3D Deep Learning for Biological Function Prediction from Physical Fields

Golkov, Vladimir; Skwark, Marcin J.; Mirchev, Atanas; Dikov, Georgi; Geanes, Alexander R.; Mendenhall, Jeffrey L.; Meiler, Jens; Cremers, Daniel

doi:10.1109/3dv50981.2020.00103

Cited by 11 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Molecular representations for processing by 3D CNN can be constructed in several ways: each atom or a group of atoms can be represented either by a separate channel or a channel which can represent some kind of superposition of atoms. For example, one can calculate interactions with a probe atom to construct 3D molecular field or use some physicochemical or DFT (3D electron density) calculations as 3D filed representations. , Both of these approaches have limitations: atom-to-channel representation leads to dramatic increase in the number of input channels, which are crucial for memory consumption. It is also inefficient because many channels are empty or sparse.…”

Section: Introductionmentioning

confidence: 99%

graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes

et al. 2020

View full text Add to dashboard Cite

In this work, we present graph-convolutional neural networks for the prediction of binding constants of protein−ligand complexes. We derived the model using multi task learning, where the target variables are the dissociation constant (K d ), inhibition constant (K i ), and half maximal inhibitory concentration (IC 50 ). Being rigorously trained on the PDBbind dataset, the model achieves the Pearson correlation coefficient of 0.87 and the RMSE value of 1.05 in pK units, outperforming recently developed 3D convolutional neural network model K deep .

show abstract

Section: Introductionmentioning

confidence: 99%

graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Besides the above rotation and translation invariant fingerprints, Gaussian-based representation (used in ROCS and SimG) is another example that strengthens this argument. When it further comes to voxelized representation, , it is a common practice to integrate this representation with supervised convolutional DNN,and promising results have been demonstrated on the prediction of the biological target or binding affinity for small molecules. − Despite all the above, there is no 3D fingerprint learned by DNN reported thus far.…”

Section: Introductionmentioning

confidence: 99%

TF3P: Three-Dimensional Force Fields Fingerprint Learned by Deep Capsular Network

Wang

Lai

et al. 2020

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Molecular fingerprints are the workhorse in ligand-based drug discovery. In recent years, an increasing number of research papers reported fascinating results on using deep neural networks to learn 2D molecular representations as fingerprints. It is anticipated that the integration of deep learning would also contribute to the prosperity of 3D fingerprints. Here, we unprecedentedly introduce deep learning into 3D small molecule fingerprints, presenting a new one we termed as the threedimensional force fields fingerprint (TF3P). TF3P is learned by a deep capsular network whose training is in no need of labeled data sets for specific predictive tasks. TF3P can encode the 3D force fields information of molecules and demonstrates the stronger ability to capture 3D structural changes, to recognize molecules alike in 3D but not in 2D, and to identify similar targets inaccessible by other 2D or 3D fingerprints based on only ligands similarity. Furthermore, TF3P is compatible with both statistical models (e.g., similarity ensemble approach) and machine learning models. Altogether, we report TF3P as a new 3D small molecule fingerprint with a promising future in ligand-based drug discovery. All codes are written in Python and available at https://github.com/canisw/ tf3p.

show abstract

“…With excellent performance in imaging, speech, machine translation, etc ( Minar and Naher, 2018 ), DL has entered into many biological fields, including genes, proteins, metabolites, microbiomes, and population-wide genetic variation, synthetic biology, drug discovery, and diseases ( Alkawaa et al., 2018 ; Golkov et al, 2020 ; Hill et al., 2018 ; Zeng et al., 2021 ). The promising DL methods include capsule networks ( Inokuma et al., 2010 ; Xi et al., 2017 ), multitask learning ( Antropova et al., 2017 ; Wang et al., 2015b ; Zhu et al., 2016 ), GANs, self-encoding decoders ( Marchi et al., 2015 ; Wang et al., 2018 ; Xu et al., 2014 ; Yao et al., 2017 ; Zhao et al., 2016 ), Variational AutoEncoders (VAEs) ( Panych et al., 2015 ), Long Short Term Memory Networks (LSTMs) ( Baytas et al., 2017 ; Gers and Schmidhuber, 2001 ; Graves et al., 2005 ; Yildirim, 2018 ), transfer learning ( Fernandes et al., 2017 ; Pan and Yang, 2010 ; Paul et al., 2016 ; Zoph et al., 2016 ), deep neural networks (DNNs) ( Yoshioka et al., 2014 ), and CNNs ( Horváth et al., 2017 ; Luo, 2015 ; Parashar et al, 2017 ; Wang, 2013 ; Xue et al., 2016 ).…”

Section: Resultsmentioning

confidence: 99%

Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models

et al. 2021

View full text Add to dashboard Cite

Summary Early quantitative structure-activity relationship (QSAR) technologies have unsatisfactory versatility and accuracy in fields such as drug discovery because they are based on traditional machine learning and interpretive expert features. The development of Big Data and deep learning technologies significantly improve the processing of unstructured data and unleash the great potential of QSAR. Here we discuss the integration of wet experiments (which provide experimental data and reliable verification), molecular dynamics simulation (which provides mechanistic interpretation at the atomic/molecular levels), and machine learning (including deep learning) techniques to improve QSAR models. We first review the history of traditional QSAR and point out its problems. We then propose a better QSAR model characterized by a new iterative framework to integrate machine learning with disparate data input. Finally, we discuss the application of QSAR and machine learning to many practical research fields, including drug development and clinical trials.

show abstract

3D Deep Learning for Biological Function Prediction from Physical Fields

Cited by 11 publications

References 20 publications

graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes

graphDelta: MPNN Scoring Function for the Affinity Prediction of Protein–Ligand Complexes

TF3P: Three-Dimensional Force Fields Fingerprint Learned by Deep Capsular Network

Comprehensive strategies of machine-learning-based quantitative structure-activity relationship models

Contact Info

Product

Resources

About