Skip to content

Instantly share code, notes, and snippets.

@hden

hden/Extract_Flanking_Sequence_(csv_to_tab).ga

Created November 22, 2012 02:49
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save hden/4129181 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save hden/4129181 to your computer and use it in GitHub Desktop.
Download ZIP
Extract flanking sequence of a SNP (Chromosome in 2nd column, position in 4th column) appends sequences in a new column
Raw
Extract_Flanking_Sequence_(csv_to_tab).ga
{
"a_galaxy_workflow": "true",
"annotation": "",
"format-version": "0.1",
"name": "Extract Flanking Sequence (csv to tab)",
"steps": {
"0": {
"annotation": "",
"id": 0,
"input_connections": {},
"inputs": [
{
"description": "",
"name": "Input Dataset"
}
],
"name": "Input dataset",
"outputs": [],
"position": {
"left": 200,
"top": 351
},
"tool_errors": null,
"tool_id": null,
"tool_state": "{\"name\": \"Input Dataset\"}",
"tool_version": null,
"type": "data_input",
"user_outputs": []
},
"1": {
"annotation": "",
"id": 1,
"input_connections": {
"input": {
"id": 0,
"output_name": "output"
}
},
"inputs": [],
"name": "Convert",
"outputs": [
{
"name": "out_file1",
"type": "tabular"
}
],
"position": {
"left": 420,
"top": 351
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Convert characters1",
"tool_state": "{\"__page__\": 0, \"convert_from\": \"\\\"C\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"input\": \"null\"}",
"tool_version": "1.0.0",
"type": "tool",
"user_outputs": []
},
"2": {
"annotation": "",
"id": 2,
"input_connections": {
"input": {
"id": 1,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Select first",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 645,
"top": 200
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Show beginning1",
"tool_state": "{\"__page__\": 0, \"input\": \"null\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"lineNum\": \"\\\"1\\\"\"}",
"tool_version": "1.0.0",
"type": "tool",
"user_outputs": []
},
"3": {
"annotation": "",
"id": 3,
"input_connections": {
"input": {
"id": 1,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Cut",
"outputs": [
{
"name": "out_file1",
"type": "tabular"
}
],
"position": {
"left": 640,
"top": 351
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Cut1",
"tool_state": "{\"columnList\": \"\\\"c2,c4\\\"\", \"input\": \"null\", \"delimiter\": \"\\\"T\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"__page__\": 0}",
"tool_version": "1.0.1",
"type": "tool",
"user_outputs": []
},
"4": {
"annotation": "",
"id": 4,
"input_connections": {
"input": {
"id": 1,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Compute",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 641,
"top": 506
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Add_a_column1",
"tool_state": "{\"__page__\": 0, \"cond\": \"\\\"c4+10\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"round\": \"\\\"yes\\\"\", \"input\": \"null\"}",
"tool_version": "1.1.0",
"type": "tool",
"user_outputs": []
},
"5": {
"annotation": "",
"id": 5,
"input_connections": {
"input": {
"id": 2,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Add column",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 903,
"top": 206
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "addValue",
"tool_state": "{\"__page__\": 0, \"input\": \"null\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"exp\": \"\\\"Flanking Sequence\\\"\", \"iterate\": \"\\\"no\\\"\"}",
"tool_version": "1.0.0",
"type": "tool",
"user_outputs": []
},
"6": {
"annotation": "",
"id": 6,
"input_connections": {
"input": {
"id": 3,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Compute",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 860,
"top": 351
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Add_a_column1",
"tool_state": "{\"__page__\": 0, \"cond\": \"\\\"c2-200\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"round\": \"\\\"yes\\\"\", \"input\": \"null\"}",
"tool_version": "1.1.0",
"type": "tool",
"user_outputs": []
},
"7": {
"annotation": "",
"id": 7,
"input_connections": {
"input": {
"id": 6,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Compute",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 1080,
