diff --git a/CHANGELOG.txt b/CHANGELOG.txt
index 8227297675eac5e2c0793ad9021fc4ed321a6cb2..01f62d91c401707e5819883e1d5695510574e301 100644
--- a/CHANGELOG.txt
+++ b/CHANGELOG.txt
@@ -1,7 +1,7 @@
-Changes in Release 2.x
+Changes in Release 2.1.0
--------------------------------------------------------------------------------
- * Use the newer voronota implementation as default in CAD-score binding
+ * Use the newer Voronota implementation as default in CAD-score binding
* Added HHblits3 support - HHblits2 still supported but considered deprecated
* HMMScore: HMM-HMM alignment score as it is optimized in HHblits searches
* Support for the new carbohydrate-extension in the mmCIF file format
diff --git a/CMakeLists.txt b/CMakeLists.txt
index 91af96562fbee8cccd2d9e6c0ae957bdbfddd485..6bd006d7804dd0bea7bb1609c9d89f40c78c5cac 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -14,7 +14,7 @@ cmake_policy(SET CMP0060 NEW)
project(OpenStructure CXX C)
set (CMAKE_EXPORT_COMPILE_COMMANDS 1)
set (OST_VERSION_MAJOR 2)
-set (OST_VERSION_MINOR 0)
+set (OST_VERSION_MINOR 1)
set (OST_VERSION_PATCH 0)
set (OST_VERSION_STRING ${OST_VERSION_MAJOR}.${OST_VERSION_MINOR}.${OST_VERSION_PATCH} )
set(CMAKE_MODULE_PATH ${CMAKE_MODULE_PATH} ${PROJECT_SOURCE_DIR}/cmake_support)
diff --git a/docker/Dockerfile b/docker/Dockerfile
index 63df3f9e4267df1c596a16410463708a6463792c..b0863e7838d088bb47e9c166dd79784fa6b014cb 100644
--- a/docker/Dockerfile
+++ b/docker/Dockerfile
@@ -2,7 +2,7 @@ FROM ubuntu:18.04
# ARGUMENTS
###########
-ARG OPENSTRUCTURE_VERSION="2.0.0"
+ARG OPENSTRUCTURE_VERSION="2.1.0"
ARG SRC_FOLDER="/usr/local/src"
ARG CPUS_FOR_MAKE=2
ARG MSMS_VERSION="2.6.1"
diff --git a/modules/bindings/pymod/hhblits.py b/modules/bindings/pymod/hhblits.py
index 0ee1f3ecad62fccb5cd77905a9500f46b01426d1..3ca019bef6e83a97a392ad73f7cbd2a9a9548d09 100644
--- a/modules/bindings/pymod/hhblits.py
+++ b/modules/bindings/pymod/hhblits.py
@@ -20,9 +20,9 @@ def GetHHblitsVersionString():
# regular expression in the form
# HHblits, whatever except newline, x.y.z
# where x.y.z are the version numerals
- version_line = re.search('HHblits[^\n]+\d+\.\d+\.\d+', proc.stdout.decode())
+ version_line = re.search(r'HHblits[^\n]+\d+\.\d+\.\d+', proc.stdout.decode())
if version_line is not None:
- version = re.search('\d+\.\d+\.\d+', version_line.group())
+ version = re.search(r'\d+\.\d+\.\d+', version_line.group())
if version is not None:
version_string = version.group()
diff --git a/modules/doc/install.rst b/modules/doc/install.rst
index ed8495c104aa747330f3696c63b7646c69d968ff..4dbfffd133bcfa2902caf828d37bf29af2da9f6f 100644
--- a/modules/doc/install.rst
+++ b/modules/doc/install.rst
@@ -300,13 +300,13 @@ observed for OpenMM versions 6.1 until 7.1.1 when compiling with gcc versions >=
from source.
-**Ubuntu 18.04 LTS / Debian 10.3.0 with GUI**
+**Ubuntu 20.04 LTS / Debian 10 with GUI**
All the dependencies can be installed from the package manager as follows:
.. code-block:: bash
- sudo apt-get install cmake g++ sip-dev libtiff-dev libfftw3-dev libeigen3-dev \
+ sudo apt-get install cmake g++ libtiff-dev libfftw3-dev libeigen3-dev \
libpng-dev python3-all python3-pyqt5 libboost-all-dev \
qt5-qmake qtbase5-dev libpng-dev libsqlite3-dev
@@ -318,11 +318,11 @@ version of OpenStructure.
.. code-block:: bash
- cmake . -DPYTHON_LIBRARIES=/usr/lib/x86_64-linux-gnu/libpython3.6m.so \
+ cmake . -DPYTHON_LIBRARIES=/usr/lib/x86_64-linux-gnu/libpython3.8.so \
-DOPTIMIZE=ON
Be careful at -DPYTHON_LIBRARIES, Debian 10 comes with Python 3.7 so that needs
-to be substituted.
+to be substituted (libpython3.8.so -> libpython3.7m.so).
**macOS (Catalina) with Homebrew**
diff --git a/modules/gui/pymod/__init__.py b/modules/gui/pymod/__init__.py
index 78c1617af5a25907fa2f21472e59fe4ec4aa45cb..fc8d1494c41b4daec849c7af1f33935119f3516a 100644
--- a/modules/gui/pymod/__init__.py
+++ b/modules/gui/pymod/__init__.py
@@ -18,8 +18,6 @@
#------------------------------------------------------------------------------
import ost.gui.trajectory_viewer
from ._ost_gui import *
-import sip
-
## \brief Opens a DataViewer
# \sa \example fft_li.py "View Fourier Transform Example" \sa \ref modulate_image.py "Modulate Image Example"
diff --git a/modules/gui/pymod/export_input.cc b/modules/gui/pymod/export_input.cc
index 06846fc98ace3c57af3d7435f3bbf72fe7dc6687..8aec22c2b7c5717905dfffaedb06e96e09701284 100644
--- a/modules/gui/pymod/export_input.cc
+++ b/modules/gui/pymod/export_input.cc
@@ -30,8 +30,8 @@ namespace {
object spnav_get_instance()
{
- static object sip_module=import("sip");
static object pyqt5_module=import("PyQt5.QtCore");
+ static object sip_module=import("sip");
SpnavInput* si = SpnavInput::Instance();
if(si->isValid()) {
return ost::gui::get_py_qobject<SpnavInput>(si);
diff --git a/modules/gui/pymod/init_context_menu.py b/modules/gui/pymod/init_context_menu.py
index 9693ef5c8db13ef1dca585a17614eb77650aaa6b..a241253f1d0e1886e2c9214b2949236591acff53 100644
--- a/modules/gui/pymod/init_context_menu.py
+++ b/modules/gui/pymod/init_context_menu.py
@@ -2,8 +2,6 @@ import platform
from PyQt5 import QtCore, QtWidgets
-import sip
-
from ost import geom, gfx, gui, seq
from ost import settings
from ost import LogError, mol
diff --git a/modules/gui/pymod/init_menubar.py b/modules/gui/pymod/init_menubar.py
index c245f0f3ceccfd682d40a22d7df94562be2feb9b..2c8f05c4d8f92c834fbe85591c496f5c3af7d7b8 100644
--- a/modules/gui/pymod/init_menubar.py
+++ b/modules/gui/pymod/init_menubar.py
@@ -19,7 +19,6 @@
import sys
from ost import gui
-import sip
from ost import gfx
import ost
