this is for holding javascript data
Steven Roberts mv files
over 9 years ago
Commit id: ef54540df7e6936ca7480b226ddad08c1481dfcc
deletions | additions
diff --git a/.gitignore b/.gitignore
index da7063c..00175b2 100644
--- a/.gitignore
+++ b/.gitignore
...
ipynb/analyses/Cgigas_v9_CG.gff
ipynb/Cgigas_v9_CG.gff
ipynb/data/Cgigas_v9_CG.gff
diff --git a/ipynb/.ipynb_checkpoints/RNA-seq-DEG-features-checkpoint.ipynb b/ipynb/.ipynb_checkpoints/RNA-seq-DEG-features-checkpoint.ipynb
deleted file mode 100644
index e8cb62e..0000000
--- a/ipynb/.ipynb_checkpoints/RNA-seq-DEG-features-checkpoint.ipynb
+++ /dev/null
...
{
"metadata": {
"name": "",
"signature": "sha256:71313570e41da41d15bd67db6a6459f594ca5972c0ae909409bd4c86c09f219a"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": []
}
diff --git a/ipynb/.ipynb_checkpoints/RNA-seq-Gene-ID-checkpoint.ipynb b/ipynb/.ipynb_checkpoints/RNA-seq-Gene-ID-checkpoint.ipynb
new file mode 100644
index 0000000..e40ef82
--- /dev/null
+++ b/ipynb/.ipynb_checkpoints/RNA-seq-Gene-ID-checkpoint.ipynb
...
{
"metadata": {
"name": "",
"signature": "sha256:73fb80bb863e1f9740209284d96835d3b1ec04c670a411cf5a64513ea8e4389b"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"for i in (\"2M_3plusmerge_Hyper\",\"2M_3plusmerge_Hypo\",\"4M_3plusmerge_Hyper\",\"4M_3plusmerge_Hypo\",\"6M_3plusmerge_Hyper\",\"6M_3plusmerge_Hypo\"):\n",
" !intersectbed \\\n",
" -u \\\n",
" -a ./analyses/{i}.gff \\\n",
" -b ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf \\\n",
" > ./analyses/{i}_intersect_rebuilt.txt\n",
" !wc -l ./analyses/{i}_intersect_rebuilt.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 0 ./analyses/2M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 38 ./analyses/2M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 4 ./analyses/4M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 6 ./analyses/4M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 4 ./analyses/6M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 7 ./analyses/6M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!head ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/transcripts.sorted_by_expression.sig.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"transcript\tgene_id\tgene_name\tsample1\tsample2\tfold_change\tdirection\ttotal_fpkm\tq-value\tgene_description\r\n",
"TCONS_00000151\tXLOC_000150\t-\tPre\tPost\t10.39\tDOWN\t73075.04\t0.00719642\t\r\n",
"EKC38373\tCGI_10021746\t.\tPre\tPost\t7.38\tDOWN\t15907.68\t0.00719642\t\r\n",
"TCONS_00059114\tXLOC_028369\t-\tPre\tPost\t3.51\tDOWN\t9471.62\t0.0127885\t\r\n",
"TCONS_00056889\tXLOC_027306\t-\tPre\tPost\t6.06\tDOWN\t7890.30\t0.00719642\t\r\n",
"TCONS_00009938\tXLOC_005260\t-\tPre\tPost\t7.58\tUP\t5938.99\t0.00719642\t\r\n",
"TCONS_00056778\tXLOC_027247\t-\tPre\tPost\t26.46\tDOWN\t4302.28\t0.00719642\t\r\n",
"CUFF.27309.3\tCGI_10020701\t.\tPre\tPost\t239.95\tDOWN\t4258.40\t0.00719642\t\r\n",
"EKC29329\tCGI_10009812\t.\tPre\tPost\t4.85\tDOWN\t4234.84\t0.00719642\t\r\n",
"EKC28175\tCGI_10014343\t.\tPre\tPost\t29.50\tDOWN\t3226.38\t0.00719642\t\r\n"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!head ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/genes.sorted_by_expression.sig.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"gene_id\tgene_name\tsample1\tsample2\tfold_change\tdirection\ttotal_fpkm\tq-value\tgene_description\r\n",
"XLOC_000150\t-\tPre\tPost\t10.39\tDOWN\t73075.04\t0.00215\t\r\n",
"CGI_10027591\tFER\tPre\tPost\t6.36\tUP\t43013.84\t0.0255944\t\r\n",
"CGI_10021746\t.\tPre\tPost\t7.38\tDOWN\t15907.68\t0.00215\t\r\n",
"CGI_10021747\t.\tPre\tPost\t3.23\tDOWN\t11600.86\t0.0409378\t\r\n",
"XLOC_016561\t-\tPre\tPost\t3.94\tUP\t10548.12\t0.00666529\t\r\n",
"XLOC_028369\t-\tPre\tPost\t3.51\tDOWN\t9471.62\t0.00382598\t\r\n",
"XLOC_027306\t-\tPre\tPost\t6.06\tDOWN\t7890.30\t0.00215\t\r\n",
