RetroGNN: Fast Estimation of Synthesizability for Virtual Screening and De Novo Design by Learning from Slow Retrosynthesis Software

Directly optimizing for synthesizability in generative molecular design using retrosynthesis models

Synthesizability in generative molecular design remains a pressing challenge. Existing methods to assess synthesizability include heuristics-based metrics or retrosynthesis models which predict a synthetic pathway. By contrast, an explicit approach anchors generation with "synthetically-feasible" chemical transformations, such that all generated molecules already have a predicted synthetic pathway. To date, retrosynthesis models have been mostly used as a post hoc filtering tool as their inference cost remains prohibitive to use directly in an optimization loop. In this work, we show that with a sufficiently sample-efficient generative model, it is straightforward to directly optimize for synthesizability using retrosynthesis models in goal-directed generation. Under a heavily-constrained computational budget, our model can generate molecules satisfying multi-parameter drug discovery optimization tasks while being synthesizable, as deemed by retrosynthesis models. We reaffirm previous findings that common synthesizability heuristics (formulated based on known bio-active molecules) can be well correlated with retrosynthesis models' solvability, such that optimizing for the latter may not be an optimal allocation of computational resources. However, going further, we show that moving to other classes of molecules, such as functional materials, current heuristics' correlations diminish, such that there is an advantage to incorporating retrosynthesis models directly in the optimization loop. Finally, we demonstrate that over-reliance on synthesizability heuristics can overlook promising molecules. The codebase is available at https://github.com/schwallergroup/saturn.

Generate what you can make: achieving in-house synthesizability with readily available resources in de novo drug design

Computer-Aided Synthesis Planning (CASP) and CASP-based approximated synthesizability scores have rarely been used as generation objectives in Computer-Aided Drug Design despite facilitating the in-silico generation of synthesizable molecules. However, these synthesizability approaches are disconnected from the reality of small laboratory drug design, where building block resources are limited, thus making the notion of in-house synthesizability with already available resources highly desirable. In this work, we show a successful in-house de novo drug design workflow generating active and in-house synthesizable ligands of monoglyceride lipase (MGLL). First, we demonstrate the successful transfer of CASP from 17.4 million commercial building blocks to a small laboratory setting of roughly 6000 building blocks with only a decrease of -12% in CASP success when accepting two reaction-steps longer synthesis routes on average. Next, we present a rapidly retrainable in-house synthesizability score, successfully capturing our in-house synthesizability without relying on external building block resources. We show that including our in-house synthesizability score in a multi-objective de novo drug design workflow, alongside a simple QSAR model, provides thousands of potentially active and easily in-house synthesizable molecules. Finally, we experimentally evaluate the synthesis and biochemical activity of three de novo candidates using their CASP-suggested synthesis routes employing only in-house building blocks. We find one candidate with evident activity, suggesting potential new ligand ideas for MGLL inhibitors while showcasing the usefulness of our in-house synthesizability score for de novo drug design.Scientific contribution Our core scientific contribution is the introduction of in-house de novo drug design, which enables the practical application of generative methods in small laboratories by utilizing a limited stock of available building blocks. Our fast-to-adapt workflow for in-house synthesizability scoring requires minimal computational retraining costs while supporting a high diversity of generated structures. We highlight the practicality of our approach through a comprehensive in-vitro case study that relies entirely on in-house resources, including in-silico generation, synthesis planning, and activity evaluation.

Artificial Intelligence in Natural Product Drug Discovery: Current Applications and Future Perspectives

Drug discovery, a multifaceted process from compound identification to regulatory approval, historically plagued by inefficiencies and time lags due to limited data utilization, now faces urgent demands for accelerated lead compound identification. Innovations in biological data and computational chemistry have spurred a shift from trial-and-error methods to holistic approaches to medicinal chemistry. Computational techniques, particularly artificial intelligence (AI), notably machine learning (ML) and deep learning (DL), have revolutionized drug development, enhancing data analysis and predictive modeling. Natural products (NPs) have long served as rich sources of biologically active compounds, with many successful drugs originating from them. Advances in information science expanded NP-related databases, enabling deeper exploration with AI. Integrating AI into NP drug discovery promises accelerated discoveries, leveraging AI's analytical prowess, including generative AI for data synthesis. This perspective illuminates AI's current landscape in NP drug discovery, addressing strengths, limitations, and future trajectories to advance this vital research domain.

