Convolutional Neural Network-based Virtual Screening

An insight into in silico strategies used for exploration of medicinal utility and toxicology of nanomaterials

Nanomaterials (NMs) and the exploration of their comprehensive uses is an emerging research area of interest. They have improved physicochemical and biological properties and diverse functionality owing to their unique shape and size and therefore they are being explored for their enormous uses, particularly as medicinal and therapeutic agents. Nanoparticles (NPs) including metal and metal oxide-based NPs have received substantial consideration because of their biological applications. Computer-aided drug design (CADD) involving different strategies like homology modelling, molecular docking, virtual screening (VS), quantitative structure-activity relationship (QSAR) etc. and virtual screening hold significant importance in CADD used for lead identification and target identification. Despite holding importance, there are very few computational studies undertaken so far to explore their binding to the target proteins and macromolecules. Although the structural properties of nanomaterials are well documented, it is worthwhile to know how they interact with the target proteins making it a pragmatic issue for comprehension. This review discusses some important computational strategies like molecular docking and simulation, Nano-QSAR, quantum chemical calculations based on Density functional Theory (DFT) and computational nanotoxicology. Nano-QSAR modelling, based on semiempirical calculations and computational simulation can be useful for biomedical applications, whereas the DFT calculations make it possible to know about the behaviour of the material by calculations based on quantum mechanics, without the requirement of higher-order material properties. Other than the beneficial interactions, it is also important to know the hazardous consequences of engineered nanostructures and NPs can penetrate more deeply into the human body, and computational nanotoxicology has emerged as a potential strategy to predict the delirious effects of NMs. Although computational tools are helpful, yet more studies like in vitro assays are still required to get the complete picture, which is essential in the development of potent and safe drug entities.

Improved Prediction of Ligand-Protein Binding Affinities by Meta-modeling

The accurate screening of candidate drug ligands against target proteins through computational approaches is of prime interest to drug development efforts. Such virtual screening depends in part on methods to predict the binding affinity between ligands and proteins. Many computational models for binding affinity prediction have been developed, but with varying results across targets. Given that ensembling or meta-modeling approaches have shown great promise in reducing model-specific biases, we develop a framework to integrate published force-field-based empirical docking and sequence-based deep learning models. In building this framework, we evaluate many combinations of individual base models, training databases, and several meta-modeling approaches. We show that many of our meta-models significantly improve affinity predictions over base models. Our best meta-models achieve comparable performance to state-of-the-art deep learning tools exclusively based on 3D structures while allowing for improved database scalability and flexibility through the explicit inclusion of features such as physicochemical properties or molecular descriptors. We further demonstrate improved generalization capability by our models using a large-scale benchmark of affinity prediction as well as a virtual screening application benchmark. Overall, we demonstrate that diverse modeling approaches can be ensembled together to gain meaningful improvement in binding affinity prediction.

Can Machine Learning Overcome the 95% Failure Rate and Reality that Only 30% of Approved Cancer Drugs Meaningfully Extend Patient Survival?

Despite implementing hundreds of strategies, cancer drug development suffers from a 95% failure rate over 30 years, with only 30% of approved cancer drugs extending patient survival beyond 2.5 months. Adding more criteria without eliminating nonessential ones is impractical and may fall into the "survivorship bias" trap. Machine learning (ML) models may enhance efficiency by saving time and cost. Yet, they may not improve success rate without identifying the root causes of failure. We propose a "STAR-guided ML system" (structure-tissue/cell selectivity-activity relationship) to enhance success rate and efficiency by addressing three overlooked interdependent factors: potency/specificity to the on/off-targets determining efficacy in tumors at clinical doses, on/off-target-driven tissue/cell selectivity influencing adverse effects in the normal organs at clinical doses, and optimal clinical doses balancing efficacy/safety as determined by potency/specificity and tissue/cell selectivity. STAR-guided ML models can directly predict clinical dose/efficacy/safety from five features to design/select the best drugs, enhancing success and efficiency of cancer drug development.

