servalcat 0.4.100__tar.gz → 0.4.105__tar.gz

{servalcat-0.4.100 → servalcat-0.4.105}/CMakeLists.txt

@@ -91,7 +91,7 @@ else()
     FetchContent_Declare(
       gemmi
       GIT_REPOSITORY https://github.com/project-gemmi/gemmi.git
-      GIT_TAG        v0.7.0
+      GIT_TAG        v0.7.1
     )
     FetchContent_GetProperties(gemmi)
     if (NOT gemmi_POPULATED)

{servalcat-0.4.100 → servalcat-0.4.105}/PKG-INFO

@@ -1,16 +1,16 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: servalcat
-Version: 0.4.100
+Version: 0.4.105
 Summary: Structure refinement and validation for crystallography and single particle analysis
 Author: Keitaro Yamashita, Garib N. Murshudov
 License: MPL-2.0
-Project-URL: Repository, https://github.com/keitaroyam/servalcat
+Project-URL: repository, https://github.com/keitaroyam/servalcat
 Requires-Python: >=3.8
 Requires-Dist: packaging
 Requires-Dist: numpy>=1.15
 Requires-Dist: scipy
 Requires-Dist: pandas>=1.1.0
-Requires-Dist: gemmi==0.7.0
+Requires-Dist: gemmi==0.7.1
 Description-Content-Type: text/markdown
 
 # Servalcat
@@ -40,7 +40,7 @@ pip install servalcat
 ```
 will install the stable version.
 
-The required GEMMI version is now [v0.7.0](https://github.com/project-gemmi/gemmi/releases/tag/v0.7.0). It may not work with the latest gemmi code from the github. The policy is in the main branch I only push the code that works with the latest package of GEMMI.
+The required GEMMI version is now [v0.7.1](https://github.com/project-gemmi/gemmi/releases/tag/v0.7.1). It may not work with the latest gemmi code from the github. The policy is in the main branch I only push the code that works with the latest package of GEMMI.
 
 To use the Refmac5 related commands, you also need to install [CCP4](https://www.ccp4.ac.uk/). For "No Refmac5" commands, you may just need [the monomer library](https://github.com/MonomerLibrary/monomers) if CCP4 is not installed.
 

{servalcat-0.4.100 → servalcat-0.4.105}/README.md

@@ -25,7 +25,7 @@ pip install servalcat
 ```
 will install the stable version.
 
-The required GEMMI version is now [v0.7.0](https://github.com/project-gemmi/gemmi/releases/tag/v0.7.0). It may not work with the latest gemmi code from the github. The policy is in the main branch I only push the code that works with the latest package of GEMMI.
+The required GEMMI version is now [v0.7.1](https://github.com/project-gemmi/gemmi/releases/tag/v0.7.1). It may not work with the latest gemmi code from the github. The policy is in the main branch I only push the code that works with the latest package of GEMMI.
 
 To use the Refmac5 related commands, you also need to install [CCP4](https://www.ccp4.ac.uk/). For "No Refmac5" commands, you may just need [the monomer library](https://github.com/MonomerLibrary/monomers) if CCP4 is not installed.
 

{servalcat-0.4.100 → servalcat-0.4.105}/pyproject.toml

@@ -1,5 +1,5 @@
 [build-system]
-requires = ["scikit-build-core~=0.10.7", "nanobind >=2.2"]
+requires = ["scikit-build-core ~=0.11.1", "nanobind >=2.2"]
 build-backend = "scikit_build_core.build"
 
 # https://packaging.python.org/en/latest/specifications/declaring-project-metadata/
@@ -7,7 +7,7 @@ build-backend = "scikit_build_core.build"
 name = "servalcat"
 dynamic = ["version"]
 requires-python = ">=3.8"
-dependencies = ['packaging', 'numpy>=1.15', 'scipy', 'pandas>=1.1.0', 'gemmi==0.7.0']
+dependencies = ['packaging', 'numpy>=1.15', 'scipy', 'pandas>=1.1.0', 'gemmi==0.7.1']
 description="Structure refinement and validation for crystallography and single particle analysis"
 readme = "README.md"
 authors = [

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/__init__.py

@@ -6,5 +6,5 @@ This software is released under the
 Mozilla Public License, version 2.0; see LICENSE.
 """
 
