Explore drug-like space with deep generative models

In-silico-based lead optimization of hit compounds targeting mitotic kinesin Eg5 for cancer management

Lead optimization is vital for turning hit compounds into therapeutic drugs. This study builds upon a prior in silico research, where the hit compounds had better binding affinity and stability compared to a reference drug. Using a genetic algorithm, 12,500 analogs of the top compounds from the prior study were generated. Virtual screening was done using a quantitative structure-activity relationship (QSAR) model. Top analogs, selected based on pChembL values below 6.000nM, underwent molecular docking targeting Human Eg5. The top five analogs from this study (Compound 9794, Compound 8592, Compound 9786, Compound 2744, and Compound 3246) demonstrated strong binding energies and interactions with key amino acids (GLU 116, GLU 117, and ARG 119). MMGBSA analysis revealed comparable affinities to the co-crystallized ligand, suggesting the top analogs' potential as Human Eg5 inhibitors. Induced fit docking highlighted Compound 9786's superior efficacy. Quantum Polarized Ligand Docking indicated promising scores for Compounds 8592 and 9786. ADMET predictions offered insights into pharmacological properties, with all compounds predicted to be HIA-positive and non-carcinogenic. Further MD simulation study confirms the stability of the top compounds in the active site of Eg5. This study shows the significance of integrated strategies in drug design. However, in vitro and in vivo studies should be conducted for these promising candidates to confirm their efficacy as Eg5 inhibitors.

Supplementary Information

The online version contains supplementary material available at 10.1007/s40203-024-00300-6.

3D molecular generation models expand chemical space exploration in drug design

Drug discovery is essential in human diseases but faces challenges because of the vast chemical space. Molecular generation models have become powerful tools to accelerate drug design by efficiently exploring chemical space. 3D molecular generation has gained popularity for explicitly incorporating spatial structural information to generate rational molecules. Herein, we summarize and compare common data sets, molecular representations, and generative strategies in 3D molecular generation. We also present case studies utilizing generative modeling for ligand design and outline future challenges in developing and applying 3D models. This work provides a reference for drug design researchers interested in 3D generative modeling.

The Chemical Space Spanned by Manually Curated Datasets of Natural and Synthetic Compounds with Activities against SARS-CoV-2

Diseases caused by viruses are challenging to contain, as their outbreak and spread could be very sudden, compounded by rapid mutations, making the development of drugs and vaccines a continued endeavour that requires fast discovery and preparedness. Targeting viral infections with small molecules remains one of the treatment options to reduce transmission and the disease burden. A lesson learned from the recent coronavirus disease (COVID-19) is to collect ready-to-screen small molecule libraries in preparation for the next viral outbreak, and potentially find a clinical candidate before it becomes a pandemic. Public availability of diverse compound libraries, well annotated in terms of chemical structures and scaffolds, modes of action, and bioactivities are, therefore, crucial to ensure the participation of academic laboratories in these screening efforts, especially in resource-limited settings where synthesis, testing and computing capacity are scarce. Here, we demonstrate a low-resource approach to populate the chemical space of naturally occurring and synthetic small molecules that have shown in vitro and/or in vivo activities against the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and its target proteins. We have manually curated two datasets of small molecules (naturally occurring and synthetically derived) by reading and collecting (hand-curating) the published literature. Information from the literature reveals that a majority of the reported SARS-CoV-2 compounds act by inhibiting the main protease, while 25% of the compounds currently have no known target. Scaffold analysis and principal component analysis revealed that the most common scaffolds in the datasets are quite distinct. We then expanded the initially manually curated dataset of over 1200 compounds via an ultra-large scale 2D and 3D similarity search, obtaining an expanded collection of over 150 k purchasable compounds. The spanned chemical space significantly extends beyond that of a commercially available coronavirus library of more than 20 k small molecules and constitutes a good starting collection for virtual screening campaigns given its manageable size and proximity to hand-curated compounds.

Interface-aware molecular generative framework for protein-protein interaction modulators

Protein-protein interactions (PPIs) play a crucial role in numerous biochemical and biological processes. Although several structure-based molecular generative models have been developed, PPI interfaces and compounds targeting PPIs exhibit distinct physicochemical properties compared to traditional binding pockets and small-molecule drugs. As a result, generating compounds that effectively target PPIs, particularly by considering PPI complexes or interface hotspot residues, remains a significant challenge. In this work, we constructed a comprehensive dataset of PPI interfaces with active and inactive compound pairs. Based on this, we propose a novel molecular generative framework tailored to PPI interfaces, named GENiPPI. Our evaluation demonstrates that GENiPPI captures the implicit relationships between the PPI interfaces and the active molecules, and can generate novel compounds that target these interfaces. Moreover, GENiPPI can generate structurally diverse novel compounds with limited PPI interface modulators. To the best of our knowledge, this is the first exploration of a structure-based molecular generative model focused on PPI interfaces, which could facilitate the design of PPI modulators. The PPI interface-based molecular generative model enriches the existing landscape of structure-based (pocket/interface) molecular generative model. SCIENTIFIC CONTRIBUTION: This study introduces GENiPPI, a protein-protein interaction (PPI) interface-aware molecular generative framework. The framework first employs Graph Attention Networks to capture atomic-level interaction features at the protein complex interface. Subsequently, Convolutional Neural Networks extract compound representations in voxel and electron density spaces. These features are integrated into a Conditional Wasserstein Generative Adversarial Network, which trains the model to generate compound representations targeting PPI interfaces. GENiPPI effectively captures the relationship between PPI interfaces and active/inactive compounds. Furthermore, in fewshot molecular generation, GENiPPI successfully generates compounds comparable to known disruptors. GENiPPI provides an efficient tool for structure-based design of PPI modulators.

A review of large language models and autonomous agents in chemistry

Large language models (LLMs) have emerged as powerful tools in chemistry, significantly impacting molecule design, property prediction, and synthesis optimization. This review highlights LLM capabilities in these domains and their potential to accelerate scientific discovery through automation. We also review LLM-based autonomous agents: LLMs with a broader set of tools to interact with their surrounding environment. These agents perform diverse tasks such as paper scraping, interfacing with automated laboratories, and synthesis planning. As agents are an emerging topic, we extend the scope of our review of agents beyond chemistry and discuss across any scientific domains. This review covers the recent history, current capabilities, and design of LLMs and autonomous agents, addressing specific challenges, opportunities, and future directions in chemistry. Key challenges include data quality and integration, model interpretability, and the need for standard benchmarks, while future directions point towards more sophisticated multi-modal agents and enhanced collaboration between agents and experimental methods. Due to the quick pace of this field, a repository has been built to keep track of the latest studies: https://github.com/ur-whitelab/LLMs-in-science.

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.

Advancing drug discovery with deep attention neural networks

In the dynamic field of drug discovery, deep attention neural networks are revolutionizing our approach to complex data. This review explores the attention mechanism and its extended architectures, including graph attention networks (GATs), transformers, bidirectional encoder representations from transformers (BERT), generative pre-trained transformers (GPTs) and bidirectional and auto-regressive transformers (BART). Delving into their core principles and multifaceted applications, we uncover their pivotal roles in catalyzing de novo drug design, predicting intricate molecular properties and deciphering elusive drug-target interactions. Despite challenges, these attention-based architectures hold unparalleled promise to drive transformative breakthroughs and accelerate progress in pharmaceutical research.

Exploring the Conformational Ensembles of Protein-Protein Complex with Transformer-Based Generative Model

Protein-protein interactions are the basis of many protein functions, and understanding the contact and conformational changes of protein-protein interactions is crucial for linking the protein structure to biological function. Although difficult to detect experimentally, molecular dynamics (MD) simulations are widely used to study the conformational ensembles and dynamics of protein-protein complexes, but there are significant limitations in sampling efficiency and computational costs. In this study, a generative neural network was trained on protein-protein complex conformations obtained from molecular simulations to directly generate novel conformations with physical realism. We demonstrated the use of a deep learning model based on the transformer architecture to explore the conformational ensembles of protein-protein complexes through MD simulations. The results showed that the learned latent space can be used to generate unsampled conformations of protein-protein complexes for obtaining new conformations complementing pre-existing ones, which can be used as an exploratory tool for the analysis and enhancement of molecular simulations of protein-protein complexes.

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.

A bidirectional interpretable compound-protein interaction prediction framework based on cross attention

The identification of compound-protein interactions (CPIs) plays a vital role in drug discovery. However, the huge cost and labor-intensive nature in vitro and vivo experiments make it urgent for researchers to develop novel CPI prediction methods. Despite emerging deep learning methods have achieved promising performance in CPI prediction, they also face ongoing challenges: (i) providing bidirectional interpretability from both the chemical and biological perspective for the prediction results; (ii) comprehensively evaluating model generalization performance; (iii) demonstrating the practical applicability of these models. To overcome the challenges posed by current deep learning methods, we propose a cross multi-head attention oriented bidirectional interpretable CPI prediction model (CmhAttCPI). First, CmhAttCPI takes molecular graphs and protein sequences as inputs, utilizing the GCW module to learn atom features and the CNN module to learn residue features, respectively. Second, the model applies cross multi-head attention module to compute attention weights for atoms and residues. Finally, CmhAttCPI employs a fully connected neural network to predict scores for CPIs. We evaluated the performance of CmhAttCPI on balanced datasets and imbalanced datasets. The results consistently show that CmhAttCPI outperforms multiple state-of-the-art methods. We constructed three scenarios based on compound and protein clustering and comprehensively evaluated the model generalization ability within these scenarios. The results demonstrate that the generalization ability of CmhAttCPI surpasses that of other models. Besides, the visualizations of attention weights reveal that CmhAttCPI provides chemical and biological interpretation for CPI prediction. Moreover, case studies confirm the practical applicability of CmhAttCPI in discovering anticancer candidates.

