Merge pull request #1 from sfu-ireceptor/AIRR-compliance

Airr compliance

Formats_rearrangement.yaml

@@ -0,0 +1,211 @@
+#
+# Schema definitions for AIRR Formats rearrangement objects
+#
+
+# The Formats rearrangements
+# Note: This is an extension of the MiAIRR rearrangements, and assumes that
+# the MiAIRR has defined the MiAIRR rearrangement objects.
+#    required:
+#      - sequence_id
+#      - sequence
+#      - sample_id
+#      - constant
+#      - functional
+#      - rev_comp
+#      - c_call
+#      - v_score
+#      - d_score
+#      - j_score
+#      - c_score
+#      - v_cigar
+#      - d_cigar
+#      - j_cigar
+#      - c_cigar
+
+
+Formats_Rearrangements:
+    discriminator: AIRRFormats
+    type: object
+    properties:
+      sequence_id:
+        type: string
+        description: Read/sequence identifier
+      sequence:
+        type: string
+        description: Nucleotide sequence (e.g., the "read" sequence; revcomp'd if
+           necessary)
+      sample_id:
+        type: string
+        description: The biological sample this read derives from (e.g., from BioSample
+             database)
+      constant:
+        type: string
+        description: Constant region gene (e.g., IGHG4, IGHA2, IGHE, TRBC)
+      functional:
+        type: boolean
+        description: VDJ sequence is predicted to be functional
+      rev_comp:
+        type: boolean
+        description: Sequence is reverse complemented
+      c_call:
+        type: string
+        description: C gene assignment        
+      v_score:
+        type: number
+        description: V alignment score
+      d_score:
+        type: number
+        description: D alignment score
+      j_score:
+        type: number
+        description: J alignment score
+      c_score:
+        type: number
+        description: C alignment score
+      v_cigar:
+        type: string
+        description: V alignment CIGAR string
+      d_cigar:
+        type: string
+        description: D alignment CIGAR string
+      j_cigar:
+        type: string
+        description: J alignment CIGAR string
+      c_cigar:
+        type: string
+        description: C alignment CIGAR string
+      v_evalue:
+        type: number
+        description: V alignment E-value (when applicable)
+      d_evalue:
+        type: number
+        description: D alignment E-value (when applicable)
+      j_evalue:
+        type: number
+        description: J alignment E-value (when applicable)
+      v_identity:
+        type: number
+        description:  V alignment identity
+      d_identity:
+        type: number
+        description:  D alignment identity
+      j_identity:
+        type: number
+        description:  J alignment identity
+      vdj_score:
+        type: number
+        description: Score for aligners that consider the full sequence as a whole
+      vdj_evalue:
+        type: number
+        description: E-value for aligners that consider the full sequence as a whole
+      vdj_identity:
+        type: number
+        description: Identity for aligners that consider the full sequence as a whole
+      vdj_cigar:
+        type: string
+        description: VDJ alignment CIGAR string
+      v_start:
+        type: integer
+        description: Position of first V nucleotide in 'sequence' field
+      v_germ_start:
+        type: integer
+        description: Position of 'v_start' field in IMGT numbered germline V(D)J sequence
+      fwr1_start:
+        type: integer
+        description: FWR1 start coordinate in sequence (transferred from germline)
+      fwr1_end:
+        type: integer
+        description: FWR1 end coordinate in sequence (transferred from germline)
+      cdr1_start:
+        type: integer
+        description: CDR1 start coord in sequence (transferred from germline)
+      cdr1_end:
+        type: integer
+        description: CDR1 end coord in sequence (transferred from germline)
+      fwr2_start:
+        type: integer
+        description: FWR2 start coord in sequence (transferred from germline)
+      fwr2_end:
+        type: integer
+        description: FWR2 end coord in sequence (transferred from germline)
+      cdr2_start:
+        type: integer
+        description: CDR2 start coord in sequence (transferred from germline)
+      cdr2_end:
+        type: integer
+        description: CDR2 end coord in sequence (transferred from germline)
+      fwr3_start:
+        type: integer
+        description: FWR3 start coord in sequence (transferred from germline)
+      fwr3_end:
+        type: integer
+        description: FWR3 end coord in sequence (transferred from germline)
+      cdr3_start:
+        type: integer
+        description: CDR3 start coord in sequence (transferred from germline)
+      cdr3_end:
+        type: integer
+        description: CDR3 end coord in sequence (transferred from germline)
+      fwr4_start:
+        type: integer
+        description: FWR3 start coord in sequence (transferred from germline)
+      fwr4_end:
+        type: integer
+        description: FWR4 end coord in sequence (transferred from germline)
+      v_end:
+        type: integer
+        description: End coordinate of the V segment (generally inside the CDR3)
+      d_start:
+        type: integer
+        description: Start coordinate of the D segment
+      d_germ_start:
+        type: integer
+        description: Position of 'd_start' field in IMGT numbered germline V(D)J sequence
+      d_end:
+        type: integer
+        description: End coordinate of the D segment
+      j_start:
+        type: integer
+        description: Start coordinate of the J segment (generally inside the CDR3)
+      j_germ_start:
+        type: integer
+        description: Position of 'j_start' field in IMGT numbered germline V(D)J sequence
+      j_end:
+        type: integer
+        description: End coordinate of the J segment
+      junction_length:
+        type: integer
+        description: Number of junction nucleotides in sequence_vdj
+      np1_length:
+        type: integer
+        description: Number of of nucleotides between sample V and D sequences
+      np2_length:
+        type: integer
+        description: Number of of nucleotides between sample D and J sequences
+      n1_length:
+        type: integer
+        description: Nucleotides 5' of the D-segment
+      n2_length:
+        type: integer
+        description: Nucleotides 3' of the D-segment
+      p3v_length:
+        type: integer
+        description: Palindromic nucleotides 3' of the V-segment
+      p5d_length:
+        type: integer
+        description: Palindromic nucleotides 5' of the D-segment
+      p3d_length:
+        type: integer
+        description: Palindromic nucleotides 3' of the D-segment
+      p5j_length:
+        type: integer
+        description: Palindromic nucleotides 5' of the J-segment
+      duplicate_count:
+        type: integer
+        description: Number of duplicate reads for this sequence
+      consensus_count:
+        type: integer
+        description: Number of reads contributing to the consensus for this sequence
+      clone:
+        type: string
+        description: Clone assignment for this sequence

