Merge ef6e63e into 5d855ea

.gitignore

@@ -21,9 +21,8 @@ example/*.hdf5
 example/*.pdb
 
 # some test file
-test/out_2d
-test/out_3d
-test/out_3d_class
+test/out_2d*
+test/out_3d*
 test/out_test
 test/*.pckl
 test/*.hdf5

.travis.yml

@@ -19,7 +19,19 @@ before_install:
  # pytest
   - conda install -c anaconda pytest
   - conda install -c conda-forge pytest-cov
-  - conda install python=3.6
+  - conda install python=3.7
+
+  # install freesasa
+  - conda install cython
+  - sudo apt-get install -y libxml2 libxml2-dev libjson0 libjson0-dev
+  - wget http://github.com/mittinatten/freesasa/releases/download/2.0.2/freesasa-2.0.2.tar.gz
+  - mkdir freesasa
+  - tar -xvf freesasa-2.0.2.tar.gz -C freesasa --strip-components=1
+  - cd freesasa
+  - ./configure --disable-xml --disable-json --enable-python-bindings --with-python=python3.7 CFLAGS="-fPIC" --prefix=$HOME
+  - make
+  - make install
+  - cd ../
 
   # codacy-coverage
   - pip install -q --upgrade pip

README.md

@@ -19,19 +19,20 @@ 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 ./`
+  * install freesasa     `https://github.com/freesasa/freesasa-python`
   * 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 :
- * the generation of the data
- * running deep leaning experiments.
+  * the generation of the data
+  * running deep leaning experiments.
 
