A collection of robust organic synthesis reactions for in silico molecule design

Target-specific novel molecules with their recipe: Incorporating synthesizability in the design process

Application of Artificial intelligence (AI) in drug discovery has led to several success stories in recent times. While traditional methods mostly relied upon screening large chemical libraries for early-stage drug-design, de novo design can help identify novel target-specific molecules by sampling from a much larger chemical space. Although this has increased the possibility of finding diverse and novel molecules from previously unexplored chemical space, this has also posed a great challenge for medicinal chemists to synthesize at least some of the de novo designed novel molecules for experimental validation. To address this challenge, in this work, we propose a novel forward synthesis-based generative AI method, which is used to explore the synthesizable chemical space. The method uses a structure-based drug design framework, where the target protein structure and a target-specific seed fragment from co-crystal structures can be the initial inputs. A random fragment from a purchasable fragment library can also be the input if a target-specific fragment is unavailable. Then a template-based forward synthesis route prediction and molecule generation is performed in parallel using the Monte Carlo Tree Search (MCTS) method where, the subsequent fragments for molecule growth can again be obtained from a purchasable fragment library. The rewards for each iteration of MCTS are computed using a drug-target affinity (DTA) model based on the docking pose of the generated reaction intermediates at the binding site of the target protein of interest. With the help of the proposed method, it is now possible to overcome one of the major obstacles posed to the AI-based drug design approaches through the ability of the method to design novel target-specific synthesizable molecules.

FragGrow: A Web Server for Structure-Based Drug Design by Fragment Growing within Constraints

Fragment growing is an important ligand design strategy in drug discovery. In this study, we present FragGrow, a web server that facilitates structure-based drug design by fragment growing. FragGrow offers two working modes: one for growing molecules through the direct replacement of hydrogen atoms or substructures and the other for growing via virtual synthesis. FragGrow works by searching for suitable fragments that meet a set of constraints from an indexed 3D fragment database and using them to create new compounds in 3D space. The users can set a range of constraints when searching for their desired fragment, including the fragment's ability to interact with specific protein sites; its size, topology, and physicochemical properties; and the presence of particular heteroatoms and functional groups within the fragment. We hope that FragGrow will serve as a useful tool for medicinal chemists in ligand design. The FragGrow server is freely available to researchers and can be accessed at https://fraggrow.xundrug.cn.

Augmenting large language models with chemistry tools

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery and materials design. By integrating 18 expert-designed tools and using GPT-4 as the LLM, ChemCrow augments the LLM performance in chemistry, and new capabilities emerge. Our agent autonomously planned and executed the syntheses of an insect repellent and three organocatalysts and guided the discovery of a novel chromophore. Our evaluation, including both LLM and expert assessments, demonstrates ChemCrow's effectiveness in automating a diverse set of chemical tasks. Our work not only aids expert chemists and lowers barriers for non-experts but also fosters scientific advancement by bridging the gap between experimental and computational chemistry.

A virtual library of small molecules mimicking dipeptides

Virtual combinatorial libraries are prevalent in drug discovery due to improvements in the prediction of synthetic reactions that can be performed. This has gone hand in hand with the development of virtual screening capabilities to effectively screen the large chemical spaces spanned by exhaustive enumeration of reaction products. In this study, we generated a small-molecule dipeptide mimic library to target proteins binding small peptides. The library was created based on the general idea of peptide synthesis, that is, amino acid mimics were reacted in silico to form the dipeptide mimics, yielding 2,036,819 unique compounds. After docking calculations, two compounds from the library were synthesized and tested against WD repeat-containing protein 5 (WDR5) and histamine receptors H1-H4 to evaluate whether these molecules are viable in assays. The compounds showed the highest potency at the histamine H3 receptor, with Ki values in the two-digit micromolar range.

ChemoDOTS: a web server to design chemistry-driven focused libraries

In drug discovery, the successful optimization of an initial hit compound into a lead molecule requires multiple cycles of chemical modification. Consequently, there is a need to efficiently generate synthesizable chemical libraries to navigate the chemical space surrounding the primary hit. To address this need, we introduce ChemoDOTS, an easy-to-use web server for hit-to-lead chemical optimization freely available at https://chemodots.marseille.inserm.fr/. With this tool, users enter an activated form of the initial hit molecule then choose from automatically detected reactive functions. The server proposes compatible chemical transformations via an ensemble of encoded chemical reactions widely used in the pharmaceutical industry during hit-to-lead optimization. After selection of the desired reactions, all compatible chemical building blocks are automatically coupled to the initial hit to generate a raw chemical library. Post-processing filters can be applied to extract a subset of compounds with specific physicochemical properties. Finally, explicit stereoisomers and tautomers are computed, and a 3D conformer is generated for each molecule. The resulting virtual library is compatible with most docking software for virtual screening campaigns. ChemoDOTS rapidly generates synthetically feasible, hit-focused, large, diverse chemical libraries with finely-tuned physicochemical properties via a user-friendly interface providing a powerful resource for researchers engaged in hit-to-lead optimization.

