Efficient Toxicity Prediction via Simple Features Using Shallow Neural Networks and Decision Trees

Karim, Abdul; Mishra, Avinash; Newton, M. A. Hakim; Sattar, Abdul

doi:10.1021/acsomega.8b03173

Cited by 56 publications

(56 citation statements)

References 71 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[74]. Abdul et al [75] developed a task-based chemical toxicity prediction framework, and used a decision tree to obtain an optimum number of features from a collection of thousands of them, which effectively help chemists perform prescreening of toxic compounds effectively.…”

Section: Classical Qsar Methodsmentioning

confidence: 99%

A Review on Applications of Computational Methods in Drug Screening and Design

2020

View full text Add to dashboard Cite

Drug development is one of the most significant processes in the pharmaceutical industry. Various computational methods have dramatically reduced the time and cost of drug discovery. In this review, we firstly discussed roles of multiscale biomolecular simulations in identifying drug binding sites on the target macromolecule and elucidating drug action mechanisms. Then, virtual screening methods (e.g., molecular docking, pharmacophore modeling, and QSAR) as well as structure-and ligand-based classical/de novo drug design were introduced and discussed. Last, we explored the development of machine learning methods and their applications in aforementioned computational methods to speed up the drug discovery process. Also, several application examples of combining various methods was discussed. A combination of different methods to jointly solve the tough problem at different scales and dimensions will be an inevitable trend in drug screening and design.Molecules 2020, 25, 1375 2 of 17 Biomolecular Simulations in Drug Screening and DesignThe Nobel Prize in Chemistry 2013 was awarded jointly to Martin Karplus, Michael Levitt, and Arieh Warshel for their pioneering contributions in the development of multiscale models for complex biochemical systems, recognizing the important role that theory and computational methods play as a direct and necessary complement to experiments [12]. Further, applications of biomolecular simulations in identifying drug binding sites and elucidating the molecular mechanisms of diseases have been subject to rapid developments [13][14][15].Depending on the biological problems to be studied, multiscale models will be used in biomolecular simulations. The combination of quantum mechanics (QM) and molecular mechanics (MM) (QM/MM) can be used to study the electronic properties [16], simulate chemical reactions (e.g., the enzyme catalysis mechanism [17]), and calculate spectra [18] in a single simulation, which can be used to elucidate the action mechanism of certain drugs. Another widely used biomolecular method is molecular dynamics (MD) simulation [19][20][21][22][23][24], which applies empirical molecular mechanics (MM) force fields and is based on classical Newtonian mechanics. According to different accuracy requirements, all-atom (AA), united-atom (UA), and coarse-grained (CG) MD simulations as well as explicit/implicit solvent models, which allow simulations of temporal and spatial scales, can be used to facilitate the drug discovery [25,26]. Generally, MD simulations have been used for the identification of potential drug binding sites on target proteins, the calculation of binding free energy between target proteins and drug molecules, the action mechanism of drug molecules, etc. [27,28]. However, it is worth mentioning that MD simulations are also limited to time and length scales. Currently, AAMD simulations can explore time-dependent phenomena of large systems such as viral capsids in atomic detail as long as microseconds or even milliseconds [21,29,30]. Therefore, different types of ...

show abstract

Section: Classical Qsar Methodsmentioning

confidence: 99%

A Review on Applications of Computational Methods in Drug Screening and Design

2020

View full text Add to dashboard Cite

show abstract

“…[71] who showed that positive transfer learning is conditioned by sharing a significant amount of input data whose labels are correlated. In general, other studies [72,73,74,75] reported that FNN performs the best for a variety of chemoinformatics problem, but only for some metrics and datasets.…”

Section: Deep Learning For Chemoinformaticsmentioning

confidence: 91%

Evaluation of network architecture and data augmentation methods for deep learning in chemogenomics