-__version__ = '0.4.100'
-__date__ = '2025-01-22'
+__version__ = '0.4.105'
+__date__ = '2025-03-26'

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/refine/refine.py

@@ -7,6 +7,7 @@ Mozilla Public License, version 2.0; see LICENSE.
 """
 from __future__ import absolute_import, division, print_function, generators
 import os
+import time
 import re
 import gemmi
 import numpy
@@ -221,7 +222,16 @@ def write_stats_json_safe(stats, json_out):
     out_tmp = json_out + ".part"
     with open(out_tmp, "w") as ofs:
         json.dump(tmp, ofs, indent=2)
-    os.replace(out_tmp, json_out)
+    for i in range(10):
+        try:
+            # On Windows, this fails when another process open the file
+            os.replace(out_tmp, json_out)
+            break
+        except PermissionError:
+            logger.writeln(f"{json_out} locked. retrying..")
+            time.sleep(0.5)
+    else:
+        raise RuntimeError(f"Cannot write {json_out}")
     logger.writeln(f"Refinement statistics saved: {json_out}")
 # write_stats_json_safe()
 

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/refine/refine_spa.py

@@ -150,8 +150,8 @@ def main(args):
         topo = None
         if args.hydrogen == "all":
             logger.writeln("\nWARNING: in unrestrained refinement hydrogen atoms are not generated.\n")
-            args.hydrogen = "yes"
-        elif args.hydrogen == "no":
+        if args.hydrogen != "yes":
+            args.hydrogen = "no"
             st.remove_hydrogens()
         for i, cra in enumerate(st[0].all()):
             cra.atom.serial = i + 1
@@ -300,8 +300,7 @@ def main(args):
     if args.hklin:
         return
     # Calc Fo-Fc (and updated) maps
-    diffmap_prefix = "{}_diffmap".format(args.output_prefix)
-    calc_fofc(refiner.st, st_expanded, maps, monlib, ".mmcif", args, diffmap_prefix=diffmap_prefix)
+    calc_fofc(refiner.st, st_expanded, maps, monlib, ".mmcif", args, diffmap_prefix=args.output_prefix)
     
     # Final summary
     adpstats_txt = ""
@@ -320,8 +319,8 @@ def main(args):
     if args.mask_for_fofc:
         map_peaks_str = """\
 List Fo-Fc map peaks in the ASU:
-servalcat util map_peaks --map {diffmap_prefix}_normalized_fofc.mrc --model {prefix}.pdb --abs_level 4.0 \
-""".format(prefix=args.output_prefix, diffmap_prefix=diffmap_prefix)
+servalcat util map_peaks --map {prefix}_normalized_fofc.mrc --model {prefix}.pdb --abs_level 4.0 \
+""".format(prefix=args.output_prefix)
     else:
         map_peaks_str = "WARNING: --mask_for_fofc was not given, so the Fo-Fc map was not normalized."
 
@@ -343,7 +342,7 @@ Weight used: {final_weight:.3e}
              If you want to change the weight, give larger (looser restraints)
              or smaller (tighter) value to --weight=.
              
-Open refined model and {diffmap_prefix}.mtz with COOT:
+Open refined model and {prefix}_maps.mtz with COOT:
 coot --script {prefix}_coot.py
 
 Open refined model, map and difference map with ChimeraX/ISOLDE:
@@ -358,7 +357,6 @@ chimerax {prefix}_chimerax.cxc
            adpstats=adpstats_txt.rstrip(),
            final_weight=args.weight,
            prefix=args.output_prefix,
-           diffmap_prefix=diffmap_prefix,
            map_peaks_msg=map_peaks_str))
 