Artificial Intelligence Methods and Models for Retro-Biosynthesis: A Scoping Review

Retrosynthesis aims to efficiently plan the synthesis of desirable chemicals by strategically breaking down molecules into readily available building block compounds. Having a long history in chemistry, retro-biosynthesis has also been used in the fields of biocatalysis and synthetic biology. Artificial intelligence (AI) is driving us toward new frontiers in synthesis planning and the exploration of chemical spaces, arriving at an opportune moment for promoting bioproduction that would better align with green chemistry, enhancing environmental practices. In this review, we summarize the recent advancements in the application of AI methods and models for retrosynthetic and retro-biosynthetic pathway design. These techniques can be based either on reaction templates or generative models and require scoring functions and planning strategies to navigate through the retrosynthetic graph of possibilities. We finally discuss limitations and promising research directions in this field.

Navigating the complexity of p53-DNA binding: implications for cancer therapy

Abstract

The tumor suppressor protein p53, a transcription factor playing a key role in cancer prevention, interacts with DNA as its primary means of determining cell fate in the event of DNA damage. When it becomes mutated, it opens damaged cells to the possibility of reproducing unchecked, which can lead to formation of cancerous tumors. Despite its critical role, therapies at the molecular level to restore p53 native function remain elusive, due to its complex nature. Nevertheless, considerable information has been amassed, and new means of investigating the problem have become available.

Objectives

We consider structural, biophysical, and bioinformatic insights and their implications for the role of direct and indirect readout and how they contribute to binding site recognition, particularly those of low consensus. We then pivot to consider advances in computational approaches to drug discovery.

Materials and methods

We have conducted a review of recent literature pertinent to the p53 protein.

Results

Considerable literature corroborates the idea that p53 is a complex allosteric protein that discriminates its binding sites not only via consensus sequence through direct H-bond contacts, but also a complex combination of factors involving the flexibility of the binding site. New computational methods have emerged capable of capturing such information, which can then be utilized as input to machine learning algorithms towards the goal of more intelligent and efficient de novo allosteric drug design.

Conclusions

Recent improvements in machine learning coupled with graph theory and sector analysis hold promise for advances to more intelligently design allosteric effectors that may be able to restore native p53-DNA binding activity to mutant proteins.

Clinical relevance

The ideas brought to light by this review constitute a significant advance that can be applied to ongoing biophysical studies of drugs for p53, paving the way for the continued development of new methodologies for allosteric drugs. Our discoveries hold promise to provide molecular therapeutics which restore p53 native activity, thereby offering new insights for cancer therapies.

Graphical Abstract

Structural representation of the p53 DBD (PDBID 1TUP). DNA consensus sequence is shown in gray, and the protein is shown in blue. Red beads indicate hotspot residue mutations, green beads represent DNA interacting residues, and yellow beads represent both.

Estimating the synthetic accessibility of molecules with building block and reaction-aware SAScore

Synthetic accessibility prediction is a task to estimate how easily a given molecule might be synthesizable in the laboratory, playing a crucial role in computer-aided molecular design. Although synthesis planning programs can determine synthesis routes, their slow processing times make them impractical for large-scale molecule screening. On the other hand, existing rapid synthesis accessibility estimation methods offer speed but typically lack integration with actual synthesis routes and building block information. In this work, we introduce BR-SAScore, an enhanced version of SAScore that integrates the available building block information (B) and reaction knowledge (R) from synthesis planning programs into the scoring process. In particular, we differentiate fragments inherent in building blocks and fragments to be derived from synthesis (reactions) when scoring synthetic accessibility. Compared to existing methods, our experimental findings demonstrate that BR-SAScore offers more accurate and precise identification of a molecule's synthetic accessibility by the synthesis planning program with a fast calculation time. Moreover, we illustrate how BR-SAScore provides chemically interpretable results, aligning with the capability of the synthesis planning program embedded with the same reaction knowledge and available building blocks.Scientific contributionWe introduce BR-SAScore, an extension of SAScore, to estimate the synthetic accessibility of molecules by leveraging known building-block and reactivity information. In our experiments, BR-SAScore shows superior prediction performance on predicting molecule synthetic accessibility compared to previous methods, including SAScore and deep-learning models, while requiring significantly less computation time. In addition, we show that BR-SAScore is able to precisely identify the chemical fragment contributing to the synthetic infeasibility, holding great potential for future molecule synthesizability optimization.