Do Chemformers Dream of Organic Matter? Evaluating a Transformer Model for Multistep Retrosynthesis

Synthesis planning of new pharmaceutical compounds is a well-known bottleneck in modern drug design. Template-free methods, such as transformers, have recently been proposed as an alternative to template-based methods for single-step retrosynthetic predictions. Here, we trained and evaluated a transformer model, called the Chemformer, for retrosynthesis predictions within drug discovery. The proprietary data set used for training comprised ∼18 M reactions from literature, patents, and electronic lab notebooks. Chemformer was evaluated for the purpose of both single-step and multistep retrosynthesis. We found that the single-step performance of Chemformer was especially good on reaction classes common in drug discovery, with most reaction classes showing a top-10 round-trip accuracy above 0.97. Moreover, Chemformer reached a higher round-trip accuracy compared to that of a template-based model. By analyzing multistep retrosynthesis experiments, we observed that Chemformer found synthetic routes, leading to commercial starting materials for 95% of the target compounds, an increase of more than 20% compared to the template-based model on a proprietary compound data set. In addition to this, we discovered that Chemformer suggested novel disconnections corresponding to reaction templates, which are not included in the template-based model. These findings were further supported by a publicly available ChEMBL compound data set. The conclusions drawn from this work allow for the design of a synthesis planning tool where template-based and template-free models work in harmony to optimize retrosynthetic recommendations.

Rxn-INSIGHT: fast chemical reaction analysis using bond-electron matrices

The challenge of devising pathways for organic synthesis remains a central issue in the field of medicinal chemistry. Over the span of six decades, computer-aided synthesis planning has given rise to a plethora of potent tools for formulating synthetic routes. Nevertheless, a significant expert task still looms: determining the appropriate solvent, catalyst, and reagents when provided with a set of reactants to achieve and optimize the desired product for a specific step in the synthesis process. Typically, chemists identify key functional groups and rings that exert crucial influences at the reaction center, classify reactions into categories, and may assign them names. This research introduces Rxn-INSIGHT, an open-source algorithm based on the bond-electron matrix approach, with the purpose of automating this endeavor. Rxn-INSIGHT not only streamlines the process but also facilitates extensive querying of reaction databases, effectively replicating the thought processes of an organic chemist. The core functions of the algorithm encompass the classification and naming of reactions, extraction of functional groups, rings, and scaffolds from the involved chemical entities. The provision of reaction condition recommendations based on the similarity and prevalence of reactions eventually arises as a side application. The performance of our rule-based model has been rigorously assessed against a carefully curated benchmark dataset, exhibiting an accuracy rate exceeding 90% in reaction classification and surpassing 95% in reaction naming. Notably, it has been discerned that a pivotal factor in selecting analogous reactions lies in the analysis of ring structures participating in the reactions. An examination of ring structures within the USPTO chemical reaction database reveals that with just 35 unique rings, a remarkable 75% of all rings found in nearly 1 million products can be encompassed. Furthermore, Rxn-INSIGHT is proficient in suggesting appropriate choices for solvents, catalysts, and reagents in entirely novel reactions, all within the span of a second, utilizing nothing more than an everyday laptop.

Protein Structure-Based Organic Chemistry-Driven Ligand Design from Ultralarge Chemical Spaces

Ultralarge chemical spaces describing several billion compounds are revolutionizing hit identification in early drug discovery. Because of their size, such chemical spaces cannot be fully enumerated and require ad-hoc computational tools to navigate them and pick potentially interesting hits. We here propose a structure-based approach to ultralarge chemical space screening in which commercial chemical reagents are first docked to the target of interest and then directly connected according to organic chemistry and topological rules, to enumerate drug-like compounds under three-dimensional constraints of the target. When applied to bespoke chemical spaces of different sizes and chemical complexity targeting two receptors of pharmaceutical interest (estrogen β receptor, dopamine D3 receptor), the computational method was able to quickly enumerate hits that were either known ligands (or very close analogs) of targeted receptors as well as chemically novel candidates that could be experimentally confirmed by in vitro binding assays. The proposed approach is generic, can be applied to any docking algorithm, and requires few computational resources to prioritize easily synthesizable hits from billion-sized chemical spaces.

Recent Advances in Automated Structure-Based De Novo Drug Design

As the number of determined and predicted protein structures and the size of druglike 'make-on-demand' libraries soar, the time-consuming nature of structure-based computer-aided drug design calls for innovative computational algorithms. De novo drug design introduces in silico heuristics to accelerate searching in the vast chemical space. This review focuses on recent advances in structure-based de novo drug design, ranging from conventional fragment-based methods, evolutionary algorithms, and Metropolis Monte Carlo methods to deep generative models. Due to the historical limitation of de novo drug design generating readily available drug-like molecules, we highlight the synthetic accessibility efforts in each category and the benchmarking strategies taken to validate the proposed framework.