"CGI_10019465\t.\tPre\tPost\t4.58\tDOWN\t7665.63\t0.00889927\t\r\n",
"XLOC_033234\t-\tPre\tPost\t2.55\tUP\t6049.62\t0.026909\t\r\n"
]
}
],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!wc -l ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/genes.sorted_by_expression.sig.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 1551 ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/genes.sorted_by_expression.sig.txt\r\n"
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!fgrep \"XLOC_027306\" /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf | head"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"scaffold444\tCufflinks\texon\t386338\t386565\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\tCDS\t386338\t386565\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\texon\t386816\t386856\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"2\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\tCDS\t386816\t386856\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"2\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n"
]
}
],
"prompt_number": 11
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!fgrep \"XLOC_027306\" /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffmerge2_heat-2014-12-20-19-14-34.8/cuffmerge_out/merged_with_ref_ids.gtf | head"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"scaffold444\tCufflinks\texon\t386338\t386565\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\texon\t386816\t386856\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"2\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n"
]
}
],
"prompt_number": 13
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!cut -f9 /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf \\\n",
"> {wd}rebuilt.gtf.c9\n",
"!head {wd}rebuilt.gtf.c9"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"gene_id XLOC_000001; tss_id \"TSS1\"; oId \"CUFF.1.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000001\"\r\n",
"gene_id XLOC_000001; tss_id \"TSS1\"; oId \"CUFF.1.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000001\"\r\n",
"gene_id XLOC_000002; tss_id \"TSS2\"; oId \"CUFF.2.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000002\"\r\n",
"gene_id XLOC_000002; tss_id \"TSS2\"; oId \"CUFF.2.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000002\"\r\n",
"gene_id XLOC_000003; tss_id \"TSS3\"; oId \"CUFF.3.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000003\"\r\n",
"gene_id XLOC_000003; tss_id \"TSS3\"; oId \"CUFF.3.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000003\"\r\n",
"gene_id XLOC_000004; tss_id \"TSS4\"; oId \"CUFF.4.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000004\"\r\n",
"gene_id XLOC_000004; tss_id \"TSS4\"; oId \"CUFF.4.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000004\"\r\n",
"gene_id XLOC_000005; tss_id \"TSS5\"; oId \"CUFF.5.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000005\"\r\n",
"gene_id XLOC_000005; tss_id \"TSS5\"; oId \"CUFF.5.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000005\"\r\n"
]
}
],
"prompt_number": 15
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!awk -F\"[; ]\" '{print $2}' {wd}rebuilt.gtf.c9 | head"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"XLOC_000001\r\n",
"XLOC_000001\r\n",
"XLOC_000002\r\n",
"XLOC_000002\r\n",
"XLOC_000003\r\n",
"XLOC_000003\r\n",
"XLOC_000004\r\n",
"XLOC_000004\r\n",
"XLOC_000005\r\n",
"XLOC_000005\r\n",
"awk: write error on /dev/stdout\r\n",
" input record number 2600, file {wd}rebuilt.gtf.c9\r\n",
" source line number 1\r\n"
]
}
],
"prompt_number": 25
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!awk '{print $1,$2}' "
],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
diff --git a/ipynb/RNA-seq-DEG-features.ipynb b/ipynb/RNA-seq-DEG-features.ipynb
deleted file mode 100644
index 945418a..0000000
--- a/ipynb/RNA-seq-DEG-features.ipynb
+++ /dev/null
...
