Merge branch 'interactions' of github.com:karolamik13/ProDy into inte…

…ractions

.github/workflows/main.yml

@@ -13,7 +13,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ["2.7", "3.8", "3.9", "3.10"]
+        python-version: ["2.7", "3.8", "3.9", "3.10", "3.11"]
 
     steps:
     - uses: actions/checkout@v2
@@ -29,8 +29,8 @@ jobs:
         if [[ ${{ matrix.python-version }} != "2.7" ]]; then conda config --add channels conda-forge; fi
         conda create --yes -n test python=${{ matrix.python-version }}
         source activate test
-        conda install --yes numpy scipy nose pyparsing requests
-        if [[ ${{ matrix.python-version }} == "2.7" ]]; then conda install --yes unittest2; else conda install --yes pdbfixer; fi
+        conda install --yes numpy scipy nose requests
+        if [[ ${{ matrix.python-version }} == "2.7" ]]; then conda install --yes unittest2; else conda install --yes pdbfixer mdtraj; fi
         pip install mmtf-python scikit-learn
         pip install .
         python setup.py build_ext --inplace --force

PKG-INFO

@@ -92,7 +92,7 @@ Classifier: Programming Language :: Python :: 3
 Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Requires: numpy (>=1.10)
-Requires: pyparsing
+Requires: pyparsing (<=3.1.1)
 Requires: biopython
 Requires: scipy
-Provides: prody (2.1.2)
+Provides: prody

README.rst

@@ -20,6 +20,57 @@ API is for interactive usage as well as application development.  ProDy also
 comes with several analysis applications and a graphical user interface for
 visual analysis.
 
+Further details are described in the ProDy papers:
+
+  | Bakan A, Meireles LM, Bahar I.
+  | *ProDy*: Protein Dynamics Inferred from Theory and Experiments.
+  | *Bioinformatics* **2011** 27(11):1575-1577.
+
+  | Bakan A, Dutta A, Mao W, Liu Y, Chennubhotla C, Lezon TR, Bahar I.
+  | *Evol* and *ProDy* for Bridging Protein Sequence Evolution and Structural Dynamics.
+  | *Bioinformatics* **2014** 30(18):2681-2683.
+
+  | Zhang S, Krieger JM, Zhang Y, Kaya C, Kaynak B, Mikulska-Ruminska K, Doruker P, Li H, Bahar I.
+  | *ProDy* 2.0: Increased Scale and Scope after 10 Years of Protein Dynamics Modelling with Python.
+  | *Bioinformatics* **2021** 37(20):3657-3659.
+
+MODULES
+--------
+
+ProDy has a modular structure with modules inside various subpackages.
+
+The main ones are:
+
+- :mod:`~prody.atomic`` handles all :class:`~prody.atomic.Atomic` objects including :class:`~prody.atomic.AtomGroup` and :class:`.Selection`
+
+- :mod:`~prody.database` interfaces with databases such as CATH, DALI, UniProt and Pfam
+
+- :mod:`~prody.dynamics` provides all the modules for normal mode analysis with various elastic network models, 
+as well as PCA, SignDy (:mod:`~prody.dynamics.signature`), hybrid methods such as :mod:`~prody.dynamics.clustenm`, 
+allosteric signal propagation methods :mod:`~prody.dynamics.perturb` (PRS) and :func:`~prody.dynamics.analysis.calcHitTime` (Markovian hitting time),
+and various analysis and plotting functions.
+
+- :mod:`~prody.ensemble` enables construction of heterogeneous structural ensembles for exploring dynamics from experiments and simulations
+
+- :mod:`~prody.proteins` provides various modules for parsing different kinds of protein structure files including PDB, mmCIF, MMTF and maps,
+as well as tools to align and compare structures, and analysis of :mod:`~prody.proteins.interactions` within and between proteins (InSty) and 
+find :mod:`~prody.proteins.waterbridges` (WatFinder).
+
+- :mod:`~prody.sequence` has all the sequence alignment and evolutionary analysis tools of Evol
+
+
+Smaller ones include:
+
+- :mod:`~prody.chromatin` specific to chromatin dynamics (ChromDy) including :mod:`~prody.chromatin.hic` and :mod:`~prody.chromatin.cluster`
+
+- :mod:`~prody.compounds` for parsing small molecule compounds/ligands from the PDB and related databases
+
+- :mod:`~prody.domain_decomposition` for Spectrus dynamical domain decomposition 
+
+- :mod:`~prody.trajectory` for trajectories in DCD format
+
+- :mod:`~prody.utilities`
+
 