An algorithmic framework for synthetic cost-aware decision making in molecular design

Small molecules exhibiting desirable property profiles are often discovered through an iterative process of designing, synthesizing and testing sets of molecules. The selection of molecules to synthesize from all possible candidates is a complex decision-making process that typically relies on expert chemist intuition. Here we propose a quantitative decision-making framework, SPARROW, that prioritizes molecules for evaluation by balancing expected information gain and synthetic cost. SPARROW integrates molecular design, property prediction and retrosynthetic planning to balance the utility of testing a molecule with the cost of batch synthesis. We demonstrate, through three case studies, that the developed algorithm captures the non-additive costs inherent to batch synthesis, leverages common reaction steps and intermediates, and scales to hundreds of molecules.

DFRscore: Deep Learning-Based Scoring of Synthetic Complexity with Drug-Focused Retrosynthetic Analysis for High-Throughput Virtual Screening

Recently emerging generative AI models enable us to produce a vast number of compounds for potential applications. While they can provide novel molecular structures, the synthetic feasibility of the generated molecules is often questioned. To address this issue, a few recent studies have attempted to use deep learning models to estimate the synthetic accessibility of many molecules rapidly. However, retrosynthetic analysis tools used to train the models rely on reaction templates automatically extracted from a large reaction database that are not domain-specific and may exhibit low chemical correctness. To overcome this limitation, we introduce DFRscore (Drug-Focused Retrosynthetic score), a deep learning-based approach for a more practical assessment of synthetic accessibility in drug discovery. The DFRscore model is trained exclusively on drug-focused reactions, providing a predicted number of minimally required synthetic steps for each compound. This approach enables practitioners to filter out compounds that do not meet their desired level of synthetic accessibility at an early stage of high-throughput virtual screening for accelerated drug discovery. The proposed strategy can be easily adapted to other domains by adjusting the synthesis planning setup of the reaction templates and starting materials.

Efficient retrosynthetic planning with MCTS exploration enhanced A* search

Retrosynthetic planning, which aims to identify synthetic pathways for target molecules from starting materials, is a fundamental problem in synthetic chemistry. Computer-aided retrosynthesis has made significant progress, in which heuristic search algorithms, including Monte Carlo Tree Search (MCTS) and A* search, have played a crucial role. However, unreliable guiding heuristics often cause search failure due to insufficient exploration. Conversely, excessive exploration also prevents the search from reaching the optimal solution. In this paper, MCTS exploration enhanced A* (MEEA*) search is proposed to incorporate the exploratory behavior of MCTS into A* by providing a look-ahead search. Path consistency is adopted as a regularization to improve the generalization performance of heuristics. Extensive experimental results on 10 molecule datasets demonstrate the effectiveness of MEEA*. Especially, on the widely used United States Patent and Trademark Office (USPTO) benchmark, MEEA* achieves a 100.0% success rate. Moreover, for natural products, MEEA* successfully identifies bio-retrosynthetic pathways for 97.68% test compounds.

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 .

Applications of artificial intelligence and machine learning in dynamic pathway engineering

Dynamic pathway engineering aims to build metabolic production systems embedded with intracellular control mechanisms for improved performance. These control systems enable host cells to self-regulate the temporal activity of a production pathway in response to perturbations, using a combination of biosensors and feedback circuits for controlling expression of heterologous enzymes. Pathway design, however, requires assembling together multiple biological parts into suitable circuit architectures, as well as careful calibration of the function of each component. This results in a large design space that is costly to navigate through experimentation alone. Methods from artificial intelligence (AI) and machine learning are gaining increasing attention as tools to accelerate the design cycle, owing to their ability to identify hidden patterns in data and rapidly screen through large collections of designs. In this review, we discuss recent developments in the application of machine learning methods to the design of dynamic pathways and their components. We cover recent successes and offer perspectives for future developments in the field. The integration of AI into metabolic engineering pipelines offers great opportunities to streamline design and discover control systems for improved production of high-value chemicals.

Fake it until you make it? Generative de novo design and virtual screening of synthesizable molecules

Computational techniques, including virtual screening, de novo design, and generative models, play an increasing role in expediting DMTA cycles for modern molecular discovery. However, computationally proposed molecules must be synthetically feasible for laboratory testing. In this perspective, we offer a succinct introduction to the subject, and showcase typical workflows to integrate synthesis planning, synthesizability scoring, and molecule generation. Finally, we address limitations and opportunities for future research.

