A deep generative model for molecule optimization via one fragment modification

Evolutionary Multiobjective Molecule Optimization in an Implicit Chemical Space

Optimization techniques play a pivotal role in advancing drug development, serving as the foundation of numerous generative methods tailored to efficiently design optimized molecules derived from existing lead compounds. However, existing methods often encounter difficulties in generating diverse, novel, and high-property molecules that simultaneously optimize multiple drug properties. To overcome this bottleneck, we propose a multiobjective molecule optimization framework (MOMO). MOMO employs a specially designed Pareto-based multiproperty evaluation strategy at the molecular sequence level to guide the evolutionary search in an implicit chemical space. A comparative analysis of MOMO with five state-of-the-art methods across two benchmark multiproperty molecule optimization tasks reveals that MOMO markedly outperforms them in terms of diversity, novelty, and optimized properties. The practical applicability of MOMO in drug discovery has also been validated on four challenging tasks in the real-world discovery problem. These results suggest that MOMO can provide a useful tool to facilitate molecule optimization problems with multiple properties.

DiffDec: Structure-Aware Scaffold Decoration with an End-to-End Diffusion Model

In molecular optimization, one popular way is R-group decoration on molecular scaffolds, and many efforts have been made to generate R-groups based on deep generative models. However, these methods mostly use information on known binding ligands, without fully utilizing target structure information. In this study, we proposed a new method, DiffDec, to involve 3D pocket constraints by a modified diffusion technique for optimizing molecules through molecular scaffold decoration. For end-to-end generation of R-groups with different sizes, we designed a novel fake atom mechanism. DiffDec was shown to be able to generate structure-aware R-groups with realistic geometric substructures by the analysis of bond angles and dihedral angles and simultaneously generate multiple R-groups for one scaffold on different growth anchors. The growth anchors could be provided by users or automatically determined by our model. DiffDec achieved R-group recovery rates of 69.67% and 45.34% in the single and multiple R-group decoration tasks, respectively, and these values were significantly higher than competing methods (37.33% and 26.85%). According to the molecular docking study, our decorated molecules obtained a better average binding affinity than baseline methods. The docking pose analysis revealed that DiffDec could decorate scaffolds with R-groups that exhibited improved binding affinities and more favorable interactions with the pocket. These results demonstrated the potential and applicability of DiffDec in real-world scaffold decoration for molecular optimization.

Kernel-elastic autoencoder for molecular design

We introduce the kernel-elastic autoencoder (KAE), a self-supervised generative model based on the transformer architecture with enhanced performance for molecular design. KAE employs two innovative loss functions: modified maximum mean discrepancy (m-MMD) and weighted reconstruction (L WCEL ). The m-MMD loss has significantly improved the generative performance of KAE when compared to using the traditional Kullback-Leibler loss of VAE, or standard maximum mean discrepancy. Including the weighted reconstruction loss L WCEL , KAE achieves valid generation and accurate reconstruction at the same time, allowing for generative behavior that is intermediate between VAE and autoencoder not available in existing generative approaches. Further advancements in KAE include its integration with conditional generation, setting a new state-of-the-art benchmark in constrained optimizations. Moreover, KAE has demonstrated its capability to generate molecules with favorable binding affinities in docking applications, as evidenced by AutoDock Vina and Glide scores, outperforming all existing candidates from the training dataset. Beyond molecular design, KAE holds promise to solve problems by generation across a broad spectrum of applications.

A domain-label-guided translation model for molecular optimization

Molecular optimization, which aims to improve molecular properties by modifying complex molecular structures, is a crucial and challenging task in drug discovery. In recent years, translation models provide a promising way to transform low-property molecules to high-property molecules, which enables molecular optimization to achieve remarkable progress. However, most existing models require matched molecular pairs, which are prone to be limited by the datasets. Although some models do not require matched molecular pairs, their performance is usually sacrificed due to the lack of useful supervising information. To address this issue, a domain-label-guided translation model is proposed in this paper, namely DLTM. In the model, the domain label information of molecules is exploited as a control condition to obtain different embedding representations, enabling the model to generate diverse molecules. Besides, the model adopts a classifier network to identify the property categories of transformed molecules, guiding the model to generate molecules with desired properties. The performance of DLTM is verified on two optimization tasks, namely the quantitative estimation of drug-likeness and penalized logP. Experimental results show that the proposed DLTM is superior to the compared baseline models.