diff --git a/modules/gui/pymod/scene/file_loader.py b/modules/gui/pymod/scene/file_loader.py
index adf747d10b27ff9b7c19b682fb9aa86d0c33f03f..567450218fa9d77cb213e7a7b799dc29a9a73ac4 100644
--- a/modules/gui/pymod/scene/file_loader.py
+++ b/modules/gui/pymod/scene/file_loader.py
@@ -20,9 +20,7 @@
from ost import gui
from ost import info
import ost
-import sip
import re
-
from PyQt5 import QtCore, QtGui, QtNetwork
from ost.gui import FileLoader
diff --git a/modules/gui/pymod/scene/init_inspector.py b/modules/gui/pymod/scene/init_inspector.py
index 99fea817bfbe79c96479494e8b040c46c4c19a37..f250b80ea0b511733fc16a32ca988040e1cf16b2 100644
--- a/modules/gui/pymod/scene/init_inspector.py
+++ b/modules/gui/pymod/scene/init_inspector.py
@@ -17,8 +17,6 @@
# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
#------------------------------------------------------------------------------
-import sip
-
from ost import gui
from ost import gfx
from PyQt5 import QtCore
diff --git a/modules/gui/pymod/scene/inspector_widget.py b/modules/gui/pymod/scene/inspector_widget.py
index f1d98d3778ef603cf3cc9849b3a01661b60fba16..5ae8b872508c8a7e77d91626c67802c43950d39d 100644
--- a/modules/gui/pymod/scene/inspector_widget.py
+++ b/modules/gui/pymod/scene/inspector_widget.py
@@ -19,7 +19,6 @@
import sys
from ost import gui
-import sip
from ost import gfx
import ost
import os
diff --git a/modules/gui/pymod/scene/scene_selection_helper.py b/modules/gui/pymod/scene/scene_selection_helper.py
index 91686daf2270378337e2935cb8ad75c733854e7f..0c2d8d09aa127d3241c7019c4f17ff25e28cc727 100644
--- a/modules/gui/pymod/scene/scene_selection_helper.py
+++ b/modules/gui/pymod/scene/scene_selection_helper.py
@@ -19,7 +19,6 @@
import sys
from ost import gui
-import sip
from ost import gfx
import ost
import os
diff --git a/modules/gui/pymod/sip_handler.hh b/modules/gui/pymod/sip_handler.hh
index c2f9c189a1a2a4710e88e125360c8e36b498a244..5a37b312ac79836b04c5cfde7ae0fb82a71ffe71 100644
--- a/modules/gui/pymod/sip_handler.hh
+++ b/modules/gui/pymod/sip_handler.hh
@@ -37,8 +37,8 @@ namespace ost { namespace gui {
template <class O> object get_py_qobject(O* cpp_object)
{
if (cpp_object != NULL){
- static object sip_module=import("sip");
static object pyqt5_module=import("PyQt5.QtCore");
+ static object sip_module=import("sip");
QObject* qobject = qobject_cast<QObject*>(cpp_object);
unsigned long addr = reinterpret_cast<unsigned long>(qobject);
object py_qobject = pyqt5_module.attr("QObject");
@@ -55,6 +55,7 @@ template <class O> O* get_cpp_qobject(object py_object)
if(PyObject_HasAttrString(py_object.ptr(), "qobject")){
py_object = py_object.attr("qobject");
}
+ static object pyqt5_module=import("PyQt5.QtCore");
static object sip_module=import("sip");
unsigned long addr = extract<unsigned long>(sip_module.attr("unwrapinstance")(py_object));
if(addr){
diff --git a/modules/io/doc/mmcif.rst b/modules/io/doc/mmcif.rst
index f0ad0c7788c5d0faa585c0a2389fad07d3be61e3..41a6ed5f2e59c0c13e915d1bc527d2de5469b498 100644
--- a/modules/io/doc/mmcif.rst
+++ b/modules/io/doc/mmcif.rst
@@ -800,7 +800,7 @@ of the annotation available.
See :attr:`operationsintervalls`
- .. function:: PDBize(asu, seqres=None, min_polymer_size=10, transformation=False)
+ .. function:: PDBize(asu, seqres=None, min_polymer_size=None, transformation=False, peptide_min_size=10, nucleicacid_min_size=10, saccharide_min_size=10)
Returns the biological assembly (bio unit) for an entity. The new entity
created is well suited to be saved as a PDB file. Therefore the function
@@ -812,7 +812,8 @@ of the annotation available.
- Each polymer gets its own chain, named A-Z 0-9 a-z.
- The description of non-polymer chains will be put into a generic string
property called description on the residue level.
- - Ligands that resemble a polymer but have less than *min_polymer_size*
+ - Ligands that resemble a polymer but have less than *min_polymer_size* /
+ *peptide_min_size* / *nucleicacid_min_size* / *saccharide_min_size*
residues are assigned the same numeric residue number. The residues are
distinguished by insertion code.
- Sometimes bio units exceed the coordinate system storable in a PDB file.
@@ -832,11 +833,21 @@ of the annotation available.
:type seqres: :class:`~ost.seq.SequenceList`
:param min_polymer_size: The minimal number of residues a polymer needs to
get its own chain. Everything below that number will be sorted into the
- ligand chain.
+ ligand chain. Overrides *peptide_min_size*, *nucleicacid_min_size* and
+ *saccharide_min_size* if set to a value different than None.
:type min_polymer_size: int
:param transformation: If set, return the transformation matrix used to
move the bounding box of the bio unit to the lower left corner.
:type transformation: :class:`bool`
+ :param peptide_min_size: Minimal size to get an individual chain for a
+ polypeptide. Is overridden by *min_polymer_size*.
+ :type peptide_min_size: :class:`int`
+ :param nucleicacid_min_size: Minimal size to get an individual chain for a
+ polynucleotide. Is overridden by *min_polymer_size*.
+ :type nucleicacid_min_size: :class:`int`
+ :param saccharide_min_size: Minimal size to get an individual chain for an
+ oligosaccharide or polysaccharide. Is overridden by *min_polymer_size*.
+ :type saccharide_min_size: :class:`int`
.. class:: MMCifInfoStructDetails
diff --git a/modules/io/pymod/__init__.py b/modules/io/pymod/__init__.py
index cf8063d011627d477fd7401d004d7b6664a621f7..a0a29a6a43a98691faf1f1b54650f1fff5a0600a 100644
--- a/modules/io/pymod/__init__.py
+++ b/modules/io/pymod/__init__.py
@@ -358,9 +358,15 @@ def LoadMMCIF(filename, fault_tolerant=None, calpha_only=None, profile='DEFAULT'
# arguement is the usual 'self'.
# documentation for this function was moved to mmcif.rst,
# MMCifInfoBioUnit.PDBize, since this function is not included in SPHINX.
-def _PDBize(biounit, asu, seqres=None, min_polymer_size=10,
- transformation=False):
- pdbizer = mol.alg.PDBize(min_polymer_size=min_polymer_size)
+def _PDBize(biounit, asu, seqres=None, min_polymer_size=None,
+ transformation=False, peptide_min_size=10, nucleicacid_min_size=10,
+ saccharide_min_size=10):
+ if min_polymer_size is not None:
+ pdbizer = mol.alg.PDBize(min_polymer_size=min_polymer_size)
+ else:
+ pdbizer = mol.alg.PDBize(peptide_min_size=peptide_min_size,
+ nucleicacid_min_size=nucleicacid_min_size,
+ saccharide_min_size=saccharide_min_size)
chains = biounit.GetChainList()
c_intvls = biounit.GetChainIntervalList()
diff --git a/modules/io/src/mol/chemdict_parser.cc b/modules/io/src/mol/chemdict_parser.cc
index 9ff88e2f0a86ab236fc8074b59f392e8e92c931b..d392692c7fbc0cca9114d8051519d0ce51ace003 100644
--- a/modules/io/src/mol/chemdict_parser.cc
+++ b/modules/io/src/mol/chemdict_parser.cc
@@ -184,14 +184,19 @@ void ChemdictParser::InitTypeMap()
tm_["L-PEPTIDE NH3 AMINO TERMINUS"]=mol::ChemClass(mol::ChemClass::L_PEPTIDE_LINKING);
tm_["L-GAMMA-PEPTIDE, C-DELTA LINKING"]=mol::ChemClass(mol::ChemClass::L_PEPTIDE_LINKING);
tm_["L-BETA-PEPTIDE, C-GAMMA LINKING"]=mol::ChemClass(mol::ChemClass::L_PEPTIDE_LINKING);
+ tm_["D-PEPTIDE COOH CARBOXY TERMINUS"]=mol::ChemClass(mol::ChemClass::D_PEPTIDE_LINKING);
tm_["D-PEPTIDE NH3 AMINO TERMINUS"]=mol::ChemClass(mol::ChemClass::D_PEPTIDE_LINKING);
tm_["D-BETA-PEPTIDE, C-GAMMA LINKING"]=mol::ChemClass(mol::ChemClass::D_PEPTIDE_LINKING);
tm_["D-GAMMA-PEPTIDE, C-DELTA LINKING"]=mol::ChemClass(mol::ChemClass::D_PEPTIDE_LINKING);
tm_["L-SACCHARIDE, ALPHA LINKING"]=mol::ChemClass(mol::ChemClass::L_SACCHARIDE);
+ tm_["L-SACCHARIDE, BETA LINKING"]=mol::ChemClass(mol::ChemClass::L_SACCHARIDE);
tm_["L-SACCHARIDE 1,4 AND 1,4 LINKING"]=mol::ChemClass(mol::ChemClass::L_SACCHARIDE);
+ tm_["L-SACCHARIDE 1,4 AND 1,6 LINKING"]=mol::ChemClass(mol::ChemClass::L_SACCHARIDE);
tm_["D-SACCHARIDE 1,4 AND 1,4 LINKING"]=mol::ChemClass(mol::ChemClass::D_SACCHARIDE);
tm_["L-SACCHARIDE"]=mol::ChemClass(mol::ChemClass::L_SACCHARIDE);
tm_["D-SACCHARIDE"]=mol::ChemClass(mol::ChemClass::D_SACCHARIDE);
+ tm_["D-SACCHARIDE, BETA LINKING"]=mol::ChemClass(mol::ChemClass::D_SACCHARIDE);
+ tm_["D-SACCHARIDE, ALPHA LINKING"]=mol::ChemClass(mol::ChemClass::D_SACCHARIDE);
tm_["SACCHARIDE"]=mol::ChemClass(mol::ChemClass::SACCHARIDE);
tm_["D-PEPTIDE LINKING"]=mol::ChemClass(mol::ChemClass::D_PEPTIDE_LINKING);
tm_["L-PEPTIDE LINKING"]=mol::ChemClass(mol::ChemClass::L_PEPTIDE_LINKING);
@@ -212,6 +217,7 @@ void ChemdictParser::InitTypeMap()
tm_["RNA OH 5 PRIME TERMINUS"]=mol::ChemClass(mol::ChemClass::RNA_LINKING);
tm_["?"]=mol::ChemClass(mol::ChemClass::UNKNOWN);
tm_["WATER"]=mol::ChemClass(mol::ChemClass::WATER);
+ tm_["OTHER"]=mol::ChemClass(mol::ChemClass::UNKNOWN);
}
void ChemdictParser::InitPDBXTypeMap()
diff --git a/modules/mol/alg/pymod/wrap_mol_alg.cc b/modules/mol/alg/pymod/wrap_mol_alg.cc
index fd5b6d94de273dc57317e270d58596534fb5131f..d36877c0fb9024c9a200ca0e327fd9b68f900cbd 100644
--- a/modules/mol/alg/pymod/wrap_mol_alg.cc
+++ b/modules/mol/alg/pymod/wrap_mol_alg.cc
@@ -439,7 +439,10 @@ BOOST_PYTHON_MODULE(_ost_mol_alg)
class_<mol::alg::PDBize>("PDBize",
- init<int>(arg("min_polymer_size")=10))
+ init<int,int,int>((arg("peptide_min_size"),
+ arg("nucleicacid_min_size"),
+ arg("saccharide_min_size"))))
+ .def(init<int>(arg("min_polymer_size")=10))
.def("Add", &mol::alg::PDBize::Add,
(arg("asu"), arg("transformations"), arg("seqres")))
.def("Finish", &mol::alg::PDBize::Finish, arg("shift_to_fit")=true)
diff --git a/modules/mol/alg/src/pdbize.cc b/modules/mol/alg/src/pdbize.cc
index 84853c6f0d20502c94d5bfb38f110ff3abf7b46d..c53749ff4bb06dd589940a1a057536a36b6a7558 100644
--- a/modules/mol/alg/src/pdbize.cc
+++ b/modules/mol/alg/src/pdbize.cc
@@ -76,12 +76,19 @@ void PDBize::Add(EntityView asu, const geom::Mat4List& transforms,
e2 =asu.GetChainList().end(); j != e2; ++j) {
ChainView chain = *j;
int chain_length = chain.GetResidueCount();
- if (chain_length < min_polymer_size_ && seqres.IsValid()) {
+ if (((chain.IsPolypeptide() && chain_length < peptide_min_size_) ||
+ (chain.IsPolynucleotide() && chain_length < nucleicacid_min_size_) ||
+ ((chain.IsOligosaccharide() || chain.IsPolysaccharide()) &&
+ chain_length < saccharide_min_size_)) &&
+ seqres.IsValid()) {
seq::SequenceHandle s = seqres.FindSequence(chain.GetName());
if (s.IsValid())
chain_length = s.GetLength();
}
- if (chain.IsPolymer() && chain_length >= min_polymer_size_) {
+ if ((chain.IsPolypeptide() && chain_length >= peptide_min_size_) ||
+ (chain.IsPolynucleotide() && chain_length >= nucleicacid_min_size_) ||
+ ((chain.IsOligosaccharide() || chain.IsPolysaccharide()) &&
+ chain_length >= saccharide_min_size_)) {
if (*curr_chain_name_ == 0) {
throw std::runtime_error("running out of chain names");
}
diff --git a/modules/mol/alg/src/pdbize.hh b/modules/mol/alg/src/pdbize.hh
index 1ddf66fc5d047d882563b5e0fe7e61dc989f8c86..79ce6744d9baaed6b2ec4dd9d9ad5ee6215929bb 100644
--- a/modules/mol/alg/src/pdbize.hh
+++ b/modules/mol/alg/src/pdbize.hh
@@ -35,7 +35,19 @@ extern const char* WATER_CHAIN_NAME;
class DLLEXPORT_OST_MOL_ALG PDBize {
public:
explicit PDBize(int min_polymer_size=10):
- min_polymer_size_(min_polymer_size), ent_(mol::CreateEntity()),
+ peptide_min_size_(min_polymer_size),
+ nucleicacid_min_size_(min_polymer_size),
+ saccharide_min_size_(min_polymer_size), ent_(mol::CreateEntity()),
+ curr_chain_name_(POLYPEPTIDE_CHAIN_NAMES), needs_adjustment_(false),
+ last_rnum_(0)
+ {}
+
+ explicit PDBize(int peptide_min_size,
+ int nucleicacid_min_size,
+ int saccharide_min_size):
+ peptide_min_size_(peptide_min_size),
+ nucleicacid_min_size_(nucleicacid_min_size),
+ saccharide_min_size_(saccharide_min_size), ent_(mol::CreateEntity()),
curr_chain_name_(POLYPEPTIDE_CHAIN_NAMES), needs_adjustment_(false),
last_rnum_(0)
{}
@@ -45,7 +57,9 @@ public:
EntityHandle Finish(bool shift_to_fit=true);
private:
- int min_polymer_size_;
+ int peptide_min_size_;
+ int nucleicacid_min_size_;
+ int saccharide_min_size_;
EntityHandle ent_;
ChainHandle ligand_chain_;
ChainHandle water_chain_;
diff --git a/modules/mol/alg/tests/test_pdbize.py b/modules/mol/alg/tests/test_pdbize.py
index 5a180b95267938eab7b1b2240ef3a5848fb02fbe..c9f67643a04877d3132de8d5f7a054830a389951 100644
--- a/modules/mol/alg/tests/test_pdbize.py
+++ b/modules/mol/alg/tests/test_pdbize.py
@@ -4,7 +4,6 @@ import os
import random
class TestPDBize(unittest.TestCase):
-
def test_numbers_water_molecules_with_ins_codes(self):
m = mol.CreateEntity()
e = m.EditXCS(mol.BUFFERED_EDIT)
@@ -94,6 +93,187 @@ class TestPDBize(unittest.TestCase):
self.assertEqual(residues[26].number.num, 2)
self.assertEqual(residues[26].number.ins_code, '\0')
+ def _CheckMinSize(self, ost_ent, seq_list, chn_nm_lst, **kwargs):
+ """Check effects of the *_min_size parameter.
+
+ :param ost_ent: OST entity to be PDBized.
+ :type ost_ent: :class:`~ost.mol.EntityHandle`
+ :param seq_list: Sequence list for the chains in ost_ent.
+ :type seq_list: :class:`~ost.seq.SequenceList`
+ :param chn_nm_lst: List of expected chain names in PDBized entity.
+ :type chn_nm_lst: :class:`list` of :class:`str`
+ """
+ if "saccharide_min_size" not in kwargs:
+ kwargs["saccharide_min_size"] = 10
+ if "nucleicacid_min_size" not in kwargs:
+ kwargs["nucleicacid_min_size"] = 10
+ if "peptide_min_size" not in kwargs:
+ kwargs["peptide_min_size"] = 10
+ transformations = geom.Mat4List()
+ transformations.append(geom.Mat4())
+ pdbizer = mol.alg.PDBize(**kwargs)
+ pdbizer.Add(ost_ent.Select(''), transformations, seq_list)
+ pdbized = pdbizer.Finish()
+ self.assertEqual(len(pdbized.chains), len(chn_nm_lst))
+ for i in range(0, len(chn_nm_lst)):
+ self.assertEqual(pdbized.chains[i].name, chn_nm_lst[i])
+ return pdbized
+
+ def test_peptide_min_size(self):
+ """Make sure the peptide_min_size parameter works, place a polypeptide in
+ chain '_'.
+ """
+ m = mol.CreateEntity()
+ e = m.EditXCS(mol.BUFFERED_EDIT)
+ c = e.InsertChain("A");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_PEPTIDE_L)
+ for i in range(10):
+ e.AppendResidue(c, "ALA")
+ seqs = seq.CreateSequenceList()
+ seqs.AddSequence(seq.CreateSequence("LotsOfAlanin", "AAAAAAAAAA"))
+
+ # test that small peptide chains end up in the ligand chain "_"
+ self._CheckMinSize(m, seqs, ["_"], peptide_min_size=11)
+
+ # test again with two small peptide chains
+ c = e.InsertChain("B");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_PEPTIDE_L)
+ for i in range(15):
+ e.AppendResidue(c, "ALA")
+ seqs.AddSequence(seq.CreateSequence("MoreAlanin", "AAAAAAAAAAAAAAA"))
+ self._CheckMinSize(m, seqs, ["_"], peptide_min_size=16)
+
+ # test one peptide in ligand chain, second as polymer chain
+ self._CheckMinSize(m, seqs, ["_", "A"], peptide_min_size=11)
+
+ # actually disabling min. polymer size
+ self._CheckMinSize(m, seqs, ["A", "B"], peptide_min_size=0)
+
+ def test_nucleicacid_min_size(self):
+ """Make sure the nucleicacid_min_size parameter works, place a
+ polynucleotide in chain '_'.
+ """
+ m = mol.CreateEntity()
+ e = m.EditXCS(mol.BUFFERED_EDIT)
+ c = e.InsertChain("A");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_DN)
+ for i in range(10):
+ e.AppendResidue(c, "DA")
+ seqs = seq.CreateSequenceList()
+ seqs.AddSequence(seq.CreateSequence("LotsOfAdenine", "AAAAAAAAAA"))
+
+ # test that small nucleotide chains end up in the ligand chain "_"
+ self._CheckMinSize(m, seqs, ["_"], nucleicacid_min_size=11)
+
+ # test again with two small nucleic acid chains
+ c = e.InsertChain("B");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_DN)
+ for i in range(15):
+ e.AppendResidue(c, "DA")
+ seqs.AddSequence(seq.CreateSequence("MoreAdenine", "AAAAAAAAAAAAAAA"))
+ self._CheckMinSize(m, seqs, ["_"], nucleicacid_min_size=16)
+
+ # test one nucleic acid in ligand chain, second as polymer chain
+ self._CheckMinSize(m, seqs, ["_", "A"], nucleicacid_min_size=11)
+
+ # actually disabling min. polymer size
+ self._CheckMinSize(m, seqs, ["A", "B"], nucleicacid_min_size=0)
+
+ def test_saccharide_min_size(self):
+ """Make sure the saccharide_min_size parameter works, place an
+ oligosaccharide in chain '_'.
+ """
+ m = mol.CreateEntity()
+ e = m.EditXCS(mol.BUFFERED_EDIT)
+ c = e.InsertChain("A");
+ e.SetChainType(c, mol.CHAINTYPE_OLIGOSACCHARIDE)
+ for i in range(10):
+ e.AppendResidue(c, "NAG")
+ seqs = seq.CreateSequenceList()
+
+ # test that small oligosaccharides end up in the ligand chain "_"
+ self._CheckMinSize(m, seqs, ["_"], saccharide_min_size=11)
+
+ # test again with two small oligosaccharide chains
+ c = e.InsertChain("B");
+ e.SetChainType(c, mol.CHAINTYPE_OLIGOSACCHARIDE)
+ for i in range(15):
+ e.AppendResidue(c, "NAG")
+ self._CheckMinSize(m, seqs, ["_"], saccharide_min_size=16)
+
+ # test one oligosaccharide in ligand chain, second as polymer chain
+ self._CheckMinSize(m, seqs, ["_", "A"], saccharide_min_size=11)
+
+ # actually disabling min. polymer size
+
+ def test_peptide_nucleicacid_saccharide_min_sizes(self):
+ """Make sure that all thre thresholds play well together.
+ """
+ m = mol.CreateEntity()
+ e = m.EditXCS(mol.BUFFERED_EDIT)
+ c = e.InsertChain("A");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_PEPTIDE_L)
+ for i in range(10):
+ e.AppendResidue(c, "ALA")
+ seqs = seq.CreateSequenceList()
+ seqs.AddSequence(seq.CreateSequence("LotsOfAlanin", "AAAAAAAAAA"))
+ c = e.InsertChain("B");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_DN)
+ for i in range(10):
+ e.AppendResidue(c, "DA")
+ seqs.AddSequence(seq.CreateSequence("LotsOfAdenine", "AAAAAAAAAA"))
+ c = e.InsertChain("C");
+ e.SetChainType(c, mol.CHAINTYPE_OLIGOSACCHARIDE)
+ for i in range(10):
+ e.AppendResidue(c, "NAG")
+
+ # Check branched entities can be abandoned in the ligand chain while
+ # peptides and nucleic acids live in their own chains.
+ pdbized = self._CheckMinSize(m, seqs, ["A", "B", "_"],
+ saccharide_min_size=11,
+ peptide_min_size=0,
+ nucleicacid_min_size=0)
+ self.assertTrue(pdbized.chains[0].IsPolypeptide())
+ self.assertTrue(pdbized.chains[1].IsPolynucleotide())
+ self.assertEqual(pdbized.chains[2].residues[0].GetStringProp("type"),
+ "oligosaccharide")
+
+ # test to store a short polynucleotide and sugar in the ligand chain but keep
+ # longer polynucleotide and the peptide outside of the ligand chain.
