Machine Learning Approaches for Quality Assessment of Protein Structures

Chen, Jiarui; Siu, Shirley W. I.

doi:10.3390/biom10040626

Cited by 20 publications

(9 citation statements)

References 101 publications

(166 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic idea of machine learning (ML) is to reproduce the human learning process by computer algorithms. Most ML algorithms can be classified into four types [ 19 , 29 ]: supervised learning, unsupervised learning, semi-supervised learning and reinforcement learning. The most commonly used method is supervised learning.…”

Section: Methodsmentioning

confidence: 99%

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Chen

et al. 2021

J Cheminform

Self Cite

View full text Add to dashboard Cite

As safety is one of the most important properties of drugs, chemical toxicology prediction has received increasing attentions in the drug discovery research. Traditionally, researchers rely on in vitro and in vivo experiments to test the toxicity of chemical compounds. However, not only are these experiments time consuming and costly, but experiments that involve animal testing are increasingly subject to ethical concerns. While traditional machine learning (ML) methods have been used in the field with some success, the limited availability of annotated toxicity data is the major hurdle for further improving model performance. Inspired by the success of semi-supervised learning (SSL) algorithms, we propose a Graph Convolution Neural Network (GCN) to predict chemical toxicity and trained the network by the Mean Teacher (MT) SSL algorithm. Using the Tox21 data, our optimal SSL-GCN models for predicting the twelve toxicological endpoints achieve an average ROC-AUC score of 0.757 in the test set, which is a 6% improvement over GCN models trained by supervised learning and conventional ML methods. Our SSL-GCN models also exhibit superior performance when compared to models constructed using the built-in DeepChem ML methods. This study demonstrates that SSL can increase the prediction power of models by learning from unannotated data. The optimal unannotated to annotated data ratio ranges between 1:1 and 4:1. This study demonstrates the success of SSL in chemical toxicity prediction; the same technique is expected to be beneficial to other chemical property prediction tasks by utilizing existing large chemical databases. Our optimal model SSL-GCN is hosted on an online server accessible through: https://app.cbbio.online/ssl-gcn/home.

show abstract

Section: Methodsmentioning

confidence: 99%

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Chen

et al. 2021

J Cheminform

Self Cite

View full text Add to dashboard Cite

show abstract

“…ML and deep learning are used for the classification of protein, structural determination, and protein‐ligand binding affinity. These two approaches (ML and deep learning) work on physiochemical, energy, and statistical aspects combining multiple types of information (Chen & Siu, 2020). ML approaches play a significant role in the modeling of the 3D structure of the target used in drug discovery programs.…”

Section: Recent Advances and Limitationsmentioning

confidence: 99%

Machine learning approaches and their applications in drug discovery and design

et al. 2022

View full text Add to dashboard Cite

This review is focused on several machine learning approaches used in chemoinformatics. Machine learning approaches provide tools and algorithms to improve drug discovery. Many physicochemical properties of drugs like toxicity, absorption, drug‐drug interaction, carcinogenesis, and distribution have been effectively modeled by QSAR techniques. Machine learning is a subset of artificial intelligence, and this technique has shown tremendous potential in the field of drug discovery. Techniques discussed in this review are capable of modeling non‐linear datasets, as well as big data of increasing depth and complexity. Various machine learning‐based approaches are being used for drug target prediction, modeling the structure of drug target, binding site prediction, ligand‐based similarity searching, de novo designing of ligands with desired properties, developing scoring functions for molecular docking, building QSAR model for biological activity prediction, and prediction of pharmacokinetic and pharmacodynamic properties of ligands. In recent years, these predictive tools and models have achieved good accuracy. By the use of more related input data, relevant parameters, and appropriate algorithms, the accuracy of these predictions can be further improved.

show abstract

“…In recent years, there have been significant improvements in the performance of estimating model accuracy (EMA) algorithms partly due to the application of Machine Learning, and EMA methods based on ML have been consistently ranked among better predictors. Please see Chen and Siu [ 67 ] for details about machine learning approaches (and a few Deep Learning approaches) published until 2019 for quality assessment of protein structures. Here, we summarize some recent DL-based advances for QA and EMA.…”

Section: Deep Learning-based Advances In Various Steps Of Protein Structure Prediction Pipelinementioning

confidence: 99%

Deep Learning-Based Advances in Protein Structure Prediction

Pakhrin

Shrestha

Adhikari

et al. 2021

IJMS

View full text Add to dashboard Cite

Obtaining an accurate description of protein structure is a fundamental step toward understanding the underpinning of biology. Although recent advances in experimental approaches have greatly enhanced our capabilities to experimentally determine protein structures, the gap between the number of protein sequences and known protein structures is ever increasing. Computational protein structure prediction is one of the ways to fill this gap. Recently, the protein structure prediction field has witnessed a lot of advances due to Deep Learning (DL)-based approaches as evidenced by the success of AlphaFold2 in the most recent Critical Assessment of protein Structure Prediction (CASP14). In this article, we highlight important milestones and progresses in the field of protein structure prediction due to DL-based methods as observed in CASP experiments. We describe advances in various steps of protein structure prediction pipeline viz. protein contact map prediction, protein distogram prediction, protein real-valued distance prediction, and Quality Assessment/refinement. We also highlight some end-to-end DL-based approaches for protein structure prediction approaches. Additionally, as there have been some recent DL-based advances in protein structure determination using Cryo-Electron (Cryo-EM) microscopy based, we also highlight some of the important progress in the field. Finally, we provide an outlook and possible future research directions for DL-based approaches in the protein structure prediction arena.

show abstract

Machine Learning Approaches for Quality Assessment of Protein Structures

Cited by 20 publications

References 101 publications

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network

Machine learning approaches and their applications in drug discovery and design

Deep Learning-Based Advances in Protein Structure Prediction

Contact Info

Product

Resources

About