Generating Potential RET-Specific Inhibitors Using a Novel LSTM Encoder-Decoder Model

The receptor tyrosine kinase RET (rearranged during transfection) plays a vital role in various cell signaling pathways and is a critical factor in the development of the nervous system. Abnormal activation of the RET kinase can lead to several cancers, including thyroid cancer and non-small-cell lung cancer. However, most RET kinase inhibitors are multi-kinase inhibitors. Therefore, the development of an effective RET-specific inhibitor continues to present a significant challenge. To address this issue, we built a molecular generation model based on fragment-based drug design (FBDD) and a long short-term memory (LSTM) encoder-decoder structure to generate receptor-specific molecules with novel scaffolds. Remarkably, our model was trained with a molecular assembly accuracy of 98.4%. Leveraging the pre-trained model, we rapidly generated a RET-specific-candidate active-molecule library by transfer learning. Virtual screening based on our molecular generation model was performed, combined with molecular dynamics simulation and binding energy calculation, to discover specific RET inhibitors, and five novel molecules were selected. Further analyses indicated that two of these molecules have good binding affinities and synthesizability, exhibiting high selectivity. Overall, this investigation demonstrates the capacity of our model to generate novel receptor-specific molecules and provides a rapid method to discover potential drugs.

Deep learning-based design and screening of benzimidazole-pyrazine derivatives as adenosine A2B receptor antagonists

The Adenosine A2B receptor (A2BAR) is considered a novel potential target for the immunotherapy of cancer, and A2BAR antagonists have an inhibitory effect on tumor growth, proliferation, and metastasis. In our previous studies, we identified a class of benzimidazole-pyrazine scaffolds whose derivatives exhibited the antagonistic effect but lacked subtype selectivity towards A2BAR. In this work, we developed a scaffold-based protocol that incorporates a deep generative model and multilayer virtual screening to design benzimidazole-pyrazine derivatives as potential selective A2BAR antagonists. By utilizing a generative model with reported A2BAR antagonists as the training set, we built up a scaffold-focused library of benzimidazole-pyrazine derivatives and processed a virtual screening protocol to discover potential A2BAR antagonists. Finally, five molecules with different Bemis-Murcko scaffolds were identified and exhibited higher binding free energies than the reference molecule 12o. Further computational analysis revealed that the 3-benzyl derivative ABA-1266 presented high selectivity toward A2BAR and showed preferred draggability, providing future potent development of selective A2BAR antagonists.Communicated by Ramaswamy H. Sarma.

A flexible data-free framework for structure-based de novo drug design with reinforcement learning

Contemporary structure-based molecular generative methods have demonstrated their potential to model the geometric and energetic complementarity between ligands and receptors, thereby facilitating the design of molecules with favorable binding affinity and target specificity. Despite the introduction of deep generative models for molecular generation, the atom-wise generation paradigm that partially contradicts chemical intuition limits the validity and synthetic accessibility of the generated molecules. Additionally, the dependence of deep learning models on large-scale structural data has hindered their adaptability across different targets. To overcome these challenges, we present a novel search-based framework, 3D-MCTS, for structure-based de novo drug design. Distinct from prevailing atom-centric methods, 3D-MCTS employs a fragment-based molecular editing strategy. The fragments decomposed from small-molecule drugs are recombined under predefined retrosynthetic rules, offering improved drug-likeness and synthesizability, overcoming the inherent limitations of atom-based approaches. Leveraging multi-threaded parallel simulations combined with a real-time energy constraint-based pruning strategy, 3D-MCTS achieves remarkable efficiency. At a fixed computational cost, it outperforms other state-of-the-art (SOTA) methods by producing molecules with enhanced binding affinity. Furthermore, its fragment-based approach ensures the generation of more dependable binding conformations, exhibiting a success rate 43.6% higher than that of other SOTAs. This advantage becomes even more pronounced when handling targets that significantly deviate from the training dataset. 3D-MCTS is capable of achieving thirty times more hits with high binding affinity than traditional virtual screening methods, which demonstrates the superior ability of 3D-MCTS to explore chemical space. Moreover, the flexibility of our framework makes it easy to incorporate domain knowledge during the process, thereby enabling the generation of molecules with desirable pharmacophores and enhanced binding affinity. The adaptability of 3D-MCTS is further showcased in metalloprotein applications, highlighting its potential across various drug design scenarios.