{
"metadata": {
"name": "",
"signature": "sha256:c806c5ee95d720500cbc841dbfe373d2a94bc5865023692b91050da4b56636fc"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"for i in (\"2M_3plusmerge_Hyper\",\"2M_3plusmerge_Hypo\",\"4M_3plusmerge_Hyper\",\"4M_3plusmerge_Hypo\",\"6M_3plusmerge_Hyper\",\"6M_3plusmerge_Hypo\"):\n",
" !intersectbed \\\n",
" -u \\\n",
" -a ./analyses/{i}.gff \\\n",
" -b ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf \\\n",
" > ./analyses/{i}_intersect_rebuilt.txt\n",
" !wc -l ./analyses/{i}_intersect_rebuilt.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 0 ./analyses/2M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 38 ./analyses/2M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 4 ./analyses/4M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 6 ./analyses/4M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 4 ./analyses/6M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 7 ./analyses/6M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!head /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/cuffdiff_out/cuffData.db"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"SQLite format 3\u0000\u0004\u0000\u0001\u0001\u0000@ \u0000\u0000\u0000H\u0000\u0001\ufffd\ufffd\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000M\u0000\u0000\u0000\u0001\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0001\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000H\u0000-\ufffd!\u0005\u0000\u0000\u0000\u0015\u0003\ufffd\u0000\u0000\u0001\ufffd|\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0003\ufffd\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000\u0000%\u0006\u0006\u00179\u0013\u0001\u0000indexsqlite_autoindex_TSS_1TSS\u0007\ufffd\b\u0004\u0007\u0017\u001b\u001b\u0001\ufffdgtablesamplessamples\u0005CREATE TABLE \"samples\"(\r\n",
" \"sample_index\" INTEGER PRIMARY KEY NOT NULL,\r\n",
" \"sample_name\" VARCHAR(45) NOT NULL\r\n",
")d\u0003\u0007\u0017\u001d",
"\u001d",
"\u0001\ufffd\u001btablebiasDatabiasData\u0004CREATE TABLE \"biasData\"(\r\n",
" \"biasData_id\" INTEGER PRIMARY KEY NOT NULL\r\n",
")\ufffdw\u0001\u0007\u0017\u0017\u0017\u0001\ufffdMtablegenesgenes\u0002CREATE TABLE \"genes\"(\r\n",
" \"gene_id\" VARCHAR(45) PRIMARY KEY NOT NULL,\r\n",
" \"class_code\" VARCHAR(45),\r\n",
" \"nearest_ref_id\" VARCHAR(45),\r\n",
" \"gene_short_name\" VARCHAR(45),\r\n"
]
}
],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
diff --git a/ipynb/RNA-seq-Gene-ID.ipynb b/ipynb/RNA-seq-Gene-ID.ipynb
new file mode 100644
index 0000000..4518162
--- /dev/null
+++ b/ipynb/RNA-seq-Gene-ID.ipynb
...
{
"metadata": {
"name": "",
"signature": "sha256:2bc54a369c1ad47665183c343b002a961fe0dc21674a89e7db94aa3457510fba"
},
"nbformat": 3,
"nbformat_minor": 0,
"worksheets": [
{
"cells": [
{
"cell_type": "code",
"collapsed": false,
"input": [
"for i in (\"2M_3plusmerge_Hyper\",\"2M_3plusmerge_Hypo\",\"4M_3plusmerge_Hyper\",\"4M_3plusmerge_Hypo\",\"6M_3plusmerge_Hyper\",\"6M_3plusmerge_Hypo\"):\n",
" !intersectbed \\\n",
" -u \\\n",
" -a ./analyses/{i}.gff \\\n",
" -b ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf \\\n",
" > ./analyses/{i}_intersect_rebuilt.txt\n",
" !wc -l ./analyses/{i}_intersect_rebuilt.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 0 ./analyses/2M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 38 ./analyses/2M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 4 ./analyses/4M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 6 ./analyses/4M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 4 ./analyses/6M_3plusmerge_Hyper_intersect_rebuilt.txt\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 7 ./analyses/6M_3plusmerge_Hypo_intersect_rebuilt.txt\r\n"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!head ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/transcripts.sorted_by_expression.sig.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"transcript\tgene_id\tgene_name\tsample1\tsample2\tfold_change\tdirection\ttotal_fpkm\tq-value\tgene_description\r\n",
