Merge pull request #107 from DeepRank/rename_package

Rename package and repo

.gitignore

@@ -8,8 +8,8 @@
 *__pycache__*
 
 # distribution
-deeprank_gnn.egg-info
-DeepRank_GNN.egg-info
+deeprankcore.egg-info
+deeprank-core.egg-info
 build/*
 dist/*
 

CITATION.CFF

@@ -2,7 +2,7 @@
 # Visit https://bit.ly/cffinit to generate yours today!
 
 cff-version: 1.2.0
-title: DeepRank-GNN
+title: deeprank-core
 message: >-
   If you use this software, please cite it using the
   metadata from this file.
@@ -21,11 +21,11 @@ authors:
 identifiers:
   - type: url
     value: ''
-    description: 'https://github.com/DeepRank/Deeprank-GNN'
-repository-code: 'https://github.com/DeepRank/Deeprank-GNN'
-url: 'https://deeprank-gnn.readthedocs.io/'
+    description: 'https://github.com/DeepRank/deeprank-core'
+repository-code: 'https://github.com/DeepRank/deeprank-core'
+url: 'https://deeprank-core.readthedocs.io/'
 abstract: >-
-  DeepRank-GNN allows ranking of Protein-protein
+  deeprank-core allows ranking of Protein-protein
   Interface using a graph representation of the
   contact residues. Graphs of such interfaces are
   used to train graph neural network for the

README.md

@@ -1,49 +1,49 @@
-# DeepRank-GNN
+# deeprank-core
 
-[![Build Status](https://github.com/DeepRank/deeprank-gnn-2/actions/workflows/ci-pipeline.yml/badge.svg)](https://github.com/DeepRank/deeprank-gnn-2/actions)
-[![Codacy Badge](https://api.codacy.com/project/badge/Grade/f3f98b2d1883493ead50e3acaa23f2cc)](https://app.codacy.com/gh/DeepRank/DeepRank-GNN?utm_source=github.com&utm_medium=referral&utm_content=DeepRank/DeepRank-GNN&utm_campaign=Badge_Grade)
-[![Coverage Status](https://coveralls.io/repos/github/DeepRank/deeprank-gnn-2/badge.svg?branch=main)](https://coveralls.io/github/DeepRank/deeprank-gnn-2?branch=main)
+[![Build Status](https://github.com/DeepRank/deeprank-core/actions/workflows/ci-pipeline.yml/badge.svg)](https://github.com/DeepRank/deeprank-core/actions)
+[![Codacy Badge](https://api.codacy.com/project/badge/Grade/f3f98b2d1883493ead50e3acaa23f2cc)](https://app.codacy.com/gh/DeepRank/deeprank-core?utm_source=github.com&utm_medium=referral&utm_content=DeepRank/deeprank-core&utm_campaign=Badge_Grade)
+[![Coverage Status](https://coveralls.io/repos/github/DeepRank/deeprank-core/badge.svg?branch=main)](https://coveralls.io/github/DeepRank/deeprank-core?branch=main)
 [![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.5705564.svg)](https://doi.org/10.5281/zenodo.5705564)
 
-![alt-text](./deeprank_gnn.png)
+![alt-text](./deeprankcore.png)
 
 ## Installation
 
 ### Dependencies
 
-Before installing DeepRank-GNN you need to install:
+Before installing deeprank-core you need to install:
 
  * [pytorch](https://pytorch.org/): `conda install pytorch -c pytorch`. Note that by default the CPU version of pytorch will be installed, but you can also customize that installation following the instructions on pytorch website.
  * [pytorch_geometric](https://pytorch-geometric.readthedocs.io/en/latest/notes/installation.html): `conda install pyg -c pyg` (recommended).
  * [msms](https://ssbio.readthedocs.io/en/latest/instructions/msms.html): `conda install -c bioconda msms`. *For MacOS with M1 chip users*: you can follow [these instructions](https://ssbio.readthedocs.io/en/latest/instructions/msms.html). 
  * [reduce](https://github.com/rlabduke/reduce) Follow the instructions in the README
 
-### DeepRank-GNN installation
+### deeprank-core installation
 
-[//]: # (Once the dependencies installed, you can install the latest release of DeepRank-GNN using the PyPi package manager:)
+[//]: # (Once the dependencies installed, you can install the latest release of deeprank-core using the PyPi package manager:)
 