An Innovative Inducer of Platelet Production, Isochlorogenic Acid A, Is Uncovered through the Application of Deep Neural Networks

(1) Background: Radiation-induced thrombocytopenia (RIT) often occurs in cancer patients undergoing radiation therapy, which can result in morbidity and even death. However, a notable deficiency exists in the availability of specific drugs designed for the treatment of RIT. (2) Methods: In our pursuit of new drugs for RIT treatment, we employed three deep learning (DL) algorithms: convolutional neural network (CNN), deep neural network (DNN), and a hybrid neural network that combines the computational characteristics of the two. These algorithms construct computational models that can screen compounds for drug activity by utilizing the distinct physicochemical properties of the molecules. The best model underwent testing using a set of 10 drugs endorsed by the US Food and Drug Administration (FDA) specifically for the treatment of thrombocytopenia. (3) Results: The Hybrid CNN+DNN (HCD) model demonstrated the most effective predictive performance on the test dataset, achieving an accuracy of 98.3% and a precision of 97.0%. Both metrics surpassed the performance of the other models, and the model predicted that seven FDA drugs would exhibit activity. Isochlorogenic acid A, identified through screening the Chinese Pharmacopoeia Natural Product Library, was subsequently subjected to experimental verification. The results indicated a substantial enhancement in the differentiation and maturation of megakaryocytes (MKs), along with a notable increase in platelet production. (4) Conclusions: This underscores the potential therapeutic efficacy of isochlorogenic acid A in addressing RIT.

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.

MATT-DDI: Predicting multi-type drug-drug interactions via heterogeneous attention mechanisms

The joint use of multiple drugs can result in adverse drug-drug interactions (DDIs) and side effects that harm the body. Accurate identification of DDIs is crucial for avoiding accidental drug side effects and understanding potential mechanisms underlying DDIs. Several computational methods have been proposed for multi-type DDI prediction, but most rely on the similarity profiles of drugs as the drug feature vectors, which may result in information leakage and overoptimistic performance when predicting interactions between new drugs. To address this issue, we propose a novel method, MATT-DDI, for predicting multi-type DDIs based on the original feature vectors of drugs and multiple attention mechanisms. MATT-DDI consists of three main modules: the top k most similar drug pair selection module, heterogeneous attention mechanism module and multi‑type DDI prediction module. Firstly, based on the feature vector of the input drug pair (IDP), k drug pairs that are most similar to the input drug pair from the training dataset are selected according to cosine similarity between drug pairs. Then, the vectors of k selected drug pairs are averaged to obtain a new drug pair (NDP). Next, IDP and NDP are fed into heterogeneous attention modules, including scaled dot product attention and bilinear attention, to extract latent feature vectors. Finally, these latent feature vectors are taken as input of the classification module to predict DDI types. We evaluated MATT-DDI on three different tasks. The experimental results show that MATT-DDI provides better or comparable performance compared to several state-of-the-art methods, and its feasibility is supported by case studies. MATT-DDI is a robust model for predicting multi-type DDIs with excellent performance and no information leakage.

Attention is all you need: utilizing attention in AI-enabled drug discovery

Recently, attention mechanism and derived models have gained significant traction in drug development due to their outstanding performance and interpretability in handling complex data structures. This review offers an in-depth exploration of the principles underlying attention-based models and their advantages in drug discovery. We further elaborate on their applications in various aspects of drug development, from molecular screening and target binding to property prediction and molecule generation. Finally, we discuss the current challenges faced in the application of attention mechanisms and Artificial Intelligence technologies, including data quality, model interpretability and computational resource constraints, along with future directions for research. Given the accelerating pace of technological advancement, we believe that attention-based models will have an increasingly prominent role in future drug discovery. We anticipate that these models will usher in revolutionary breakthroughs in the pharmaceutical domain, significantly accelerating the pace of drug development.

MolFilterGAN: a progressively augmented generative adversarial network for triaging AI-designed molecules

Artificial intelligence (AI)-based molecular design methods, especially deep generative models for generating novel molecule structures, have gratified our imagination to explore unknown chemical space without relying on brute-force exploration. However, whether designed by AI or human experts, the molecules need to be accessibly synthesized and biologically evaluated, and the trial-and-error process remains a resources-intensive endeavor. Therefore, AI-based drug design methods face a major challenge of how to prioritize the molecular structures with potential for subsequent drug development. This study indicates that common filtering approaches based on traditional screening metrics fail to differentiate AI-designed molecules. To address this issue, we propose a novel molecular filtering method, MolFilterGAN, based on a progressively augmented generative adversarial network. Comparative analysis shows that MolFilterGAN outperforms conventional screening approaches based on drug-likeness or synthetic ability metrics. Retrospective analysis of AI-designed discoidin domain receptor 1 (DDR1) inhibitors shows that MolFilterGAN significantly increases the efficiency of molecular triaging. Further evaluation of MolFilterGAN on eight external ligand sets suggests that MolFilterGAN is useful in triaging or enriching bioactive compounds across a wide range of target types. These results highlighted the importance of MolFilterGAN in evaluating molecules integrally and further accelerating molecular discovery especially combined with advanced AI generative models.