modelcraft 5.0.2__py3-none-any.whl → 6.0.0__py3-none-any.whl

modelcraft/__init__.py

@@ -1,16 +1,11 @@
-__version__ = "5.0.2"
+__version__ = "6.0.0"
 
 from .cell import max_distortion as max_cell_distortion
-from .cell import remove_scale
-from .cell import update_cell
-from .contents import AsuContents
-from .contents import PolymerType
-from .geometry import rmsz
+from .cell import remove_scale, update_cell
+from .contents import AsuContents, PolymerType
 from .jobs.acedrg import Acedrg
 from .jobs.buccaneer import Buccaneer
 from .jobs.comit import Comit
-from .jobs.coot import FixSideChains
-from .jobs.coot import Prune
 from .jobs.ctruncate import CTruncate
 from .jobs.emda import EmdaMapMask
 from .jobs.findwaters import FindWaters
@@ -19,26 +14,21 @@ from .jobs.molrep import Molrep
 from .jobs.nautilus import Nautilus
 from .jobs.parrot import Parrot
 from .jobs.phasematch import PhaseMatch
-from .jobs.refmac import Refmac
-from .jobs.refmac import RefmacMapToMtz
-from .jobs.servalcat import ServalcatNemap
-from .jobs.servalcat import ServalcatRefine
-from .jobs.servalcat import ServalcatTrim
+from .jobs.refmac import Refmac, RefmacMapToMtz
+from .jobs.servalcat import ServalcatNemap, ServalcatRefine, ServalcatTrim
 from .jobs.sheetbend import Sheetbend
+from .monlib import MonLib
 from .pipeline import Pipeline
-from .reflections import DataItem
-from .reflections import write_mtz
-from .scripts.contents import _entry_contents as entry_contents
+from .reflections import DataItem, write_mtz
 from .scripts.modelcraft import main as run
-from .solvent import solvent_fraction
-from .structure import contains_residue
-from .structure import ModelStats
-from .structure import read_structure
-from .structure import remove_non_library_atoms
-from .structure import remove_non_protein
-from .structure import remove_residues
-from .structure import write_mmcif
-
+from .structure import (
+    ModelStats,
+    contains_residue,
+    read_structure,
+    remove_non_protein,
+    remove_residues,
+    write_mmcif,
+)
 
 __all__ = [
     "Acedrg",
@@ -49,33 +39,28 @@ __all__ = [
     "CTruncate",
     "DataItem",
     "EmdaMapMask",
-    "entry_contents",
     "FindWaters",
-    "FixSideChains",
     "FreeRFlag",
     "max_cell_distortion",
     "ModelStats",
     "Molrep",
+    "MonLib",
     "Nautilus",
     "Parrot",
     "PhaseMatch",
     "Pipeline",
     "PolymerType",
-    "Prune",
     "read_structure",
     "Refmac",
     "RefmacMapToMtz",
-    "remove_non_library_atoms",
     "remove_non_protein",
     "remove_residues",
     "remove_scale",
-    "rmsz",
     "run",
     "ServalcatNemap",
     "ServalcatRefine",
     "ServalcatTrim",
     "Sheetbend",
-    "solvent_fraction",
     "update_cell",
     "write_mmcif",
     "write_mtz",

modelcraft/__main__.py

@@ -1,5 +1,4 @@
 from .scripts.modelcraft import main
 
-
 if __name__ == "__main__":
     main()

modelcraft/arguments.py

@@ -1,15 +1,16 @@
-from typing import List, Optional
 import argparse
 import os
 import sys
+from typing import List, Optional
+
 import gemmi
 import numpy as np
+
 from . import __version__
 from .contents import AsuContents
 from .reflections import DataItem
 from .structure import read_structure
 
