Bug fix for gisaid name overwriting genbank name for fasta file

CDCgov · Apr 15, 2024 · 18f77f1 · 18f77f1
1 parent 67d14c9
commit 18f77f1
Show file tree

Hide file tree

Showing 50 changed files with 5,494 additions and 3,560 deletions.
diff --git a/TEST_COV/config.yaml b/TEST_COV/config.yaml
@@ -0,0 +1,35 @@
+Submission:
+  NCBI:
+    Username: username
+    Password: password
+    Table2asn: False
+    Submission_Position: 2
+    Description:
+      Title: cov_test_submission
+      Comment: This is a test submission
+      Organization:
+        '@role': owner
+        '@type': institute
+        Name: CDC
+        Address:
+           Affil: Centers for Disease Control and Prevention
+           Div: Respiratory Viruses Branch, Division of Viral Diseases
+           Street: 1600 Clifton Rd
+           City: Atlanta
+           Sub: GA
+           Postal_code: 30329
+           Country: USA
+           Email: [email protected]
+           Phone: ""
+        Submitter:
+          '@email': [email protected]
+          '@alt_email':
+          Name:
+            First: Jane
+            Last: Doe
+  GISAID:
+    Client-Id: TEST-EA76875B00C3
+    Username: username
+    Password: password
+    Submission_Position: 1
+
diff --git a/TEST_COV/metadata.csv b/TEST_COV/metadata.csv
@@ -0,0 +1,3 @@
+organism,collection_date,authors,ncbi-spuid,ncbi-spuid_namespace,ncbi-bioproject,bs-isolate,bs-package,bs-description,bs-collected_by, bs-host, bs-host_disease,bs-isolation_source,bs-geo_loc_name,bs-host_sex,bs-host_age,sra-file_location,sra-file_name,sra-library_name,sra-instrument_model,sra-library_strategy,sra-library_source,sra-library_selection,sra-library_layout,sra-library_construction_protocol,sra-loader,sequence_name,gb-seq_id,gb-subm_lab,gb-subm_lab_division,gb-subm_lab_addr,gb-authors,gb-publication_status,gb-publication_title,src-isolate,src-country,src-host,src-isolation_source,cmt-StructuredCommentPrefix,cmt-Assembly Method,cmt-Coverage,cmt-Sequencing Technology,cmt-StructuredCommentSuffix,gs-virus_name,gs-type,gs-passage,gs-location,gs-add_location,gs-host,gs-add_host_info,gs-sampling_strategy,gs-gender,gs-patient_age,gs-patient_status,gs-specimen,gs-outbreak,gs-last_vaccinated,gs-treatment,gs-seq_technology,gs-assembly_method,gs-coverage,gs-orig_lab,gs-orig_lab_addr,gs-provider_sample_id,gs-subm_lab,gs-subm_lab_addr,gs-subm_sample_id,gs-consortium,gs-comment,gs-comment_type
+Severe acute respiratory syndrome coronavirus 2,3/28/2020,"Doe, John, R.; Doe, Jane;",SARS-CoV-2/human/USA/GA_2741/2020,CDC-OAMD,PRJNA512913,SARS-CoV-2/human/USA/GA_2741/2020,SARS-CoV-2.cl.1.0,Sars CoV2 Sequencing Baseline Constellation,Helix,Homo sapiens,COVID-19,nasal swab,United States: Georgia,Male,28,local,"fastq_1_R1.fastq.gz, fastq_1_R2.fastq.gz",Helix COVID-19 and Flu Test,Illumina NovaSeq 6000,AMPLICON,VIRAL RNA,RT-PCR,PAIRED,Helix Hybrid-Capture Test,latf-load,GA_2741,SARS-CoV-2/human/USA/GA_2741/2020,NIH,NCBI,"10 Center Dr, Bethesda, MD, USA 20895","Doe, John, R.; Doe, Jane;",unpublished,,SARS-CoV-2/human/USA/GA_2741/2020,USA: GA,Homo sapiens,nasal swab,Assembly-Data,Newbler v. 2.3,100x,Illumina ,Assembly-Data,hCoV-19/USA/GA-2741/2022,betacoronavirus,Original,North America/USA/Georgia,unknown,Human,,,unknown,unknown,unknown,,,,,Illumina NextSeq 550,,3000x,Bio1 Mel,"16 Info St, Mel, Aus",,Bio2 Mel,"32 Data St, Mel, Aus",,,,
+Severe acute respiratory syndrome coronavirus 2,4/29/2020,"Doe, John; Doe, Jane;",SARS-CoV-2/human/USA/GA_3742/2020,CDC-OAMD,PRJNA512962,SARS-CoV-2/human/USA/GA_3742/2020,SARS-CoV-2.cl.1.0,Sars CoV2 Sequencing Baseline Constellation,Helix,Homo sapiens,COVID-20,nasal swab,United States: Georgia,Male,45,local,"fastq_2_R1.fastq.gz, fastq_2_R2.fastq.gz",Helix COVID-19 and Flu Test,Illumina NovaSeq 6000,AMPLICON,VIRAL RNA,RT-PCR,PAIRED,Helix Hybrid-Capture Test,latf-load,GA_2742,SARS-CoV-2/human/USA/GA_3742/2020,NIH,NCBI,"10 Center Dr, Bethesda, MD, USA 20895","Doe, John; Doe, Jane;",unpublished,,SARS-CoV-2/human/USA/GA_3742/2020,USA: GA,Homo sapiens,nasal swab,Assembly-Data,Newbler v. 2.3,100x,Illumina,Assembly-Data ,hCoV-19/USA/GA_2742/2022,betacoronavirus,Original,North America/USA/Georgia,unknown,Human,,,unknown,unknown,unknown,,,,,Illumina NextSeq 550,,3000x,Bio1 Mel,"16 Info St, Mel, Aus",,Bio2 Mel,"33 Data St, Mel, Aus",,,,
diff --git a/TEST_COV/raw_reads/fastq_1_R1.fastq.gz b/TEST_COV/raw_reads/fastq_1_R1.fastq.gz
diff --git a/TEST_COV/raw_reads/fastq_1_R2.fastq.gz b/TEST_COV/raw_reads/fastq_1_R2.fastq.gz
diff --git a/TEST_COV/raw_reads/fastq_2_R1.fastq.gz b/TEST_COV/raw_reads/fastq_2_R1.fastq.gz
diff --git a/TEST_COV/raw_reads/fastq_2_R2.fastq.gz b/TEST_COV/raw_reads/fastq_2_R2.fastq.gz
diff --git a/TEST_COV/sequence.fasta b/TEST_COV/sequence.fasta
diff --git a/TEST_COV/submission_files/BIOSAMPLE/submission.xml b/TEST_COV/submission_files/BIOSAMPLE/submission.xml
@@ -0,0 +1,90 @@
+<?xml version='1.0' encoding='utf-8'?>
+<Submission>
+  <Description>
+    <Title>cov_test_submission</Title>
+    <Comment>This is a test submission</Comment>
+    <Organization type="institute" role="owner">
+      <Name>CDC</Name>
+      <Contact email="[email protected]">
+        <Name>
+          <First>Jane</First>
+          <Last>Doe</Last>
+        </Name>
+      </Contact>
+    </Organization>
+  </Description>
+  <Action>
+    <AddData target_db="BioSample">
+      <Data content_type="xml">
+        <XmlContent>
+          <BioSample schema_version="2.0">
+            <SampleId>
+              <SPUID spuid_namespace="CDC-OAMD">SARS-CoV-2/human/USA/GA_2741/2020</SPUID>
+            </SampleId>
+            <Descriptor>
+              <Title>Sars CoV2 Sequencing Baseline Constellation</Title>
+            </Descriptor>
+            <Organism>
+              <OrganismName>Severe acute respiratory syndrome coronavirus 2</OrganismName>
+            </Organism>
+            <BioProject>
+              <PrimaryId db="BioProject">PRJNA512913</PrimaryId>
+            </BioProject>
+            <Package>SARS-CoV-2.cl.1.0</Package>
+            <Attributes>
+              <Attribute attribute_name="isolate">SARS-CoV-2/human/USA/GA_2741/2020</Attribute>
+              <Attribute attribute_name="collected_by">Helix</Attribute>
+              <Attribute attribute_name="host">Homo sapiens</Attribute>
+              <Attribute attribute_name="host_disease">COVID-19</Attribute>
+              <Attribute attribute_name="isolation_source">nasal swab</Attribute>
+              <Attribute attribute_name="geo_loc_name">United States: Georgia</Attribute>
+              <Attribute attribute_name="host_sex">Male</Attribute>
+              <Attribute attribute_name="host_age">28</Attribute>
+              <Attribute attribute_name="collection_date">2020-03-28</Attribute>
+            </Attributes>
+          </BioSample>
+        </XmlContent>
+      </Data>
+      <Identifier>
+        <SPUID spuid_namespace="CDC-OAMD_bs">SARS-CoV-2/human/USA/GA_2741/2020</SPUID>
+      </Identifier>
+    </AddData>
+  </Action>
+  <Action>
+    <AddData target_db="BioSample">
+      <Data content_type="xml">
+        <XmlContent>
+          <BioSample schema_version="2.0">
+            <SampleId>
+              <SPUID spuid_namespace="CDC-OAMD">SARS-CoV-2/human/USA/GA_3742/2020</SPUID>
+            </SampleId>
+            <Descriptor>
+              <Title>Sars CoV2 Sequencing Baseline Constellation</Title>
+            </Descriptor>
+            <Organism>
+              <OrganismName>Severe acute respiratory syndrome coronavirus 2</OrganismName>