 [//]: # (```)
-[//]: # (pip install DeepRank-GNN)
+[//]: # (pip install deeprankcore)
 [//]: # (```)
 
 You can get all the new developments by cloning the repo and installing the code with
 
 ```
-git clone https://github.com/DeepRank/deeprank-gnn-2
-cd deeprank-gnn-2
+git clone https://github.com/DeepRank/deeprank-core
+cd deeprankcore
 pip install -e ./
 ```
 
-[//]: # (The documentation can be found here : https://deeprank-gnn.readthedocs.io/)
+[//]: # (The documentation can be found here : https://deeprank-core.readthedocs.io/)
 
 ## Generate Graphs
 
 The process of generating graphs is called preprocessing. In order to do so, one needs query objects, describing how the graphs should be built.
 
 ```python
-from deeprank_gnn.preprocess import preprocess
-from deeprank_gnn.models.query import ProteinProteinInterfaceResidueQuery
-from deeprank_gnn.feature import bsa, pssm, amino_acid, biopython
+from deeprankcore.preprocess import preprocess
+from deeprankcore.models.query import ProteinProteinInterfaceResidueQuery
+from deeprankcore.feature import bsa, pssm, amino_acid, biopython
 
 feature_modules = [bsa, pssm, amino_acid, biopython]
 
@@ -75,10 +75,10 @@ Using the graph interaction network is rather simple :
 
 
 ```python
-from deeprank_gnn.NeuralNet import NeuralNet
-from deeprank_gnn.DataSet import HDF5DataSet
-from deeprank_gnn.ginet import GINet
-from deeprank_gnn.models.metrics import OutputExporter, ScatterPlotExporter
+from deeprankcore.NeuralNet import NeuralNet
+from deeprankcore.DataSet import HDF5DataSet
+from deeprankcore.ginet import GINet
+from deeprankcore.models.metrics import OutputExporter, ScatterPlotExporter
 
 database = './hdf5/1ACB_residue.hdf5'
 
@@ -191,6 +191,6 @@ nn.train(nepoch=50)
 
 ## h5x support
 
-After installing  `h5xplorer`  (https://github.com/DeepRank/h5xplorer), you can execute the python file `deeprank_gnn/h5x/h5x.py` to explorer the connection graph used by DeepRank-GNN. The context menu (right click on the name of the structure) allows to automatically plot the graphs using `plotly` as shown below.
+After installing  `h5xplorer`  (https://github.com/DeepRank/h5xplorer), you can execute the python file `deeprankcore/h5x/h5x.py` to explorer the connection graph used by deeprank-core. The context menu (right click on the name of the structure) allows to automatically plot the graphs using `plotly` as shown below.
 
-![alt-text](./h5_deeprank_gnn.png)
+![alt-text](./h5_deeprankcore.png)

deeprank_gnn/DataSet.py → deeprankcore/DataSet.py

@@ -12,7 +12,7 @@
 import h5py
 import copy
 from ast import literal_eval
-from deeprank_gnn.community_pooling import community_detection, community_pooling
+from deeprankcore.community_pooling import community_detection, community_pooling
 
 
 _log = logging.getLogger(__name__)
@@ -140,9 +140,9 @@ def __init__( # pylint: disable=too-many-arguments
 
             node_feature (str or list, optional): consider all pre-computed node features ("all")
             or some defined node features (provide a list, example: ["type", "polarity", "bsa"]).
-            The complete list can be found in deeprank_gnn/domain/features.py
+            The complete list can be found in deeprankcore/domain/features.py
 
-            edge_feature (list, optional): the complete list can be found in deeprank_gnn/domain/features.py.
+            edge_feature (list, optional): the complete list can be found in deeprankcore/domain/features.py.
             Defaults to ["dist"], distance.
 
             clustering_method (str, optional): perform node clustering ('mcl', Markov Clustering,

deeprank_gnn/GraphGenMP.py → deeprankcore/GraphGenMP.py

@@ -6,14 +6,14 @@
 import h5py
 from tqdm import tqdm
 
-from deeprank_gnn.preprocess import preprocess
-from deeprank_gnn.models.query import ProteinProteinInterfaceResidueQuery
-from deeprank_gnn.tools.score import get_all_scores
-import deeprank_gnn.feature.amino_acid
-import deeprank_gnn.feature.atomic_contact
-import deeprank_gnn.feature.biopython
-import deeprank_gnn.feature.bsa
-import deeprank_gnn.feature.pssm
+from deeprankcore.preprocess import preprocess
+from deeprankcore.models.query import ProteinProteinInterfaceResidueQuery
+from deeprankcore.tools.score import get_all_scores
+import deeprankcore.feature.amino_acid
+import deeprankcore.feature.atomic_contact
+import deeprankcore.feature.biopython
+import deeprankcore.feature.bsa
+import deeprankcore.feature.pssm
 
