Merging improvements from https://github.com/skodapetr/funpdbe-validator skodapetr@github - "fix multiple molecules issue"

data/funpdbe_schema.json

@@ -1,6 +1,6 @@
 {
   "$schema": "http://json-schema.org/draft-06/schema#",
-  "$id": "https://github.com/funpdbe-consortium/funpdbe_schema/blob/master/funpdbe_schema.v0.0.1.json",
+  "$id": "https://gitlab.ebi.ac.uk/pdbe-kb/funpdbe/funpdbe-schema/raw/master/funpdbe_schema.json",
   "title": "funpdbe_schema",
   "type": "object",
   "properties": {
@@ -32,7 +32,8 @@
     },
     "additional_entry_annotations": {
       "type": "object",
-      "description": "Additional entry-level annotations"
+      "description": "Additional entry-level annotations",
+      "additionalProperties": true
     },
     "chains": {
       "type": "array",
@@ -45,7 +46,8 @@
           },
           "additional_chain_annotations": {
             "type": "object",
-            "description": "Additional chain-level annotations"
+            "description": "Additional chain-level annotations",
+            "additionalProperties": true
           },
           "residues": {
             "type": "array",
@@ -63,7 +65,8 @@
                 },
                 "additional_residue_annotations": {
                   "type": "object",
-                  "description": "Additional residue-level annotations"
+                  "description": "Additional residue-level annotations",
+                  "additionalProperties": true
                 },
                 "site_data": {
                   "type": "array",
@@ -80,9 +83,8 @@
                       },
                       "confidence_score": {
                         "type": "number",
-                        "description": "Confidence level of the annotation (0-1)",
+                        "description": "Confidence level of the annotation (0-1, except if the method justifies otherwise)",
-                        "minimum": 0.0,
+                        "minimum": 0.0
-                        "maximum": 1.0
                       },
                       "confidence_classification": {
                         "type": "string",
@@ -91,14 +93,18 @@
                           "high",
                           "medium",
                           "low",
-                          "null"
+                          "null",
+                          "curated"
                         ]
+                      },
+                      "aa_variant": {
+                        "type": "string",
+                        "description": "Three-letter amino acid code of variant/mutant",
+                        "pattern": "^[A-Za-z0-9]+$"
                       }
                     },
                     "required": [
                       "site_id_ref",
-                      "raw_score",
-                      "confidence_score",
                       "confidence_classification"
                     ],
                     "additionalProperties": false
@@ -155,7 +161,8 @@
           },
           "additional_site_annotations": {
             "type": "object",
-            "description": "Additional site-level annotations"
+            "description": "Additional site-level annotations",
+            "additionalProperties": true
           }
         },
         "required": [
@@ -199,4 +206,4 @@
     "sites"
   ],
   "additionalProperties": false
-}
+}

validator/residue_index.py

@@ -2,11 +2,9 @@
 
 """
 Copyright 2018 EMBL - European Bioinformatics Institute
-
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
 You may obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0
-
 Unless required by applicable law or agreed to in writing,
 software distributed under the License is distributed on an
 "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
@@ -27,7 +25,6 @@ class ResidueIndexes(object):
     and each has to match the indices in the official PDB entry
     This class relies on the PDBe API to get the current residue
     indices
-
     Example usage:
     check_indexes = ResidueIndexes(your_json_object)
     if check_indexes.check_every_residue():
@@ -119,17 +116,22 @@ class ResidueIndexes(object):
         :param depositor_aa_type: Residue amino acid code provided by user
         :return: True is residue numbering is valid, False if not
         """
-        flag = None
+        flag = False
         for item in data:
             sub_data = item[label]
             if label == "chains":
-                flag = self._recursive_loop(sub_data, "residues", depositor_residue_number, depositor_aa_type,
+                flag |= self._recursive_loop(sub_data, "residues", depositor_residue_number, depositor_aa_type,
                                             depositor_chain_id)
             elif label == "residues":
                 return self._process_residues(sub_data, depositor_residue_number, depositor_aa_type, depositor_chain_id)
+
         if label == "chains":
             return flag
 
+        if label == "residues":
+            # We were checking residues and none was found, so not match found -> False.
+            return False
+
     def _process_residues(self, residues, depositor_residue_number, depositor_aa_type, depositor_chain_id):
         """
         This method grabs the residue information and call the comparator if the
@@ -158,9 +160,9 @@ class ResidueIndexes(object):
         :param depositor_residue_number: Residue number provided by the user
         :return: True is residue numbering is valid, False if not
         """
-        if residue_name == depositor_aa_type:
+        if residue_name.lower() == depositor_aa_type.lower():
             return True
         mismatch = "residue %s_%s (%s) in data does not match residue %s (%s) in PDB" % (
             depositor_chain_id, depositor_residue_number, depositor_aa_type, depositor_residue_number, residue_name)
         self.mismatches.append(mismatch)
-        return False
+        return False