Full Modification Control over Retrosynthetic Routes for Guided Optimization of Lead Structures

Synthesizability is essential for compounds designed in silico. Regardless, synthetic accessibility is often considered only as an afterthought in the design and optimization process. In addition, the trend with modern computer-aided drug design methods is going toward full automation and away from the possibility of incorporating user knowledge. With this work, we present the second major release of our software tool, Synthesia, for synthesis-aware lead structure modification, where the user's expertise is now fully utilized. A provided retrosynthetic route is used as a pathway to guide structural modifications that introduce desired structural changes in the target compound. Moreover, the approach allows the user to define the exact position or component in the retrosynthetic route, which should be modified, further integrating the user's expert knowledge. This paper describes the functionality of Synthesia, its basic concepts, and several application scenarios ranging from simple examples to a comparison of the effects of the different exchange functions to an analysis of a set of bioisosteric linker structures, highlighting potential synthetically feasible replacements.

Probabilistic generative transformer language models for generative design of molecules

Self-supervised neural language models have recently found wide applications in the generative design of organic molecules and protein sequences as well as representation learning for downstream structure classification and functional prediction. However, most of the existing deep learning models for molecule design usually require a big dataset and have a black-box architecture, which makes it difficult to interpret their design logic. Here we propose the Generative Molecular Transformer (GMTransformer), a probabilistic neural network model for generative design of molecules. Our model is built on the blank filling language model originally developed for text processing, which has demonstrated unique advantages in learning the "molecules grammars" with high-quality generation, interpretability, and data efficiency. Benchmarked on the MOSES datasets, our models achieve high novelty and Scaf compared to other baselines. The probabilistic generation steps have the potential in tinkering with molecule design due to their capability of recommending how to modify existing molecules with explanation, guided by the learned implicit molecule chemistry. The source code and datasets can be accessed freely at https://github.com/usccolumbia/GMTransformer.

School of cheminformatics in Latin America

We report the major highlights of the School of Cheminformatics in Latin America, Mexico City, November 24-25, 2022. Six lectures, one workshop, and one roundtable with four editors were presented during an online public event with speakers from academia, big pharma, and public research institutions. One thousand one hundred eighty-one students and academics from seventy-nine countries registered for the meeting. As part of the meeting, advances in enumeration and visualization of chemical space, applications in natural product-based drug discovery, drug discovery for neglected diseases, toxicity prediction, and general guidelines for data analysis were discussed. Experts from ChEMBL presented a workshop on how to use the resources of this major compounds database used in cheminformatics. The school also included a round table with editors of cheminformatics journals. The full program of the meeting and the recordings of the sessions are publicly available at https://www.youtube.com/@SchoolChemInfLA/featured .

Evaluation of the Topology Space of DNA-Encoded Libraries

DNA-encoded libraries (DELs) are widely used in the discovery of drug candidates, and understanding their design principles is critical for accessing better libraries. Most DELs are combinatorial in nature and are synthesized by assembling sets of building blocks in specific topologies. In this study, different aspects of library topology were explored and their effect on DEL properties and chemical diversity was analyzed. We introduce a descriptor for DEL topological assignment (DELTA) and use it to examine the landscape of possible DEL topologies and their coverage in the literature. A generative topographic mapping analysis revealed that the impact of library topology on chemical space coverage is secondary to building block selection. Furthermore, it became apparent that the descriptor used to analyze chemical space dictates how structures cluster, with the effects of topology being apparent when using three-dimensional descriptors but not with common two-dimensional descriptors. This outcome points to potential challenges of attempts to predict DEL productivity based on chemical space analyses alone. While topology is rather inconsequential for defining the chemical space of encoded compounds, it greatly affects possible interactions with target proteins as illustrated in docking studies using NAD/NADP binding proteins as model receptors.

Relevance of the Trillion-Sized Chemical Space "eXplore" as a Source for Drug Discovery

Within the past two decades, virtual combinatorial compound collections, so-called chemical spaces, became an important molecule source for pharmaceutical research all over the world. The emergence of compound vendor chemical spaces with rapidly growing numbers of molecules raises questions about their application suitability and the quality of the content. Here, we examine the composition of the recently published and, so far, biggest chemical space, "eXplore", which comprises approximately 2.8 trillion virtual product molecules. The utility of eXplore to retrieve interesting chemistry around approved drugs and common Bemis Murcko scaffolds has been assessed with several methods (FTrees, SpaceLight, SpaceMACS). Further, the overlap between several vendor chemical spaces and a physicochemical property distribution analysis has been performed. Despite the straightforward chemical reactions underlying its setup, eXplore is demonstrated to provide relevant and, most importantly, easily accessible molecules for drug discovery campaigns.