 
 _log = logging.getLogger(__name__)
@@ -55,14 +55,14 @@ def __init__( # pylint: disable=too-many-arguments, too-many-locals
         """
 
         self._feature_modules = [
-            deeprank_gnn.feature.amino_acid,
-            deeprank_gnn.feature.atomic_contact,
-            deeprank_gnn.feature.bsa,
+            deeprankcore.feature.amino_acid,
+            deeprankcore.feature.atomic_contact,
+            deeprankcore.feature.bsa,
         ]
         if pssm_path is not None:
-            self._feature_modules.append(deeprank_gnn.feature.pssm)
+            self._feature_modules.append(deeprankcore.feature.pssm)
         if biopython:
-            self._feature_modules.append(deeprank_gnn.feature.biopython)
+            self._feature_modules.append(deeprankcore.feature.biopython)
 
         # get the list of PDB names
         pdbs = list(filter(lambda x: x.endswith(".pdb"), os.listdir(pdb_path)))

deeprank_gnn/NeuralNet.py → deeprankcore/NeuralNet.py

@@ -10,9 +10,9 @@
 import torch.nn.functional as F
 from torch_geometric.data import DataLoader
 
-# deeprank_gnn import
-from deeprank_gnn.models.metrics import MetricsExporterCollection, MetricsExporter
-from deeprank_gnn.DataSet import DivideDataSet, PreCluster
+# deeprankcore import
+from deeprankcore.models.metrics import MetricsExporterCollection, MetricsExporter
+from deeprankcore.DataSet import DivideDataSet, PreCluster
 
 _log = logging.getLogger(__name__)
 

deeprank_gnn/domain/amino_acid.py → deeprankcore/domain/amino_acid.py

@@ -1,5 +1,5 @@
-from deeprank_gnn.models.amino_acid import AminoAcid
-from deeprank_gnn.models.polarity import Polarity
+from deeprankcore.models.amino_acid import AminoAcid
+from deeprankcore.models.polarity import Polarity
 
 alanine = AminoAcid(
     "Alanine",

deeprank_gnn/domain/forcefield/__init__.py → deeprankcore/domain/forcefield/__init__.py

@@ -1,13 +1,13 @@
 import os
 import logging
 import numpy
-from deeprank_gnn.models.structure import Atom, Residue
-from deeprank_gnn.models.forcefield.patch import PatchActionType
-from deeprank_gnn.tools.forcefield.top import TopParser
-from deeprank_gnn.tools.forcefield.patch import PatchParser
-from deeprank_gnn.tools.forcefield.residue import ResidueClassParser
-from deeprank_gnn.tools.forcefield.param import ParamParser
-from deeprank_gnn.models.error import UnknownAtomError
+from deeprankcore.models.structure import Atom, Residue
+from deeprankcore.models.forcefield.patch import PatchActionType
+from deeprankcore.tools.forcefield.top import TopParser
+from deeprankcore.tools.forcefield.patch import PatchParser
+from deeprankcore.tools.forcefield.residue import ResidueClassParser
+from deeprankcore.tools.forcefield.param import ParamParser
+from deeprankcore.models.error import UnknownAtomError
 
 logging.getLogger(__name__)
 

deeprank_gnn/feature/amino_acid.py → deeprankcore/feature/amino_acid.py

@@ -1,10 +1,10 @@
 from typing import Optional
 
 import numpy
-from deeprank_gnn.models.graph import Graph
-from deeprank_gnn.models.variant import SingleResidueVariant
-from deeprank_gnn.models.structure import Atom, Residue
-from deeprank_gnn.domain.feature import (FEATURENAME_AMINOACID, FEATURENAME_VARIANTAMINOACID,
+from deeprankcore.models.graph import Graph
+from deeprankcore.models.variant import SingleResidueVariant
+from deeprankcore.models.structure import Atom, Residue
+from deeprankcore.domain.feature import (FEATURENAME_AMINOACID, FEATURENAME_VARIANTAMINOACID,
                                          FEATURENAME_SIZE, FEATURENAME_POLARITY,
                                          FEATURENAME_SIZEDIFFERENCE, FEATURENAME_POLARITYDIFFERENCE,
                                          FEATURENAME_HYDROGENBONDDONORS, FEATURENAME_HYDROGENBONDDONORSDIFFERENCE,

