fix citations

paper/paper.bib

@@ -158,7 +158,7 @@ @article{dove_gnn
 
 @article{fout_protein_nodate,
 title = {Protein Interface Prediction using Graph Convolutional Networks},
-author = {Fout, Alex and Byrd, Jonathon and Shariat, Basir and Ben-Hur, Asa},
+author = {Fout, Alex and Byrd, Jonathon and Shariat, Basir and Ben/-Hur, Asa},
 langid = {english},
 file = {Fout et al. - Protein Interface Prediction using Graph Convoluti.pdf:/Users/giuliacrocioni/Zotero/storage/RGUZWGRE/Fout et al. - Protein Interface Prediction using Graph Convoluti.pdf:application/pdf},
 }
@@ -192,7 +192,7 @@ @article{shroff
 }
 
 @article{mut_cnn,
-author = {B. Li and YT. Yang and JA. Capra and MB. Gerstein},
+author = {Li, B. and Yang, YT. and Capra, JA. and Gerstein, MB.},
 title = {Predicting changes in protein thermodynamic stability upon point mutation with deep 3D convolutional neural networks},
 journal = {PLoS Comput Biol.},
 year = {2020},
@@ -201,7 +201,7 @@ @article{mut_cnn
 }
 
 @INPROCEEDINGS {deepatom,
-author = {Y. Li and M. A. Rezaei and C. Li and X. Li},
+author = {Li, Y. and Rezaei, M. A. and Li, C. and Li, X.},
 booktitle = {2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)},
 title = {DeepAtom: A Framework for Protein-Ligand Binding Affinity Prediction},
 year = {2019},
@@ -248,9 +248,3 @@ @article{netket
 	title = {{NetKet} 3: Machine Learning Toolbox for Many-Body Quantum Systems},
 	journal = {{SciPost} Physics Codebases}
 }
-
-@misc{hdf5,
-  title = {HDF5},
-  howpublished = {\url{https://www.hdfgroup.org/solutions/hdf5/}},
-  note = {Accessed: 2023-09-15}
-}

paper/paper.md

@@ -86,7 +86,7 @@ As input, DeepRank2 takes [PDB-formatted](https://www.cgl.ucsf.edu/chimera/docs/
 -  PPIs, for mining interaction patterns within protein-protein complexes;
 -  SRVs, for mining mutation phenotypes within protein structures.
 
-Graphs can either be used directly or mapped to volumetric grids (i.e., 3D image-like representations). Then the physico-chemical and geometrical features for the grids and/or graphs are computed and assigned to each node and edge. The user can choose which features to generate from several pre-existing options defined in the package, or define custom features modules, as explained in the documentation. Examples of pre-defined node features are the type of the amino acid, its size and polarity, as well as more complex features such as its buried surface area and secondary structure features. Examples of pre-defined edge features are distance, covalency, and potential energy. A detailed list of predefined features can be found in the [documentation's features page](https://deeprank2.readthedocs.io/en/latest/features.html). Multiple CPUs can be used to parallelize and speed up the featurization process. The processed data are saved into HDF5 files, designed to efficiently store and organize big data [@hdf5]. Users can then use the data for any ML or DL framework suited for the application. Specifically, graphs can be used for the training of GNNs, and 3D grids can be used for the training of CNNs.
+Graphs can either be used directly or mapped to volumetric grids (i.e., 3D image-like representations). Then the physico-chemical and geometrical features for the grids and/or graphs are computed and assigned to each node and edge. The user can choose which features to generate from several pre-existing options defined in the package, or define custom features modules, as explained in the documentation. Examples of pre-defined node features are the type of the amino acid, its size and polarity, as well as more complex features such as its buried surface area and secondary structure features. Examples of pre-defined edge features are distance, covalency, and potential energy. A detailed list of predefined features can be found in the [documentation's features page](https://deeprank2.readthedocs.io/en/latest/features.html). Multiple CPUs can be used to parallelize and speed up the featurization process. The processed data are saved into HDF5 files, designed to efficiently store and organize big data. Users can then use the data for any ML or DL framework suited for the application. Specifically, graphs can be used for the training of GNNs, and 3D grids can be used for the training of CNNs.
 
 DeepRank2 also provides convenient pre-implemented modules for training simple [PyTorch](https://pytorch.org/)-based GNNs and CNNs using the data generated in the previous step. Alternatively, users can implement custom PyTorch networks in the DeepRank package (or export the data to external software). Data can be loaded across multiple CPUs, and the training can be run on GPUs. The data stored within the HDF5 files are read into customized datasets, and the user-friendly API allows for selection of individual features (from those generated above), definition of the targets, and the predictive task (classfication or regression), among other settings. Then the datasets can be used for training, validating, and testing the chosen neural network. The final model and results can be saved using built-in data exporter modules.