Navigating large chemical spaces in early-phase drug discovery

The size of actionable chemical spaces is surging, owing to a variety of novel techniques, both computational and experimental. As a consequence, novel molecular matter is now at our fingertips that cannot and should not be neglected in early-phase drug discovery. Huge, combinatorial, make-on-demand chemical spaces with high probability of synthetic success rise exponentially in content, generative machine learning models go hand in hand with synthesis prediction, and DNA-encoded libraries offer new ways of hit structure discovery. These technologies enable to search for new chemical matter in a much broader and deeper manner with less effort and fewer financial resources. These transformational developments require new cheminformatics approaches to make huge chemical spaces searchable and analyzable with low resources, and with as little energy consumption as possible. Substantial progress has been made in the past years with respect to computation as well as organic synthesis. First examples of bioactive compounds resulting from the successful use of these novel technologies demonstrate their power to contribute to tomorrow's drug discovery programs. This article gives a compact overview of the state-of-the-art.

Computational approaches streamlining drug discovery

Computer-aided drug discovery has been around for decades, although the past few years have seen a tectonic shift towards embracing computational technologies in both academia and pharma. This shift is largely defined by the flood of data on ligand properties and binding to therapeutic targets and their 3D structures, abundant computing capacities and the advent of on-demand virtual libraries of drug-like small molecules in their billions. Taking full advantage of these resources requires fast computational methods for effective ligand screening. This includes structure-based virtual screening of gigascale chemical spaces, further facilitated by fast iterative screening approaches. Highly synergistic are developments in deep learning predictions of ligand properties and target activities in lieu of receptor structure. Here we review recent advances in ligand discovery technologies, their potential for reshaping the whole process of drug discovery and development, as well as the challenges they encounter. We also discuss how the rapid identification of highly diverse, potent, target-selective and drug-like ligands to protein targets can democratize the drug discovery process, presenting new opportunities for the cost-effective development of safer and more effective small-molecule treatments.

Discovery of a PDZ Domain Inhibitor Targeting the Syndecan/Syntenin Protein-Protein Interaction: A Semi-Automated "Hit Identification-to-Optimization" Approach

The rapid identification of early hits by fragment-based approaches and subsequent hit-to-lead optimization represents a challenge for drug discovery. To address this challenge, we created a strategy called "DOTS" that combines molecular dynamic simulations, computer-based library design (chemoDOTS) with encoded medicinal chemistry reactions, constrained docking, and automated compound evaluation. To validate its utility, we applied our DOTS strategy to the challenging target syntenin, a PDZ domain containing protein and oncology target. Herein, we describe the creation of a "best-in-class" sub-micromolar small molecule inhibitor for the second PDZ domain of syntenin validated in cancer cell assays. Key to the success of our DOTS approach was the integration of protein conformational sampling during hit identification stage and the synthetic feasibility ranking of the designed compounds throughout the optimization process. This approach can be broadly applied to other protein targets with known 3D structures to rapidly identify and optimize compounds as chemical probes and therapeutic candidates.

Visualizing Generic Reaction Patterns

Reaction schemes for organic molecules play a crucial role in modern in silico drug design processes. In contrast to the classical drawn reaction diagrams, computational chemists prefer SMARTS based line notations due to a substantially increased expressiveness and precision. They are used to search databases, calculate synthesizability, generate new molecules, or simulate novel reactions. Working with computer-readable representations of reaction schemes can be challenging due to the complexity of the features to be represented. Line representations of reaction schemes can often be cryptic, even to experienced users. To simplify the work with Reaction SMARTS for synthetic, computational, and medicinal chemists, we introduce a visualization technique for reaction schemes and provide a respective tool, called ReactionViewer. ReactionViewer is able to convert reaction schemes encoded as Reaction SMILES, Reaction SMARTS, or SMIRKS into a visual representation. The visualization technique is based on the concept of structure diagrams and follows IUPAC's "Compendium of Chemical Terminology" definition of chemical reaction equations for the reaction symbols. We demonstrate the applicability of the method using two data sets of organic synthesis reaction schemes taken from recent publications. We discuss various properties of the visualization and highlight its readability and interpretability.

