Merge pull request #423 from DeepRank/joss_paper_gcroci2

docs: joss paper

.github/workflows/draft-pdf.yml

@@ -0,0 +1,26 @@
+name: Build JOSS PDF
+
+on:
+  workflow_dispatch:
+
+jobs:
+  paper:
+    runs-on: ubuntu-latest
+    name: Paper Draft
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v3
+      - name: Build draft PDF
+        uses: openjournals/openjournals-draft-action@master
+        with:
+          journal: joss
+          # This should be the path to the paper within your repo.
+          paper-path: paper/paper.md
+      - name: Upload
+        uses: actions/upload-artifact@v1
+        with:
+          name: paper
+          # This is the output path where Pandoc will write the compiled
+          # PDF. Note, this should be the same directory as the input
+          # paper.md
+          path: paper/paper.pdf

.zenodo.json

@@ -5,14 +5,24 @@
             "name": "Giulia Crocioni",
             "orcid": "0000-0002-0823-0121"
         },
+        {
+            "affiliation": "Netherlands eScience Center",
+            "name": "Dani L. Bodor",
+            "orcid": "0000-0003-2109-2349"
+        },
         {
             "affiliation": "Radboud University Medical Center",
             "name": "Coos Baakman",
             "orcid": "0000-0003-4317-1566"
         },
         {
             "affiliation": "Radboud University Medical Center",
-            "name": "Daniel Rademaker",
+            "name": "Farzaneh M. Parizi",
+            "orcid": "0000-0003-4230-7492"
+        },
+        {
+            "affiliation": "Radboud University Medical Center",
+            "name": "Daniel T. Rademaker",
             "orcid": "0000-0003-1959-1317"
         },
         {
@@ -27,8 +37,12 @@
         },
         {
             "affiliation": "Radboud University Medical Center",
-            "name": "Farzaneh Meimandi Parizi",
-            "orcid": "0000-0003-4230-7492"
+            "name": "Dario F. Marzella",
+            "orcid": "0000-0002-0043-3055"
+        },
+        {
+            "name": "João M. C. Teixeira",
+            "orcid": "0000-0002-9113-0622"
         },
         {
             "affiliation": "Radboud University Medical Center",
@@ -37,10 +51,11 @@
         }
     ],
     "keywords": [
-        "Graph Neural Networks",
-        "Convolutional Neural Networks",
-        "Protein-Protein Interface",
-        "Deeprank"
+        "Graph neural networks",
+        "Convolutional neural networks",
+        "Protein-protein interface",
+        "Single-residue variant",
+        "DeepRank"
     ],
     "license": {
         "id": "Apache-2.0"

CITATION.cff

@@ -44,17 +44,15 @@ authors:
     affiliation: Radboud University Medical Center
     orcid: 'https://orcid.org/0000-0002-2613-538X'
 abstract: >-
-  deeprank2 allows ranking of protein-protein
-  interface using a graph representation of the
-  contact residues or atoms. Graphs of such
-  interfaces are used to train graph neural networks
-  for the prediction of the experimental validity of
-  the interface.
+  DeepRank2 is an open-source deep learning
+  framework for data mining of protein-protein interfaces
+  or single-residue variants.
 keywords:
-  - Graph Neural Networks
-  - Convolutional Neural Networks
-  - Protein-Protein Interface
-  - Deeprank
+  - Graph neural networks
+  - Convolutional neural networks
+  - Protein-protein interface
+  - Single-residue variant
+  - DeepRank
 license: Apache-2.0
 commit: 4e8823758ba03f824b4281f5689cb6a335ab2f6c
 version: "2.0.0"

README.md

@@ -13,7 +13,7 @@
 
 ![alt-text](./deeprank2.png)
 
-DeepRank2 is an open-source deep learning (DL) framework for data mining of protein-protein interfaces (PPIs) or single-residue missense variants. This package is an improved and unified version of two previously developed packages: [DeepRank](https://github.com/DeepRank/deeprank) and [DeepRank-GNN](https://github.com/DeepRank/Deeprank-GNN).
+DeepRank2 is an open-source deep learning (DL) framework for data mining of protein-protein interfaces (PPIs) or single-residue variants (SRVs). This package is an improved and unified version of three previously developed packages: [DeepRank](https://github.com/DeepRank/deeprank), [DeepRank-GNN](https://github.com/DeepRank/Deeprank-GNN), and [DeepRank-Mut](https://github.com/DeepRank/DeepRank-Mut).
 
 DeepRank2 allows for transformation of (pdb formatted) molecular data into 3D representations (either grids or graphs) containing structural and physico-chemical information, which can be used for training neural networks. DeepRank2 also offers a pre-implemented training pipeline, using either [CNNs](https://en.wikipedia.org/wiki/Convolutional_neural_network) (for grids) or [GNNs](https://en.wikipedia.org/wiki/Graph_neural_network) (for graphs), as well as output exporters for evaluating performances.
 
@@ -40,7 +40,6 @@ DeepRank2 extensive documentation can be found [here](https://deeprank2.rtfd.io/
     - [Deeprank2 Package](#deeprank2-package)
     - [Test installation](#test-installation)
     - [Contributing](#contributing)
-  - [Quick start](#quick-start)
     - [Data generation](#data-generation)
     - [Datasets](#datasets)
       - [GraphDataset](#graphdataset)
@@ -98,15 +97,13 @@ Run `pytest tests/test_integration.py` for the quick test or just `pytest` for t
 
 If you would like to contribute to the package in any way, please see [our guidelines](CONTRIBUTING.rst).
 
-## Quick start
-
-The following section serves as a first guide to start using the package, using Protein-Protein Interface (PPI) queries as example.
-For an enhanced learning experience, we provide in-depth [tutorial notebooks](https://github.com/DeepRank/deeprank2/tree/main/tutorials) for generating PPI data, generating variants data, and for the training pipeline.
+The following section serves as a first guide to start using the package, using protein-protein Interface (PPI) queries
+as example. For an enhanced learning experience, we provide in-depth [tutorial notebooks](https://github.com/DeepRank/deeprank2/tree/main/tutorials) for generating PPI data, generating SVR data, and for the training pipeline.
 For more details, see the [extended documentation](https://deeprank2.rtfd.io/).
 
 ### Data generation
 
-For each protein-protein complex (or protein structure containing a missense variant), a query can be created and added to the `QueryCollection` object, to be processed later on. Different types of queries exist:
+For each protein-protein complex (or protein structure containing a SRV), a query can be created and added to the `QueryCollection` object, to be processed later on. Different types of queries exist:
 - In a `ProteinProteinInterfaceResidueQuery` and `SingleResidueVariantResidueQuery`, each node represents one amino acid residue.
 - In a `ProteinProteinInterfaceAtomicQuery` and `SingleResidueVariantAtomicQuery`, each node represents one atom within the amino acid residues.
 

deeprank2/query.py

@@ -96,7 +96,7 @@ def _check_pssm(pdb_path: str, pssm_paths: Dict[str, str], suppress: bool, verbo
 class Query:
 
     def __init__(self, model_id: str, targets: Optional[Dict[str, Union[float, int]]] = None, suppress_pssm_errors: bool = False):
-        """Represents one entity of interest, like a single residue variant or a protein-protein interface.
+        """Represents one entity of interest, like a single-residue variant or a protein-protein interface.
 
         :class:`Query` objects are used to generate graphs from structures, and they should be created before any model is loaded.
         They can have target values associated with them, which will be stored with the resulting graph.
@@ -388,7 +388,7 @@ def __init__(  # pylint: disable=too-many-arguments
         suppress_pssm_errors: bool = False,
     ):
         """
-        Creates a residue graph from a single residue variant in a .PDB file.
+        Creates a residue graph from a single-residue variant in a .PDB file.
 
         Args:
             pdb_path (str): The path to the PDB file.
@@ -507,7 +507,7 @@ def __init__(  # pylint: disable=too-many-arguments
         suppress_pssm_errors: bool = False,
     ):
         """
-        Creates an atomic graph for a single residue variant in a .PDB file.
+        Creates an atomic graph for a single-residue variant in a .PDB file.
 
         Args:
             pdb_path (str): The path to the .PDB file.

docs/getstarted.md

@@ -1,12 +1,12 @@
 # Get started
 
-The following section serves as a first guide to start using the package, using Protein-Protein Interface (PPI) queries as example.
-For an enhanced learning experience, we provide in-depth [tutorial notebooks](https://github.com/DeepRank/deeprank2/tree/main/tutorials) for generating PPI data, generating variants data, and for the training pipeline.
+The following section serves as a first guide to start using the package, using protein-protein interface (PPI) queries as example.
+For an enhanced learning experience, we provide in-depth [tutorial notebooks](https://github.com/DeepRank/deeprank2/tree/main/tutorials) for generating PPI data, generating SRVs data, and for the training pipeline.
 For more details, see the [extended documentation](https://deeprank2.rtfd.io/).
 
 ## Data generation
 
-For each protein-protein complex (or protein structure containing a missense variant), a query can be created and added to the `QueryCollection` object, to be processed later on. Different types of queries exist:
+For each protein-protein complex (or protein structure containing a SRV), a query can be created and added to the `QueryCollection` object, to be processed later on. Different types of queries exist:
 - In a `ProteinProteinInterfaceResidueQuery` and `SingleResidueVariantResidueQuery`, each node represents one amino acid residue.
 - In a `ProteinProteinInterfaceAtomicQuery` and `SingleResidueVariantAtomicQuery`, each node represents one atom within the amino acid residues.
 

docs/index.rst

@@ -1,7 +1,8 @@
 DeepRank2 |version| documentation
 ========================================
 
-DeepRank2 is an open-source deep learning (DL) framework for data mining of protein-protein interfaces (PPIs) or single-residue missense variants. This package is an improved and unified version of two previously developed packages: `DeepRank`_ and `DeepRank-GNN`_.
+DeepRank2 is an open-source deep learning (DL) framework for data mining of protein-protein interfaces (PPIs) or single-residue variants (SRVs).
+This package is an improved and unified version of three previously developed packages: `DeepRank`_, `DeepRank-GNN`_, and `DeepRank-Mut`_.
 
 DeepRank2 allows for transformation of (pdb formatted) molecular data into 3D representations (either grids or graphs) containing structural and physico-chemical information, which can be used for training neural networks. DeepRank2 also offers a pre-implemented training pipeline, using either `convolutional neural networks`_ (for grids) or `graph neural networks`_ (for graphs), as well as output exporters for evaluating performances. 
 
@@ -16,6 +17,7 @@ Main features:
 
 .. _DeepRank: https://github.com/DeepRank/deeprank
 .. _DeepRank-GNN: https://github.com/DeepRank/Deeprank-GNN
+.. _DeepRank-Mut: https://github.com/DeepRank/DeepRank-Mut
 .. _convolutional neural networks: https://en.wikipedia.org/wiki/Convolutional_neural_network
 .. _graph neural networks: https://en.wikipedia.org/wiki/Graph_neural_network
 .. _here: https://deeprank2.readthedocs.io/en/latest/features.html