The clinical efficacy and safety of a drug is determined by its molecular properties and targets in humans. However, proteome-wide evaluation of all compounds in humans, or even animal models, is challenging. In this study, we present an unsupervised pretraining deep learning framework, named ImageMol, pretrained on 10 million unlabelled drug-like, bioactive molecules, to predict molecular targets of candidate compounds. The ImageMol framework is designed to pretrain chemical representations from unlabelled molecular images on the basis of local and global structural characteristics of molecules from pixels. We demonstrate high performance of ImageMol in evaluation of molecular properties (that is, the drug’s metabolism, brain penetration and toxicity) and molecular target profiles (that is, beta-secretase enzyme and kinases) across 51 benchmark datasets. ImageMol shows high accuracy in identifying anti-SARS-CoV-2 molecules across 13 high-throughput experimental datasets from the National Center for Advancing Translational Sciences. Via ImageMol, we identified candidate clinical 3C-like protease inhibitors for potential treatment of COVID-19.

Motivation: Adverse drug–drug interactions (DDIs) are crucial for drug research and mainly cause morbidity and mortality. Thus, the identification of potential DDIs is essential for doctors, patients and the society. Existing traditional machine learning models rely heavily on handcraft features and lack generalization. Recently, the deep learning approaches that can automatically learn drug features from the molecular graph or drug-related network have improved the ability of computational models to predict unknown DDIs. However, previous works utilized large labeled data and merely considered the structure or sequence information of drugs without considering the relations or topological information between drug and other biomedical objects (e.g. gene, disease and pathway), or considered knowledge graph (KG) without considering the information from the drug molecular structure. Results: Accordingly, to effectively explore the joint effect of drug molecular structure and semantic information of drugs in knowledge graph for DDI prediction, we propose a multi-scale feature fusion deep learning model named MUFFIN. MUFFIN can jointly learn the drug representation based on both the drug-self structure information and the KG with rich bio-medical information. In MUFFIN, we designed a bi-level cross strategy that includes cross- and scalar-level components to fuse multi-modal features well. MUFFIN can alleviate the restriction of limited labeled data on deep learning models by crossing the features learned from large-scale KG and drug molecular graph. We evaluated our approach on three datasets and three different tasks including binary-class, multi-class and multi-label DDI prediction tasks. The results showed that MUFFIN outperformed other state-of-the-art baselines. Availability and implementation: The source code and data are available at https://github.com/xzenglab/MUFFIN.

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.

Lung cancer is known as the highest mortality rate cancer, which needs biopsy to determine its subtype for further treatment. Recently, deep learning has provided powerful tools in lung cancer diagnose and therapeutic regimen making. However, it is still a challenge to identify the pathological type of lung cancer in early stage by CT images due to the lack of public training data set and powerful artificial intelligent models. In this work, we firstly build up a data set of CT images from 125 patients of lung cancer in early stage. The data set is enhanced by revolving, shifting and reproducing operations to avoid its inherent imbalance. After that, a deep convolutional neural network namely VGG16-T is proposed and multiple VGG16-T worked as weak classifiers are trained with a boosting strategy. Such method achieves significant performance in identifying pathological type of lung cancer with CT images by joint voting. Experiments conducted on the enhanced data set of CT images show that 3 weak classifiers VGG16-T are sufficient to achieve accuracy 86.58% in identifying pathological type, which performs better than some state-of-the-art deep learning models, including AlexNet, ResNet-34 and DenseNet with or without Softmax weights. As well, VGG16-T is with accuracy 85% by diagnosing 20 randomly selected CT images, while two respiratory doctors from Grade 3A level hospitals obtain accuracy 55% and 65% by handcrafted diagnosing, respectively. To our best acknowledge, this is the first attempt of using deep models and boosting to identify pathological type of lung cancer in early stage from small scale CT images.

We construct a protein–protein interaction (PPI) targeted drug-likeness dataset and propose a deep molecular generative framework to generate novel drug-likeness molecules from the features of the seed compounds. This framework gains inspiration from published molecular generative models, uses the key features associated with PPI inhibitors as input and develops deep molecular generative models for de novo molecular design of PPI inhibitors. For the first time, quantitative estimation index for compounds targeting PPI was applied to the evaluation of the molecular generation model for de novo design of PPI-targeted compounds. Our results estimated that the generated molecules had better PPI-targeted drug-likeness and drug-likeness. Additionally, our model also exhibits comparable performance to other several state-of-the-art molecule generation models. The generated molecules share chemical space with iPPI-DB inhibitors as demonstrated by chemical space analysis. The peptide characterization-oriented design of PPI inhibitors and the ligand-based design of PPI inhibitors are explored. Finally, we recommend that this framework will be an important step forward for the de novo design of PPI-targeted therapeutics.