MegaSyn: Integrating Generative Molecular Design, Automated Analog Designer, and Synthetic Viability Prediction

Generative machine learning models have become widely adopted in drug discovery and other fields to produce new molecules and explore molecular space, with the goal of discovering novel compounds with optimized properties. These generative models are frequently combined with transfer learning or scoring of the physicochemical properties to steer generative design, yet often, they are not capable of addressing a wide variety of potential problems, as well as converge into similar molecular space when combined with a scoring function for the desired properties. In addition, these generated compounds may not be synthetically feasible, reducing their capabilities and limiting their usefulness in real-world scenarios. Here, we introduce a suite of automated tools called MegaSyn representing three components: a new hill-climb algorithm, which makes use of SMILES-based recurrent neural network (RNN) generative models, analog generation software, and retrosynthetic analysis coupled with fragment analysis to score molecules for their synthetic feasibility. We show that by deconstructing the targeted molecules and focusing on substructures, combined with an ensemble of generative models, MegaSyn generally performs well for the specific tasks of generating new scaffolds as well as targeted analogs, which are likely synthesizable and druglike. We now describe the development, benchmarking, and testing of this suite of tools and propose how they might be used to optimize molecules or prioritize promising lead compounds using these RNN examples provided by multiple test case examples.

Drugsniffer: An Open Source Workflow for Virtually Screening Billions of Molecules for Binding Affinity to Protein Targets

The SARS-CoV2 pandemic has highlighted the importance of efficient and effective methods for identification of therapeutic drugs, and in particular has laid bare the need for methods that allow exploration of the full diversity of synthesizable small molecules. While classical high-throughput screening methods may consider up to millions of molecules, virtual screening methods hold the promise of enabling appraisal of billions of candidate molecules, thus expanding the search space while concurrently reducing costs and speeding discovery. Here, we describe a new screening pipeline, called drugsniffer, that is capable of rapidly exploring drug candidates from a library of billions of molecules, and is designed to support distributed computation on cluster and cloud resources. As an example of performance, our pipeline required ∼40,000 total compute hours to screen for potential drugs targeting three SARS-CoV2 proteins among a library of ∼3.7 billion candidate molecules.

Exploration of Ultralarge Compound Collections for Drug Discovery

Designing new medicines more cheaply and quickly is tightly linked to the quest of exploring chemical space more widely and efficiently. Chemical space is monumentally large, but recent advances in computer software and hardware have enabled researchers to navigate virtual chemical spaces containing billions of chemical structures. This review specifically concerns collections of many millions or even billions of enumerated chemical structures as well as even larger chemical spaces that are not fully enumerated. We present examples of chemical libraries and spaces and the means used to construct them, and we discuss new technologies for searching huge libraries and for searching combinatorially in chemical space. We also cover space navigation techniques and consider new approaches to de novo drug design and the impact of the "autonomous laboratory" on synthesis of designed compounds. Finally, we summarize some other challenges and opportunities for the future.

Fragment-to-lead tailored in silico design

Fragment-based drug discovery (FBDD) emerged as a disruptive technology and became established during the last two decades. Its rationality and low entry costs make it appealing, and the numerous examples of approved drugs discovered through FBDD validate the approach. However, FBDD still faces numerous challenges. Perhaps the most important one is the transformation of the initial fragment hits into viable leads. Fragment-to-lead (F2L) optimization is resource-intensive and is therefore limited in the possibilities that can be actively pursued. In silico strategies play an important role in F2L, as they can perform a deeper exploration of chemical space, prioritize molecules with high probabilities of being active and generate non-obvious ideas. Here we provide a critical overview of current in silico strategies in F2L optimization and highlight their remarkable impact. While very effective, most solutions are target- or fragment- specific. We propose that fully integrated in silico strategies, capable of automatically and systematically exploring the fast-growing available chemical space can have a significant impact on accelerating the release of fragment originated drugs.

De novo molecular drug design benchmarking

De novo molecular design for drug discovery is a growing field. Deep neural networks (DNNs) are becoming more widespread in their use for machine learning models. As more DNN models are proposed for molecular design, benchmarking methods are crucial for the comparision and validation of these models. This review looks at recently proposed benchmarking methods Fréchet ChemNet Distance, GuacaMol and Molecular Sets (MOSES), and provides a commentary on their future potential applications in de novo molecular drug design and possible next steps for further validation of these benchmarking methods.

Learning from Nature: From a Marine Natural Product to Synthetic Cyclooxygenase-1 Inhibitors by Automated De Novo Design

The repertoire of natural products offers tremendous opportunities for chemical biology and drug discovery. Natural product-inspired synthetic molecules represent an ecologically and economically sustainable alternative to the direct utilization of natural products. De novo design with machine intelligence bridges the gap between the worlds of bioactive natural products and synthetic molecules. On employing the compound Marinopyrrole A from marine Streptomyces as a design template, the algorithm constructs innovative small molecules that can be synthesized in three steps, following the computationally suggested synthesis route. Computational activity prediction reveals cyclooxygenase (COX) as a putative target of both Marinopyrrole A and the de novo designs. The molecular designs are experimentally confirmed as selective COX-1 inhibitors with nanomolar potency. X-ray structure analysis reveals the binding of the most selective compound to COX-1. This molecular design approach provides a blueprint for natural product-inspired hit and lead identification for drug discovery with machine intelligence.

