Binding Affinity Prediction by Pairwise Function Based on Neural Network

Zhu, Fangqiang; Zhang, Xiaohua; Allen, Jonathan; Jones, Derek; Lightstone, Felice C.

doi:10.1021/acs.jcim.0c00026

Cited by 55 publications

(48 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is important to note that, in contrast to some famous MLbased scoring functions which have been trained based on atom pair contact counts, such as RF-Score, [16] CScore, [36] and OnionNet, [24] our featurization model includes the significance of differences in interatomic distance values for each atom-pair contact and discriminates between close and far contacts by the above weighting scheme -the closer contacts will gain more weight and the farther distances will have less weight, in line with chemical intuition. It should be added here that, very recently Zhu et al [37] have used the inverse of distance and some atomic properties as inputs for training Neural Networks to predict protein-ligand binding affinity. Finally, the contribution of each particular ligand-protein atom type pair to the complex featurization (x i,j ) was derived from a linear summation of all same atom type pairs in the complex.…”

Section: Defining Descriptorsmentioning

confidence: 99%

ET‐score: Improving Protein‐ligand Binding Affinity Prediction Based on Distance‐weighted Interatomic Contact Features Using Extremely Randomized Trees Algorithm

Rayka

Karimi‐Jafari

Firouzi

2021

Molecular Informatics

View full text Add to dashboard Cite

The molecular docking simulation is a key computational tool in modern drug discovery research that its predictive performance strongly depends on the employed scoring functions. Many recent studies have shown that the application of machine learning algorithms in the development of scoring functions has led to a significant improvement in docking performance. In this work, we introduce a new machine learning (ML) based scoring function called ET-Score, which employs the distanceweighted interatomic contacts between atom type pairs of the ligand and the protein for featurizing protein À ligand complexes and Extremely Randomized Trees algorithm for the training process. The performance of ET-Score is compared with some successful ML-based scoring functions and several popular classical scoring functions on the PDBbind 2016v core set. It is shown that our ET-Score model (with Pearson's correlation of 0.827 and RMSE of 1.332) achieves very good performance in comparison with most of the ML-based scoring functions and all classical scoring functions despite its extremely low computational cost. ET-Score's codes are freely available on the web at https://github.com/miladrayka/ET_Score.

show abstract

Section: Defining Descriptorsmentioning

confidence: 99%

ET‐score: Improving Protein‐ligand Binding Affinity Prediction Based on Distance‐weighted Interatomic Contact Features Using Extremely Randomized Trees Algorithm

Rayka

Karimi‐Jafari

Firouzi

2021

Molecular Informatics

View full text Add to dashboard Cite

show abstract

“…Also, simply the protein-ligand atom pairs together with their distances can be used as input. In the work by Zhu et al [ 98 ], all atom pair energy contributions are summed, where the contributions themselves are learned through a neural network considering the properties of the two atoms and their distances. Similarly, Pereira et al [ 99 ] introduced the atom context method to represent the environment of the interacting atoms, i.e., atom and amino acid embeddings.…”

Section: Methods and Datamentioning

confidence: 99%

Deep Learning in Virtual Screening: Recent Applications and Developments

Kimber

Chen

Volkamer

2021

IJMS

133

View full text Add to dashboard Cite

Drug discovery is a cost and time-intensive process that is often assisted by computational methods, such as virtual screening, to speed up and guide the design of new compounds. For many years, machine learning methods have been successfully applied in the context of computer-aided drug discovery. Recently, thanks to the rise of novel technologies as well as the increasing amount of available chemical and bioactivity data, deep learning has gained a tremendous impact in rational active compound discovery. Herein, recent applications and developments of machine learning, with a focus on deep learning, in virtual screening for active compound design are reviewed. This includes introducing different compound and protein encodings, deep learning techniques as well as frequently used bioactivity and benchmark data sets for model training and testing. Finally, the present state-of-the-art, including the current challenges and emerging problems, are examined and discussed.

show abstract

“…However, large chemical libraries can be screened earlier, starting with hit identification. There has also been some success applying machine learning (ML) to predict small molecule binding to the protein target (Zhu et al, 2020). LBDD is used when no structural information is available, and initial hit identification is frequently acquired experimentally by running high-throughput biochemical assays.…”

Section: Overview Of the Problemmentioning

confidence: 99%

Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

Jacobs

Moon

McLoughlin

et al. 2021

The International Journal of High Performance Computing Applica

Self Cite

View full text Add to dashboard Cite

We improved the quality and reduced the time to produce machine learned models for use in small molecule antiviral design. Our globally asynchronous multi-level parallel training approach strong scales to all of Sierra with up to 97.7% efficiency. We trained a novel, character-based Wasserstein autoencoder that produces a higher quality model trained on 1.613 billion compounds in 23 minutes while the previous state of the art takes a day on 1 million compounds. Reducing training time from a day to minutes shifts the model creation bottleneck from computer job turnaround time to human innovation time. Our implementation achieves 318 PFLOPs for 17.1% of half-precision peak. We will incorporate this model into our molecular design loop enabling the generation of more diverse compounds; searching for novel, candidate antiviral drugs improves and reduces the time to synthesize compounds to be tested in the lab.

show abstract

Binding Affinity Prediction by Pairwise Function Based on Neural Network

Cited by 55 publications

References 29 publications

ET‐score: Improving Protein‐ligand Binding Affinity Prediction Based on Distance‐weighted Interatomic Contact Features Using Extremely Randomized Trees Algorithm

ET‐score: Improving Protein‐ligand Binding Affinity Prediction Based on Distance‐weighted Interatomic Contact Features Using Extremely Randomized Trees Algorithm

Deep Learning in Virtual Screening: Recent Applications and Developments

Enabling rapid COVID-19 small molecule drug design through scalable deep learning of generative models

Contact Info

Product

Resources

About