 # main()

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/refine/refine_xtal.py

@@ -24,11 +24,15 @@ b_to_u = utils.model.b_to_u
 def add_arguments(parser):
     parser.description = "program to refine crystallographic structures"
     parser.add_argument("--hklin", required=True)
+    parser.add_argument('--hklin_free',
+                        help='Input MTZ file for test flags')
     parser.add_argument("-d", '--d_min', type=float)
     parser.add_argument('--d_max', type=float)
     parser.add_argument('--nbins', type=int, 
                         help="Number of bins (default: auto)")
     parser.add_argument("--labin", help="F,SIGF,FREE input")
+    parser.add_argument('--labin_free',
+                        help='MTZ column of --hklin_free')
     parser.add_argument('--free', type=int,
                         help='flag number for test set')
     parser.add_argument('--model', required=True,
@@ -128,7 +132,7 @@ def main(args):
     elif utils.fileio.is_mmhkl_file(hklin):
         hklin = utils.fileio.read_mmhkl(hklin)
         labin = decide_mtz_labels(hklin)
-        
+    software_items = utils.fileio.software_items_from_mtz(hklin)
     try:
         hkldata, sts, fc_labs, centric_and_selections, args.free = process_input(hklin=hklin,
                                                                                  labin=labin,
@@ -141,7 +145,10 @@ def main(args):
                                                                                  use="work" if args.use_work_in_est else "test",
                                                                                  max_bins=30,
                                                                                  keep_charges=args.keep_charges,
-                                                                                 allow_unusual_occupancies=args.allow_unusual_occupancies)
+                                                                                 allow_unusual_occupancies=args.allow_unusual_occupancies,
+                                                                                 hklin_free=args.hklin_free,
+                                                                                 labin_free=args.labin_free)
+
     except RuntimeError as e:
         raise SystemExit("Error: {}".format(e))
 
@@ -161,12 +168,13 @@ def main(args):
     if args.unrestrained:
         monlib = gemmi.MonLib()
         topo = None
-        h_change = gemmi.HydrogenChange.NoChange
-        if args.hydrogen == "all":
-            logger.writeln("\nWARNING: in unrestrained refinement hydrogen atoms are not generated.\n")
-        elif args.hydrogen == "no":
-            st.remove_hydrogens()
+        if args.hydrogen == "yes":
+            h_change = gemmi.HydrogenChange.NoChange
+        else:
             h_change = gemmi.HydrogenChange.Remove
+            st.remove_hydrogens()
+            if args.hydrogen == "all":
+                logger.writeln("\nWARNING: in unrestrained refinement hydrogen atoms are not generated.\n")
         for i, cra in enumerate(st[0].all()):
             cra.atom.serial = i + 1
     else:
@@ -235,6 +243,7 @@ def main(args):
                                weight_adjust_bond_rmsz_range=args.target_bond_rmsz_range,
                                stats_json_out=args.output_prefix + "_stats.json")
     update_meta(st, stats[-1], ll)
+    st.meta.software = software_items + st.meta.software
     refiner.st.name = args.output_prefix
     utils.fileio.write_model(refiner.st, args.output_prefix, pdb=True, cif=True, hout=args.hout)
     if params["write_trajectory"]:
@@ -253,12 +262,12 @@ def main(args):
 
     # Write mtz file
     if ll.twin_data:
-        labs = ["F_est", "F_exp", "FOM"]
+        labs = ["F_est", "F_exp"]
     elif is_int:
-        labs = ["I", "SIGI", "FOM"]
+        labs = ["I", "SIGI", "F_est"]
     else:
-        labs = ["FP", "SIGFP", "FOM"]
-    labs.extend(["FWT", "DELFWT", "FC"])
+        labs = ["FP", "SIGFP"]
+    labs.extend(["FOM", "FWT", "DELFWT", "FC"])
     if "FAN" in hkldata.df:
         labs.append("FAN")
     if not args.no_solvent:

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/refmac/refmac_wrapper.py

@@ -33,6 +33,8 @@ def add_arguments(parser):
     parser.add_argument('--keep_original_output', action='store_true', help="with .org extension")
     parser.add_argument("--keep_entities", action='store_true',
                         help="Do not override entities")
+    parser.add_argument("--tls_addu", action='store_true',
+                        help="Write prefix_addu.mmcif where TLS contribution is added to aniso U. Don't use this with 'tlso addu' keyword.")
     parser.add_argument('--prefix', help="output prefix")
     parser.add_argument("-v", "--version", action="version",
                         version=logger.versions_str())
@@ -222,7 +224,7 @@ def get_output_model_names(xyzout):
     return pdb, mmcif
 # get_output_model_names()
 