Fragment-based drug design targeting syntenin PDZ2 domain involved in exosomal release and tumour spread

Syntenin stimulates exosome production and its expression is upregulated in many cancers and implicated in the spread of metastatic tumor. These effects are supported by syntenin PDZ domains interacting with syndecans. We therefore aimed to develop, through a fragment-based drug design approach, novel inhibitors targeting syntenin-syndecan interactions. We describe here the optimization of a fragment, 'hit' C58, identified by in vitro screening of a PDZ-focused fragment library, which binds specifically to the syntenin-PDZ2 domain at the same binding site as the syndecan-2 peptide. X-ray crystallographic structures and computational docking were used to guide our optimization process and lead to compounds 45 and 57 (IC₅₀ = 33 μM and 47 μM; respectively), two representatives of syntenin-syndecan interactions inhibitors, that selectively affect the syntenin-exosome release. These findings demonstrate that it is possible to identify small molecules inhibiting syntenin-syndecan interaction and exosome release that may be useful for cancer therapy.

De novo molecular design and generative models

Molecular design strategies are integral to therapeutic progress in drug discovery. Computational approaches for de novo molecular design have been developed over the past three decades and, recently, thanks in part to advances in machine learning (ML) and artificial intelligence (AI), the drug discovery field has gained practical experience. Here, we review these learnings and present de novo approaches according to the coarseness of their molecular representation: that is, whether molecular design is modeled on an atom-based, fragment-based, or reaction-based paradigm. Furthermore, we emphasize the value of strong benchmarks, describe the main challenges to using these methods in practice, and provide a viewpoint on further opportunities for exploration and challenges to be tackled in the upcoming years.

Meta Learning for Low-Resource Molecular Optimization

The goal of molecular optimization (MO) is to discover molecules that acquire improved pharmaceutical properties over a known starting molecule. Despite many recent successes of new approaches for MO, these methods were typically developed for particular properties with rich annotated training examples. Thus, these approaches are difficult to implement in real scenes where only a small amount of pharmaceutical data is usually available due to the expense and significant effort required for the data collection. Here, we propose a new approach, Meta-MO, for molecular optimization with a handful of training samples based on the well-recognized first-order meta-learning algorithms. By using a set of meta tasks with rich training samples, Meta-MO trains a meta model through the meta-learning optimization and adapts the learned model to new low-resource MO tasks. Meta-MO was shown to consistently outperform several pretraining and multitask training procedures, providing an average improvement in the success rate of 4.3% on a large-scale bioactivity data set with diverse target variations. We also observed that Meta-MO resulted in the best performing models across fine-tuning sets with only dozens of samples. To the best of our knowledge, this is the first study to apply meta learning to MO tasks. More importantly, such a strategy could be further extended to many low-resource scenarios in real-world drug design.

Transformer neural network for protein-specific de novo drug generation as a machine translation problem

Drug discovery for a protein target is a very laborious, long and costly process. Machine learning approaches and, in particular, deep generative networks can substantially reduce development time and costs. However, the majority of methods imply prior knowledge of protein binders, their physicochemical characteristics or the three-dimensional structure of the protein. The method proposed in this work generates novel molecules with predicted ability to bind a target protein by relying on its amino acid sequence only. We consider target-specific de novo drug design as a translational problem between the amino acid “language” and simplified molecular input line entry system representation of the molecule. To tackle this problem, we apply Transformer neural network architecture, a state-of-the-art approach in sequence transduction tasks. Transformer is based on a self-attention technique, which allows the capture of long-range dependencies between items in sequence. The model generates realistic diverse compounds with structural novelty. The computed physicochemical properties and common metrics used in drug discovery fall within the plausible drug-like range of values.

Valid, Plausible, and Diverse Retrosynthesis Using Tied Two-Way Transformers with Latent Variables

Retrosynthesis is an essential task in organic chemistry for identifying the synthesis pathways of newly discovered materials, and with the recent advances in deep learning, there have been growing attempts to solve the retrosynthesis problem through transformer models, which are the state-of-the-art in neural machine translation, by converting the problem into a machine translation problem. However, the pure transformer provides unsatisfactory results that lack grammatical validity, chemical plausibility, and diversity in reactant candidates. In this study, we develop tied two-way transformers with latent modeling to solve those problems using cycle consistency checks, parameter sharing, and multinomial latent variables. Experimental results obtained using public and in-house datasets demonstrate that the proposed model improves the retrosynthesis accuracy, grammatical error, and diversity, and qualitative evaluation results verify its ability to suggest valid and plausible results.