deeprank_gnn/feature/atomic_contact.py → deeprankcore/feature/atomic_contact.py

@@ -2,14 +2,14 @@
 import logging
 import numpy
 from scipy.spatial import distance_matrix
-from deeprank_gnn.models.structure import Atom
-from deeprank_gnn.models.graph import Graph, Edge
-from deeprank_gnn.models.contact import ResidueContact, AtomicContact
-from deeprank_gnn.domain.feature import (FEATURENAME_EDGEDISTANCE, FEATURENAME_EDGEVANDERWAALS,
+from deeprankcore.models.structure import Atom
+from deeprankcore.models.graph import Graph, Edge
+from deeprankcore.models.contact import ResidueContact, AtomicContact
+from deeprankcore.domain.feature import (FEATURENAME_EDGEDISTANCE, FEATURENAME_EDGEVANDERWAALS,
                                          FEATURENAME_EDGECOULOMB, FEATURENAME_COVALENT)
-from deeprank_gnn.domain.forcefield import atomic_forcefield, COULOMB_CONSTANT, EPSILON0, MAX_COVALENT_DISTANCE
-from deeprank_gnn.models.forcefield.vanderwaals import VanderwaalsParam
-from deeprank_gnn.models.error import UnknownAtomError
+from deeprankcore.domain.forcefield import atomic_forcefield, COULOMB_CONSTANT, EPSILON0, MAX_COVALENT_DISTANCE
+from deeprankcore.models.forcefield.vanderwaals import VanderwaalsParam
+from deeprankcore.models.error import UnknownAtomError
 
 
 _log = logging.getLogger(__name__)

deeprank_gnn/feature/biopython.py → deeprankcore/feature/biopython.py

@@ -3,9 +3,9 @@
 from Bio.PDB.PDBParser import PDBParser
 from Bio.PDB.ResidueDepth import get_surface, residue_depth
 from Bio.PDB.HSExposure import HSExposureCA
-from deeprank_gnn.domain.feature import FEATURENAME_RESIDUEDEPTH, FEATURENAME_HALFSPHEREEXPOSURE
-from deeprank_gnn.models.structure import Atom, Residue
-from deeprank_gnn.models.graph import Graph
+from deeprankcore.domain.feature import FEATURENAME_RESIDUEDEPTH, FEATURENAME_HALFSPHEREEXPOSURE
+from deeprankcore.models.structure import Atom, Residue
+from deeprankcore.models.graph import Graph
 
 
 logging.getLogger(__name__)

deeprank_gnn/feature/bsa.py → deeprankcore/feature/bsa.py

@@ -1,8 +1,8 @@
 import logging
 import freesasa
-from deeprank_gnn.models.graph import Graph
-from deeprank_gnn.models.structure import Residue, Atom
-from deeprank_gnn.domain.feature import FEATURENAME_BURIEDSURFACEAREA
+from deeprankcore.models.graph import Graph
+from deeprankcore.models.structure import Residue, Atom
+from deeprankcore.domain.feature import FEATURENAME_BURIEDSURFACEAREA
 
 
 logging.getLogger(__name__)

deeprank_gnn/feature/pssm.py → deeprankcore/feature/pssm.py

@@ -1,10 +1,10 @@
 from typing import Optional
 import numpy
-from deeprank_gnn.models.variant import SingleResidueVariant
-from deeprank_gnn.domain.amino_acid import amino_acids
-from deeprank_gnn.models.structure import Residue, Atom
-from deeprank_gnn.models.graph import Graph
-from deeprank_gnn.domain.feature import (FEATURENAME_PSSM, FEATURENAME_PSSMDIFFERENCE,
+from deeprankcore.models.variant import SingleResidueVariant
+from deeprankcore.domain.amino_acid import amino_acids
+from deeprankcore.models.structure import Residue, Atom
+from deeprankcore.models.graph import Graph
+from deeprankcore.domain.feature import (FEATURENAME_PSSM, FEATURENAME_PSSMDIFFERENCE,
                                          FEATURENAME_PSSMWILDTYPE, FEATURENAME_PSSMVARIANT,
                                          FEATURENAME_INFORMATIONCONTENT)
 