 GETTING PRODY
 -------------
@@ -45,6 +96,8 @@ DOCUMENTATION
 
 * Changes: http://prody.csb.pitt.edu/manual/release
 
+See also https://github.com/prody/ProDy-website for latest versions.
+
 
 SOURCE CODE
 -----------

docs/docs

@@ -1 +1 @@
-ProDy/docs
+.

docs/reference/dynamics/signature.rst

@@ -1,5 +1,5 @@
-Signature Dynamics of Protein Families
-======================================
+Signature Dynamics of Protein Families (SignDy)
+===============================================
 
 .. automodule:: prody.dynamics.signature
    :members:

docs/reference/proteins/interactions.rst

@@ -1,5 +1,5 @@
-Interactions Tools
-======================
+Interactions and Stability (InSty)
+===================================
 
 .. automodule:: prody.proteins.interactions
    :members:

docs/reference/proteins/waterbridges.rst

@@ -0,0 +1,6 @@
+Water bridge finder (WatFinder)
+===================================
+
+.. automodule:: prody.proteins.waterbridges
+   :members:
+   :undoc-members:

prody/apps/prody_apps/prody_clustenm.py

@@ -44,7 +44,9 @@
     ('write_params', 'whether to write parameters', False),
     ('fitmap', 'map to fit by filtering conformations like MDeNMD-EMFit', None),
     ('fit_resolution', 'resolution for blurring structures for fitting cc', 5),
-    ('map_cutoff', 'min_cutoff for passing map for fitting', 0)]:
+    ('map_cutoff', 'min_cutoff for passing map for fitting', 0),
+    ('replace_filtered', 'whether to keep sampling again to replace filtered conformers', False),
+    ('platform', 'openmm platform (OpenCL, CUDA, CPU or None)', None)]:
 
     DEFAULTS[key] = val
     HELPTEXT[key] = txt
@@ -85,6 +87,7 @@ def prody_clustenm(pdb, **kwargs):
     model = kwargs.pop('model')
     altloc = kwargs.pop('altloc')
     turbo = kwargs.pop('turbo')
+    nproc = kwargs.pop('nproc')
 
     ngens = kwargs.pop('ngens')
     nconfs = kwargs.pop('nconfs')
@@ -153,7 +156,8 @@ def prody_clustenm(pdb, **kwargs):
             outlier=outlier, mzscore=mzscore,
             sparse=sparse, kdtree=kdtree, turbo=turbo,
             parallel=parallel, fitmap=fitmap, 
-            fit_resolution=fit_resolution, **kwargs)
+            fit_resolution=fit_resolution,
+            nproc=nproc, **kwargs)
 
     single = not kwargs.pop('multiple')
     outname = join(outdir, prefix)
@@ -199,7 +203,7 @@ def addCommand(commands):
   $ prody clustenm 1aar -s "calpha and chain A and resnum < 70" -A""",
   test_examples=[0, 1])
 
-    group = addNMAParameters(subparser, include_nproc=False)
+    group = addNMAParameters(subparser, include_nproc=True)
 
     group.add_argument('-c', '--cutoff', dest='cutoff', type=str,
         default=DEFAULTS['cutoff'], metavar='FLOAT',
@@ -267,7 +271,7 @@ def addCommand(commands):
         default=DEFAULTS['ionicStrength'], metavar='FLOAT',
         help=HELPTEXT['ionicStrength'] + ' (default: %(default)s)')
 
-    group.add_argument('-P', '--padding', dest='padding', type=float,
+    group.add_argument('-Q', '--padding', dest='padding', type=float,
         default=DEFAULTS['padding'], metavar='FLOAT',
         help=HELPTEXT['padding'] + ' (default: %(default)s)')
 
@@ -331,6 +335,14 @@ def addCommand(commands):
         default=DEFAULTS['map_cutoff'], metavar='FLOAT',
         help=HELPTEXT['map_cutoff'] + ' (default: %(default)s)')
 
+    group.add_argument('-O', '--replace_filtered', dest='replace_filtered',
+        action='store_true',
+        default=DEFAULTS['replace_filtered'], help=HELPTEXT['replace_filtered'])
+
+    group.add_argument('-V', '--platform', dest='platform', type=str,
+        default=DEFAULTS['platform'], metavar='STR',
+        help=HELPTEXT['platform'] + ' (default: %(default)s)')
+
     subparser.add_argument('pdb', help='PDB identifier or filename')
 