Everything is connected: Graph neural networks

In many ways, graphs are the main modality of data we receive from nature. This is due to the fact that most of the patterns we see, both in natural and artificial systems, are elegantly representable using the language of graph structures. Prominent examples include molecules (represented as graphs of atoms and bonds), social networks and transportation networks. This potential has already been seen by key scientific and industrial groups, with already-impacted application areas including traffic forecasting, drug discovery, social network analysis and recommender systems. Further, some of the most successful domains of application for machine learning in previous years-images, text and speech processing-can be seen as special cases of graph representation learning, and consequently there has been significant exchange of information between these areas. The main aim of this short survey is to enable the reader to assimilate the key concepts in the area, and position graph representation learning in a proper context with related fields.

Critical assessment of synthetic accessibility scores in computer-assisted synthesis planning

Modern computer-assisted synthesis planning tools provide strong support for this problem. However, they are still limited by computational complexity. This limitation may be overcome by scoring the synthetic accessibility as a pre-retrosynthesis heuristic. A wide range of machine learning scoring approaches is available, however, their applicability and correctness were studied to a limited extent. Moreover, there is a lack of critical assessment of synthetic accessibility scores with common test conditions.In the present work, we assess if synthetic accessibility scores can reliably predict the outcomes of retrosynthesis planning. Using a specially prepared compounds database, we examine the outcomes of the retrosynthetic tool AiZynthFinder. We test whether synthetic accessibility scores: SAscore, SYBA, SCScore, and RAscore accurately predict the results of retrosynthesis planning. Furthermore, we investigate if synthetic accessibility scores can speed up retrosynthesis planning by better prioritizing explored partial synthetic routes and thus reducing the size of the search space. For that purpose, we analyze the AiZynthFinder partial solutions search trees, their structure, and complexity parameters, such as the number of nodes, or treewidth.We confirm that synthetic accessibility scores in most cases well discriminate feasible molecules from infeasible ones and can be potential boosters of retrosynthesis planning tools. Moreover, we show the current challenges of designing computer-assisted synthesis planning tools. We conclude that hybrid machine learning and human intuition-based synthetic accessibility scores can efficiently boost the effectiveness of computer-assisted retrosynthesis planning, however, they need to be carefully crafted for retrosynthesis planning algorithms.The source code of this work is publicly available at https://github.com/grzsko/ASAP .

Predictive chemistry: machine learning for reaction deployment, reaction development, and reaction discovery

The field of predictive chemistry relates to the development of models able to describe how molecules interact and react. It encompasses the long-standing task of computer-aided retrosynthesis, but is far more reaching and ambitious in its goals. In this review, we summarize several areas where predictive chemistry models hold the potential to accelerate the deployment, development, and discovery of organic reactions and advance synthetic chemistry.

Organic Compound Synthetic Accessibility Prediction Based on the Graph Attention Mechanism

Accurate estimation of the synthetic accessibility of small molecules is needed in many phases of drug discovery. Several expert-crafted scoring methods and descriptor-based quantitative structure-activity relationship (QSAR) models have been developed for synthetic accessibility assessment, but their practical applications in drug discovery are still quite limited because of relatively low prediction accuracy and poor model interpretability. In this study, we proposed a data-driven interpretable prediction framework called GASA (Graph Attention-based assessment of Synthetic Accessibility) to evaluate the synthetic accessibility of small molecules by distinguishing compounds to be easy- (ES) or hard-to-synthesize (HS). GASA is a graph neural network (GNN) architecture that makes self-feature deduction by applying an attention mechanism to automatically capture the most important structural features related to synthetic accessibility. The sampling around the hypothetical classification boundary was used to improve the ability of GASA to distinguish structurally similar molecules. GASA was extensively evaluated and compared with two descriptor-based machine learning methods (random forest, RF; eXtreme gradient boosting, XGBoost) and four existing scores (SYBA: SYnthetic Bayesian Accessibility; SCScore: Synthetic Complexity score; RAscore: Retrosynthetic Accessibility score; SAscore: Synthetic Accessibility score). Our analysis demonstrates that GASA achieved remarkable performance in distinguishing similar molecules compared with other methods and had a broader applicability domain. In addition, we show how GASA learns the important features that affect molecular synthetic accessibility by assigning attention weights to different atoms. An online prediction service for GASA was offered at http://cadd.zju.edu.cn/gasa/.