+            </Organism>
+            <BioProject>
+              <PrimaryId db="BioProject">PRJNA512962</PrimaryId>
+            </BioProject>
+            <Package>SARS-CoV-2.cl.1.0</Package>
+            <Attributes>
+              <Attribute attribute_name="isolate">SARS-CoV-2/human/USA/GA_3742/2020</Attribute>
+              <Attribute attribute_name="collected_by">Helix</Attribute>
+              <Attribute attribute_name="host">Homo sapiens</Attribute>
+              <Attribute attribute_name="host_disease">COVID-20</Attribute>
+              <Attribute attribute_name="isolation_source">nasal swab</Attribute>
+              <Attribute attribute_name="geo_loc_name">United States: Georgia</Attribute>
+              <Attribute attribute_name="host_sex">Male</Attribute>
+              <Attribute attribute_name="host_age">45</Attribute>
+              <Attribute attribute_name="collection_date">2020-04-29</Attribute>
+            </Attributes>
+          </BioSample>
+        </XmlContent>
+      </Data>
+      <Identifier>
+        <SPUID spuid_namespace="CDC-OAMD_bs">SARS-CoV-2/human/USA/GA_3742/2020</SPUID>
+      </Identifier>
+    </AddData>
+  </Action>
+</Submission>
diff --git a/TEST_COV/submission_files/GENBANK/TEST_COV.zip b/TEST_COV/submission_files/GENBANK/TEST_COV.zip
diff --git a/TEST_COV/submission_files/GENBANK/authorset.sbt b/TEST_COV/submission_files/GENBANK/authorset.sbt
@@ -0,0 +1,88 @@
+Submit-block ::= {
+  contact {
+    contact {
+      name name {
+        last "Doe",
+        first "Jane",
+        middle "",
+        initials "",
+        suffix "",
+        title ""
+      },
+      affil std {
+        affil "Centers for Disease Control and Prevention",
+        div "Respiratory Viruses Branch, Division of Viral Diseases",
+        city "Atlanta",
+        sub "GA",
+        country "USA",
+        street "1600 Clifton Rd",
+        email "[email protected]",
+        phone "",
+        postal-code "30329"
+      }
+    }
+  },
+  cit {
+    authors {
+      names std {
+        {
+          name name {
+            last "Doe",
+            first "John",
+            suffix "R."
+          }
+        },
+        {
+          name name {
+            last "Doe",
+            first "Jane"
+          }
+        }
+      },
+      affil std {
+        affil "Centers for Disease Control and Prevention",
+        div "Respiratory Viruses Branch, Division of Viral Diseases",
+        city "Atlanta",
+        sub "GA",
+        country "USA",
+        street "1600 Clifton Rd",
+        postal-code "30329"
+      }
+    }
+  },
+  subtype new
+}
+Seqdesc ::= pub {
+  pub {
+    gen {
+      cit "unpublished",
+      authors {
+        names std {
+          {
+            name name {
+              last "Doe",
+              first "John",
+              suffix "R."
+            }
+          },
+          {
+            name name {
+              last "Doe",
+              first "Jane"
+            }
+          }
+        }
+      },
+      title ""
+    }
+  }
+}
+Seqdesc ::= user {
+  type str "Submission",
+  data {
+    {
+      label str "AdditionalComment",
+      data str "Submission Title: TEST_COV"
+    }
+  }
+}
diff --git a/TEST_COV/submission_files/GENBANK/comment.cmt b/TEST_COV/submission_files/GENBANK/comment.cmt
@@ -0,0 +1,3 @@
+SeqID	StructuredCommentPrefix	organism	collection_date	Assembly Method	Coverage	Sequencing Technology	StructuredCommentSuffix
+SARS-CoV-2/human/USA/GA_2741/2020	Assembly-Data	Severe acute respiratory syndrome coronavirus 2	2020-03-28	Newbler v. 2.3	100x	Illumina 	Assembly-Data
+SARS-CoV-2/human/USA/GA_3742/2020	Assembly-Data	Severe acute respiratory syndrome coronavirus 2	2020-04-29	Newbler v. 2.3	100x	Illumina	Assembly-Data