"TCONS_00000151\tXLOC_000150\t-\tPre\tPost\t10.39\tDOWN\t73075.04\t0.00719642\t\r\n",
"EKC38373\tCGI_10021746\t.\tPre\tPost\t7.38\tDOWN\t15907.68\t0.00719642\t\r\n",
"TCONS_00059114\tXLOC_028369\t-\tPre\tPost\t3.51\tDOWN\t9471.62\t0.0127885\t\r\n",
"TCONS_00056889\tXLOC_027306\t-\tPre\tPost\t6.06\tDOWN\t7890.30\t0.00719642\t\r\n",
"TCONS_00009938\tXLOC_005260\t-\tPre\tPost\t7.58\tUP\t5938.99\t0.00719642\t\r\n",
"TCONS_00056778\tXLOC_027247\t-\tPre\tPost\t26.46\tDOWN\t4302.28\t0.00719642\t\r\n",
"CUFF.27309.3\tCGI_10020701\t.\tPre\tPost\t239.95\tDOWN\t4258.40\t0.00719642\t\r\n",
"EKC29329\tCGI_10009812\t.\tPre\tPost\t4.85\tDOWN\t4234.84\t0.00719642\t\r\n",
"EKC28175\tCGI_10014343\t.\tPre\tPost\t29.50\tDOWN\t3226.38\t0.00719642\t\r\n"
]
}
],
"prompt_number": 2
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!head ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/genes.sorted_by_expression.sig.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"gene_id\tgene_name\tsample1\tsample2\tfold_change\tdirection\ttotal_fpkm\tq-value\tgene_description\r\n",
"XLOC_000150\t-\tPre\tPost\t10.39\tDOWN\t73075.04\t0.00215\t\r\n",
"CGI_10027591\tFER\tPre\tPost\t6.36\tUP\t43013.84\t0.0255944\t\r\n",
"CGI_10021746\t.\tPre\tPost\t7.38\tDOWN\t15907.68\t0.00215\t\r\n",
"CGI_10021747\t.\tPre\tPost\t3.23\tDOWN\t11600.86\t0.0409378\t\r\n",
"XLOC_016561\t-\tPre\tPost\t3.94\tUP\t10548.12\t0.00666529\t\r\n",
"XLOC_028369\t-\tPre\tPost\t3.51\tDOWN\t9471.62\t0.00382598\t\r\n",
"XLOC_027306\t-\tPre\tPost\t6.06\tDOWN\t7890.30\t0.00215\t\r\n",
"CGI_10019465\t.\tPre\tPost\t4.58\tDOWN\t7665.63\t0.00889927\t\r\n",
"XLOC_033234\t-\tPre\tPost\t2.55\tUP\t6049.62\t0.026909\t\r\n"
]
}
],
"prompt_number": 3
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!wc -l ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/genes.sorted_by_expression.sig.txt"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 1551 ./data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/sorted_data/genes.sorted_by_expression.sig.txt\r\n"
]
}
],
"prompt_number": 4
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!fgrep \"XLOC_027306\" /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf | head"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"scaffold444\tCufflinks\texon\t386338\t386565\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\tCDS\t386338\t386565\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\texon\t386816\t386856\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"2\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\tCDS\t386816\t386856\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"2\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n"
]
}
],
"prompt_number": 11
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!fgrep \"XLOC_027306\" /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffmerge2_heat-2014-12-20-19-14-34.8/cuffmerge_out/merged_with_ref_ids.gtf | head"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"scaffold444\tCufflinks\texon\t386338\t386565\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n",
"scaffold444\tCufflinks\texon\t386816\t386856\t.\t-\t.\tgene_id XLOC_027306; tss_id \"TSS41263\"; oId \"CUFF.21767.1\"; exon_number \"2\"; class_code \"u\"; transcript_id \"TCONS_00056889\"\r\n"
]
}
],
"prompt_number": 13
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!cut -f9 /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf \\\n",
"> {wd}rebuilt.gtf.c9\n",
"!head {wd}rebuilt.gtf.c9"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"gene_id XLOC_000001; tss_id \"TSS1\"; oId \"CUFF.1.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000001\"\r\n",
"gene_id XLOC_000001; tss_id \"TSS1\"; oId \"CUFF.1.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000001\"\r\n",
"gene_id XLOC_000002; tss_id \"TSS2\"; oId \"CUFF.2.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000002\"\r\n",
"gene_id XLOC_000002; tss_id \"TSS2\"; oId \"CUFF.2.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000002\"\r\n",
"gene_id XLOC_000003; tss_id \"TSS3\"; oId \"CUFF.3.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000003\"\r\n",
"gene_id XLOC_000003; tss_id \"TSS3\"; oId \"CUFF.3.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000003\"\r\n",
"gene_id XLOC_000004; tss_id \"TSS4\"; oId \"CUFF.4.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000004\"\r\n",
"gene_id XLOC_000004; tss_id \"TSS4\"; oId \"CUFF.4.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000004\"\r\n",
"gene_id XLOC_000005; tss_id \"TSS5\"; oId \"CUFF.5.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000005\"\r\n",
"gene_id XLOC_000005; tss_id \"TSS5\"; oId \"CUFF.5.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000005\"\r\n"
]
}
],
"prompt_number": 15
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!awk -F\"[; ]\" '{print $2}' {wd}rebuilt.gtf.c9 | head"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"XLOC_000001\r\n",
"XLOC_000001\r\n",
"XLOC_000002\r\n",
"XLOC_000002\r\n",
"XLOC_000003\r\n",
"XLOC_000003\r\n",
"XLOC_000004\r\n",
"XLOC_000004\r\n",
"XLOC_000005\r\n",
"XLOC_000005\r\n",
"awk: write error on /dev/stdout\r\n",
" input record number 2600, file {wd}rebuilt.gtf.c9\r\n",
" source line number 1\r\n"
]
}
],
"prompt_number": 25
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!cp /Users/sr320/git-repos/paper-Temp-stress/ipynb/data/Cuffdiff2_heat-b-2014-12-20-22-27-15.4/rebuilt.gtf \\\n",
"/Users/sr320/data-genomic/tentacle/"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 31
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!tail /Users/sr320/data-genomic/tentacle/rebuilt.gtf"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"scaffold999\tCufflinks\texon\t122398\t122535\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"7\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\tCDS\t122398\t122535\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"7\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\texon\t123424\t123555\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"8\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\tCDS\t123424\t123555\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"8\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\texon\t124859\t124996\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"9\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\tCDS\t124859\t124996\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"9\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\texon\t126012\t126143\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"10\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\tCDS\t126012\t126143\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"10\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\texon\t126617\t126675\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"11\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n",
"scaffold999\tCufflinks\tCDS\t126617\t126675\t.\t+\t.\tgene_id CGI_10006973; tss_id \"TSS54790\"; nearest_ref \"EKC31257\"; exon_number \"11\"; class_code \"=\"; p_id \"P26083\"; gene_name \"CGI_10006973\"; transcript_id \"EKC31257\"\r\n"
]
}
],
"prompt_number": 40
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!awk '{print $10}' /Users/sr320/data-genomic/tentacle/rebuilt.gtf | rev | cut -c 2- | rev > \\\n",
"/Users/sr320/data-genomic/tentacle/rebuilt.gtf.geneID\n",
"!head /Users/sr320/data-genomic/tentacle/rebuilt.gtf.geneID\n",
"!wc -l /Users/sr320/data-genomic/tentacle/rebuilt.gtf.geneID"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"XLOC_000001\r\n",
"XLOC_000001\r\n",
"XLOC_000002\r\n",
"XLOC_000002\r\n",
"XLOC_000003\r\n",
"XLOC_000003\r\n",
"XLOC_000004\r\n",
"XLOC_000004\r\n",
"XLOC_000005\r\n",
"XLOC_000005\r\n"
]
},
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 1347244 /Users/sr320/data-genomic/tentacle/rebuilt.gtf.geneID\r\n"
]
}
],
"prompt_number": 57
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!wc -l /Users/sr320/data-genomic/tentacle/rebuilt.gtf"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
" 1347244 /Users/sr320/data-genomic/tentacle/rebuilt.gtf\r\n"
]
}
],
"prompt_number": 58
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!paste /Users/sr320/data-genomic/tentacle/rebuilt.gtf \\\n",
"/Users/sr320/data-genomic/tentacle/rebuilt.gtf.geneID \\\n",
"> /Users/sr320/data-genomic/tentacle/rebuilt.gtf.geneIDend"
],
"language": "python",
"metadata": {},
"outputs": [],
"prompt_number": 60
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!head /Users/sr320/data-genomic/tentacle/rebuilt.gtf.geneIDend"
],
"language": "python",
"metadata": {},
"outputs": [
{
"output_type": "stream",
"stream": "stdout",
"text": [
"C12764\tCufflinks\texon\t28\t201\t.\t.\t.\tgene_id XLOC_000001; tss_id \"TSS1\"; oId \"CUFF.1.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000001\"\tXLOC_000001\r\n",
"C12764\tCufflinks\tCDS\t28\t201\t.\t.\t.\tgene_id XLOC_000001; tss_id \"TSS1\"; oId \"CUFF.1.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000001\"\tXLOC_000001\r\n",
"C12768\tCufflinks\texon\t4\t189\t.\t.\t.\tgene_id XLOC_000002; tss_id \"TSS2\"; oId \"CUFF.2.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000002\"\tXLOC_000002\r\n",
"C12768\tCufflinks\tCDS\t4\t189\t.\t.\t.\tgene_id XLOC_000002; tss_id \"TSS2\"; oId \"CUFF.2.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000002\"\tXLOC_000002\r\n",
"C12830\tCufflinks\texon\t1\t198\t.\t.\t.\tgene_id XLOC_000003; tss_id \"TSS3\"; oId \"CUFF.3.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000003\"\tXLOC_000003\r\n",
"C12830\tCufflinks\tCDS\t1\t198\t.\t.\t.\tgene_id XLOC_000003; tss_id \"TSS3\"; oId \"CUFF.3.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000003\"\tXLOC_000003\r\n",
"C13102\tCufflinks\texon\t1\t209\t.\t.\t.\tgene_id XLOC_000004; tss_id \"TSS4\"; oId \"CUFF.4.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000004\"\tXLOC_000004\r\n",
"C13102\tCufflinks\tCDS\t1\t209\t.\t.\t.\tgene_id XLOC_000004; tss_id \"TSS4\"; oId \"CUFF.4.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000004\"\tXLOC_000004\r\n",
"C13868\tCufflinks\texon\t3\t203\t.\t.\t.\tgene_id XLOC_000005; tss_id \"TSS5\"; oId \"CUFF.5.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000005\"\tXLOC_000005\r\n",
"C13868\tCufflinks\tCDS\t3\t203\t.\t.\t.\tgene_id XLOC_000005; tss_id \"TSS5\"; oId \"CUFF.5.1\"; exon_number \"1\"; class_code \"u\"; transcript_id \"TCONS_00000005\"\tXLOC_000005\r\n"
]
}
],
"prompt_number": 61
},
{
"cell_type": "code",
"collapsed": false,
"input": [],
"language": "python",
"metadata": {},
"outputs": []
},
{
"cell_type": "code",
"collapsed": false,
"input": [
"!python {sqls}singleupload.py \\\n",
"-d _blast_sprot \\\n",
"../analyses/{sp}_sprot_sql.tab "
],
"language": "python",
"metadata": {},
"outputs": []
}
],
"metadata": {}
}
]
}
diff --git a/ipynb/Cgigas_v9_1k5p_gene_promoter.gff b/ipynb/data/Cgigas_v9_1k5p_gene_promoter.gff
similarity index 100%
rename from ipynb/Cgigas_v9_1k5p_gene_promoter.gff
rename to ipynb/data/Cgigas_v9_1k5p_gene_promoter.gff
diff --git a/ipynb/Cgigas_v9_TEx.gff b/ipynb/data/Cgigas_v9_TEx.gff
similarity index 100%
rename from ipynb/Cgigas_v9_TEx.gff
rename to ipynb/data/Cgigas_v9_TEx.gff
diff --git a/ipynb/Cgigas_v9_exon.gff b/ipynb/data/Cgigas_v9_exon.gff
similarity index 100%
rename from ipynb/Cgigas_v9_exon.gff
rename to ipynb/data/Cgigas_v9_exon.gff
diff --git a/ipynb/Cgigas_v9_gene.gff b/ipynb/data/Cgigas_v9_gene.gff
similarity index 100%
rename from ipynb/Cgigas_v9_gene.gff
rename to ipynb/data/Cgigas_v9_gene.gff
diff --git a/ipynb/Cgigas_v9_intron.gff b/ipynb/data/Cgigas_v9_intron.gff
similarity index 100%
rename from ipynb/Cgigas_v9_intron.gff
rename to ipynb/data/Cgigas_v9_intron.gff