RetroBioCat as a computer-aided synthesis planning tool for biocatalytic reactions and cascades

As the enzyme toolbox for biocatalysis has expanded, so has the potential for the construction of powerful enzymatic cascades for efficient and selective synthesis of target molecules. Additionally, recent advances in computer-aided synthesis planning are revolutionising synthesis design in both synthetic biology and organic chemistry. However, the potential for biocatalysis is not well captured by tools currently available in either field. Here we present RetroBioCat, an intuitive and accessible tool for computer-aided design of biocatalytic cascades, freely available at retrobiocat.com. Our approach uses a set of expertly encoded reaction rules encompassing the enzyme toolbox for biocatalysis, and a system for identifying literature precedent for enzymes with the correct substrate specificity where this is available. Applying these rules for automated biocatalytic retrosynthesis, we show our tool to be capable of identifying promising biocatalytic pathways to target molecules, validated using a test-set of recent cascades described in the literature.

Transmol: repurposing a language model for molecular generation

Recent advances in convolutional neural networks have inspired the application of deep learning to other disciplines. Even though image processing and natural language processing have turned out to be the most successful, there are many other domains that have also benefited; among them, life sciences in general and chemistry and drug design in particular. In concordance with this observation, from 2018 the scientific community has seen a surge of methodologies related to the generation of diverse molecular libraries using machine learning. However to date, attention mechanisms have not been employed for the problem of de novo molecular generation. Here we employ a variant of transformers, an architecture recently developed for natural language processing, for this purpose. Our results indicate that the adapted Transmol model is indeed applicable for the task of generating molecular libraries and leads to statistically significant increases in some of the core metrics of the MOSES benchmark. The presented model can be tuned to either input-guided or diversity-driven generation modes by applying a standard one-seed and a novel two-seed approach, respectively. Accordingly, the one-seed approach is best suited for the targeted generation of focused libraries composed of close analogues of the seed structure, while the two-seeds approach allows us to dive deeper into under-explored regions of the chemical space by attempting to generate the molecules that resemble both seeds. To gain more insights about the scope of the one-seed approach, we devised a new validation workflow that involves the recreation of known ligands for an important biological target vitamin D receptor. To further benefit the chemical community, the Transmol algorithm has been incorporated into our cheML.io web database of ML-generated molecules as a second generation on-demand methodology.

A novel molecular generation pipeline employing an attention-based neural network.

DeepCOMO: from structure-activity relationship diagnostics to generative molecular design using the compound optimization monitor methodology

The compound optimization monitor (COMO) approach was originally developed as a diagnostic approach to aid in evaluating development stages of analog series and progress made during lead optimization. COMO uses virtual analog populations for the assessment of chemical saturation of analog series and has been further developed to bridge between optimization diagnostics and compound design. Herein, we discuss key methodological features of COMO in its scientific context and present a deep learning extension of COMO for generative molecular design, leading to the introduction of DeepCOMO. Applications on exemplary analog series are reported to illustrate the entire DeepCOMO repertoire, ranging from chemical saturation and structure-activity relationship progression diagnostics to the evaluation of different analog design strategies and prioritization of virtual candidates for optimization efforts, taking into account the development stage of individual analog series.

SAVI, in silico generation of billions of easily synthesizable compounds through expert-system type rules

We have made available a database of over 1 billion compounds predicted to be easily synthesizable, called Synthetically Accessible Virtual Inventory (SAVI). They have been created by a set of transforms based on an adaptation and extension of the CHMTRN/PATRAN programming languages describing chemical synthesis expert knowledge, which originally stem from the LHASA project. The chemoinformatics toolkit CACTVS was used to apply a total of 53 transforms to about 150,000 readily available building blocks (enamine.net). Only single-step, two-reactant syntheses were calculated for this database even though the technology can execute multi-step reactions. The possibility to incorporate scoring systems in CHMTRN allowed us to subdivide the database of 1.75 billion compounds in sets according to their predicted synthesizability, with the most-synthesizable class comprising 1.09 billion synthetic products. Properties calculated for all SAVI products show that the database should be well-suited for drug discovery. It is being made publicly available for free download from https://doi.org/10.35115/37n9-5738.

AutoGrow4: an open-source genetic algorithm for de novo drug design and lead optimization

We here present AutoGrow4, an open-source program for semi-automated computer-aided drug discovery. AutoGrow4 uses a genetic algorithm to evolve predicted ligands on demand and so is not limited to a virtual library of pre-enumerated compounds. It is a useful tool for generating entirely novel drug-like molecules and for optimizing preexisting ligands. By leveraging recent computational and cheminformatics advancements, AutoGrow4 is faster, more stable, and more modular than previous versions. It implements new docking-program compatibility, chemical filters, multithreading options, and selection methods to support a wide range of user needs. To illustrate both de novo design and lead optimization, we here apply AutoGrow4 to the catalytic domain of poly(ADP-ribose) polymerase 1 (PARP-1), a well characterized DNA-damage-recognition protein. AutoGrow4 produces drug-like compounds with better predicted binding affinities than FDA-approved PARP-1 inhibitors (positive controls). The predicted binding modes of the AutoGrow4 compounds mimic those of the known inhibitors, even when AutoGrow4 is seeded with random small molecules. AutoGrow4 is available under the terms of the Apache License, Version 2.0. A copy can be downloaded free of charge from http://durrantlab.com/autogrow4.

