Skip empty features

.github/ISSUE_TEMPLATE/bug-report.md

@@ -0,0 +1,32 @@
+---
+name: Bug report
+about: Create a report to help us improve
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Describe the bug**
+A clear and concise description of what the bug is.
+
+**Environment:**
+- OS system:
+- Version:
+- Branch commit ID: 
+- Inputs:
+
+**To Reproduce**
+Steps/commands to reproduce the behaviour:
+ 1.  
+ 2.
+ 3. 
+
+**Expected Results**
+A clear and concise description of what you expected to happen.
+
+**Actual Results or Error Info**
+If applicable, add screenshots to help explain your problem.
+
+**Additional Context**
+Add any other context about the problem here.

.github/ISSUE_TEMPLATE/feature_request.md

@@ -0,0 +1,20 @@
+---
+name: Feature request
+about: Suggest an idea for this project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**Is your feature request related to a problem? Please describe.**
+A clear and concise description of what the problem is. Ex. I'm always frustrated when [...]
+
+**Describe the solution you'd like**
+A clear and concise description of what you want to happen.
+
+**Describe alternatives you've considered**
+A clear and concise description of any alternative solutions or features you've considered.
+
+**Additional context**
+Add any other context or screenshots about the feature request here.

.gitignore

@@ -1,9 +1,13 @@
 Byte-compiled / optimized
 *__pycache__*
 
+
+
 # distribution
 deeprank.egg-info
 database*
+dist
+build 
 
 # specific architure files
 deeprank/learn/arch_*
@@ -44,10 +48,15 @@ test/*.pdb
 #docs/_static
 #docs/_templates
 
+
 # vscode setting
 .vscode
 
 .DS_Store
 test/1AK4/atomic_features/test_1AK4_100w.dat
 test/2OUL/atomic_features/test_2OUL_1.dat
 test/atomic_pair_interaction.dat
+
+# Mac OSX files
+.DS_Store
+

.travis.yml

@@ -16,7 +16,7 @@ before_install:
   # Useful for debugging any issues with conda
   - conda info -a
 
- # python
+  # python
   - conda install python=3.7
 
   # install openmpi for mpi4py

README.md

@@ -5,7 +5,7 @@
 [![Build Status](https://secure.travis-ci.org/DeepRank/deeprank.svg?branch=master)](https://travis-ci.org/DeepRank/deeprank)
 [![Codacy Badge](https://api.codacy.com/project/badge/Grade/9252e59633cf46a7ada0c3c614c175ea)](https://www.codacy.com/app/NicoRenaud/deeprank?utm_source=github.com&utm_medium=referral&utm_content=DeepRank/deeprank&utm_campaign=Badge_Grade)
 [![Coverage Status](https://coveralls.io/repos/github/DeepRank/deeprank/badge.svg?branch=master)](https://coveralls.io/github/DeepRank/deeprank?branch=master)
-[![Documentation Status](https://readthedocs.org/projects/deeprank/badge/?version=latest)](http://deeprank.readthedocs.io/?badge=latest)
+[![Documentation Status](https://readthedocs.org/projects/deeprank/badge/?version=latest)](http://deeprank.readthedocs.io/?badge=latest) [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.3735042.svg)](https://doi.org/10.5281/zenodo.3735042)
 
 The documentation of the module can be found on readthedocs :
 <http://deeprank.readthedocs.io/en/latest/>
@@ -16,12 +16,14 @@ The documentation of the module can be found on readthedocs :
 
 Minimal information to install the module
 
+
 -   clone the repository `git clone https://github.com/DeepRank/deeprank.git`
 -   go there             `cd deeprank`
 -   install the module   `pip install -e ./`
 -   go int the test dir `cd test`
 -   run the test suite `pytest`
 
+
 ## 2 . Tutorial
 
 We give here the tutorial like introduction to the DeepRank machinery. More informatoin can be found in the documentation <http://deeprank.readthedocs.io/en/latest/>.  We quickly illsutrate here the two main steps of Deeprank :

deeprank/__version__.py

@@ -1 +1 @@
-__version__ = '0.0.1'
+__version__ = '0.1.0'

deeprank/features/AtomicFeature.py

@@ -61,7 +61,7 @@ def __init__(self, pdbfile, param_charge=None, param_vdw=None,
         >>> atfeat.evaluate_pair_interaction(save_interactions=test_name)
         >>>
         >>> # close the db
-        >>> atfeat.sqldb.close()
+        >>> atfeat.sqldb._close()
         """
 
         super().__init__("Atomic")
@@ -939,7 +939,7 @@ def __compute_feature__(pdb_data, featgrp, featgrp_raw):
     atfeat.export_data_hdf5(featgrp_raw)
 