deeprank_gnn/feature/sasa.py → deeprankcore/feature/sasa.py

@@ -1,9 +1,9 @@
 from typing import List
 import numpy
 import freesasa
-from deeprank_gnn.models.structure import Residue, Atom
-from deeprank_gnn.models.graph import Node, Graph
-from deeprank_gnn.domain.feature import FEATURENAME_SASA
+from deeprankcore.models.structure import Residue, Atom
+from deeprankcore.models.graph import Node, Graph
+from deeprankcore.domain.feature import FEATURENAME_SASA
 
 
 def add_features_for_residues(structure: freesasa.Structure, # pylint: disable=c-extension-no-member

deeprank_gnn/foutnet.py → deeprankcore/foutnet.py

@@ -8,7 +8,7 @@
 from torch_geometric.nn.inits import uniform
 from torch_geometric.nn import max_pool_x
 
-from deeprank_gnn.community_pooling import get_preloaded_cluster, community_pooling
+from deeprankcore.community_pooling import get_preloaded_cluster, community_pooling
 
 
 class FoutLayer(torch.nn.Module):

deeprank_gnn/ginet.py → deeprankcore/ginet.py

@@ -9,8 +9,8 @@
 from torch_geometric.nn.inits import uniform
 from torch_geometric.nn import max_pool_x
 
-# deeprank_gnn import
-from deeprank_gnn.community_pooling import get_preloaded_cluster, community_pooling
+# deeprankcore import
+from deeprankcore.community_pooling import get_preloaded_cluster, community_pooling
 
 
 class GINetConvLayer(torch.nn.Module):

deeprank_gnn/h5x/baseimport.py → deeprankcore/h5x/baseimport.py

@@ -1,4 +1,4 @@
-from deeprank_gnn.tools.visualization import hdf5_to_networkx, plotly_3d, plotly_2d
+from deeprankcore.tools.visualization import hdf5_to_networkx, plotly_3d, plotly_2d
 import plotly.offline as py
 
 def tsne_graph(grp, method):

deeprank_gnn/h5x/h5x.py → deeprankcore/h5x/h5x.py

@@ -4,7 +4,6 @@
 from h5xplorer.h5xplorer import h5xplorer
 import h5x_menu
 
-#baseimport = '/home/nico/Documents/projects/deeprank/DeepRank-GNN/deeprank_gnn/h5x/baseimport.py'
 baseimport = os.path.dirname(
     os.path.abspath(__file__)) + "/baseimport.py"
 app = h5xplorer(h5x_menu.context_menu,

deeprank_gnn/models/amino_acid.py → deeprankcore/models/amino_acid.py

@@ -1,6 +1,6 @@
 import numpy
 
-from deeprank_gnn.models.polarity import Polarity
+from deeprankcore.models.polarity import Polarity
 
 
 class AminoAcid:

deeprank_gnn/models/contact.py → deeprankcore/models/contact.py

@@ -1,6 +1,6 @@
 from abc import ABC
-from deeprank_gnn.models.pair import Pair
-from deeprank_gnn.models.structure import Residue, Atom
+from deeprankcore.models.pair import Pair
+from deeprankcore.models.structure import Residue, Atom
 
 class Contact(Pair, ABC):
     pass

deeprank_gnn/models/graph.py → deeprankcore/models/graph.py

@@ -5,10 +5,10 @@
 import numpy
 import h5py
 
-from deeprank_gnn.models.structure import Atom, Residue
-from deeprank_gnn.models.contact import Contact
-from deeprank_gnn.models.grid import MapMethod, Grid, GridSettings
-from deeprank_gnn.domain.storage import (
+from deeprankcore.models.structure import Atom, Residue
+from deeprankcore.models.contact import Contact
+from deeprankcore.models.grid import MapMethod, Grid, GridSettings
+from deeprankcore.domain.storage import (
     HDF5KEY_GRAPH_SCORE,
     HDF5KEY_GRAPH_NODENAMES,
     HDF5KEY_GRAPH_NODEFEATURES,

deeprank_gnn/models/grid.py → deeprankcore/models/grid.py

@@ -9,7 +9,7 @@
 import h5py
 import itertools
 from scipy.signal import bspline
-from deeprank_gnn.domain.storage import (
+from deeprankcore.domain.storage import (
     HDF5KEY_GRID_POINTS,
     HDF5KEY_GRID_X,
     HDF5KEY_GRID_Y,