GcForest-based compound-protein interaction prediction model and its application in discovering small-molecule drugs targeting CD47

Identifying compound-protein interaction plays a vital role in drug discovery. Artificial intelligence (AI), especially machine learning (ML) and deep learning (DL) algorithms, are playing increasingly important roles in compound-protein interaction (CPI) prediction. However, ML relies on learning from large sample data. And the CPI for specific target often has a small amount of data available. To overcome the dilemma, we propose a virtual screening model, in which word2vec is used as an embedding tool to generate low-dimensional vectors of SMILES of compounds and amino acid sequences of proteins, and the modified multi-grained cascade forest based gcForest is used as the classifier. This proposed method is capable of constructing a model from raw data, adjusting model complexity according to the scale of datasets, especially for small scale datasets, and is robust with few hyper-parameters and without over-fitting. We found that the proposed model is superior to other CPI prediction models and performs well on the constructed challenging dataset. We finally predicted 2 new inhibitors for clusters of differentiation 47(CD47) which has few known inhibitors. The IC50s of enzyme activities of these 2 new small molecular inhibitors targeting CD47-SIRPα interaction are 3.57 and 4.79 μM respectively. These results fully demonstrate the competence of this concise but efficient tool for CPI prediction.

DeePred-BBB: A Blood Brain Barrier Permeability Prediction Model With Improved Accuracy

The blood-brain barrier (BBB) is a selective and semipermeable boundary that maintains homeostasis inside the central nervous system (CNS). The BBB permeability of compounds is an important consideration during CNS-acting drug development and is difficult to formulate in a succinct manner. Clinical experiments are the most accurate method of measuring BBB permeability. However, they are time taking and labor-intensive. Therefore, numerous efforts have been made to predict the BBB permeability of compounds using computational methods. However, the accuracy of BBB permeability prediction models has always been an issue. To improve the accuracy of the BBB permeability prediction, we applied deep learning and machine learning algorithms to a dataset of 3,605 diverse compounds. Each compound was encoded with 1,917 features containing 1,444 physicochemical (1D and 2D) properties, 166 molecular access system fingerprints (MACCS), and 307 substructure fingerprints. The prediction performance metrics of the developed models were compared and analyzed. The prediction accuracy of the deep neural network (DNN), one-dimensional convolutional neural network, and convolutional neural network by transfer learning was found to be 98.07, 97.44, and 97.61%, respectively. The best performing DNN-based model was selected for the development of the “DeePred-BBB” model, which can predict the BBB permeability of compounds using their simplified molecular input line entry system (SMILES) notations. It could be useful in the screening of compounds based on their BBB permeability at the preliminary stages of drug development. The DeePred-BBB is made available at https://github.com/12rajnish/DeePred-BBB.

Machine-learning methods for ligand-protein molecular docking

Artificial intelligence (AI) is often presented as a new Industrial Revolution. Many domains use AI, including molecular simulation for drug discovery. In this review, we provide an overview of ligand-protein molecular docking and how machine learning (ML), especially deep learning (DL), a subset of ML, is transforming the field by tackling the associated challenges.

Construction and Drug Evaluation Based on Convolutional Neural Network System Optimized by Grey Correlation Analysis

Incidence rate of mental illness is increasing year by year with the development of city. The amount of modern medical data is huge and complex. In many cases, it is difficult to realize the rational allocation of resources, which puts forward an urgent demand for the artificial intelligence of modern medicine and brings great pressure to the development of the medical industry. The purpose of this study is to develop and construct a grey correlation analysis and related drug evaluation system of mental diseases based on deep convolution neural network. The establishment of the system can effectively improve the automation and intelligence of modern psychiatric treatment process. In this article, the grey correlation analysis of patient data is carried out, and then, the optimized deep convolution neural network is constructed. Combined with the medical knowledge base, the analysis of disease results is realized, and on this basis, the efficacy of related drugs in the treatment of mental diseases is evaluated. The results show that the advantage of the deep convolution neural network system is to effectively improve the induction rate. What's more, compared with other algorithms, this algorithm has higher accuracy and efficiency. It improves the comprehensiveness and informatization of disease screening methods, improves the accuracy of screening, reduces the consumption of doctors' human resources, and provides a theoretical basis for the digitization of the medical industry in the future.