MiAIRR_rearrangement.yaml

@@ -0,0 +1,50 @@
+#
+# Schema definitions for AIRR minimal standards rearrangement objects
+#
+
+# The MiAIRR rearrangements
+
+MiAIRR_Rearrangements:
+   discriminator: MiAIRR
+   type: object
+   properties:
+        germline_database:
+          type: string
+          description: >
+            Source of germline V(D)J segments, with version number or
+            date accessed (e.g. IMGT/V-QUEST Release 201736-4 (7 September 2017)) (AIRR)
+        cell_index:
+          type: integer
+          description: |
+            Cell Index (UID linking sequences from the same cell) (AIRR)
+        v_allele:
+          type: string
+          description: |
+            V gene with allele (e.g. IGHV4-59*01) (AIRR)
+        d_allele:
+          type: string
+          description: |
+            D gene with allele (e.g. IGHD3-10*01) (AIRR)
+        j_allele:
+          type: string
+          description: |
+            J gene with allele (e.g. IGHJ4*02) (AIRR)
+        c_allele:
+          type: string
+          description: |
+            C region with allele (AIRR)                     
+        junction_nt:
+          type: string
+          description: >
+            JUNCTION nucleotide sequence (Sequence of the CDR3
+            region (nucleotide)) (AIRR)
+        junction_aa:
+          type: string
+          description: >
+            JUNCTION amino acid sequence (Sequence of the CDR3
+            region (amino acid)) (AIRR)
+        duplicate_count:
+          type: integer
+          description: |
+            Number of times the sequence has been duplicated in a file (AIRR)
+            

README.md

@@ -16,7 +16,7 @@ JSON files are generated by Swagger editor.
 
 ## Development Guidelines
 
-** Git Structure
+### Git Structure
 
  * This project uses the Git Flow methodology for code management and development: <https://www.atlassian.com/git/tutorials/comparing-workflows/gitflow-workflow>.
 
@@ -25,17 +25,17 @@ JSON files are generated by Swagger editor.
    double-check your branches and merge operations so the two versions
    do not get mixed up.
 
- * The *v1-master* branch is the master branch for ongoing V1 API
-   work, with *v1-develop* as its develop branch.
+ * The **v1-master** branch is the master branch for ongoing V1 API
+   work, with **v1-develop** as its develop branch.
 
- * The *master* branch is for ongoing V2 API work, with *develop* as
+ * The **master** branch is for ongoing V2 API work, with **develop** as
    its develop branch.
 
  * New development and features should be done on branches that are
-   cloned from the *develop* (for V2) or *v1-develop* (for V1) branch,
+   cloned from the **develop** (for V2) or **v1-develop** (for V1) branch,
    and then merged into this branch when completed.
 
- * Releases should merge *develop* into *master* (for V2) or
-   *v1-develop* into *v1-master* (for V1). Tag *master* or *v1-master*
-   *with the appropriate version.
+ * Releases should merge **develop** into **master** (for V2) or
+   **v1-develop** into **v1-master** (for V1). Tag **master** or **v1-master**
+   with the appropriate version.