From 649e779100c95d1cedcd28b03959ed351d518c6a Mon Sep 17 00:00:00 2001
From: valasatava <yana.valasatava@gmail.com>
Date: Tue, 9 May 2023 07:27:42 -0700
Subject: [PATCH] Add HYP to the list of amino acids (#815)

* add modified amino acid "hydroxyproline" (HYP) present in collagen molecules to the list of amino acids

* update changelog
---
 CHANGELOG.md                           | 1 +
 docs/interesting-pdb-entries.md        | 1 +
 src/mol-model/structure/model/types.ts | 2 +-
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index aa18fddab..d32f33ebb 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -16,6 +16,7 @@ Note that since we don't clearly distinguish between a public and private interf
   - uses custom mmcif categories `_sb_ncbr_partial_atomic_charges_meta` and `_sb_ncbr_partial_atomic_charges` (more info in [README.md](./src/extensions/sb-ncbr/README.md))
 - Parse HEADER record when reading PDB file
 - Support `ignoreHydrogens` in interactions representation
+- Add hydroxyproline (HYP) commonly present in collagen molecules to the list of amino acids
 
 ## [v3.34.0] - 2023-04-16
 
diff --git a/docs/interesting-pdb-entries.md b/docs/interesting-pdb-entries.md
index 8f405dc68..54d2c2145 100644
--- a/docs/interesting-pdb-entries.md
+++ b/docs/interesting-pdb-entries.md
@@ -26,6 +26,7 @@
 * Non-standard residues
     * Protein (1BRR, 5Z6Y)
     * DNA (5D3G)
+    * Collagen (6JEC)
 * Multiple models with different sets of ligands or missing ligands (1J6T, 1VRC, 2ICY, 1O2F)
 * Long linear sugar chain (4HG6)
 * Anisotropic B-factors/Ellipsoids (1EJG)
diff --git a/src/mol-model/structure/model/types.ts b/src/mol-model/structure/model/types.ts
index 2643c4d8f..31c1cab3c 100644
--- a/src/mol-model/structure/model/types.ts
+++ b/src/mol-model/structure/model/types.ts
@@ -252,7 +252,7 @@ export const AminoAcidNamesL = new Set([
     'HIS', 'ARG', 'LYS', 'ILE', 'PHE', 'LEU', 'TRP', 'ALA', 'MET', 'PRO', 'CYS',
     'ASN', 'VAL', 'GLY', 'SER', 'GLN', 'TYR', 'ASP', 'GLU', 'THR', 'SEC', 'PYL',
     'UNK', // unknown amino acid from CCD
-    'MSE', 'SEP', 'TPO', 'PTR', 'PCA', // common from CCD
+    'MSE', 'SEP', 'TPO', 'PTR', 'PCA', 'HYP', // common from CCD
 
     // charmm ff
     'HSD', 'HSE', 'HSP', 'LSN', 'ASPP', 'GLUP',
-- 
GitLab