GTN Proteogenomics1 Database Creation

Last updated Feb 9, 2021

Launch in Tutorial Mode question
License: None Specified, defaults to CC-BY-4.0
Tests: ❌ Results: Not yet automated

flowchart TD
  0["ℹ️ Input Dataset\nFASTQ_ProB_22LIST.fastqsanger"];
  style 0 stroke:#2c3143,stroke-width:4px;
  1["ℹ️ Input Dataset\nMus_musculus.GRCm38.86.gtf"];
  style 1 stroke:#2c3143,stroke-width:4px;
  2["ℹ️ Input Dataset\nTrimmed_ref_5000_uniprot_cRAP.fasta"];
  style 2 stroke:#2c3143,stroke-width:4px;
  3["HISAT2"];
  0 -->|output| 3;
  4["Editing GTF File"];
  1 -->|output| 4;
  70b6f719-803f-4fa9-8394-a3b64b71ec01["Output\nchr_corrected_gtf"];
  4 --> 70b6f719-803f-4fa9-8394-a3b64b71ec01;
  style 70b6f719-803f-4fa9-8394-a3b64b71ec01 stroke:#2c3143,stroke-width:4px;
  5["FASTA-to-Tabular"];
  2 -->|output| 5;
  6["FreeBayes"];
  3 -->|output_alignments| 6;
  7["StringTie"];
  4 -->|outfile| 7;
  3 -->|output_alignments| 7;
  8["Filter Tabular"];
  5 -->|output| 8;
  9["CustomProDB"];
  3 -->|output_alignments| 9;
  6 -->|output_vcf| 9;
  10["GffCompare"];
  4 -->|outfile| 10;
  7 -->|output_gtf| 10;
  11["SQLite to tabular"];
  9 -->|output_genomic_mapping_sqlite| 11;
  12["SQLite to tabular"];
  9 -->|output_variant_annotation_sqlite| 12;
  13["FASTA Merge Files and Filter Unique Sequences"];
  9 -->|output_rpkm| 13;
  9 -->|output_snv| 13;
  9 -->|output_indel| 13;
  a5054be9-dd74-4d60-a4c6-494fdbcb97a1["Output\nCustomProDB_FASTA"];
  13 --> a5054be9-dd74-4d60-a4c6-494fdbcb97a1;
  style a5054be9-dd74-4d60-a4c6-494fdbcb97a1 stroke:#2c3143,stroke-width:4px;
  14["FASTA-to-Tabular"];
  9 -->|output_rpkm| 14;
  15["Convert gffCompare annotated GTF to BED"];
  10 -->|transcripts_annotated| 15;
  16["Column Regex Find And Replace"];
  11 -->|query_results| 16;
  17["Column Regex Find And Replace"];
  12 -->|query_results| 17;
  18["FASTA-to-Tabular"];
  13 -->|output| 18;
  19["Filter Tabular"];
  14 -->|output| 19;
  20["Translate BED transcripts"];
  15 -->|output| 20;
  21["Query Tabular"];
  17 -->|out_file1| 21;
  e9468479-4ebd-4ced-8086-c10e916b97c5["Output\nvariant_annoation_sqlite"];
  21 --> e9468479-4ebd-4ced-8086-c10e916b97c5;
  style e9468479-4ebd-4ced-8086-c10e916b97c5 stroke:#2c3143,stroke-width:4px;
  22["Column Regex Find And Replace"];
  18 -->|output| 22;
  23["Reference Protein Accessions"];
  19 -->|output| 23;
  8 -->|output| 23;
  19aa5a85-5933-4ab5-ae76-e4b1ec5b2f85["Output\nReference_Protein_Accessions"];
  23 --> 19aa5a85-5933-4ab5-ae76-e4b1ec5b2f85;
  style 19aa5a85-5933-4ab5-ae76-e4b1ec5b2f85 stroke:#2c3143,stroke-width:4px;
  24["bed to protein map"];
  20 -->|translation_bed| 24;
  25["Tabular-to-FASTA"];
  22 -->|out_file1| 25;
  26["Concatenate datasets"];
  24 -->|output| 26;
  16 -->|out_file1| 26;
  27["FASTA Merge Files and Filter Unique Sequences"];
  2 -->|output| 27;
  25 -->|output| 27;
  20 -->|translation_fasta| 27;
  924bce7c-5c6a-4cb3-a459-18784a55ae01["Output\nUniprot_cRAP_SAV_indel_translatedbed_FASTA"];
  27 --> 924bce7c-5c6a-4cb3-a459-18784a55ae01;
  style 924bce7c-5c6a-4cb3-a459-18784a55ae01 stroke:#2c3143,stroke-width:4px;
  28["Genomic_mapping_sqlite"];
  26 -->|out_file1| 28;
  6542c4e5-289a-4be4-9b42-7a4e170ba198["Output\ngenomic_mapping_sqlite"];
  28 --> 6542c4e5-289a-4be4-9b42-7a4e170ba198;
  style 6542c4e5-289a-4be4-9b42-7a4e170ba198 stroke:#2c3143,stroke-width:4px;