"top": 351
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Add_a_column1",
"tool_state": "{\"__page__\": 0, \"cond\": \"\\\"c2+200\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"round\": \"\\\"yes\\\"\", \"input\": \"null\"}",
"tool_version": "1.1.0",
"type": "tool",
"user_outputs": []
},
"8": {
"annotation": "",
"id": 8,
"input_connections": {
"input": {
"id": 7,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Cut",
"outputs": [
{
"name": "out_file1",
"type": "tabular"
}
],
"position": {
"left": 1300,
"top": 351
},
"post_job_actions": {
"ChangeDatatypeActionout_file1": {
"action_arguments": {
"newtype": "interval"
},
"action_type": "ChangeDatatypeAction",
"output_name": "out_file1"
}
},
"tool_errors": null,
"tool_id": "Cut1",
"tool_state": "{\"columnList\": \"\\\"c1,c3,c4\\\"\", \"input\": \"null\", \"delimiter\": \"\\\"T\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"__page__\": 0}",
"tool_version": "1.0.1",
"type": "tool",
"user_outputs": []
},
"9": {
"annotation": "",
"id": 9,
"input_connections": {
"input": {
"id": 8,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Extract Genomic DNA",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 1520,
"top": 351
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Extract genomic DNA 1",
"tool_state": "{\"out_format\": \"\\\"fasta\\\"\", \"__page__\": 0, \"interpret_features\": \"\\\"yes\\\"\", \"seq_source\": \"{\\\"index_source\\\": \\\"cached\\\", \\\"__current_case__\\\": 0}\", \"input\": \"null\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\"}",
"tool_version": "2.2.2",
"type": "tool",
"user_outputs": []
},
"10": {
"annotation": "",
"id": 10,
"input_connections": {
"input": {
"id": 9,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "FASTA-to-Tabular",
"outputs": [
{
"name": "output",
"type": "tabular"
}
],
"position": {
"left": 1740,
"top": 351
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "fasta2tab",
"tool_state": "{\"input\": \"null\", \"keep_first\": \"\\\"0\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"descr_columns\": \"\\\"1\\\"\", \"__page__\": 0}",
"tool_version": "1.1.0",
"type": "tool",
"user_outputs": []
},
"11": {
"annotation": "",
"id": 11,
"input_connections": {
"input1": {
"id": 4,
"output_name": "out_file1"
},
"input2": {
"id": 10,
"output_name": "output"
}
},
"inputs": [],
"name": "Paste",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 1962,
"top": 464
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Paste1",
"tool_state": "{\"input2\": \"null\", \"__page__\": 0, \"delimiter\": \"\\\"T\\\"\", \"input1\": \"null\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\"}",
"tool_version": "1.0.0",
"type": "tool",
"user_outputs": []
},
"12": {
"annotation": "",
"id": 12,
"input_connections": {
"input": {
"id": 11,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Cut",
"outputs": [
{
"name": "out_file1",
"type": "tabular"
}
],
"position": {
"left": 2180,
"top": 351
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "Cut1",
"tool_state": "{\"columnList\": \"\\\"c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c19\\\"\", \"input\": \"null\", \"delimiter\": \"\\\"T\\\"\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"__page__\": 0}",
"tool_version": "1.0.1",
"type": "tool",
"user_outputs": []
},
"13": {
"annotation": "",
"id": 13,
"input_connections": {
"input1": {
"id": 5,
"output_name": "out_file1"
},
"queries_0|input2": {
"id": 12,
"output_name": "out_file1"
}
},
"inputs": [],
"name": "Concatenate datasets",
"outputs": [
{
"name": "out_file1",
"type": "input"
}
],
"position": {
"left": 2391,
"top": 243
},
"post_job_actions": {},
"tool_errors": null,
"tool_id": "cat1",
"tool_state": "{\"__page__\": 0, \"input1\": \"null\", \"chromInfo\": \"\\\"/galaxy/home/g2main/galaxy_main/tool-data/shared/ucsc/chrom/hg19.len\\\"\", \"queries\": \"[{\\\"input2\\\": null, \\\"__index__\\\": 0}]\"}",
"tool_version": "1.0.0",
"type": "tool",
"user_outputs": []
}
}
}
@sanjeevksh
Copy link

sanjeevksh commented May 18, 2016

Hi hden,
Can this script put the target SNP alleles in square bracket and also flag up the SNPs in flanking sequences as IUPAC codes?
Regards,
SS

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment