Molecular substructure tree generative model for de novo drug design

Adaptive Space Search-based Molecular Evolution Optimization Algorithm

MOTIVATION

In drug development process, a significant portion of budget and research time are dedicated to the lead compound optimization procedure in order to identify potential drugs. This procedure focuses on enhancing the pharmacological and bioactive properties of compounds by optimizing their local substructures. However, due to the vast and discrete chemical structure space and the unpredictable element combinations within this space, the optimization process is inherently complex. Various structure enumeration-based combinatorial optimization methods have shown certain advantages. However, they still have limitations. Those methods fail to consider the differences between molecules and struggle to explore the unknown outer search space.

RESULTS

In this study, we propose an adaptive space search-based molecular evolution optimization algorithm (ASSMOEA). It consists of three key modules: construction of molecule-specific search space, molecular evolutionary optimization, and adaptive expansion of molecule-specific search space. Specifically, we design a fragment similarity tree in molecule-specific search space, and apply a dynamic mutation strategy in this space to guide molecular optimization. Then we utilize an encoder-encoder structure to adaptively expand the space. Those three modules are circled iteratively to optimize molecules. Our experiments demonstrate that ASSMOEA outperforms existing methods in terms of molecular optimization. It not only enhances the efficiency of the molecular optimization process, but also exhibits a robust ability to search for correct solutions.

AVAILABILITY AND IMPLEMENTATION

The code is freely available on the web at https://github.com/bbbbb-b/MEOAFST.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Geometric deep learning methods and applications in 3D structure-based drug design

3D structure-based drug design (SBDD) is considered a challenging and rational way for innovative drug discovery. Geometric deep learning is a promising approach that solves the accurate model training of 3D SBDD through building neural network models to learn non-Euclidean data, such as 3D molecular graphs and manifold data. Here, we summarize geometric deep learning methods and applications that contain 3D molecular representations, equivariant graph neural networks (EGNNs), and six generative model methods [diffusion model, flow-based model, generative adversarial networks (GANs), variational autoencoder (VAE), autoregressive models, and energy-based models]. Our review provides insights into geometric deep learning methods and advanced applications of 3D SBDD that will be of relevance for the drug discovery community.

Deep Generative Models in De Novo Drug Molecule Generation

The discovery of new drugs has important implications for human health. Traditional methods for drug discovery rely on experiments to optimize the structure of lead molecules, which are time-consuming and high-cost. Recently, artificial intelligence has exhibited promising and efficient performance for drug-like molecule generation. In particular, deep generative models achieve great success in de novo generation of drug-like molecules with desired properties, showing massive potential for novel drug discovery. In this study, we review the recent progress of molecule generation using deep generative models, mainly focusing on molecule representations, public databases, data processing tools, and advanced artificial intelligence based molecule generation frameworks. In particular, we present a comprehensive comparison of state-of-the-art deep generative models for molecule generation and a summary of commonly used molecular design strategies. We identify research gaps and challenges of molecule generation such as the need for better databases, missing 3D information in molecular representation, and the lack of high-precision evaluation metrics. We suggest future directions for molecular generation and drug discovery.

Transformer-Based Molecular Generative Model for Antiviral Drug Design

Since the Simplified Molecular Input Line Entry System (SMILES) is oriented to the atomic-level representation of molecules and is not friendly in terms of human readability and editable, however, IUPAC is the closest to natural language and is very friendly in terms of human-oriented readability and performing molecular editing, we can manipulate IUPAC to generate corresponding new molecules and produce programming-friendly molecular forms of SMILES. In addition, antiviral drug design, especially analogue-based drug design, is also more appropriate to edit and design directly from the functional group level of IUPAC than from the atomic level of SMILES, since designing analogues involves altering the R group only, which is closer to the knowledge-based molecular design of a chemist. Herein, we present a novel data-driven self-supervised pretraining generative model called "TransAntivirus" to make select-and-replace edits and convert organic molecules into the desired properties for design of antiviral candidate analogues. The results indicated that TransAntivirus is significantly superior to the control models in terms of novelty, validity, uniqueness, and diversity. TransAntivirus showed excellent performance in the design and optimization of nucleoside and non-nucleoside analogues by chemical space analysis and property prediction analysis. Furthermore, to validate the applicability of TransAntivirus in the design of antiviral drugs, we conducted two case studies on the design of nucleoside analogues and non-nucleoside analogues and screened four candidate lead compounds against anticoronavirus disease (COVID-19). Finally, we recommend this framework for accelerating antiviral drug discovery.

ChemSpaceAL: An Efficient Active Learning Methodology Applied to Protein-Specific Molecular Generation

The incredible capabilities of generative artificial intelligence models have inevitably led to their application in the domain of drug discovery. Within this domain, the vastness of chemical space motivates the development of more efficient methods for identifying regions with molecules that exhibit desired characteristics. In this work, we present a computationally efficient active learning methodology and demonstrate its applicability to targeted molecular generation. When applied to c-Abl kinase, a protein with FDA-approved small-molecule inhibitors, the model learns to generate molecules similar to the inhibitors without prior knowledge of their existence and even reproduces two of them exactly. We also show that the methodology is effective for a protein without any commercially available small-molecule inhibitors, the HNH domain of the CRISPR-associated protein 9 (Cas9) enzyme. To facilitate implementation and reproducibility, we made all of our software available through the open-source ChemSpaceAL Python package.

MARPPI: boosting prediction of protein-protein interactions with multi-scale architecture residual network

Protein-protein interactions (PPIs) are a major component of the cellular biochemical reaction network. Rich sequence information and machine learning techniques reduce the dependence of exploring PPIs on wet experiments, which are costly and time-consuming. This paper proposes a PPI prediction model, multi-scale architecture residual network for PPIs (MARPPI), based on dual-channel and multi-feature. Multi-feature leverages Res2vec to obtain the association information between residues, and utilizes pseudo amino acid composition, autocorrelation descriptors and multivariate mutual information to achieve the amino acid composition and order information, physicochemical properties and information entropy, respectively. Dual channel utilizes multi-scale architecture improved ResNet network which extracts protein sequence features to reduce protein feature loss. Compared with other advanced methods, MARPPI achieves 96.03%, 99.01% and 91.80% accuracy in the intraspecific datasets of Saccharomyces cerevisiae, Human and Helicobacter pylori, respectively. The accuracy on the two interspecific datasets of Human-Bacillus anthracis and Human-Yersinia pestis is 97.29%, and 95.30%, respectively. In addition, results on specific datasets of disease (neurodegenerative and metabolic disorders) demonstrate the ability to detect hidden interactions. To better illustrate the performance of MARPPI, evaluations on independent datasets and PPIs network suggest that MARPPI can be used to predict cross-species interactions. The above shows that MARPPI can be regarded as a concise, efficient and accurate tool for PPI datasets.

Exploring the effects of drug, disease, and protein dependencies on biomedical named entity recognition: A comparative analysis

Background: Biomedical named entity recognition is one of the important tasks of biomedical literature mining. With the development of natural language processing technology, many deep learning models are used to extract valuable information from the biomedical literature, which promotes the development of effective BioNER models. However, for specialized domains with diverse and complex contexts and a richer set of semantically related entity types (e.g., drug molecules, targets, pathways, etc., in the biomedical domain), whether the dependencies of these drugs, diseases, and targets can be helpful still needs to be explored. Method: Providing additional dependency information beyond context, a method based on the graph attention network and BERT pre-training model named MKGAT is proposed to improve BioNER performance in the biomedical domain. To enhance BioNER by using external dependency knowledge, we integrate BERT-processed text embeddings and entity dependencies to construct better entity embedding representations for biomedical named entity recognition. Results: The proposed method obtains competitive accuracy and higher efficiency than the state-of-the-art method on three datasets, namely, NCBI-disease corpus, BC2GM, and BC5CDR-chem, with a precision of 90.71%, 88.19%, and 95.71%, recall of 92.52%, 88.05%, and 95.62%, and F1-scores of 91.61%, 88.12%, and 95.66%, respectively, which performs better than existing methods. Conclusion: Drug, disease, and protein dependencies can allow entities to be better represented in neural networks, thereby improving the performance of BioNER.

TransCluster: A Cell-Type Identification Method for single-cell RNA-Seq data using deep learning based on transformer

Recent advances in single-cell RNA sequencing (scRNA-seq) have accelerated the development of techniques to classify thousands of cells through transcriptome profiling. As more and more scRNA-seq data become available, supervised cell type classification methods using externally well-annotated source data become more popular than unsupervised clustering algorithms. However, accurate cellular annotation of single cell transcription data remains a significant challenge. Here, we propose a hybrid network structure called TransCluster, which uses linear discriminant analysis and a modified Transformer to enhance feature learning. It is a cell-type identification tool for single-cell transcriptomic maps. It shows high accuracy and robustness in many cell data sets of different human tissues. It is superior to other known methods in external test data set. To our knowledge, TransCluster is the first attempt to use Transformer for annotating cell types of scRNA-seq, which greatly improves the accuracy of cell-type identification.

Deep learning methods for molecular representation and property prediction

With advances in artificial intelligence (AI) methods, computer-aided drug design (CADD) has developed rapidly in recent years. Effective molecular representation and accurate property prediction are crucial tasks in CADD workflows. In this review, we summarize contemporary applications of deep learning (DL) methods for molecular representation and property prediction. We categorize DL methods according to the format of molecular data (1D, 2D, and 3D). In addition, we discuss some common DL models, such as ensemble learning and transfer learning, and analyze the interpretability methods for these models. We also highlight the challenges and opportunities of DL methods for molecular representation and property prediction.