+ c = e.InsertChain("D");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_DN)
+ for i in range(5):
+ e.AppendResidue(c, "DG")
+ seqs.AddSequence(seq.CreateSequence("LotsOfGuanine", "GGGGG"))
+ pdbized = self._CheckMinSize(m, seqs, ["A", "B", "_"],
+ saccharide_min_size=11,
+ peptide_min_size=0,
+ nucleicacid_min_size=6)
+ self.assertTrue(pdbized.chains[0].IsPolypeptide())
+ self.assertTrue(pdbized.chains[1].IsPolynucleotide())
+ self.assertEqual(pdbized.chains[2].residues[0].GetStringProp("type"),
+ "oligosaccharide")
+ self.assertEqual(pdbized.chains[2].residues[-1].GetStringProp("type"),
+ "polydeoxyribonucleotide")
+
+ # test to add a small peptide to the ligand chain
+ c = e.InsertChain("E");
+ e.SetChainType(c, mol.CHAINTYPE_POLY_PEPTIDE_L)
+ for i in range(5):
+ e.AppendResidue(c, "ALA")
+ seqs.AddSequence(seq.CreateSequence("SomeAlanin", "AAAAA"))
+ pdbized = self._CheckMinSize(m, seqs, ["A", "B", "_", "C"],
+ saccharide_min_size=11,
+ peptide_min_size=6,
+ nucleicacid_min_size=3)
+ self.assertTrue(pdbized.chains[0].IsPolypeptide())
+ self.assertTrue(pdbized.chains[1].IsPolynucleotide())
+ self.assertEqual(pdbized.chains[2].residues[0].GetStringProp("type"),
+ "oligosaccharide")
+ self.assertEqual(pdbized.chains[2].residues[-1].GetStringProp("type"),
+ "polypeptide(L)")
+
+
if __name__ == "__main__":
from ost import testutils
testutils.RunTests()
diff --git a/modules/mol/base/doc/entity.rst b/modules/mol/base/doc/entity.rst
index 3a4d0d292748f1c8f7546468d8f8b4657c9d10c2..aeb18459f28e01c33c3c09a48dd8d9b9ee342822 100644
--- a/modules/mol/base/doc/entity.rst
+++ b/modules/mol/base/doc/entity.rst
@@ -342,7 +342,94 @@ The Handle Classes
A chain of one or more :class:`residues <ResidueHandle>`. Chains are always
part of an entity.
-
+
+ .. attribute:: atoms
+
+ Get list of all atoms of this chain. To access a single atom, use
+ :meth:`FindAtom`.
+
+ This property is read-only. Also available as :meth:`GetAtomList`
+
+ :type: :class:`AtomHandleList` (list of :class:`AtomHandle`)
+
+ .. attribute:: bounds
+
+ Axis-aligned bounding box of the chain. Read-only
+
+ :type: :class:`ost.geom.AlignedCuboid`
+
+ .. attribute:: center_of_atoms
+
+ Center of atoms (not mass weighted). Also available as
+ :meth:`GetCenterOfAtoms`.
+
+ :type: :class:`~ost.geom.Vec3`
+
+ .. attribute:: center_of_mass
+
+ Center of mass. Also available as :meth:`GetCenterOfMass`
+
+ :type: :class:`~ost.geom.Vec3`
+
+ .. attribute:: description
+
+ Details about the chain. Not categorised, just text.
+
+ .. attribute:: in_sequence
+
+ Whether the residue numbers are in ascending order. For example:
+
+ .. code-block:: python
+
+ chain=ent.FindChain("A")
+ print(chain.residues) # [A.GLY1, A.GLY2, A.GLY4A, A.GLY4B]
+ print(chain.in_sequence) # prints true
+
+ chain=ent.FindChain("B")
+ print(chain.residues) # [B.GLY1, B.GLY4, B.GLY3]
+ print(chain.in_sequence) # prints false
+
+ .. attribute:: is_oligosaccharide
+
+ Indicates if the chain is an oligosaccharide, a branched, non-linear entity
+ of multiple sugars. Also available as :meth:`IsOligosaccharide`.
+
+ :type: :class:`bool`
+
+ .. attribute:: is_polymer
+
+ Indicates if a chain is a polymer. True for polypeptides, polynucleotides,
+ polysaccharides, oligosaccharides and branched chains. Also available as
+ :meth:`IsPolymer`.
+
+ :type: :class:`bool`
+
+ .. attribute:: is_polynucleotide
+
+ Indicates if a chain is a nucleic acid. Also available as
+ :meth:`IsPolynucleotide`.
+
+ :type: :class:`bool`
+
+ .. attribute:: is_polypeptide
+
+ Indicates if a chain is a protein. Also available as :meth:`IsPolypeptide`.
+
+ :type: :class:`bool`
+
+ .. attribute:: is_polysaccharide
+
+ Indicates if a chain is a polysaccharide. Also available as
+ :meth:`IsPolysaccharide()`.
+
+ :type: :class:`bool`
+
+ .. attribute:: mass
+
+ The total mass of this chain in Dalton. Also available as :meth:`GetMass`
+
+ :type: float
+
.. attribute:: name
The chain name. The name uniquely identifies the chain in the entity. In
@@ -356,15 +443,11 @@ The Handle Classes
:type: str
- .. attribute:: type
-
- Describes the type of the chain.
-
- :type: :class:`ChainType`.
+ .. attribute:: residue_count
- .. attribute:: description
+ Number of residues. Read-only. See :meth:`GetResidueCount`.
- Details about the chain. Not categorised, just text.
+ :type: :class:`int`
.. attribute:: residues
@@ -387,59 +470,11 @@ The Handle Classes
:type: :class:`ResidueHandleList` (list of :class:`ResidueHandle`)
- .. attribute:: in_sequence
-
- Whether the residue numbers are in ascending order. For example:
-
- .. code-block:: python
-
- chain=ent.FindChain("A")
- print(chain.residues) # [A.GLY1, A.GLY2, A.GLY4A, A.GLY4B]
- print(chain.in_sequence) # prints true
-
- chain=ent.FindChain("B")
- print(chain.residues) # [B.GLY1, B.GLY4, B.GLY3]
- print(chain.in_sequence) # prints false
-
- .. attribute:: residue_count
-
- Number of residues. Read-only. See :meth:`GetResidueCount`.
-
- :type: :class:`int`
-
- .. attribute:: atoms
-
- Get list of all atoms of this chain. To access a single atom, use
- :meth:`FindAtom`.
-
- This property is read-only. Also available as :meth:`GetAtomList`
-
- :type: :class:`AtomHandleList` (list of :class:`AtomHandle`)
-
- .. attribute:: bounds
-
- Axis-aligned bounding box of the chain. Read-only
-
- :type: :class:`ost.geom.AlignedCuboid`
-
- .. attribute:: mass
-
- The total mass of this chain in Dalton. Also available as :meth:`GetMass`
-
- :type: float
+ .. attribute:: type
- .. attribute:: center_of_mass
+ Describes the type of the chain.
- Center of mass. Also available as :meth:`GetCenterOfMass`
-
- :type: :class:`~ost.geom.Vec3`
-
- .. attribute:: center_of_atoms
-
- Center of atoms (not mass weighted). Also available as
- :meth:`GetCenterOfAtoms`.
-
- :type: :class:`~ost.geom.Vec3`
+ :type: :class:`ChainType`.