     # close
-    atfeat.sqldb.close()
+    atfeat.sqldb._close()
 
 
 ########################################################################

deeprank/features/BSA.py

@@ -31,7 +31,7 @@ def __init__(self, pdb_data, chainA='A', chainB='B'):
         >>> bsa = BSA('1AK4.pdb')
         >>> bsa.get_structure()
         >>> bsa.get_contact_residue_sasa()
-        >>> bsa.sql.close()
+        >>> bsa.sql._close()
         """
         self.pdb_data = pdb_data
         self.sql = pdb2sql.interface(pdb_data)
@@ -117,13 +117,9 @@ def get_contact_residue_sasa(self, cutoff=5.5):
             # define the xyz key : (chain,x,y,z)
             chain = {'A': 0, 'B': 1}[res[0]]
 
-            atcenter = 'CB'
-            if res[2] == 'GLY':
-                atcenter = 'CA'
-            xyz = self.sql.get(
-                'x,y,z', resSeq=res[1], chainID=res[0], name=atcenter)[0]
-            # xyz = np.mean(self.sql.get('x,y,z',resSeq=r[1],chainID=r[0]),0)
-            xyzkey = tuple([chain] + xyz)
+            # get the center            
+            _, xyz = self.get_residue_center(self.sql, res=res)
+            xyzkey = tuple([chain] + xyz[0])
 
             # put the data in dict
             self.bsa_data[res] = [bsa]
@@ -156,7 +152,7 @@ def __compute_feature__(pdb_data, featgrp, featgrp_raw):
     bsa.export_data_hdf5(featgrp_raw)
 
     # close the file
-    bsa.sql.close()
+    bsa.sql._close()
 
 
 ########################################################################
@@ -177,7 +173,7 @@ def __compute_feature__(pdb_data, featgrp, featgrp_raw):
     bsa = BSA(pdb_file)
     bsa.get_structure()
     bsa.get_contact_residue_sasa()
-    bsa.sql.close()
+    bsa.sql._close()
 
     pprint(bsa.feature_data)
     print()

deeprank/features/FeatureClass.py

@@ -1,12 +1,14 @@
 import numpy as np
 
-
 class FeatureClass(object):
 
     def __init__(self, feature_type):
-        """Master class from which all the other feature classes should be
-        derived.
+        """Master class from which all the other feature classes should be derived.
+
+        Arguments
+            feature_type(str): 'Atomic' or 'Residue'
 
+        Notes:
             Each subclass must compute:
 
             - self.feature_data: dictionary of features in
@@ -28,22 +30,25 @@ def __init__(self, feature_type):
                 {'coulomb': data_dict_clb, 'vdwaals': data_dict_vdw}
                     data_dict_clb = {xyz_info: [values]}
                         xyz_info = (chainNum, x, y, z)
-
-        Args:
-            feature_type(str): 'Atomic' or 'Residue'
         """
+
         self.type = feature_type
         self.feature_data = {}
         self.feature_data_xyz = {}
 
     def export_data_hdf5(self, featgrp):
-        """Export the data in human readable format to HDF5's group.
-
-        - For atomic features, the format of the data must be:
-            {(chainID, resSeq, resName, name): [values]}
-        - For residue features, the format must be:
-            {(chainID, resSeq, resName): [values]}
+        """Export the data in xyz-val format in an HDF5 file group.
+
+        Arguments:
+            featgrp {[hdf5_group]} -- The hdf5 group of the feature
+
+        Notes:
+            - For atomic features, the format of the data must be:
+                {(chainID, resSeq, resName, name): [values]}
+            - For residue features, the format must be:
+                {(chainID, resSeq, resName): [values]}
         """
+
         # loop through the datadict and name
         for name, data in self.feature_data.items():
 
@@ -84,22 +89,14 @@ def export_data_hdf5(self, featgrp):
             else:
                 featgrp.create_dataset(name + '_raw', data=ds)
 