Comparison of Large Chemical Spaces

Chemical libraries are commonplace in computer-aided drug discovery, and assessing their overlap/complementarity is a routine task. For this purpose, different techniques are applied, ranging from exact matching to comparing physicochemical properties. However, these techniques are applicable only if the compound sets are not too big. Particularly for chemical spaces, containing billions of compounds, alternative ways of assessment are required. Random subsets could be enumerated and compared one-to-one, but given the vast sizes of the chemical spaces assessed here, such samples can at best provide a rough estimate of any overlap. Here we describe a novel way to compare chemical spaces utilizing a panel of query compounds. We applied this technique to three different types of spaces and obtained insight into their structural overlap, their coverage of the chemical universe, and their density. As chemical feasibility of virtual compounds is particularly important, we included related in silico predictions in our assessment.

Application of the SwissDrugDesign Online Resources in Virtual Screening

SwissDrugDesign is an important initiative led by the Molecular Modeling Group of the SIB Swiss Institute of Bioinformatics. This project provides a collection of freely available online tools for computer-aided drug design. Some of these web-based methods, i.e., SwissSimilarity and SwissTargetPrediction, were especially developed to perform virtual screening, while others such as SwissADME, SwissDock, SwissParam and SwissBioisostere can find applications in related activities. The present review aims at providing a short description of these methods together with examples of their application in virtual screening, where SwissDrugDesign tools successfully supported the discovery of bioactive small molecules.

Reaction-Based Enumeration, Active Learning, and Free Energy Calculations To Rapidly Explore Synthetically Tractable Chemical Space and Optimize Potency of Cyclin-Dependent Kinase 2 Inhibitors

The hit-to-lead and lead optimization processes usually involve the design, synthesis, and profiling of thousands of analogs prior to clinical candidate nomination. A hit finding campaign may begin with a virtual screen that explores millions of compounds, if not more. However, this scale of computational profiling is not frequently performed in the hit-to-lead or lead optimization phases of drug discovery. This is likely due to the lack of appropriate computational tools to generate synthetically tractable lead-like compounds in silico, and a lack of computational methods to accurately profile compounds prospectively on a large scale. Recent advances in computational power and methods provide the ability to profile much larger libraries of ligands than previously possible. Herein, we report a new computational technique, referred to as "PathFinder", that uses retrosynthetic analysis followed by combinatorial synthesis to generate novel compounds in synthetically accessible chemical space. In this work, the integration of PathFinder-driven compound generation, cloud-based FEP simulations, and active learning are used to rapidly optimize R-groups, and generate new cores for inhibitors of cyclin-dependent kinase 2 (CDK2). Using this approach, we explored >300 000 ideas, performed >5000 FEP simulations, and identified >100 ligands with a predicted IC₅₀ < 100 nM, including four unique cores. To our knowledge, this is the largest set of FEP calculations disclosed in the literature to date. The rapid turnaround time, and scale of chemical exploration, suggests that this is a useful approach to accelerate the discovery of novel chemical matter in drug discovery campaigns.

CovaDOTS: In Silico Chemistry-Driven Tool to Design Covalent Inhibitors Using a Linking Strategy

We recently reported an integrated fragment-based optimization strategy called DOTS (Diversity Oriented Target-focused Synthesis) that combines automated virtual screening (VS) with semirobotized organic synthesis coupled to in vitro evaluation. The molecular modeling part consists of hit-to-lead chemistry, based on the growing paradigm. Here, we have extended the applicability of the DOTS strategy by adding new functionalities, allowing a generic chemistry-driven linking approach with a particular emphasis on covalent drugs. Indeed, the covalent mode of action can be described as a specific case of linking, where suitable linkers are sought to fuse a bound organic compound with a nucleophilic protein side chain. The proof of concept is established using three retrospective study cases in which known noncovalent inhibitors have been converted to covalent inhibitors. Our method is able to automatically design reference covalent inhibitors (and/or analogs) from an initial activated substructure and predict their binding mode. More importantly, the reference compounds are ranked high among several hundred putative adducts, demonstrating the utility of the approach to design covalent inhibitors.

Virtual Chemical Libraries

Advances in computer processing speed and storage capacity have enabled researchers to generate virtual chemical libraries containing billions of molecules. While these numbers appear large, they are only a small fraction of the number of organic molecules that could potentially be synthesized. This review provides an overview of recent advances in the generation and use of virtual chemical libraries in medicinal chemistry. We also consider the practical implications of these libraries in drug discovery programs and highlight a number of current and future challenges.