-
 _PROG = None
 if os.path.basename(sys.argv[0]) == "__main__.py":
     _PROG = f"{sys.executable} -m modelcraft"
@@ -23,12 +24,16 @@ _GROUP.add_argument(
     required=True,
     metavar="X",
     help=(
-        "A file with a description of the assymetric unit contents, "
+        "A file with a description of the full asymmetric unit contents, "
         "either as a sequence file (in FASTA or PIR format) "
         "with both protein and nucleic acid sequences, "
         "or a more detailed contents file in JSON format. "
         "Example JSON files for existing PDB entries "
-        "can be created using the modelcraft-contents script."
+        "can be created using the modelcraft-contents script. "
+        "Currently, the only advantage of using the JSON format "
+        "is a more accurate calculation of the solvent fraction "
+        "for Parrot density modification in the X-ray pipeline. "
+        "Otherwise, the solvent fraction will be calculated using Matthews probability."
     ),
 )
 _GROUP = _PARENT.add_argument_group("optional arguments (shared)")
@@ -181,6 +186,16 @@ _GROUP.add_argument(
         "This is not required if the MTZ only contains one free-R flag."
     ),
 )
+_GROUP.add_argument(
+    "--freerflag-value",
+    type=int,
+    metavar="X",
+    help=(
+        "Value of the free-R flag to identify reflections as free. "
+        "It defaults to the lowest flag with <50% of reflections. "
+        "If the chosen flag is not 0 it will changed to match the CCP4 convention."
+    ),
+)
 _GROUP.add_argument(
     "--unbiased",
     action="store_true",
@@ -387,9 +402,22 @@ def _parse_freerflag(args: argparse.Namespace, mtz: gemmi.Mtz):
     else:
         args.freer = _item_from_label(mtz, args.freerflag_label, ["I"])
     values = list(args.freer.columns[-1])
-    percentage = values.count(0) / len(values) * 100
-    if percentage == 0 or percentage > 50:
-        _PARSER.error(f"{percentage}% of the reflections are in the free set (flag 0)")
+    if args.freerflag_value is None:
+        for value in sorted(set(values)):
+            fraction = values.count(value) / len(values)
+            if fraction < 0.5:
+                args.freerflag_value = value
+                break
+        else:
+            _PARSER.error("No suitable value found for the free-R flag")
+    else:
+        percentage = values.count(args.freerflag_value) / len(values) * 100
+        if percentage == 0 or percentage > 50:
+            _PARSER.error(f"{percentage}% of the reflections are in the free set")
+    if args.freerflag_value != 0:
+        print("Changing the free-R flag to match CCP4 convention", flush=True)
+        values = [0 if v == args.freerflag_value else 1 for v in values]
+        args.freer.array[:, -1] = values
 
 
 def _parse_phases(args: argparse.Namespace, mtz: gemmi.Mtz):

modelcraft/combine.py

@@ -1,23 +1,29 @@
 import gemmi
+
 from .jobs.refmac import RefmacResult
-from .monlib import is_protein, is_nucleic
+from .monlib import MonLib
+from .structure import remove_isolated_fragments
 
 
-def combine_results(buccaneer: RefmacResult, nautilus: RefmacResult) -> gemmi.Structure:
+def combine_results(
+    buccaneer: RefmacResult, nautilus: RefmacResult, monlib: MonLib
+) -> gemmi.Structure:
     structure = buccaneer.structure.clone()
     for i, chain in reversed(list(enumerate(structure[0]))):
-        if _is_nucleic_chain(chain):
+        if _is_nucleic_chain(chain, monlib):
             del structure[0][i]
-    chains_to_add, clashing_to_remove = _resolve_clashes(structure, buccaneer, nautilus)
+    chains_to_add, clashing_to_remove = _resolve_clashes(
+        structure, buccaneer, nautilus, monlib
+    )
     for chain in structure[0]:
-        protein = _is_protein_chain(chain)
+        protein = _is_protein_chain(chain, monlib)
         any_removed = False
         for i, residue in reversed(list(enumerate(chain))):
             if _key(chain, residue) in clashing_to_remove:
                 del chain[i]
                 any_removed = True
         if protein and any_removed:
-            _remove_isolated_fragments(chain, _are_joined_protein, min_length=6)
+            remove_isolated_fragments(chain, monlib, max_length=5)
     structure.remove_empty_chains()
     for chain in chains_to_add:
         structure[0].add_chain(chain, unique_name=True)
@@ -25,7 +31,10 @@ def combine_results(buccaneer: RefmacResult, nautilus: RefmacResult) -> gemmi.St
 