     subparser.set_defaults(func=lambda ns: prody_clustenm(ns.__dict__.pop('pdb'),

prody/atomic/flags.py

@@ -132,8 +132,15 @@
 
     'nucleobase': set(['GUN', 'ADE', 'CYT', 'THY', 'URA']),
     'nucleotide': set(['DA', 'DC', 'DG', 'DT', 'DU', 'A', 'C', 'G', 'T', 'U']),
-    'nucleoside': set(['AMP', 'ADP', 'ATP', 'CDP', 'CTP', 'GMP', 'GDP', 'GTP',
-                       'TMP', 'TTP', 'UMP', 'UDP', 'UTP']),
+    'nucleoside': set(['ADN', 'AMP', 'ADP', 'ATP',
+                       'CMP', # cyclic AMP
+                       'A2P', 'A3P', # multi site diphosphates
+                       'AGS', # ATP-gamma-S
+                       'CTN', 'C5P', 'CDP', 'CTP',
+                       'C2P', 'C3P', # other site monophosphates
+                       'GMP', '5GP', 'GDP', 'GTP',
+                       'THM', 'TMP', 'TPP', 'TTP',
+                       'URI', 'UMP', 'UDP', 'UTP']),
 
     'at': set(['ADE', 'A', 'THY', 'T']),
     'cg': set(['CYT', 'C', 'GUN', 'G']),
@@ -418,19 +425,36 @@ def changeBackbone(flag, names):
       =======  ==================================
 
    nucleoside
-      indicates following nucleoside derivatives that are recognized by *PDB*:
+      indicates following nucleosides and their derivatives that are recognized by *PDB*:
 
       =======  ================================
-      `AMP`_   adenosine monophosphate
+      `ADN`_   adenosine
+      `AMP`_   adenosine-5'-monophosphate
       `ADP`_   adenosine-5'-diphosphate
       `ATP`_   adenosine-5'-triphosphate
+      `AGS`_   adenosine-5'-triphosphate-gamma-S
+      `CMP`_   cyclic adenosine-3',5'-monophosphate
+      `A2P`_   adenosine-2',5'-diphosphate
+      `A3P`_   adenosine-3',5'-diphosphate
+
+      `CTN`_   cytidine
+      `C2P`_   cytidine-2'-monophosphate
+      `C3P`_   cytidine-3'-monophosphate
+      `C5P`_   cytidine-5'-monophosphate
       `CDP`_   cytidine-5'-diphosphate
       `CTP`_   cytidine-5'-triphosphate
+
       `GMP`_   guanosine
+      `5GP`_   guanosine-5'-monophosphate
       `GDP`_   guanosine-5'-diphosphate
       `GTP`_   guanosine-5'-triphosphate
-      `TMP`_   thymidine-5'-phosphate
+
+      `THM`_   thymidine
+      `TMP`_   thymidine-5'-monophosphate
+      `TPP`_   thymidine-5'-diphosphate
       `TTP`_   thymidine-5'-triphosphate
+
+      `URI`_   uridine (uracil plus ribose)
       `UMP`_   2'-deoxyuridine 5'-monophosphate
       `UDP`_   uridine 5'-diphosphate
       `UTP`_   uridine 5'-triphosphate

prody/compounds/pdbligands.py

@@ -158,9 +158,9 @@ def fetchPDBLigand(cci, filename=None):
     resnums = np.ones(n_atoms, dtype=ATOMIC_FIELDS['charge'].dtype)
 
     alternate_atomnames = np.zeros(n_atoms, dtype=ATOMIC_FIELDS['name'].dtype)
-    leaving_atom_flags = np.zeros(n_atoms, np.bool)
-    aromatic_flags = np.zeros(n_atoms, np.bool)
-    stereo_configs = np.zeros(n_atoms, np.bool)
+    leaving_atom_flags = np.zeros(n_atoms, bool)
+    aromatic_flags = np.zeros(n_atoms, bool)
+    stereo_configs = np.zeros(n_atoms, bool)
     ordinals = np.zeros(n_atoms, int)
 
     name2index = {}

prody/database/__init__.py

@@ -72,11 +72,21 @@
 Interpro
 ====
 
-The following functions can be used to search and retrieve Pfam_ data:
+The following functions can be used to search and retrieve Interpro_ data:
 
   * :func:`.searchInterpro` - search for domain families of a protein
 
-.. _Pfam: https://www.ebi.ac.uk/interpro/
+.. _Interpro: https://www.ebi.ac.uk/interpro/
+
+BioExcel-CV19
+====
+
+The following functions can be used to retrieve BioExcel-CV19_ data:
+
+  * :func:`.fetchBioexcelPDB` - fetch PDB files for starting structures for trajectories
+
+.. _BioExcel-CV19: https://bioexcel-cv19-dev.bsc.es/
+
 """
 
 __all__ = []
@@ -108,3 +118,7 @@
 from . import interpro
 from .interpro import *
 __all__.extend(interpro.__all__)
+
+from . import bioexcel
+from .bioexcel import *
+__all__.extend(bioexcel.__all__)