DeepSA: a deep-learning driven predictor of compound synthesis accessibility

With the continuous development of artificial intelligence technology, more and more computational models for generating new molecules are being developed. However, we are often confronted with the question of whether these compounds are easy or difficult to synthesize, which refers to synthetic accessibility of compounds. In this study, a deep learning based computational model called DeepSA, was proposed to predict the synthesis accessibility of compounds, which provides a useful tool to choose molecules. DeepSA is a chemical language model that was developed by training on a dataset of 3,593,053 molecules using various natural language processing (NLP) algorithms, offering advantages over state-of-the-art methods and having a much higher area under the receiver operating characteristic curve (AUROC), i.e., 89.6%, in discriminating those molecules that are difficult to synthesize. This helps users select less expensive molecules for synthesis, reducing the time and cost required for drug discovery and development. Interestingly, a comparison of DeepSA with a Graph Attention-based method shows that using SMILES alone can also efficiently visualize and extract compound's informative features. DeepSA is available online on the below web server ( https://bailab.siais.shanghaitech.edu.cn/services/deepsa/ ) of our group, and the code is available at https://github.com/Shihang-Wang-58/DeepSA .

Low-Data Drug Design with Few-Shot Generative Domain Adaptation

Developing new drugs for emerging diseases, such as COVID-19, is crucial for promoting public health. In recent years, the application of artificial intelligence (AI) has significantly advanced drug discovery pipelines. Generative models, such as generative adversarial networks (GANs), exhibit the potential for discovering novel drug molecules by relying on a vast number of training samples. However, for new diseases, only a few samples are typically available, posing a significant challenge to learning a generative model that produces both high-quality and diverse molecules under limited supervision. To address this low-data drug generation issue, we propose a novel molecule generative domain adaptation paradigm (Mol-GenDA), which transfers a pre-trained GAN on a large-scale drug molecule dataset to a new disease domain using only a few references. Specifically, we introduce a molecule adaptor into the GAN generator during the fine tuning, allowing the generator to reuse prior knowledge learned in pre-training to the greatest extent and maintain the quality and diversity of the generated molecules. Comprehensive downstream experiments demonstrate that Mol-GenDA can produce high-quality and diverse drug candidates. In summary, the proposed approach offers a promising solution to expedite drug discovery for new diseases, which could lead to the timely development of effective drugs to combat emerging outbreaks.

Material symmetry recognition and property prediction accomplished by crystal capsule representation

Learning the global crystal symmetry and interpreting the equivariant information is crucial for accurately predicting material properties, yet remains to be fully accomplished by existing algorithms based on convolution networks. To overcome this challenge, here we develop a machine learning (ML) model, named symmetry-enhanced equivariance network (SEN), to build material representation with joint structure-chemical patterns, to encode important clusters embedded in the crystal structure, and to learn pattern equivariance in different scales via capsule transformers. Quantitative analyses of the intermediate matrices demonstrate that the intrinsic crystal symmetries and interactions between clusters have been exactly perceived by the SEN model and critically affect the prediction performances by reducing effective feature space. The mean absolute errors (MAEs) of 0.181 eV and 0.0161 eV/atom are obtained for predicting bandgap and formation energy in the MatBench dataset. The general and interpretable SEN model reveals the potential to design ML models by implicitly encoding feature relationship based on physical mechanisms.

G2Retro as a two-step graph generative models for retrosynthesis prediction

Retrosynthesis is a procedure where a target molecule is transformed into potential reactants and thus the synthesis routes can be identified. Recently, computational approaches have been developed to accelerate the design of synthesis routes. In this paper,we develop a generative framework G²Retro for one-step retrosynthesis prediction. G²Retro imitates the reversed logic of synthetic reactions. It first predicts the reaction centers in the target molecules (products), identifies the synthons needed to assemble the products, and transforms these synthons into reactants. G²Retro defines a comprehensive set of reaction center types, and learns from the molecular graphs of the products to predict potential reaction centers. To complete synthons into reactants, G²Retro considers all the involved synthon structures and the product structures to identify the optimal completion paths, and accordingly attaches small substructures sequentially to the synthons. Here we show that G²Retro is able to better predict the reactants for given products in the benchmark dataset than the state-of-the-art methods.

