ACS Publications. Most Trusted. Most Cited. Most Read
My Activity

Figure 1Loading Img
RETURN TO ISSUEPREVMachine Learning and...Machine Learning and Deep LearningNEXT

GalaxyWater-CNN: Prediction of Water Positions on the Protein Structure by a 3D-Convolutional Neural Network

Cite this: J. Chem. Inf. Model. 2022, 62, 13, 3157–3168
Publication Date (Web):June 24, 2022
Copyright © 2022 American Chemical Society

    Article Views





    Other access options
    Supporting Info (1)»


    Abstract Image

    Proteins interact with numerous water molecules to perform their physiological functions in biological organisms. Most water molecules act as solvent media; hence, their roles may be considered implicitly in theoretical treatments of protein structure and function. However, some water molecules interact intimately with proteins and require explicit treatment to understand their effects. Most physics-based computational methods are limited in their ability to accurately locate water molecules on protein surfaces because of inaccurate energy functions. Instead of relying on an energy function, this study attempts to learn the locations of water molecules from structural data. GalaxyWater-convolutional neural network (CNN) predicts water positions on protein chains, protein–protein interfaces, and protein–compound binding sites using a 3D-CNN model that is trained to generate a water score map on a given protein structure. The training data are compiled from high-resolution protein crystal structures resolved together with water molecules. GalaxyWater-CNN shows improved water prediction performance both in the coverage of crystal water molecules and in the accuracy of the predicted water positions when compared with previous energy-based methods. This method shows a superior performance in predicting water molecules that form hydrogen-bond networks precisely. The web service and the source code of this water prediction method are freely available at and, respectively.

    Read this article

    To access this article, please review the available access options below.

    Get instant access

    Purchase Access

    Read this article for 48 hours. Check out below using your ACS ID or as a guest.


    Access through Your Institution

    You may have access to this article through your institution.

    Your institution does not have access to this content. You can change your affiliated institution below.

    Supporting Information

    Jump To

    The Supporting Information is available free of charge at

    • Variation of the observed number of water molecules in the crystal structures; performance comparison showing the effects of omitting certain features of the network model of GalaxyWater-CNN; performance comparison between GalaxyWater-CNN and GIST; and performance of GalaxtWater-CNN at different score cutoff values (PDF)

    Terms & Conditions

    Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system:

    Cited By

    This article is cited by 9 publications.

    1. Andreas Zamanos, George Ioannakis, Ioannis Z. Emiris. HydraProt: A New Deep Learning Tool for Fast and Accurate Prediction of Water Molecule Positions for Protein Structures. Journal of Chemical Information and Modeling 2024, 64 (7) , 2594-2611.
    2. Bing Rao, Xuan Yu, Jie Bai, Jun Hu. E2EATP: Fast and High-Accuracy Protein–ATP Binding Residue Prediction via Protein Language Model Embedding. Journal of Chemical Information and Modeling 2024, 64 (1) , 289-300.
    3. Petr Kouba, Pavel Kohout, Faraneh Haddadi, Anton Bushuiev, Raman Samusevich, Jiri Sedlar, Jiri Damborsky, Tomas Pluskal, Josef Sivic, Stanislav Mazurenko. Machine Learning-Guided Protein Engineering. ACS Catalysis 2023, 13 (21) , 13863-13895.
    4. Rodrigo S. Hormazabal, Jeong Won Kang, Kiho Park, Dae Ryook Yang. Not from Scratch: Predicting Thermophysical Properties through Model-Based Transfer Learning Using Graph Convolutional Networks. Journal of Chemical Information and Modeling 2022, 62 (22) , 5411-5424.
    5. Brajesh K. Rai, James R. Apgar, Eric M. Bennett. Low-data interpretable deep learning prediction of antibody viscosity using a biophysically meaningful representation. Scientific Reports 2023, 13 (1)
    6. Kochi Sato, Mao Oide, Masayoshi Nakasako. Prediction of hydrophilic and hydrophobic hydration structure of protein by neural network optimized using experimental data. Scientific Reports 2023, 13 (1)
    7. Yasunari Matsuzaka, Ryu Yashiro. In Silico Protein Structure Analysis for SARS-CoV-2 Vaccines Using Deep Learning. BioMedInformatics 2023, 3 (1) , 54-72.
    8. Changsoo Lee, Jinsol Yang, Sohee Kwon, Chaok Seok. GalaxyDock2‐HEME : P rotein–ligand docking for heme proteins. Journal of Computational Chemistry 2023, 76
    9. Piotr Misiak, Daniel Szempruch. Automated Quality Inspection of High Voltage Equipment Supported by Machine Learning and Computer Vision. 2022, 211-222.

    Pair your accounts.

    Export articles to Mendeley

    Get article recommendations from ACS based on references in your Mendeley library.

    Pair your accounts.

    Export articles to Mendeley

    Get article recommendations from ACS based on references in your Mendeley library.

    You’ve supercharged your research process with ACS and Mendeley!

    STEP 1:
    Click to create an ACS ID

    Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

    Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

    Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

    Your Mendeley pairing has expired. Please reconnect