 ### A . Generate the data set (using MPI)
 
-The generation of the data require only require PDBs files of decoys and their native and the PSSM if needed. All the features/targets and mapped features onto grid points will be auomatically calculated and store in a HDF5 file. 
+The generation of the data require only require PDBs files of decoys and their native and the PSSM if needed. All the features/targets and mapped features onto grid points will be auomatically calculated and store in a HDF5 file.
 
 ```python
 from deeprank.generate import *
@@ -150,4 +151,3 @@ model.train(nepoch = 50,divide_trainset=0.8, train_batch_size = 5,num_workers=0)
 In the first part of the script we create a Torch database from the HDF5 file. We can specify one or several HDF5 files and even select some conformations using the `dict_filter` argument. Other options of `DataSet` can be used to specify the features/targets the normalization, etc ...
 
 We then create a `NeuralNet` instance that takes the dataset as input argument. Several options are available to specify the task to do, the GPU use, etc ... We then have simply to train the model. Simple !
-

deeprank/features/AtomicFeature.py

@@ -2,9 +2,9 @@
 import warnings
 
 import numpy as np
+import pdb2sql
 
 from deeprank.features import FeatureClass
-from deeprank.tools import pdb2sql
 
 
 class AtomicFeature(FeatureClass):
@@ -81,7 +81,7 @@ def __init__(self, pdbfile, param_charge=None, param_vdw=None,
         self.atom_key = 'chainID, resSeq, resName, name'
 
         # read the pdb as an sql
-        self.sqldb = pdb2sql(self.pdbfile)
+        self.sqldb = pdb2sql.pdb2sql(self.pdbfile)
 
         # read the force field
         self.read_charge_file()

deeprank/features/BSA.py

@@ -1,7 +1,8 @@
 import warnings
 
+import pdb2sql
+
 from deeprank.features import FeatureClass
-from deeprank.tools import pdb2sql
 
 try:
     import freesasa
@@ -33,7 +34,7 @@ def __init__(self, pdb_data, chainA='A', chainB='B'):
         >>> bsa.sql.close()
         """
         self.pdb_data = pdb_data
-        self.sql = pdb2sql(pdb_data)
+        self.sql = pdb2sql.interface(pdb_data)
         self.chains_label = [chainA, chainB]
 
         self.feature_data = {}
@@ -83,9 +84,8 @@ def get_contact_residue_sasa(self, cutoff=5.5):
         self.bsa_data = {}
         self.bsa_data_xyz = {}
 
-        # res = ([chain1 residues], [chain2 residues])
-        ctc_res = self.sql.get_contact_residue(cutoff=cutoff)
-        ctc_res = ctc_res[0] + ctc_res[1]
+        ctc_res = self.sql.get_contact_residues(cutoff=cutoff)
+        ctc_res = ctc_res["A"] + ctc_res["B"]
 
         # handle with small interface or no interface
         total_res = len(ctc_res)

deeprank/features/FullPSSM.py

@@ -2,10 +2,10 @@
 import warnings
 
 import numpy as np
+import pdb2sql
 
 from deeprank import config
 from deeprank.features import FeatureClass
-from deeprank.tools import pdb2sql
 
 ########################################################################
 #
@@ -163,7 +163,7 @@ def read_PSSM_data(self):
     def get_feature_value(self, cutoff=5.5):
         """get the feature value."""
 
-        sql = pdb2sql(self.pdb_file)
+        sql = pdb2sql.interface(self.pdb_file)
 
         # set achors for all residues and get their xyz
         xyz_info = sql.get('chainID,resSeq,resName', name='CB')
@@ -178,10 +178,10 @@ def get_feature_value(self, cutoff=5.5):
             xyz_dict[tuple(info)] = pos
 
         # get interface contact residues
-        # ctc_res = ([chain 1 residues], [chain2 residues])
-        ctc_res = sql.get_contact_residue(cutoff=cutoff)
+        # ctc_res = {"A":[chain 1 residues], "B": [chain2 residues]}
+        ctc_res = sql.get_contact_residues(cutoff=cutoff)
         sql.close()
-        ctc_res = ctc_res[0] + ctc_res[1]
+        ctc_res = ctc_res["A"] + ctc_res["B"]
 
         # handle with small interface or no interface
         total_res = len(ctc_res)

deeprank/features/NaivePSSM.py

@@ -2,9 +2,10 @@
 from time import time
 
 import numpy as np
+import pdb2sql
 
 from deeprank.features import FeatureClass
-from deeprank.tools import SASA, pdb2sql
+from deeprank.tools import SASA
 
 
 def printif(string, cond): return print(string) if cond else None
@@ -148,7 +149,7 @@ def _smooth_pssm(pssm_data, msmooth=3):
     def get_feature_value(self, contact_only=True):
         """get the feature value."""
 
-        sql = pdb2sql(self.pdbfile)
+        sql = pdb2sql.interface(self.pdbfile)
         xyz_info = sql.get('chainID,resSeq,resName', name='CB')
         xyz = sql.get('x,y,z', name='CB')
 
@@ -157,7 +158,7 @@ def get_feature_value(self, contact_only=True):
             xyz_dict[tuple(info)] = pos
 
         contact_residue = sql.get_contact_residue(cutoff=5.5)
-        contact_residue = contact_residue[0] + contact_residue[1]
+        contact_residue = contact_residue["A"] + contact_residue["B"]
         sql.close()
 
         pssm_data_xyz = {}

deeprank/features/ResidueDensity.py

@@ -1,8 +1,8 @@
 import itertools
 import warnings
+import pdb2sql
 
 from deeprank.features import FeatureClass
-from deeprank.tools import pdb2sql
 from deeprank import config
 
 
@@ -23,7 +23,7 @@ def __init__(self, pdb_data, chainA='A', chainB='B'):
         """
 
         self.pdb_data = pdb_data
-        self.sql = pdb2sql(pdb_data)
+        self.sql = pdb2sql.interface(pdb_data)
         self.chains_label = [chainA, chainB]
 
         self.feature_data = {}
@@ -40,7 +40,7 @@ def get(self, cutoff=5.5):
         # res = {('chainA,resSeq,resName'): set(
         #                               ('chainB,res1Seq,res1Name),
         #                               ('chainB,res2Seq,res2Name'))}
-        res = self.sql.get_contact_residue(chain1=self.chains_label[0],
+        res = self.sql.get_contact_residues(chain1=self.chains_label[0],
                                            chain2=self.chains_label[1],
                                            cutoff=cutoff,
                                            return_contact_pairs=True)