-def modify_output(pdbout, cifout, fixes, hout, cispeps, keep_original_output=False):
+def modify_output(pdbout, cifout, fixes, hout, cispeps, software_items, keep_original_output=False, tls_addu=False):
     st = utils.fileio.read_structure(cifout)
     st.cispeps = cispeps
     if os.path.exists(pdbout):
@@ -256,11 +258,37 @@ def modify_output(pdbout, cifout, fixes, hout, cispeps, keep_original_output=Fal
     # add servalcat version
     if len(st.meta.software) > 0 and st.meta.software[-1].name == "refmac":
         st.meta.software[-1].version += f" (refmacat {servalcat.__version__})"
+    st.meta.software = software_items + st.meta.software
     
     suffix = ".org"
     os.rename(cifout, cifout + suffix)
     utils.fileio.write_mmcif(st, cifout, cifout + suffix)
 
+    if tls_addu:
+        doc_ref = gemmi.cif.read(cifout + suffix)
+        tls_groups = {int(x.id): x for x in st.meta.refinement[0].tls_groups}
+        tls_details = doc_ref[0].find_value("_ccp4_refine_tls.details")
+        if tls_groups and gemmi.cif.as_string(tls_details) == "U values: residual only":
+            st2 = st.clone()
+            for cra in st2[0].all():
+                tlsgr = tls_groups.get(cra.atom.tls_group_id)
+                if cra.atom.tls_group_id > 0 and tlsgr is not None:
+                    if not cra.atom.aniso.nonzero():
+                        u = cra.atom.b_iso * utils.model.b_to_u
+                        cra.atom.aniso = gemmi.SMat33f(u, u, u, 0, 0, 0)
+                    u_from_tls = gemmi.calculate_u_from_tls(tlsgr, cra.atom.pos)
+                    cra.atom.aniso += gemmi.SMat33f(*u_from_tls.elements_pdb())
+                    cra.atom.b_iso = cra.atom.aniso.trace() / 3. * utils.model.u_to_b
+            cifout2 = cifout[:cifout.rindex(".")] + "_addu" + cifout[cifout.rindex("."):]
+            doc_ref[0].set_pair("_ccp4_refine_tls.details", gemmi.cif.quote("U values: with tls added"))
+            utils.fileio.write_mmcif(st2, cifout2, cif_ref_doc=doc_ref)
+        else:
+            if not tls_groups:
+                msg = "TLS group definition not found in the model"
+            else:
+                msg = "TLS already applied to the U values"
+            logger.writeln(f"Error: --tls_addu requested, but {msg}.")
+
     if st.has_d_fraction:
         st.store_deuterium_as_fraction(False) # also useful for pdb
         logger.writeln("will write a H/D expanded mmcif file")
@@ -313,6 +341,11 @@ def main(args):
     # TODO what if restin is given or make cr prepared is given?
     # TODO check make pept/link/suga/ss/conn/symm/chain
 
+    if "hklin" in opts: # for history
+        software_items = utils.fileio.software_items_from_mtz(opts["hklin"])
+    else:
+        software_items = []
+    
     # Process model
     crdout = None
     refmac_fixes = None
@@ -380,7 +413,8 @@ def main(args):
     if xyzin is not None:
         pdbout, cifout = get_output_model_names(opts.get("xyzout"))
         if os.path.exists(cifout):
-            modify_output(pdbout, cifout, refmac_fixes, keywords["make"].get("hout"), cispeps, args.keep_original_output)
+            modify_output(pdbout, cifout, refmac_fixes, keywords["make"].get("hout"), cispeps,
+                          software_items, args.keep_original_output, args.tls_addu)
 # main()
 
 def command_line():

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/spa/fofc.py

@@ -357,7 +357,7 @@ def write_files(hkldata, map_labs, grid_start, stats_str,
             hkldata2.translate(lab, -shifts)
         hkldata = hkldata2
         
-    dump_to_mtz(hkldata, map_labs, "{}.mtz".format(output_prefix))
+    dump_to_mtz(hkldata, map_labs, "{}_maps.mtz".format(output_prefix))
     if stats_str: open("{}_Fstats.log".format(output_prefix), "w").write(stats_str)
 # write_files()
 
