DNMG: Deep molecular generative model by fusion of 3D information for de novo drug design.

Deep learning is improving and changing the process of de novo molecular design at a rapid pace. In recent years, great progress has been made in drug discovery and development by using deep generative models for de novo molecular design. However, most of the existing methods are string-based or graph-based and are limited by the lack of some very important properties, such as the three-dimensional information of molecules. We propose DNMG, a deep generative adversarial network (GAN) combined with transfer learning. Specifically, we use a Wasserstein-variant GAN based network architecture that considers the 3D grid spatial information of the ligand with atomic physicochemical properties to generate a representation of the molecule, which is then parsed into SMILES strings using an improved captioning network. Comprehensive in experiments demonstrate the ability of DNMG to generate valid and novel drug-like ligands. The DNMG model is used to design inhibitors for three targets, MK14, FNTA, and CDK2. The computational results show that the molecules generated by DNMG have better binding ability to the target proteins and better physicochemical properties. Overall, our deep generative model has excellent potential to generate molecules with high binding affinity for targets and explore the space of drug-like chemistry.

DockingGA: enhancing targeted molecule generation using transformer neural network and genetic algorithm with docking simulation.

Generative molecular models generate novel molecules with desired properties by searching chemical space. Traditional combinatorial optimization methods, such as genetic algorithms, have demonstrated superior performance in various molecular optimization tasks. However, these methods do not utilize docking simulation to inform the design process, and heavy dependence on the quality and quantity of available data, as well as require additional structural optimization to become candidate drugs. To address this limitation, we propose a novel model named DockingGA that combines Transformer neural networks and genetic algorithms to generate molecules with better binding affinity for specific targets. In order to generate high quality molecules, we chose the Self-referencing Chemical Structure Strings to represent the molecule and optimize the binding affinity of the molecules to different targets. Compared to other baseline models, DockingGA proves to be the optimal model in all docking results for the top 1, 10 and 100 molecules, while maintaining 100% novelty. Furthermore, the distribution of physicochemical properties demonstrates the ability of DockingGA to generate molecules with favorable and appropriate properties. This innovation creates new opportunities for the application of generative models in practical drug discovery.

MulCNN: An efficient and accurate deep learning method based on gene embedding for cell type identification in single-cell RNA-seq data.

Advancements in single-cell sequencing research have revolutionized our understanding of cellular heterogeneity and functional diversity through the analysis of single-cell transcriptomes and genomes. A crucial step in single-cell RNA sequencing (scRNA-seq) analysis is identifying cell types. However, scRNA-seq data are often high dimensional and sparse, and manual cell type identification can be time-consuming, subjective, and lack reproducibility. Consequently, analyzing scRNA-seq data remains a computational challenge. With the increasing availability of well-annotated scRNA-seq datasets, advanced methods are emerging to aid in cell type identification by leveraging this information. Deep learning neural networks have great potential for analyzing single-cell data. This paper proposes MulCNN, a multi-level convolutional neural network that uses a unique cell type-specific gene expression feature extraction method. This method extracts critical features through multi-scale convolution while filtering noise. Extensive testing using datasets from various species and comparisons with popular classification methods show that MulCNN has outstanding performance and offers a new and scalable direction for scRNA-seq analysis.

QuantumTox: Utilizing quantum chemistry with ensemble learning for molecular toxicity prediction.

Molecular toxicity prediction plays an important role in drug discovery, which is directly related to human health and drug fate. Accurately determining the toxicity of molecules can help weed out low-quality molecules in the early stage of drug discovery process and avoid depletion later in the drug development process. Nowadays, more and more researchers are starting to use machine learning methods to predict the toxicity of molecules, but these models do not fully exploit the 3D information of molecules. Quantum chemical information, which provides stereo structural information of molecules, can influence their toxicity. To this end, we propose QuantumTox, the first application of quantum chemistry in the field of drug molecule toxicity prediction compared to existing work. We extract the quantum chemical information of molecules as their 3D features. In the downstream prediction phase, we use Gradient Boosting Decision Tree and Bagging ensemble learning methods together to improve the accuracy and generalization of the model. A series of experiments on various tasks show that our model consistently outperforms the baseline model and that the model still performs well on small datasets of less than 300.