Molecular Generative Model via Retrosynthetically Prepared Chemical Building Block Assembly

Deep generative models are attracting attention as a smart molecular design strategy. However, previous models often render molecules with low synthesizability, hindering their real-world applications. Here, a novel graph-based conditional generative model which makes molecules by tailoring retrosynthetically prepared chemical building blocks until achieving target properties in an auto-regressive fashion is proposed. This strategy improves the synthesizability and property control of the resulting molecules and also helps learn how to select appropriate building blocks and bind them together to achieve target properties. By applying a negative sampling method to the selection process of building blocks, this model overcame a critical limitation of previous fragment-based models, which can only use molecules from the training set during generation. As a result, the model works equally well with unseen building blocks without sacrificing computational efficiency. It is demonstrated that the model can generate potential inhibitors with high docking scores against the 3CL protease of SARS-COV-2.

Hierarchical Molecular Graph Self-Supervised Learning for property prediction

Molecular graph representation learning has shown considerable strength in molecular analysis and drug discovery. Due to the difficulty of obtaining molecular property labels, pre-training models based on self-supervised learning has become increasingly popular in molecular representation learning. Notably, Graph Neural Networks (GNN) are employed as the backbones to encode implicit representations of molecules in most existing works. However, vanilla GNN encoders ignore chemical structural information and functions implied in molecular motifs, and obtaining the graph-level representation via the READOUT function hinders the interaction of graph and node representations. In this paper, we propose Hierarchical Molecular Graph Self-supervised Learning (HiMol), which introduces a pre-training framework to learn molecule representation for property prediction. First, we present a Hierarchical Molecular Graph Neural Network (HMGNN), which encodes motif structure and extracts node-motif-graph hierarchical molecular representations. Then, we introduce Multi-level Self-supervised Pre-training (MSP), in which corresponding multi-level generative and predictive tasks are designed as self-supervised signals of HiMol model. Finally, superior molecular property prediction results on both classification and regression tasks demonstrate the effectiveness of HiMol. Moreover, the visualization performance in the downstream dataset shows that the molecule representations learned by HiMol can capture chemical semantic information and properties.

DoubleSG-DTA: Deep Learning for Drug Discovery: Case Study on the Non-Small Cell Lung Cancer with EGFRT790M Mutation

Drug-targeted therapies are promising approaches to treating tumors, and research on receptor-ligand interactions for discovering high-affinity targeted drugs has been accelerating drug development. This study presents a mechanism-driven deep learning-based computational model to learn double drug sequences, protein sequences, and drug graphs to project drug-target affinities (DTAs), which was termed the DoubleSG-DTA. We deployed lightweight graph isomorphism networks to aggregate drug graph representations and discriminate between molecular structures, and stacked multilayer squeeze-and-excitation networks to selectively enhance spatial features of drug and protein sequences. What is more, cross-multi-head attentions were constructed to further model the non-covalent molecular docking behavior. The multiple cross-validation experimental evaluations on various datasets indicated that DoubleSG-DTA consistently outperformed all previously reported works. To showcase the value of DoubleSG-DTA, we applied it to generate promising hit compounds of Non-Small Cell Lung Cancer harboring EGFRT790M mutation from natural products, which were consistent with reported laboratory studies. Afterward, we further investigated the interpretability of the graph-based "black box" model and highlighted the active structures that contributed the most. DoubleSG-DTA thus provides a powerful and interpretable framework that extrapolates for potential chemicals to modulate the systemic response to disease.

COMA: efficient structure-constrained molecular generation using contractive and margin losses

BACKGROUND

Structure-constrained molecular generation is a promising approach to drug discovery. The goal of structure-constrained molecular generation is to produce a novel molecule that is similar to a given source molecule (e.g. hit molecules) but has enhanced chemical properties (for lead optimization). Many structure-constrained molecular generation models with superior performance in improving chemical properties have been proposed; however, they still have difficulty producing many novel molecules that satisfy both the high structural similarities to each source molecule and improved molecular properties.