DCSE:Double-Channel-Siamese-Ensemble model for protein protein interaction prediction

Background

Protein-protein interaction (PPI) is very important for many biochemical processes. Therefore, accurate prediction of PPI can help us better understand the role of proteins in biochemical processes. Although there are many methods to predict PPI in biology, they are time-consuming and lack accuracy, so it is necessary to build an efficiently and accurately computational model in the field of PPI prediction.

Results

We present a novel sequence-based computational approach called DCSE (Double-Channel-Siamese-Ensemble) to predict potential PPI. In the encoding layer, we treat each amino acid as a word, and map it into an N-dimensional vector. In the feature extraction layer, we extract features from local and global perspectives by Multilayer Convolutional Neural Network (MCN) and Multilayer Bidirectional Gated Recurrent Unit with Convolutional Neural Networks (MBC). Finally, the output of the feature extraction layer is then fed into the prediction layer to output whether the input protein pair will interact each other. The MCN and MBC are siamese and ensemble based network, which can effectively improve the performance of the model. In order to demonstrate our model’s performance, we compare it with four machine learning based and three deep learning based models. The results show that our method outperforms other models in all evaluation criteria. The Accuracy, Precision, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_{1}$$\end{document}F1, Recall and MCC of our model are 0.9303, 0.9091, 0.9268, 0.9452, 0.8609. For the other seven models, the highest Accuracy, Precision, \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$F_{1}$$\end{document}F1, Recall and MCC are 0.9288, 0.9243, 0.9246, 0.9250, 0.8572. We also test our model in the imbalanced dataset and transfer our model to another species. The results show our model is excellent.

Conclusion

Our model achieves the best performance by comparing it with seven other models. NLP-based coding method has a good effect on PPI prediction task. MCN and MBC extract protein sequence features from local and global perspectives and these two feature extraction layers are based on siamese and ensemble network structures. Siamese-based network structure can keep the features consistent and ensemble based network structure can effectively improve the accuracy of the model.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12864-022-08772-6.

SDNN-PPI: self-attention with deep neural network effect on protein-protein interaction prediction

BACKGROUND

Protein-protein interactions (PPIs) dominate intracellular molecules to perform a series of tasks such as transcriptional regulation, information transduction, and drug signalling. The traditional wet experiment method to obtain PPIs information is costly and time-consuming.

RESULT

In this paper, SDNN-PPI, a PPI prediction method based on self-attention and deep learning is proposed. The method adopts amino acid composition (AAC), conjoint triad (CT), and auto covariance (AC) to extract global and local features of protein sequences, and leverages self-attention to enhance DNN feature extraction to more effectively accomplish the prediction of PPIs. In order to verify the generalization ability of SDNN-PPI, a 5-fold cross-validation on the intraspecific interactions dataset of Saccharomyces cerevisiae (core subset) and human is used to measure our model in which the accuracy reaches 95.48% and 98.94% respectively. The accuracy of 93.15% and 88.33% are obtained in the interspecific interactions dataset of human-Bacillus Anthracis and Human-Yersinia pestis, respectively. In the independent data set Caenorhabditis elegans, Escherichia coli, Homo sapiens, and Mus musculus, all prediction accuracy is 100%, which is higher than the previous PPIs prediction methods. To further evaluate the advantages and disadvantages of the model, the one-core and crossover network are conducted to predict PPIs, and the data show that the model correctly predicts the interaction pairs in the network.

CONCLUSION

In this paper, AAC, CT and AC methods are used to encode the sequence, and SDNN-PPI method is proposed to predict PPIs based on self-attention deep learning neural network. Satisfactory results are obtained on interspecific and intraspecific data sets, and good performance is also achieved in cross-species prediction. It can also correctly predict the protein interaction of cell and tumor information contained in one-core network and crossover network.The SDNN-PPI proposed in this paper not only explores the mechanism of protein-protein interaction, but also provides new ideas for drug design and disease prevention.

Sequence-based drug-target affinity prediction using weighted graph neural networks

BACKGROUND

Affinity prediction between molecule and protein is an important step of virtual screening, which is usually called drug-target affinity (DTA) prediction. Its accuracy directly influences the progress of drug development. Sequence-based drug-target affinity prediction can predict the affinity according to protein sequence, which is fast and can be applied to large datasets. However, due to the lack of protein structure information, the accuracy needs to be improved.

RESULTS

The proposed model which is called WGNN-DTA can be competent in drug-target affinity (DTA) and compound-protein interaction (CPI) prediction tasks. Various experiments are designed to verify the performance of the proposed method in different scenarios, which proves that WGNN-DTA has the advantages of simplicity and high accuracy. Moreover, because it does not need complex steps such as multiple sequence alignment (MSA), it has fast execution speed, and can be suitable for the screening of large databases.

CONCLUSION

We construct protein and molecular graphs through sequence and SMILES that can effectively reflect their structures. To utilize the detail contact information of protein, graph neural network is used to extract features and predict the binding affinity based on the graphs, which is called weighted graph neural networks drug-target affinity predictor (WGNN-DTA). The proposed method has the advantages of simplicity and high accuracy.