 
 def _resolve_clashes(
-    structure: gemmi.Structure, buccaneer: RefmacResult, nautilus: RefmacResult
+    structure: gemmi.Structure,
+    buccaneer: RefmacResult,
+    nautilus: RefmacResult,
+    monlib: MonLib,
 ) -> tuple:
     chains_to_add = []
     clashing_to_remove = set()
@@ -33,7 +42,7 @@ def _resolve_clashes(
     naut_scores = _scores(nautilus)
     search = gemmi.NeighborSearch(structure, max_radius=1).populate()
     for chain in nautilus.structure[0]:
-        if _is_nucleic_chain(chain):
+        if _is_nucleic_chain(chain, monlib):
             residues_to_remove = set()
             for keys, clashing in _clashing_zones(chain, search, structure):
                 if _mean_score(keys, naut_scores) < _mean_score(clashing, bucc_scores):
@@ -44,7 +53,7 @@ def _resolve_clashes(
                 for i, residue in reversed(list(enumerate(chain))):
                     if _key(chain, residue) in residues_to_remove:
                         del chain[i]
-                _remove_isolated_fragments(chain, _are_joined_nucleic, min_length=2)
+                remove_isolated_fragments(chain, monlib, max_length=1)
             if len(chain) > 0:
                 chains_to_add.append(chain)
     return chains_to_add, clashing_to_remove
@@ -74,12 +83,12 @@ def _key(chain: gemmi.Chain, residue: gemmi.Residue) -> tuple:
     return (chain.name, residue.seqid.num, residue.seqid.icode)
 
 
-def _is_nucleic_chain(chain: gemmi.Chain) -> bool:
-    return len(chain) > 1 and all(is_nucleic(res.name) for res in chain)
+def _is_nucleic_chain(chain: gemmi.Chain, monlib: MonLib) -> bool:
+    return len(chain) > 1 and all(monlib.is_nucleic(res.name) for res in chain)
 
 
-def _is_protein_chain(chain: gemmi.Chain) -> bool:
-    return len(chain) > 1 and all(is_protein(res.name) for res in chain)
+def _is_protein_chain(chain: gemmi.Chain, monlib: MonLib) -> bool:
+    return len(chain) > 1 and all(monlib.is_protein(res.name) for res in chain)
 
 
 def _clashing_zones(
@@ -106,31 +115,3 @@ def _clashing_zones(
 
 def _mean_score(keys: set, scores: dict) -> float:
     return sum(scores[key] for key in keys) / len(keys)
-
-
-def _remove_isolated_fragments(chain: gemmi.Chain, are_joined, min_length: int):
-    to_remove = []
-    fragment = []
-    for i, residue in enumerate(chain):
-        if i > 0 and are_joined(chain[i - 1], residue):
-            fragment.append(i)
-        else:
-            if len(fragment) < min_length:
-                to_remove.extend(fragment)
-            fragment = [i]
-    if len(fragment) < min_length:
-        to_remove.extend(fragment)
-    for i in reversed(to_remove):
-        del chain[i]
-
-
-def _are_joined_protein(res1: gemmi.Residue, res2: gemmi.Residue) -> bool:
-    return "C" in res1 and "N" in res2 and res1["C"][0].pos.dist(res2["N"][0].pos) < 2.5
-
-
-def _are_joined_nucleic(res1: gemmi.Residue, res2: gemmi.Residue) -> bool:
-    return (
-        "O3'" in res1
-        and "P" in res2
-        and res1["O3'"][0].pos.dist(res2["P"][0].pos) < 2.5
-    )