@@ -458,15 +458,15 @@ def main(args):
 
     py_out = "{}_coot.py".format(args.output_prefix)
     write_coot_script(py_out, model_file=args.model,
-                      mtz_file=args.output_prefix+".mtz",
+                      mtz_file=args.output_prefix+"_maps.mtz",
                       contour_fo=None if mask is None else 1.2,
                       contour_fofc=None if mask is None else 3.0,
                       ncs_ops=ncs_org)
-    logger.writeln("\nOpen model and diffmap.mtz with COOT:")
+    logger.writeln("\nOpen model and diffmap mtz with COOT:")
     logger.writeln("coot --script " + py_out)
     if mask is not None:
         logger.writeln("\nWant to list Fo-Fc map peaks? Try:")
-        if omit_h_electron:
+        if args.omit_h_electron:
             logger.writeln("servalcat util map_peaks --map {}_normalized_fofc_flipsign.mrc --model {} --abs_level 4.0".format(args.output_prefix, args.model))
         else:
             logger.writeln("servalcat util map_peaks --map {}_normalized_fofc.mrc --model {} --abs_level 4.0".format(args.output_prefix, args.model))

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/spa/run_refmac.py

@@ -125,7 +125,7 @@ def add_arguments(parser):
     group = parser.add_mutually_exclusive_group()
     group.add_argument('--mask_for_fofc', help="Mask file for Fo-Fc map calculation")
     group.add_argument('--mask_radius_for_fofc', type=float, help="Mask radius for Fo-Fc map calculation")
-    parser.add_argument('--trim_fofc_mtz', action="store_true", help="diffmap.mtz will have smaller cell (if --mask_for_fofc is given)")
+    parser.add_argument('--trim_fofc_mtz', action="store_true", help="maps mtz will have smaller cell (if --mask_for_fofc is given)")
     parser.add_argument("--fsc_resolution", type=float,
                         help="High resolution limit for FSC calculation. Default: Nyquist")
 
@@ -312,7 +312,7 @@ def calc_fofc(st, st_expanded, maps, monlib, model_format, args, diffmap_prefix=
     # Create Coot script
     spa.fofc.write_coot_script("{}_coot.py".format(args.output_prefix),
                                model_file="{}.pdb".format(args.output_prefix), # as Coot is not good at mmcif file..
-                               mtz_file="{}.mtz".format(diffmap_prefix),
+                               mtz_file="{}_maps.mtz".format(diffmap_prefix),
                                contour_fo=None if mask is None else 1.2,
                                contour_fofc=None if mask is None else 3.0,
                                ncs_ops=st.ncs)
@@ -364,7 +364,7 @@ Weight used: {final_weight}
              If you want to change the weight, give larger (looser restraints)
              or smaller (tighter) value to --weight_auto_scale=.
              
-Open refined model and diffmap.mtz with COOT:
+Open refined model and maps mtz with COOT:
 coot --script {prefix}_coot.py
 
 Open refined model, map and difference map with ChimeraX/ISOLDE:

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/utils/commands.py

@@ -330,7 +330,7 @@ def symmodel(args):
     map_and_start = None
     if args.map:
         logger.writeln("Reading cell from map")
-        map_and_start = fileio.read_ccp4_map(args.map)
+        map_and_start = fileio.read_ccp4_map(args.map, header_only=True)
         st.cell = map_and_start[0].unit_cell
     elif args.cell:
         st.cell = gemmi.UnitCell(*args.cell)
@@ -388,7 +388,7 @@ def helical_biomt(args):
     map_and_start = None
     if args.map:
         logger.writeln("Reading cell from map")
-        map_and_start = fileio.read_ccp4_map(args.map)
+        map_and_start = fileio.read_ccp4_map(args.map, header_only=True)
         st.cell = map_and_start[0].unit_cell
     elif args.cell:
         st.cell = gemmi.UnitCell(*args.cell)
@@ -1307,7 +1307,7 @@ def mask_from_model(args):
     st = fileio.read_structure(args.model) # TODO option to (or not to) expand NCS
     if args.selection:
         gemmi.Selection(args.selection).remove_not_selected(st)
-    gr, grid_start, _ = fileio.read_ccp4_map(args.map)
+    gr, grid_start, _ = fileio.read_ccp4_map(args.map, header_only=True)
     mask = maps.mask_from_model(st, args.radius, soft_edge=args.soft_edge, grid=gr)
     maps.write_ccp4_map(args.output, mask, grid_start=grid_start)
 # mask_from_model()
@@ -1367,7 +1367,7 @@ def map2mtz(args):
 
 def sm2mm(args):
     if args.output_prefix is None:
-        args.output_prefix = fileio.splitext(args.files[0])[0]
+        args.output_prefix = os.path.basename(fileio.splitext(args.files[0])[0])
     st, mtz = fileio.read_small_molecule_files(args.files)
     if st is not None:
         fileio.write_model(st, prefix=args.output_prefix, pdb=True, cif=True)