Playe

Stoven

2019

Preprint

View full text Add to dashboard Cite

Among virtual screening methods that have been developed to facilitate the drug discovery process, chemogenomics presents the particularity to tackle the question of predicting ligands for proteins, at at scales both in the protein and chemical spaces. Therefore, in addition to to predict drug candidates for a given therapeutic protein target, like more classical ligand-based or receptor-based methods do, chemogenomics can also predict off-targets at the proteome level, and therefore, identify potential side-effects or drug repositioning opportunities. In this study, we study and compare machinelearning and deep learning approaches for chemogenomics, that are applicable to screen large sets of compounds against large sets of druggable proteins. State-of-the-art drug chemogenomics methods rely on expert-based chemical and protein descriptors or similarity measures. The recent development of deep learning approaches enabled to design algorithms that learn numerical abstract representations of molecular graphs and protein sequences in an end-to-end fashion, i.e., so that the learnt features optimise the objective function of the drug-target interaction prediction task. In this paper, we address drug-target interaction prediction at the druggable proteome-level, with what we define as the chemogenomic neuron network. This network consists of a feed-forward neuron network taking as input the combination of molecular and protein representations learnt by molecular graph and protein sequence encoders. We first propose a standard formulation of this chemogenomic neuron network. Then, we compare the performances of the standard chemogenomic network to reference deep learning or shallow (machine-learning without deep learning) methods. In particular, we show that such a representation learning approach is competitive with state-of-the-art chemogenomics with shallow methods, but not ultimately superior. We evaluate the most promising neuron network architectures and data augmentation techniques, such as multi-view and transfer learning, to improve the prediction performance of the chemogenomic network. Our results shed new insights on the design of chemogenomics approaches based on representation learning algorithms. Most importantly, we conclude from our observations that a promising research direction is to integrate heterogeneous sources of data such as various bioactivity datasets, or independently, multiple molecule and protein attribute views, instead of focusing on sophisticated, yet intuitively relevant, encoder's neuron network architecture.

show abstract

“…SwissADME webserver was used for computing ADMET properties of top-scoring compounds such as Lipinski rule of 5 [50], gastro-intestinal (GI) absorption, blood-brain barrier (BBB) permeant, cytochrome inhibition [51,52]. The SMILES format of these compounds was submitted to SwissADME webserver.…”

Section: Lipinski's Rule and Admet Predictionmentioning

confidence: 99%

Identification of potential inhibitors of coronavirus hemagglutinin-esterase using molecular docking, molecular dynamics simulation and binding free energy calculation

et al. 2020

View full text Add to dashboard Cite

The pandemic outbreak of the Corona viral infection has become a critical global health issue. Biophysical and structural evidence shows that spike protein possesses a high binding affinity towards host angiotensin-converting enzyme 2 and viral hemagglutinin-acetylesterase (HE) glycoprotein receptor. We selected HE as a target in this study to identify potential inhibitors using a combination of various computational approaches such as molecular docking, ADMET analysis, dynamics simulations and binding free energy calculations. Virtual screening of NPACT compounds identified 3,4,5-Trihydroxy-1,8-bis[(2R,3R)-3,5,7-trihydroxy-3,4-dihydro-2H-chromen-2-yl]benzo[7]annulen-6-one, Silymarin, Withanolide D, Spirosolane and Oridonin as potential HE inhibitors with better binding energy. Furthermore, molecular dynamics simulations for 100 ns time scale revealed that most of the key HE contacts were retained throughout the simulations trajectories. Binding free energy calculations using MM/PBSA approach ranked the top-five potential NPACT compounds which can act as effective HE inhibitors.

show abstract

Efficient Toxicity Prediction via Simple Features Using Shallow Neural Networks and Decision Trees

Cited by 56 publications

References 71 publications

A Review on Applications of Computational Methods in Drug Screening and Design

A Review on Applications of Computational Methods in Drug Screening and Design

Evaluation of network architecture and data augmentation methods for deep learning in chemogenomics

Identification of potential inhibitors of coronavirus hemagglutinin-esterase using molecular docking, molecular dynamics simulation and binding free energy calculation

Contact Info

Product

Resources

About