KDEEP: Protein-Ligand Absolute Binding Affinity Prediction via 3D-Convolutional Neural Networks

By J. Jiménez, Miha Škalič, Gerard Martínez-Rosell, G. de Fabritiis. 2018

726 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Computational Chemistry & Drug Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Anastasiia V. Sadybekov
2. Mostafa Karimi
3. Vignesh Ram Somnath
4. Fergus Boyles
5. F. Silva-Jr
6. Paula Jofily
7. Tomohide Masuda
8. Andreas Krause

In Materials Chemistry

1. Anastasiia V. Sadybekov
2. Mostafa Karimi
3. Vignesh Ram Somnath
4. Fergus Boyles
5. F. Silva-Jr
6. Paula Jofily
7. Tomohide Masuda
8. John A. Capra

In Molecular Biology

1. David L. Mobley
2. Fergus Boyles
3. F. Silva-Jr
4. Paula Jofily
5. Pedro H. M. Torres
6. A. C. Sodero
7. Anastasiia V. Sadybekov
8. Mostafa Karimi

In Computational Chemistry & Drug Discovery

1. Anastasiia V. Sadybekov
2. Mostafa Karimi
3. Vignesh Ram Somnath
4. F. Silva-Jr
5. Paula Jofily
6. Tomohide Masuda
7. John A. Capra
8. Andreas Krause

Citations in the corpus

• An overview of deep learning in medical imaging focusing on MRI (2018, background): “seizures [17] and cardiac arrests [18], to computer-aided detection [19] and diagnosis [20] supporting clinical decision making and survival analysis [21], to drug discovery [22] and as an aid in therapy selection and pharmacogenomics [23], to increased operational efficiency [24], stratified care d”
• Multi-Scale Representation Learning on Proteins (2022, methodology): “3D convolutional neural networks have been utilized for protein quality assessment [Derevyanko et al., 2018], protein contact prediction [Townshend et al., 2019] and protein-ligand binding affinity tasks [Ragoza et al., 2017, Jiménez et al., 2018, Townshend et al., 2020].”
• DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks (2018, methodology): “(Jimenez et al., 2018) also used 3D CNN with molecular representation of 3D voxels assigned to various physicochemical property channels.”
• Best practices for constructing, preparing, and evaluating protein-ligand binding affinity benchmarks [Article v0.2] (2021, methodology): “In the absence of other significant efforts to curate benchmark sets, this set (often called the "Schrödinger JACS set") has become the de facto dataset for most large scale RBFE reports, used to compare the performance of Amber/TI calculations [23], Flare’s FEP (a collaboration between Cresset and ”
• Predicting changes in protein thermodynamic stability upon point mutation with deep 3D convolutional neural networks (2020, methodology): “To predict the ∆∆G of a point mutation, we take advantage of recent advances in deep learning 120 for computer vision (29) and the successes of deep convolutional neural networks in biophysical 121 problems (27, 28, 30-32).”
• Best Practices for Constructing, Preparing, and Evaluating Protein-Ligand Binding Affinity Benchmarks [Article v1.0] (2021, methodology): “In the absence of other significant efforts to curate benchmark sets, this set (often called the "Schrödinger JACS set") has become the de facto dataset for most large scale RBFE reports, used to compare the performance of Amber/TI calculations [23], Flare’s FEP (a collaboration between Cresset and ”
• Protein-Ligand Interaction Graphs: Learning from Ligand-Shaped 3D Interaction Graphs to Improve Binding Affinity Prediction (2022, methodology): “These models employ a diverse set of ML architectures and features, from classical ML techniques such as random forests and gradient boosted trees ([8, 9, 10]) to deep learning (DL) models ([11, 12, 13]).”