.. attribute:: valid
@@ -491,6 +526,26 @@ The Handle Classes
See :attr:`type`
+ .. method:: IsOligosaccharide()
+
+ See :attr:`is_oligosaccharide`
+
+ .. method:: IsPolymer()
+
+ See :attr:`is_polymer`
+
+ .. method:: IsPolynucleotide()
+
+ See :attr:`is_polynucleotide`
+
+ .. method:: IsPolypeptide()
+
+ See :attr:`is_polypeptide`
+
+ .. method:: IsPolysaccharide()
+
+ See :attr:`is_polysaccharide`
+
.. method:: GetDescription()
See :attr:`description`
diff --git a/modules/mol/base/pymod/export_chain.cc b/modules/mol/base/pymod/export_chain.cc
index 1664c13a33ed03c1fbdc404bbac9b081522c8e4a..b5ce6d91cba30b6a3dab3a83a066f044139e1d41 100644
--- a/modules/mol/base/pymod/export_chain.cc
+++ b/modules/mol/base/pymod/export_chain.cc
@@ -58,10 +58,12 @@ void export_Chain()
.def("IsPolypeptide", &ChainBase::IsPolypeptide)
.def("IsPolynucleotide", &ChainBase::IsPolynucleotide)
.def("IsPolysaccharide", &ChainBase::IsPolysaccharide)
+ .def("IsOligosaccharide", &ChainBase::IsOligosaccharide)
.def("IsPolymer", &ChainBase::IsPolymer)
.add_property("is_polypeptide", &ChainBase::IsPolypeptide)
.add_property("is_polynucleotide", &ChainBase::IsPolynucleotide)
.add_property("is_polysaccharide", &ChainBase::IsPolysaccharide)
+ .add_property("is_oligosaccharide", &ChainBase::IsOligosaccharide)
.add_property("is_polymer", &ChainBase::IsPolymer)
.add_property("type", &ChainBase::GetType)
.add_property("description", &ChainBase::GetDescription)
diff --git a/modules/mol/base/src/chain_base.cc b/modules/mol/base/src/chain_base.cc
index 4114a1462be137b7ea2e84cac6618df2309849e3..2b693b7fc031d07bf3da2492a1644db649557b30 100644
--- a/modules/mol/base/src/chain_base.cc
+++ b/modules/mol/base/src/chain_base.cc
@@ -81,6 +81,13 @@ bool ChainBase::IsPolysaccharide() const
}
+bool ChainBase::IsOligosaccharide() const
+{
+ this->CheckValidity();
+ return impl_->IsOligosaccharide();
+
+}
+
bool ChainBase::IsPolypeptide() const
{
this->CheckValidity();
diff --git a/modules/mol/base/src/chain_base.hh b/modules/mol/base/src/chain_base.hh
index 5463ef0a8627eac578b12e801618da69bc74c898..0ab82a3dbaf784193d3ba09fe1e687af4f96eaeb 100644
--- a/modules/mol/base/src/chain_base.hh
+++ b/modules/mol/base/src/chain_base.hh
@@ -82,7 +82,10 @@ public:
/// \brief whether the chain is a polysaccharide
bool IsPolysaccharide() const;
-
+
+ /// \brief whether the chain is an oligsaccharide (branched mmCIF entity)
+ bool IsOligosaccharide() const;
+
/// \brief whether the chain is a polypeptide
bool IsPolypeptide() const;
diff --git a/modules/mol/base/src/impl/chain_impl.hh b/modules/mol/base/src/impl/chain_impl.hh
index a3a7a97dcec720f024c39a2bcf73ff0bc108e9b6..e5bc7aac338d1d3c82c81730b9b5709eba7cf569 100644
--- a/modules/mol/base/src/impl/chain_impl.hh
+++ b/modules/mol/base/src/impl/chain_impl.hh
@@ -69,14 +69,20 @@ public:
{
return type_==CHAINTYPE_POLY || this->IsPolypeptide() ||
this->IsPolynucleotide() || this->IsPolysaccharide() ||
- type_==CHAINTYPE_POLY_PEPTIDE_DN_RN ||
- type_==CHAINTYPE_OLIGOSACCHARIDE;
+ this->IsOligosaccharide() ||
+ type_==CHAINTYPE_POLY_PEPTIDE_DN_RN || type_==CHAINTYPE_BRANCHED;
}
/// \brief whether the chain is a polysaccharide
bool IsPolysaccharide() const
{
return type_==CHAINTYPE_POLY_SAC_D || type_==CHAINTYPE_POLY_SAC_L;
}
+
+ /// \brief whether the chain is a polysaccharide
+ bool IsOligosaccharide() const
+ {
+ return type_==CHAINTYPE_OLIGOSACCHARIDE;
+ }
/// \brief whether the chain is a polypeptide
bool IsPolypeptide() const
{
diff --git a/modules/mol/base/src/transfer_connectivity.cc b/modules/mol/base/src/transfer_connectivity.cc
index b7536f4871d261f5aa5560217d60a1af1bb0e07a..448fde12e4af18822210a6d371d7979a2a289540 100644
--- a/modules/mol/base/src/transfer_connectivity.cc
+++ b/modules/mol/base/src/transfer_connectivity.cc
@@ -73,6 +73,32 @@ public:
return false;
}
+ bool CheckInsertionCode(ResidueHandle chk_res, ResidueHandle src_res,
+ ResidueHandle dst_res) {
+ // This is a hack to make GetDestAtomForSrcAtom work with mol::alg::PDBize,
+ // maybe with insertion codes in general...
+ // Depending on the value of min_polymer_size, PDBize puts small polymers in
+ // the ligand chain called '_'. The original chain is annotated by all
+ // residues having the same residue number but different insertion codes.
+ // That can lead to the same issue described further down for branched
+ // entities. Basically the problem is that in branched entities the residues
+ // do not need to be connected with their immediate neighbours breaking the
+ // original mechanics of GetDestAtomForSrcAtom.
+ // check if residue has an insertion code
+ if (chk_res.GetNumber().GetInsCode() != '\0') {
+ // check if the original residue also had no inscode
+ if (src_res.GetNumber().GetInsCode() == '\0') {
+ // There must be another residue with the same number and since
+ // this function is only used by PDBize, that residue originates
+ // from the same chain as dst_res and may be the correct partner.
+ if (chk_res.GetNumber().GetNum() != dst_res.GetNumber().GetNum()) {
+ return false;
+ }
+ }
+ }
+ return true;
+ }
+
AtomHandle GetDestAtomForSrcAtom(AtomHandle src_atom, ResidueHandle src_res,
ResidueHandle dst_res,
const std::map<String, AtomHandle>& name_to_atom) {
@@ -87,19 +113,61 @@ public:
j = to_from_->find(dst_res.GetPrev());
if (j != to_from_->end()) {
if (j->second == r) {
- return j->first.FindAtom(src_atom.GetName());
+ if (CheckInsertionCode(
+ j->first.FindAtom(src_atom.GetName()).GetResidue(),
+ r, dst_res)) {
+ return j->first.FindAtom(src_atom.GetName());
+ }
}
}
j = to_from_->find(dst_res.GetNext());
if (j != to_from_->end()) {
if (j->second == r) {
- return j->first.FindAtom(src_atom.GetName());
+ if (CheckInsertionCode(
+ j->first.FindAtom(src_atom.GetName()).GetResidue(),
+ r, dst_res)) {
+ return j->first.FindAtom(src_atom.GetName());
+ }
}
}
// still nothing. scan linearly through all residues.
for ( j = to_from_->begin(); j != to_from_->end(); ++j) {
if (j->second == r) {
- return j->first.FindAtom(src_atom.GetName());
+ // Check that we are connecting to the same chain, otherwise we need to
+ // check that the found residue also connects outwards.
+ if (j->first.GetChain() == dst_res.GetChain()) {
+ if (CheckInsertionCode(
+ j->first.FindAtom(src_atom.GetName()).GetResidue(),
+ r, dst_res)) {
+ return j->first.FindAtom(src_atom.GetName());
+ }
+ }
+ // Using the found residue would mean connecting to a different chain
+ // which is unusual. So we make sure that in the residue we transfer
+ // from, there is also a bond to a different chain. Otherwise the
+ // search continues.