METHODS

We propose a structure-constrained molecular generation model that utilizes contractive and margin loss terms to simultaneously achieve property improvement and high structural similarity. The proposed model has two training phases; a generator first learns molecular representation vectors using metric learning with contractive and margin losses and then explores optimized molecular structure for target property improvement via reinforcement learning.

RESULTS

We demonstrate the superiority of our proposed method by comparing it with various state-of-the-art baselines and through ablation studies. Furthermore, we demonstrate the use of our method in drug discovery using an example of sorafenib-like molecular generation in patients with drug resistance.

Targeting the super elongation complex for oncogenic transcription driven tumor malignancies: Progress in structure, mechanisms and small molecular inhibitor discovery

Oncogenic transcription activation is associated with tumor development and resistance derived from chemotherapy or target therapy. The super elongation complex (SEC) is an important complex regulating gene transcription and expression in metazoans closely related to physiological activities. In normal transcriptional regulation, SEC can trigger promoter escape, limit proteolytic degradation of transcription elongation factors and increase the synthesis of RNA polymerase II (POL II), and regulate many normal human genes to stimulate RNA elongation. Dysregulation of SEC accompanied by multiple transcription factors in cancer promotes rapid transcription of oncogenes and induce cancer development. In this review, we summarized recent progress in understanding the mechanisms of SEC in regulating normal transcription, and importantly its roles in cancer development. We also highlighted the discovery of SEC complex target related inhibitors and their potential applications in cancer treatment.

A Scaffold-based Deep Generative Model Considering Molecular Stereochemical Information

Designing molecules with specific scaffolds can facilitate the discovery and optimization of lead compounds. Some scaffold-based molecular generation models have been developed using deep-learning methods based on specific scaffolds, although incorporating scaffold generalization is expected to achieve scaffold hopping. Moreover, most of the existing models focus on the 2D shape of the scaffold and overlook the stereochemical properties of the compound, especially for natural products. In this study, we optimized the scaffold-based molecular generation model designed by Lim et al. (Chemical Science 2020, 11, 1153-1164). Real-time ultrafast shape recognition with pharmacophore constraints (USRCAT) was introduced into the model to search for molecules similar to the 3D conformation and pharmacophore of the input scaffold sourced from the training set; the searched molecules were then used as new scaffolds to execute scaffold hopping. The optimized model could generate new molecules with the same chirality as the input scaffold. Furthermore, the probability distribution of the molecular structure and various physicochemical properties were analyzed to evaluate the model's generation capability. We thus believe that the optimized model can provide a basis for medicinal chemists to explore a wider chemical space toward optimization of the lead compounds and to screen the virtual compound library.

Application of Computational Biology and Artificial Intelligence in Drug Design

Traditional drug design requires a great amount of research time and developmental expense. Booming computational approaches, including computational biology, computer-aided drug design, and artificial intelligence, have the potential to expedite the efficiency of drug discovery by minimizing the time and financial cost. In recent years, computational approaches are being widely used to improve the efficacy and effectiveness of drug discovery and pipeline, leading to the approval of plenty of new drugs for marketing. The present review emphasizes on the applications of these indispensable computational approaches in aiding target identification, lead discovery, and lead optimization. Some challenges of using these approaches for drug design are also discussed. Moreover, we propose a methodology for integrating various computational techniques into new drug discovery and design.

ChemistGA: A Chemical Synthesizable Accessible Molecular Generation Algorithm for Real-World Drug Discovery

Many deep learning (DL)-based molecular generative models have been proposed to design novel molecules. These models may perform well on benchmarks, but they usually do not take real-world constraints into account, such as available training data set, synthetic accessibility, and scaffold diversity in drug discovery. In this study, a new algorithm, ChemistGA, was proposed by combining the traditional heuristic algorithm with DL, in which the crossover of the traditional genetic algorithm (GA) was redefined by DL in conjunction with GA, and an innovative backcrossing operation was implemented to generate desired molecules. Our results clearly show that ChemistGA not only retains the strength of the traditional GA but also greatly enhances the synthetic accessibility and success rate of the generated molecules with desired properties. Calculations on the two benchmarks illustrate that ChemistGA achieves impressive performance among the state-of-the-art baselines, and it opens a new avenue for the application of generative models to real-world drug discovery scenarios.