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/utils/fileio.py

@@ -18,6 +18,7 @@ import subprocess
 import gemmi
 import numpy
 import gzip
+import traceback
 
 def splitext(path):
     if path.endswith((".bz2",".gz")):
@@ -66,14 +67,15 @@ def check_model_format(xyzin):
         return ".pdb"
 # check_model_format()
 
-def write_mmcif(st, cif_out, cif_ref=None):
+def write_mmcif(st, cif_out, cif_ref=None, cif_ref_doc=None):
     """
     Refmac fails if _entry.id is longer than 80 chars including quotations
     """
     st_new = st.clone()
     logger.writeln("Writing mmCIF file: {}".format(cif_out))
-    if cif_ref:
-        logger.writeln("  using mmCIF metadata from: {}".format(cif_ref))
+    if cif_ref or cif_ref_doc:
+        if cif_ref:
+            logger.writeln("  using mmCIF metadata from: {}".format(cif_ref))
         groups = gemmi.MmcifOutputGroups(False)
         groups.group_pdb = True
         groups.ncs = True
@@ -88,18 +90,19 @@ def write_mmcif(st, cif_out, cif_ref=None):
         groups.conn = True
         groups.software = True
         groups.auth_all = True
-        # FIXME is this all? 
-        try:
-            doc = read_cif_safe(cif_ref)
-        except Exception as e:
-            # Sometimes refmac writes a broken mmcif file..
-            logger.error("Error in mmCIF reading: {}".format(e))
-            logger.error("  Give up using cif reference.")
-            return write_mmcif(st, cif_out)
+        # FIXME is this all?
+        if cif_ref:
+            try:
+                cif_ref_doc = read_cif_safe(cif_ref)
+            except Exception as e:
+                # Sometimes refmac writes a broken mmcif file..
+                logger.error("Error in mmCIF reading: {}".format(e))
+                logger.error("  Give up using cif reference.")
+                return write_mmcif(st, cif_out)
             
-        blocks = list(filter(lambda b: b.find_loop("_atom_site.id"), doc))
+        blocks = list(filter(lambda b: b.find_loop("_atom_site.id"), cif_ref_doc))
         if len(blocks) == 0:
-            logger.writeln("No _atom_site found in {}".format(cif_ref))
+            logger.writeln("No _atom_site found in reference")
             logger.writeln("  Give up using cif reference.")
             return write_mmcif(st, cif_out)
         block = blocks[0]
@@ -108,7 +111,7 @@ def write_mmcif(st, cif_out, cif_ref=None):
         block.find_mmcif_category("_atom_sites.").erase()
         st_new.update_mmcif_block(block, groups)
         if "_entry.id" in st_new.info: st_new.info["_entry.id"] = st_new.info["_entry.id"][:78]
-        doc.write_file(cif_out, options=gemmi.cif.Style.Aligned)
+        cif_ref_doc.write_file(cif_out, options=gemmi.cif.Style.Aligned)
     else:
         st_new.name = st_new.name[:78] # this will become _entry.id
         if "_entry.id" in st_new.info: st_new.info["_entry.id"] = st_new.info["_entry.id"][:78]
@@ -162,17 +165,20 @@ def read_shifts_txt(shifts_txt):
     return ret
 # read_shifts_txt()
 