+ // For branched mmCIF entities where connected residues may be not
+ // direct neighbours since branched entities are non-linear, that gave
+ // a problem when a bio unit doubled an oligosaccharide and the search
+ // found the bond of the copied oligosaccharide first. In that case the
+ // copied oligosaccharide is a different chain and the residue from the
+ // same chain comes later in the list.
+ BondHandleList jbonds = src_atom.GetBondList();
+ for (BondHandleList::iterator k = jbonds.begin(), e2 = jbonds.end();
+ k !=e2; ++k) {
+ // determine which "side" the src_res sits on
+ if (k->GetFirst() == src_atom) {
+ if (src_atom.GetResidue().GetChain()
+ != k->GetSecond().GetResidue().GetChain()) {
+ return j->first.FindAtom(src_atom.GetName());
+ }
+ continue;
+ }
+ if (src_atom.GetResidue().GetChain()
+ != k->GetFirst().GetResidue().GetChain()) {
+ return j->first.FindAtom(src_atom.GetName());
+ }
+ }
}
}
return AtomHandle();
@@ -117,3 +185,5 @@ void TransferConnectivity(EntityHandle dest,
}
}}
+
+// LocalWords: PDBize ligand
diff --git a/modules/mol/base/tests/test_chain.cc b/modules/mol/base/tests/test_chain.cc
index 2154bdeab94555e73c89892847e6f9cac1759af4..f965fced69eb87d610baec27f4830e8d82202369 100644
--- a/modules/mol/base/tests/test_chain.cc
+++ b/modules/mol/base/tests/test_chain.cc
@@ -235,59 +235,69 @@ BOOST_AUTO_TEST_CASE(chain_type)
BOOST_CHECK(ch1.GetType() == CHAINTYPE_UNKNOWN);
BOOST_CHECK(!ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_POLY);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_NON_POLY);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_NON_POLY);
BOOST_CHECK(!ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_WATER);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_WATER);
BOOST_CHECK(!ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_POLY_PEPTIDE_D);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_PEPTIDE_D);
e.SetChainType(ch1, CHAINTYPE_POLY_PEPTIDE_L);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_PEPTIDE_L);
e.SetChainType(ch1, CHAINTYPE_POLY_DN);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(ch1.IsPolynucleotide());
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_DN);
e.SetChainType(ch1, CHAINTYPE_POLY_RN);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(ch1.IsPolynucleotide());
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_RN);
e.SetChainType(ch1, CHAINTYPE_POLY_SAC_D);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_SAC_D);
e.SetChainType(ch1, CHAINTYPE_POLY_SAC_L);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_SAC_L);
@@ -295,6 +305,7 @@ BOOST_AUTO_TEST_CASE(chain_type)
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_DN_RN);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_N_CHAINTYPES);
@@ -305,30 +316,35 @@ BOOST_AUTO_TEST_CASE(chain_type)
BOOST_CHECK(ch1.GetType() == CHAINTYPE_MACROLIDE);
BOOST_CHECK(!ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_CYCLIC_PSEUDO_PEPTIDE);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_CYCLIC_PSEUDO_PEPTIDE);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_POLY_PEPTIDE_DN_RN);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_POLY_PEPTIDE_DN_RN);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_BRANCHED);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_BRANCHED);
- BOOST_CHECK(!ch1.IsPolymer());
+ BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(!ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
e.SetChainType(ch1, CHAINTYPE_OLIGOSACCHARIDE);
BOOST_CHECK(ch1.GetType() == CHAINTYPE_OLIGOSACCHARIDE);
BOOST_CHECK(ch1.IsPolymer());
BOOST_CHECK(!ch1.IsPolysaccharide());
+ BOOST_CHECK(ch1.IsOligosaccharide());
BOOST_CHECK(!ch1.IsPolypeptide());
BOOST_CHECK(!ch1.IsPolynucleotide());
diff --git a/modules/mol/base/tests/test_transfer_connectivity.cc b/modules/mol/base/tests/test_transfer_connectivity.cc
index 36ad6dc2cd5c1a0060b594ef28fa4119dfdb904a..e97be09fd66aff1a680316e978aa37a110024809 100644
--- a/modules/mol/base/tests/test_transfer_connectivity.cc
+++ b/modules/mol/base/tests/test_transfer_connectivity.cc
@@ -72,6 +72,150 @@ BOOST_AUTO_TEST_CASE(test_transfer_conn)
BOOST_CHECK_EQUAL(12, ent2.GetBondCount());
}
+BOOST_AUTO_TEST_CASE(test_transfer_two_from_one_chain)
+{
+ // Test that if, like by PDBize, a single chain is used to connect two chains,
+ // all the bonds stay in the right chain.
+ EntityHandle src = CreateEntity();
+ XCSEditor edi = src.EditXCS();
+ ChainHandle fst_chain = edi.InsertChain(String("A"));
+ ResidueHandle bma1 = edi.AppendResidue(fst_chain, "BMA");
+ ResidueHandle man1 = edi.AppendResidue(fst_chain, "MAN");
+ ResidueHandle man2 = edi.AppendResidue(fst_chain, "MAN");
+
+ AtomHandle bma_o3;
+ AtomHandle bma_o6;
+ AtomHandle man_c1;
+
+ bma_o3 = edi.InsertAtom(bma1, "O3", geom::Vec3(9.646, -29.415, 33.307));
+ bma_o6 = edi.InsertAtom(bma1, "O6", geom::Vec3(8.642, -28.695, 27.405));
+
+ man_c1 = edi.InsertAtom(man1, "C1", geom::Vec3(10.253, -30.563, 33.946));
+ edi.Connect(bma_o3, man_c1);
+
+ man_c1 = edi.InsertAtom(man2, "C1", geom::Vec3(8.091, -29.369, 26.233));
+ edi.Connect(bma_o6, man_c1);
+
+ EntityHandle dst = CreateEntity();
+ edi = dst.EditXCS();
+ fst_chain = edi.InsertChain(String("B"));
+ bma1 = edi.AppendResidue(fst_chain, "BMA");
+ man1 = edi.AppendResidue(fst_chain, "MAN");
+ man2 = edi.AppendResidue(fst_chain, "MAN");
+
+ edi.InsertAtom(bma1, "O3", geom::Vec3(9.646, -29.415, 33.307));
+ edi.InsertAtom(bma1, "O6", geom::Vec3(8.642, -28.695, 27.405));
+
+ edi.InsertAtom(man1, "C1", geom::Vec3(10.253, -30.563, 33.946));
+
+ edi.InsertAtom(man2, "C1", geom::Vec3(8.091, -29.369, 26.233));
+
+ ChainHandle snd_chain = edi.InsertChain(String("C"));
+ bma1 = edi.AppendResidue(snd_chain, "BMA");
+ man1 = edi.AppendResidue(snd_chain, "MAN");
+ man2 = edi.AppendResidue(snd_chain, "MAN");
+
+ edi.InsertAtom(bma1, "O3", geom::Vec3(-9.646, 29.415, 33.307));
+ edi.InsertAtom(bma1, "O6", geom::Vec3(-8.642, 28.695, 27.405));
+
+ edi.InsertAtom(man1, "C1", geom::Vec3(-10.253, 30.563, 33.946));
+
+ edi.InsertAtom(man2, "C1", geom::Vec3(-8.091, 29.369, 26.233));
+
+ std::map<ResidueHandle, ResidueHandle> to_from;
+ ResidueHandleList r1 = src.GetResidueList();
+ ResidueHandleList r2 = fst_chain.GetResidueList();
+ for (size_t i = 0; i < r1.size(); ++i) {
+ to_from[r2[i]] = r1[i];
+ }
+ r2 = snd_chain.GetResidueList();
+ for (size_t i = 0; i < r1.size(); ++i) {
+ to_from[r2[i]] = r1[i];
+ }
+
+ TransferConnectivity(dst, to_from);
+ BOOST_CHECK(BondExists(dst.FindAtom("B", 1, "O3"),
+ dst.FindAtom("B", 2, "C1")));
+ BOOST_CHECK(BondExists(dst.FindAtom("B", 1, "O6"),
+ dst.FindAtom("B", 3, "C1")));
+ BOOST_CHECK(BondExists(dst.FindAtom("C", 1, "O3"),
+ dst.FindAtom("C", 2, "C1")));
+ BOOST_CHECK(BondExists(dst.FindAtom("C", 1, "O6"),
+ dst.FindAtom("C", 3, "C1")));
+ BOOST_CHECK_EQUAL(BondExists(dst.FindAtom("C", 1, "O6"),
+ dst.FindAtom("B", 3, "C1")), false);
+ BOOST_CHECK_EQUAL(BondExists(dst.FindAtom("B", 1, "O6"),
+ dst.FindAtom("C", 3, "C1")), false);
+}
+
+BOOST_AUTO_TEST_CASE(test_transfer_two_combined_one_chain)
+{
+ // Test that if, like by PDBize, a single chain ends up two times in '_', the
+ // connectivity does not get messy.
