File size: 4,115 Bytes
6aab6b3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | entities:
- protein:
id: G
sequence: 15..20AAAAAAVTTTT18PPP # range between 15 and 20 inclusive on both sides
residue_constraints:
- position: 1
allowed: A # Only Alanine at position 1
- position: 3..5
disallowed: CM # No Cysteine or Methionine at positions 3-5
- position: 8
allowed: AGS # Only Ala, Gly, or Ser at position 8
- protein:
id: R
sequence: 3..5C6C3 # Random number of design residues between 3 and 5, then a Cystein, then 6 design residues, then ...
- ligand:
id: Q
ccd: WHL
- protein:
id: H
sequence: 17
secondary_structure: # No secondary structure specified, defaults
- file:
path: 7rpz.cif
include:
- chain:
id: A
- chain:
id: B
include_proximity:
- chain:
id: A
res_index: 10..16
radius: 35
binding_types:
- chain:
id: A
binding: 5..7,13
- chain:
id: B
not_binding: "all"
structure_groups:
- group:
visibility: 1
id: A
res_index: 10..16
- group:
visibility: 2
id: B
- group:
visibility: 0
id: A
res_index: 13
design:
- chain:
id: A
res_index: ..4,20..27
secondary_structure:
- chain:
id: A
loop: 1
helix: 2..3
sheet: 4
design_insertions:
- insertion:
id: A
res_index: 20 # The 20th residue will be a designed one (starting to count from 1)
num_residues: 2..9
secondary_structure: HELIX # One of UNSPECIFIED (default), LOOP, HELIX, SHEET.
- protein:
id: A
sequence: AAAAAAAAAAAAAAAAAAAAAAAA
binding_types: uuuuBBBuNNNuBuu # the missing specifications will be 'u' by default
- file:
path: 7rpz.cif
fuse: A
include:
- chain:
id: A
res_index: ..5
- protein:
id: B
sequence: AAAAAAAAAAAAAAAAAAAAAAAA
binding_types:
binding: 5..7,13
not_binding: 9..11
- ligand:
id: [C, D]
ccd: SAH
- ligand:
id: [E, F]
smiles: 'N[C@@H](Cc1ccc(O)cc1)C(=O)O'
binding_types: B
- file:
path: 7rpz.cif
include: "all"
exclude:
- chain:
id: A
res_index: ..5
structure_groups:
- group:
visibility: 1
id: "all"
- group:
visibility: 0
id: A
res_index: 10..16
- file:
path: 8r3a.cif
include:
- chain:
id: A
- chain:
id: B
binding_types:
- chain:
id: A
binding: 5..7,13
- chain:
id: B
not_binding: "all"
structure_groups:
- group:
visibility: 1
id: A
res_index: 10..13
- group:
visibility: 2
id: B
- group:
visibility: 0
id: A
res_index: 13
design:
- chain:
id: A
res_index: 14..19
secondary_structure:
- chain:
id: A
loop: 14
helix: 15..17
sheet: 19
- protein:
id: S
sequence: 10C6C3
- protein:
id: T
sequence: C10C6C3C
cyclic: true
constraints:
# specify connections as if the minimum possible number of residues was sampled
- bond:
atom1: [R, 4, SG] # connection for a helical peptides with WHL staple
atom2: [Q, 1, CK]
- bond:
atom1: [R, 11, SG]
atom2: [Q, 1, CH]
- bond:
atom1: [S, 11, SG] # connection for a disulfide bond
atom2: [S, 18, SG]
- bond:
atom1: [T, 12, SG]
atom2: [T, 19, SG]
- total_len:
min: 10
max: 20 |