-def read_ccp4_map(filename, setup=True, default_value=0., pixel_size=None, ignore_origin=True):
-    m = gemmi.read_ccp4_map(filename)
-    g = m.grid
+def read_ccp4_map(filename, header_only=False, setup=True, default_value=0., pixel_size=None, ignore_origin=True):
+    if header_only:
+        m = gemmi.read_ccp4_header(filename)
+    else:
+        m = gemmi.read_ccp4_map(filename)
     grid_cell = [m.header_i32(x) for x in (8,9,10)]
     grid_start = [m.header_i32(x) for x in (5,6,7)]
     grid_shape = [m.header_i32(x) for x in (1,2,3)]
     axis_pos = m.axis_positions()
     axis_letters = ["","",""]
     for i, l in zip(axis_pos, "XYZ"): axis_letters[i] = l
-    spacings = [1./g.unit_cell.reciprocal().parameters[i]/grid_cell[i] for i in (0,1,2)]
-    voxel_size = [g.unit_cell.parameters[i]/grid_cell[i] for i in (0,1,2)]
+    cell = gemmi.UnitCell(*(m.header_float(x) for x in range(11,17)))
+    spacings = [1./cell.reciprocal().parameters[i]/grid_cell[i] for i in (0,1,2)]
+    voxel_size = [cell.parameters[i]/grid_cell[i] for i in (0,1,2)]
     origin = [m.header_float(x) for x in (50,51,52)]
     label = m.header_str(57, 80)
     label = label[:label.find("\0")]
@@ -181,7 +187,7 @@ def read_ccp4_map(filename, setup=True, default_value=0., pixel_size=None, ignor
     logger.writeln("    Map mode: {}".format(m.header_i32(4)))
     logger.writeln("       Start: {:4d} {:4d} {:4d}".format(*grid_start))
     logger.writeln("       Shape: {:4d} {:4d} {:4d}".format(*grid_shape))
-    logger.writeln("        Cell: {} {} {} {} {} {}".format(*g.unit_cell.parameters))
+    logger.writeln("        Cell: {} {} {} {} {} {}".format(*cell.parameters))
     logger.writeln("  Axis order: {}".format(" ".join(axis_letters)))
     logger.writeln(" Space group: {}".format(m.header_i32(23)))
     logger.writeln("     Spacing: {:.6f} {:.6f} {:.6f}".format(*spacings))
@@ -195,9 +201,17 @@ def read_ccp4_map(filename, setup=True, default_value=0., pixel_size=None, ignor
     logger.writeln("       Label: {}".format(label))
     logger.writeln("")
 
+    if header_only:
+        grid = gemmi.FloatGrid(*grid_cell if setup else grid_shape) # waste of memory, but unavoidable for now
+        grid.set_unit_cell(cell)
+        grid.spacegroup = gemmi.find_spacegroup_by_number(m.header_i32(23))
+    else:
+        grid = m.grid
+
     if setup:
-        if default_value is None: default_value = float("nan")
-        m.setup(default_value)
+        if not header_only:
+            if default_value is None: default_value = float("nan")
+            m.setup(default_value)
         grid_start = [grid_start[i] for i in axis_pos]
         
     if pixel_size is not None:
@@ -207,13 +221,13 @@ def read_ccp4_map(filename, setup=True, default_value=0., pixel_size=None, ignor
             pixel_size = [pixel_size, pixel_size, pixel_size]
             
         logger.writeln("Overriding pixel size with {:.6f} {:.6f} {:.6f}".format(*pixel_size))
-        orgc = m.grid.unit_cell.parameters
+        orgc = grid.unit_cell.parameters
         new_abc = [orgc[i]*pixel_size[i]/voxel_size[i] for i in (0,1,2)]
-        m.grid.unit_cell = gemmi.UnitCell(new_abc[0], new_abc[1], new_abc[2],
-                                          orgc[3], orgc[4], orgc[5])
-        logger.writeln(" New cell= {:.1f} {:.1f} {:.1f} {:.1f} {:.1f} {:.1f}".format(*m.grid.unit_cell.parameters))
+        new_cell = gemmi.UnitCell(new_abc[0], new_abc[1], new_abc[2], orgc[3], orgc[4], orgc[5])
+        grid.set_unit_cell(new_cell)
+        logger.writeln(" New cell= {:.1f} {:.1f} {:.1f} {:.1f} {:.1f} {:.1f}".format(*grid.unit_cell.parameters))
 
-    return [m.grid, grid_start, grid_shape]
+    return [grid, grid_start, grid_shape]
 # read_ccp4_map()
 
 def read_halfmaps(files, pixel_size=None, fail=True):
@@ -267,6 +281,19 @@ def is_mmhkl_file(hklin):
     # otherwise cannot decide
 # is_smhkl()
 