+ EntityHandle src = CreateEntity();
+ XCSEditor edi = src.EditXCS();
+ ChainHandle fst_chain = edi.InsertChain(String("A"));
+ ResidueHandle bma1 = edi.AppendResidue(fst_chain, "BMA");
+ ResidueHandle man1 = edi.AppendResidue(fst_chain, "MAN");
+ ResidueHandle man2 = edi.AppendResidue(fst_chain, "MAN");
+
+ AtomHandle bma_o3;
+ AtomHandle bma_o6;
+ AtomHandle man_c1;
+
+ bma_o3 = edi.InsertAtom(bma1, "O3", geom::Vec3(9.646, -29.415, 33.307));
+ bma_o6 = edi.InsertAtom(bma1, "O6", geom::Vec3(8.642, -28.695, 27.405));
+
+ man_c1 = edi.InsertAtom(man1, "C1", geom::Vec3(10.253, -30.563, 33.946));
+ edi.Connect(bma_o3, man_c1);
+
+ man_c1 = edi.InsertAtom(man2, "C1", geom::Vec3(8.091, -29.369, 26.233));
+ edi.Connect(bma_o6, man_c1);
+
+ EntityHandle dst = CreateEntity();
+ edi = dst.EditXCS();
+ fst_chain = edi.InsertChain(String("_"));
+ bma1 = edi.AppendResidue(fst_chain, "BMA", ResNum(1, 'A'));
+ man1 = edi.AppendResidue(fst_chain, "MAN", ResNum(1, 'B'));
+ man2 = edi.AppendResidue(fst_chain, "MAN", ResNum(1, 'C'));
+
+ edi.InsertAtom(bma1, "O3", geom::Vec3(9.646, -29.415, 33.307));
+ edi.InsertAtom(bma1, "O6", geom::Vec3(8.642, -28.695, 27.405));
+ edi.InsertAtom(man1, "C1", geom::Vec3(10.253, -30.563, 33.946));
+ edi.InsertAtom(man2, "C1", geom::Vec3(8.091, -29.369, 26.233));
+
+ bma1 = edi.AppendResidue(fst_chain, "BMA", ResNum(2, 'A'));
+ man1 = edi.AppendResidue(fst_chain, "MAN", ResNum(2, 'B'));
+ man2 = edi.AppendResidue(fst_chain, "MAN", ResNum(2, 'C'));
+
+ edi.InsertAtom(bma1, "O3", geom::Vec3(-9.646, 29.415, 33.307));
+ edi.InsertAtom(bma1, "O6", geom::Vec3(-8.642, 28.695, 27.405));
+ edi.InsertAtom(man1, "C1", geom::Vec3(-10.253, 30.563, 33.946));
+ edi.InsertAtom(man2, "C1", geom::Vec3(-8.091, 29.369, 26.233));
+
+ std::map<ResidueHandle, ResidueHandle> to_from;
+ ResidueHandleList r1 = src.GetResidueList();
+ ResidueHandleList r2 = fst_chain.GetResidueList();
+ for (size_t i = 0; i < r1.size(); ++i) {
+ to_from[r2[i]] = r1[i];
+ }
+ for (size_t i = 0; i < r1.size(); ++i) {
+ to_from[r2[i+3]] = r1[i];
+ }
+
+ TransferConnectivity(dst, to_from);
+
+ BOOST_CHECK(BondExists(dst.FindAtom("_", ResNum(1, 'A'), "O3"),
+ dst.FindAtom("_", ResNum(1, 'B'), "C1")));
+ BOOST_CHECK(BondExists(dst.FindAtom("_", ResNum(1, 'A'), "O6"),
+ dst.FindAtom("_", ResNum(1, 'C'), "C1")));
+ BOOST_CHECK(BondExists(dst.FindAtom("_", ResNum(2, 'A'), "O3"),
+ dst.FindAtom("_", ResNum(2, 'B'), "C1")));
+ BOOST_CHECK(BondExists(dst.FindAtom("_", ResNum(2, 'A'), "O6"),
+ dst.FindAtom("_", ResNum(2, 'C'), "C1")));
+ BOOST_CHECK_EQUAL(BondExists(dst.FindAtom("B", ResNum(2, 'A'), "O6"),
+ dst.FindAtom("C", ResNum(1, 'C'), "C1")), false);
+}
BOOST_AUTO_TEST_SUITE_END();
diff --git a/modules/seq/alg/pymod/__init__.py b/modules/seq/alg/pymod/__init__.py
index 2e9c5fcffca4375afb80a13cea941658f62c508a..3be1b5845184ad08c6284694a9410427909888dd 100644
--- a/modules/seq/alg/pymod/__init__.py
+++ b/modules/seq/alg/pymod/__init__.py
@@ -100,16 +100,29 @@ def AlignToSEQRES(chain, seqres, try_resnum_first=False, validate=True):
return seq.CreateAlignment()
if try_resnum_first:
aln_seq = seq.CreateSequence('atoms', '-'*len(seqres))
+ aligned_resnums = set()
for r1 in residues:
+ if r1.number.num in aligned_resnums:
+ LogWarning('Residue numbers must be unique. Already observed %i, ' \
+ 'cannot align %s anymore.'%(r1.number.num, r1.qualified_name))
+ try_resnum_first = False
+ break
if r1.number.num <= len(seqres) and r1.number.num > 0:
if IsEqual(seqres[r1.number.num - 1], r1.one_letter_code):
aln_seq[r1.number.num - 1] = r1.one_letter_code
+ aligned_resnums.add(r1.number.num)
else:
LogWarning('Sequence mismatch: chain has "' + r1.one_letter_code +
'", while SEQRES is "' + seqres[r1.number.num - 1] +
'" at the corresponding position.')
try_resnum_first = False
break
+ else:
+ warning = 'Residue with number %i is outside of the range covered by '\
+ 'SEQRES [1, %i]'%(r1.number.num, len(seqres))
+ LogWarning(warning)
+ try_resnum_first = False
+ break
if not try_resnum_first:
fragments=[residues[0].one_letter_code]
for r1, r2 in zip(residues[:-1], residues[1:]):
diff --git a/singularity/Singularity b/singularity/Singularity
index 9e445f865b89d6e3e1501eb2847720ca868b8005..9aa5176634186bfea200cc4fb2efaa60b3700ad2 100644
--- a/singularity/Singularity
+++ b/singularity/Singularity
@@ -1,6 +1,5 @@
BootStrap: docker
-From: registry.scicore.unibas.ch/schwede/openstructure:2.0.0-bionic
-
+From: registry.scicore.unibas.ch/schwede/openstructure:2.1.0-bionic
%post
##############################################################################
# POST