From 1abe7390449c665e7ccba40e3bfaa8a7b670b109 Mon Sep 17 00:00:00 2001 From: mvaradi Date: Fri, 12 Oct 2018 17:25:27 +0100 Subject: [PATCH] Adding mock data JSONs --- data/funpdbe_schema.json | 202 ++++++++++++++++++++++++++++++++++ data/test_data.json | 88 +++++++++++++++ data/test_data_malformed.json | 0 3 files changed, 290 insertions(+) create mode 100644 data/funpdbe_schema.json create mode 100644 data/test_data.json create mode 100644 data/test_data_malformed.json diff --git a/data/funpdbe_schema.json b/data/funpdbe_schema.json new file mode 100644 index 0000000..def38ee --- /dev/null +++ b/data/funpdbe_schema.json @@ -0,0 +1,202 @@ +{ + "$schema": "http://json-schema.org/draft-06/schema#", + "$id": "https://github.com/funpdbe-consortium/funpdbe_schema/blob/master/funpdbe_schema.v0.0.1.json", + "title": "funpdbe_schema", + "type": "object", + "properties": { + "data_resource": { + "type": "string", + "description": "Name of the database or software" + }, + "resource_version": { + "type": "string", + "description": "Version of the resource" + }, + "software_version": { + "type": "string", + "description": "Version of the software used" + }, + "resource_entry_url": { + "type": "string", + "description": "URL linking to the entry at the partner resource" + }, + "release_date": { + "type": "string", + "description": "Release date of the annotation", + "pattern": "^[0-3]*[0-9]/[0-1]*[0-9]/[1-2][0-9]{3}$" + }, + "pdb_id": { + "type": "string", + "description": "PDB identifier", + "pattern": "^[1-9][a-zA-Z0-9]{3}$" + }, + "additional_entry_annotations": { + "type": "object", + "description": "Additional entry-level annotations" + }, + "chains": { + "type": "array", + "items": { + "type": "object", + "properties": { + "chain_label": { + "type": "string", + "description": "PDB chain identifier" + }, + "additional_chain_annotations": { + "type": "object", + "description": "Additional chain-level annotations" + }, + "residues": { + "type": "array", + "items": { + "type": "object", + "properties": { + "pdb_res_label": { + "type": "string", + "description": "Residue index from the related PDB entry" + }, + "aa_type": { + "type": "string", + "description": "Three-letter amino acid code", + "pattern": "^[A-Za-z0-9]+$" + }, + "additional_residue_annotations": { + "type": "object", + "description": "Additional residue-level annotations" + }, + "site_data": { + "type": "array", + "items": { + "type": "object", + "properties": { + "site_id_ref": { + "type": "integer", + "description": "Reference to site_id" + }, + "raw_score": { + "type": "number", + "description": "Raw calculated score" + }, + "confidence_score": { + "type": "number", + "description": "Confidence level of the annotation (0-1)", + "minimum": 0.0, + "maximum": 1.0 + }, + "confidence_classification": { + "type": "string", + "description": "Confidence classification of the residue", + "enum": [ + "high", + "medium", + "low", + "null" + ] + } + }, + "required": [ + "site_id_ref", + "raw_score", + "confidence_score", + "confidence_classification" + ], + "additionalProperties": false + }, + "minItems": 1, + "uniqueItems": true + } + }, + "required": [ + "pdb_res_label", + "aa_type", + "site_data" + ], + "additionalProperties": false + }, + "minItems": 1, + "uniqueItems": true + } + }, + "required": [ + "chain_label", + "residues" + ], + "additionalProperties": false + }, + "minItems": 1, + "uniqueItems": true + }, + "sites": { + "type": "array", + "items": { + "type": "object", + "properties": { + "site_id": { + "type": "integer", + "description": "Site identifier" + }, + "label": { + "type": "string", + "description": "Site label" + }, + "source_database": { + "type": "string", + "description": "Name of the source database" + }, + "source_accession": { + "type": "string", + "description": "Accession identifier" + }, + "source_release_date": { + "type": "string", + "description": "Date of acquiring data from source", + "pattern": "^[0-3]*[0-9]/[0-1]*[0-9]/[1-2][0-9]{3}$" + }, + "additional_site_annotations": { + "type": "object", + "description": "Additional site-level annotations" + } + }, + "required": [ + "site_id", + "label" + ], + "additionalProperties": false + }, + "minItems": 1, + "uniqueItems": true + }, + "evidence_code_ontology": { + "type": "array", + "items": { + "type": "object", + "properties": { + "eco_term": { + "type": "string", + "description": "Evidence Code Ontology (ECO) term - http://www.evidenceontology.org/" + }, + "eco_code": { + "type": "string", + "description": "Evidence Code Ontology (ECO) code - http://www.evidenceontology.org/", + "pattern": "^ECO_[0-9]{7}$" + } + }, + "required": [ + "eco_code" + ], + "additionalProperties": false + }, + "minItems": 1, + "uniqueItems": true + } + }, + "required": [ + "data_resource", + "pdb_id", + "chains", + "evidence_code_ontology", + "sites" + ], + "additionalProperties": false +} \ No newline at end of file diff --git a/data/test_data.json b/data/test_data.json new file mode 100644 index 0000000..e85b9d8 --- /dev/null +++ b/data/test_data.json @@ -0,0 +1,88 @@ +{ + "data_resource": "ProKinO", + "resource_version": "2.0", + "software_version": "2.0", + "resource_entry_url": "http://vulcan.cs.uga.edu/prokino/", + "release_date": "10/02/2017", + "pdb_id": "2gs6", + "chains": [ + { + "additional_chain_annotations": {}, + "residues": [ + { + "additional_residue_annotations": {}, + "pdb_res_label": 811, + "aa_type": "HIS", + "site_data": [ + { + "confidence_score": 1, + "site_id_ref": 811, + "confidence_classification": "high", + "raw_score": 1 + } + ] + }, + { + "additional_residue_annotations": {}, + "pdb_res_label": 812, + "aa_type": "ARG", + "site_data": [ + { + "confidence_score": 1, + "site_id_ref": 812, + "confidence_classification": "high", + "raw_score": 1 + } + ] + }, + { + "additional_residue_annotations": {}, + "pdb_res_label": 813, + "aa_type": "ASP", + "site_data": [ + { + "confidence_score": 1, + "site_id_ref": 813, + "confidence_classification": "high", + "raw_score": 1 + } + ] + } + ], + "chain_label": "A" + } + ], + "sites": [ + { + "additional_site_annotations": {}, + "source_release_date": "06/20/2006", + "site_id": 811, + "label": "HRD motif", + "source_accession": "2gs6", + "source_database": "pdb" + }, + { + "additional_site_annotations": {}, + "source_release_date": "06/20/2006", + "site_id": 812, + "label": "HRD motif", + "source_accession": "2gs6", + "source_database": "pdb" + }, + { + "additional_site_annotations": {}, + "source_release_date": "06/20/2006", + "site_id": 813, + "label": "HRD motif", + "source_accession": "2gs6", + "source_database": "pdb" + } + ], + "additional_entry_annotations": {}, + "evidence_code_ontology": [ + { + "eco_term": "computational combinatorial evidence", + "eco_code": "ECO_0000246" + } + ] +} \ No newline at end of file diff --git a/data/test_data_malformed.json b/data/test_data_malformed.json new file mode 100644 index 0000000..e69de29