+def software_items_from_mtz(hklin):
+    try:
+        if type(hklin) is gemmi.Mtz:
+            mtz = hklin
+        else:
+            mtz = gemmi.read_mtz_file(hklin, with_data=False)
+        return gemmi.get_software_from_mtz_history(mtz.history)
+    except:
+        logger.writeln(f"Failed to read software info from {hklin}")
+        logger.writeln(traceback.format_exc())
+        return []
+# software_items_from_mtz()
+
 def read_map_from_mtz(mtz_in, cols, grid_size=None, sample_rate=3):
     mtz = read_mmhkl(mtz_in)
     d_min = mtz.resolution_high() # TODO get resolution for column?
@@ -551,9 +578,16 @@ def read_shelx_ins(ins_in=None, lines_in=None, ignore_q_peaks=True): # TODO supp
             if len(sp) > 11:
                 u = list(map(float, sp[6:12]))
                 site.aniso = gemmi.SMat33d(u[0], u[1], u[2], u[5], u[4], u[3])
-                #TODO site.u_iso needs to be set?
+                site.u_iso = sum(u[:3]) / 3.
             else:
                 site.u_iso = float(sp[6])
+                if site.u_iso < 0:
+                    # most recently defined non-hydrogen atom
+                    u_p = next((s.u_iso for s in reversed(ss.sites) if not s.element.is_hydrogen), None)
+                    if u_p is not None:
+                        site.u_iso *= -u_p
+                    else:
+                        logger.writeln(f"WARNING: parent atom not found for {site.label}")
 
             ss.add_site(site)
 
@@ -693,20 +727,21 @@ def read_small_molecule_files(files):
     # first pass - find structure
     for filename in files:
         ext = splitext(filename)[1]
-        if ext in (".cif", ".res", ".ins"):
+        if ext in (".cif", ".res", ".ins", ".pdb", ".ent", ".mmcif"):
             try:
                 st = read_structure(filename)
             except:
                 continue
             logger.writeln("Coordinates read from: {}".format(filename))
-            if ext == ".cif":
-                b = gemmi.cif.read(filename).sole_block()
-                res_str = b.find_value("_shelx_res_file")
-            else:
-                res_str = open(filename).read()
-            if res_str:
-                _, info = read_shelx_ins(lines_in=res_str.splitlines())
-                hklf = info["hklf"]
+            if ext in (".cif", ".res", ".ins"):
+                if ext == ".cif":
+                    b = gemmi.cif.read(filename).sole_block()
+                    res_str = b.find_value("_shelx_res_file")
+                else:
+                    res_str = open(filename).read()
+                if res_str:
+                    _, info = read_shelx_ins(lines_in=res_str.splitlines())
+                    hklf = info["hklf"]
     if st is None:
         logger.writeln("ERROR: coordinates not found.")
         return None, None
@@ -733,12 +768,16 @@ def read_sequence_file(f):
     # TODO needs improvement
     # return a list of [name, sequence]
     ret = []
-    for l in open(f):
+    for i, l in enumerate(open(f)):
         l = l.strip()
         if l.startswith(">"):
             name = l[1:].strip()
             ret.append([name, ""])
         elif l:
             if not ret: ret.append(["", ""])
-            ret[-1][1] += l.replace("*", "").replace("-", "").upper()
+            tmp = l.replace("*", "").replace("-", "").upper()
+            r = re.search("[^A-Z]", tmp)
+            if r:
+                raise RuntimeError(f"Invalid character in the sequence file: {f}:{i+1}")
+            ret[-1][1] += tmp
     return ret

{servalcat-0.4.100 → servalcat-0.4.105}/servalcat/utils/model.py

@@ -494,9 +494,10 @@ def filter_contacting_ncs(st, cutoff=5.):
     st.setup_cell_images()
     ns = gemmi.NeighborSearch(st[0], st.cell, cutoff*2).populate() # This is considered crystallographic cell if not 1 1 1. Undesirable result may be seen.
     cs = gemmi.ContactSearch(cutoff)
+    cs.twice = True # since we need all image_idx
     cs.ignore = gemmi.ContactSearch.Ignore.SameAsu
     results = cs.find_contacts(ns)
-    indices = set([r.image_idx for r in results])
+    indices = {r.image_idx for r in results}
     logger.writeln(" contacting copies: {}".format(indices))
     ops = [st.ncs[i-1] for i in indices] # XXX is this correct? maybe yes as long as identity operator is not there
     st.ncs.clear()