-    ########################################
-    #
-    # export the data in an HDF5 file group
-    # the format of the data is here
-    # PRO : fast when mapping
-    # CON : only usefull for deeprank
-    #
-    ########################################
-
+
     def export_dataxyz_hdf5(self, featgrp):
         """Export the data in xyz-val format in an HDF5 file group.
-
-        For atomic and residue the format of the data must be:
-        {(chainNum(0 or 1), x, y, z): [values]}
+        
+        Arguments:
+            featgrp {[hdf5_group]} -- The hdf5 group of the feature
         """
-
+        
         # loop through the datadict and name
         for name, data in self.feature_data_xyz.items():
 
@@ -112,3 +109,77 @@ def export_dataxyz_hdf5(self, featgrp):
                 old[...] = ds
             else:
                 featgrp.create_dataset(name, data=ds)
+
+    @staticmethod
+    def get_residue_center(sql, centers=['CB','CA','mean'], res=None):
+        """Computes the center of each residue by trying different options
+
+        Arguments:
+            sql {pdb2sql} -- The pdb2sql instance
+
+        Keyword Arguments:
+            centers {list} -- list of strings (default: {['CB','CA','mean']})
+            res {list} -- list of residue to be considered ([[chainID, resSeq, resName]])
+
+        Raises:
+            ValueError: [description]
+
+        Returns:
+            [type] -- list(res), list(xyz)
+        """
+
+        # get all residues if None were provided
+        # [chainID, resName, resSeq]
+        if res is None:
+            res = [tuple(x) for x in sql.get('chainID,resSeq,resName')]
+            res = sorted(set(res), key=res.index)
+
+
+        # make sure that we have a list of res
+        # even if ony 1 res was provided
+        # res=[chainID, resSeq, resName] -> res=[[chainID, resSeq, resName]]
+        elif not isinstance(res[0],list):
+            res = [res]            
+
+        # make sure that we have a list of possible centers
+        if not isinstance(centers,list):
+            centers = list(centers)
+
+        xyz = []
+
+        for r in res:
+
+            for ctr in centers:
+
+                if ctr in ['CB','CA']:
+
+                    xyz_res = sql.get('x,y,z', 
+                                      chainID=r[0],
+                                      resSeq=r[1],
+                                      resName=r[2],
+                                      name=ctr)
+
+                elif ctr == 'mean':
+                    xyz_res = [np.mean(sql.get('x,y,z',
+                                       chainID=r[0],
+                                       resSeq=r[1],
+                                       resName=r[2]),axis=0).tolist()]
+
+                else:
+                    raise ValueError('Center %s not recognized' %c)
+
+                if len(xyz_res) == 0:
+                    continue
+
+                elif len(xyz_res) == 1:
+                    xyz.append(xyz_res[0])
+                    break
+
+                else:
+                    raise ValueError('Residue center not found')
+
+        if len(xyz) == 0:
+            raise ValueError('Center not found')
+
+        return res, xyz
+

deeprank/features/FullPSSM.py

@@ -166,12 +166,7 @@ def get_feature_value(self, cutoff=5.5):
         sql = pdb2sql.interface(self.pdb_file)
 
         # set achors for all residues and get their xyz
-        xyz_info = sql.get('chainID,resSeq,resName', name='CB')
-        xyz_info += sql.get('chainID,resSeq,resName', name='CA',
-                            resName='GLY')
-
-        xyz = sql.get('x,y,z', name='CB')
-        xyz += sql.get('x,y,z', name='CA', resName='GLY')
+        xyz_info, xyz = self.get_residue_center(sql)
 
         xyz_dict = {}
         for pos, info in zip(xyz, xyz_info):
@@ -180,7 +175,7 @@ def get_feature_value(self, cutoff=5.5):
         # get interface contact residues
         # ctc_res = {"A":[chain 1 residues], "B": [chain2 residues]}
         ctc_res = sql.get_contact_residues(cutoff=cutoff)
-        sql.close()
+        sql._close()
         ctc_res = ctc_res["A"] + ctc_res["B"]
 
         # handle with small interface or no interface
@@ -212,6 +207,7 @@ def get_feature_value(self, cutoff=5.5):
                 f"{self.mol_name}: The following interface residues have "
                 f" no pssm value:\n {ctc_res_wo_pssm}"
             )
+
         else:
             ctc_res_with_pssm = ctc_res