0/jkbiolib/__init__.py ADDED
File without changes
jkbiolib-1.0.0/jkbiolib/data/thousg-rna-long_read-samples.tsv ADDED
@@ -0,0 +1,61 @@
1
+ url md5 Data collection Data type Analysis group Sample Population Data reuse policy
2
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350342/GM06985.tar.gz 5e55f6c25b4a8dd72851aa04b6f32d07 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA06985 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
3
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350343/GM07037.tar.gz 7c9f3efb29c365c4b5ad6eb5554299bd Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA07037 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
4
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350344/GM07051.tar.gz fe5ebc7ce6dd4baeede24595c0f06020 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA07051 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
5
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350345/GM07357.tar.gz 96f6567d1268bf4f399071e628f89b2a Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA07357 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
6
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350346/GM10847.tar.gz 71d3222b14768e93209b43c09f1aabde Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA10847 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
7
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350347/GM10851.tar.gz 4354057946f195e8549618dd30a649a8 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA10851 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
8
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350348/GM11831.tar.gz 2ab938ff9a1670be4666bd9894f998bc Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA11831 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
9
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350349/GM11840.tar.gz 47b2f0f3668deebadfcd65339b8e7ba7 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA11840 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
10
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350350/GM11894.tar.gz 93ddb0c2b57eb442c32de930fb8d1554 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA11894 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
11
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350351/GM11918.tar.gz 64e731c50cbf0f6dd49e18239d0d7b85 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA11918 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
12
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350352/GM11992.tar.gz 6dcb8af09a537d06a2e47f5dc4b19fec Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA11992 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
13
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350353/GM11993.tar.gz 59b432d8cc3f539af93959b1c016a745 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA11993 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
14
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350354/GM11994.tar.gz 732b89e6d6f3fcde92268eb9552efc91 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA11994 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
15
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350355/GM12005.tar.gz b0b673c282d154af072006e00f0b9281 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12005 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
16
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350356/GM12156.tar.gz 5afb01776021c1c60f99faece9648ea0 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12156 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
17
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350357/GM12249.tar.gz f06c78fa683addd20d3c8cf8590794e1 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12249 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
18
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350358/GM12275.tar.gz 1431eb99b77c4b0a55f8357b110bb450 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12275 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
19
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350359/GM12286.tar.gz a2da00a3c147917ae1c47b05f21522ed Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12286 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
20
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350360/GM12383.tar.gz a8e7faf957a35c86088750e4470ea5c5 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12383 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
21
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350361/GM12489.tar.gz 8608b5ff9debac557b81f2fb5c82d8c7 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12489 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
22
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350362/GM12750.tar.gz e0aab4706be7d2c54fc125017a23903d Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12750 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
23
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350363/GM12760.tar.gz c26930c706e99bc1c1a209cdb8ad7063 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12760 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
24
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350364/GM12761.tar.gz 60f323115dd262b3971be38f8bc67e7c Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12761 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
25
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350365/GM12762.tar.gz 769f458006befd6e11b1e3c9fde70384 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12762 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
26
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350366/GM12763.tar.gz a19dcd260599ec42dfc674a8dc2224b9 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12763 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
27
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350367/GM12776.tar.gz b83edb429ccd3555450fda977f31798d Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12776 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
28
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350368/GM12812.tar.gz 603a91d1a055e3b28a3226437aaf9766 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12812 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
29
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350369/GM12813.tar.gz 59de7e4a4387b89142c16f41b6416fc7 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12813 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
30
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350370/GM12814.tar.gz 56113ff30164818244637ae4c90065ca Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12814 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
31
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350371/GM12815.tar.gz 58bff2d010d3e8f19711482389541571 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12815 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
32
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350372/GM12873.tar.gz 1b858582e07309b7fe4c2c370c305dc3 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies NA12873 Utah residents (CEPH) with Northern and Western European ancestry http://www.1000genomes.org/about#g1k_data_reuse
33
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350373/HG00098.tar.gz de639cdc32fc6d5a0ab373be768c99c0 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00098 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
34
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350374/HG00099.tar.gz d0745aaff02a70b6a16a5e5e39fe4170 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00099 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
35
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350375/HG00100.tar.gz 5c01d82cd25f9cfd26b8e3e3ea5e6721 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00100 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
36
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350376/HG00101.tar.gz 55424d079761e1b38054db8f3631a047 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00101 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
37
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350377/HG00102.tar.gz e4d3ca2794ea3e75cd4a7294e8224e7d Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00102 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
38
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350378/HG00103.tar.gz 65075a30b943c4033b834d45ae509eb5 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00103 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
39
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350379/HG00104.tar.gz 235ffd94e2e49f6dcacdd60eaa6c075f Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00104 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
40
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350380/HG00110.tar.gz ca3398c8790b8e27beb817e637083e95 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00110 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
41
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350381/HG00111.tar.gz 46504e5257ff4d25f387efc6f5dd9f3a Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00111 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
42
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350382/HG00112.tar.gz 49176b49b9d9394b4170de16dccc7589 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00112 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
43
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350383/HG00115.tar.gz 1a988fea123244007decf033fba633e4 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00115 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
44
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350384/HG00116.tar.gz cea3629c75e550dbb2a2b9699fe7f7b9 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00116 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
45
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350385/HG00117.tar.gz b69df0ce2e7217e18e2a1463785d4bde Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00117 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
46
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350386/HG00118.tar.gz 20158e83e92efe6e922f3e9ad9de3ff0 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00118 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
47
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350387/HG00119.tar.gz bc88bdc0c69b198b4cfbb8d97559fb0e Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00119 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
48
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350388/HG00121.tar.gz 855cabb05728a6c996a106a313404b06 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00121 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
49
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350389/HG00124.tar.gz 9f7f02579f88c8f98e1759117fa1a3f1 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00124 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
50
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350390/HG00126.tar.gz 84fc336839ff5fd24b52d2c05359890d Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00126 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
51
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350391/HG00128.tar.gz 20f7bd42256c3cd3bb92c1d13d371c20 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00128 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
52
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350392/HG00138.tar.gz 29a133d31647fd7c2b20b82d5bec29fb Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00138 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
53
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350393/HG00142.tar.gz 50e184dcfe7a0691f07a19c245002867 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00142 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
54
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350394/HG00149.tar.gz 427915c313fa0687098aa5aeda237718 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00149 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
55
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350395/HG00238.tar.gz 66e42de67e270efdf829ad07ac4cbc19 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00238 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
56
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350396/HG00249.tar.gz e015b1adbfe7c1feb1888e591218359d Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00249 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
57
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350397/HG00253.tar.gz b66189725182fdceb47d909cfd10c07f Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00253 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
58
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350398/HG00260.tar.gz 247d7c4d540e8ef5e95a0f5c301d9971 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00260 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
59
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350399/HG00262.tar.gz 136ae1ca9cb2bff46627835d8b2ffe54 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00262 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
60
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350400/HG00263.tar.gz bab4d6bb49ea265e25da28ff5437ec1c Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00263 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse
61
+ ftp://ftp.sra.ebi.ac.uk/vol1/run/ERR133/ERR13350401/HG00265.tar.gz 2cc0c97a92b88af84b8280d2b03945f0 Long-read direct RNA sequencing (ONT) of 60 EUR sequence Oxford Nanopore Technologies HG00265 British in England and Scotland http://www.1000genomes.org/about#g1k_data_reuse