FOG: Fragment Optimized Growth Algorithm for the de Novo Generation of Molecules Occupying Druglike Chemical Space

Navigating the frontier of drug-like chemical space with cutting-edge generative AI models

Deep generative models (GMs) have transformed the exploration of drug-like chemical space (CS) by generating novel molecules through complex, nontransparent processes, bypassing direct structural similarity. This review examines five key architectures for CS exploration: recurrent neural networks (RNNs), variational autoencoders (VAEs), generative adversarial networks (GANs), normalizing flows (NF), and transformers. It discusses molecular representation choices, training strategies for focused CS exploration, evaluation criteria for CS coverage, and related challenges. Future directions include refining models, exploring new notations, improving benchmarks, and enhancing interpretability to better understand biologically relevant molecular properties.

Chemoinformatic approaches for navigating large chemical spaces

INTRODUCTION

Large chemical spaces (CSs) include traditional large compound collections, combinatorial libraries covering billions to trillions of molecules, DNA-encoded chemical libraries comprising complete combinatorial CSs in a single mixture, and virtual CSs explored by generative models. The diverse nature of these types of CSs require different chemoinformatic approaches for navigation.

AREAS COVERED

An overview of different types of large CSs is provided. Molecular representations and similarity metrics suitable for large CS exploration are discussed. A summary of navigation of CSs in generative models is provided. Methods for characterizing and comparing CSs are discussed.

EXPERT OPINION

The size of large CSs might restrict navigation to specialized algorithms and limit it to considering neighborhoods of structurally similar molecules. Efficient navigation of large CSs not only requires methods that scale with size but also requires smart approaches that focus on better but not necessarily larger molecule selections. Deep generative models aim to provide such approaches by implicitly learning features relevant for targeted biological properties. It is unclear whether these models can fulfill this ideal as validation is difficult as long as the covered CSs remain mainly virtual without experimental verification.

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.

Molecule auto-correction to facilitate molecular design

Ensuring that computationally designed molecules are chemically reasonable is at best cumbersome. We present a molecule correction algorithm that morphs invalid molecular graphs into structurally related valid analogs. The algorithm is implemented as a tree search, guided by a set of policies to minimize its cost. We showcase how the algorithm can be applied to molecular design, either as a post-processing step or as an integral part of molecule generators.

High-frequency stock market order transitions during the US-China trade war 2018: A discrete-time Markov chain analysis

Statistical analysis of high-frequency stock market order transaction data is conducted to understand order transition dynamics. We employ a first-order time-homogeneous discrete-time Markov chain model to the sequence of orders of stocks belonging to six different sectors during the US-China trade war of 2018. The Markov property of the order sequence is validated by the Chi-square test. We estimate the transition probability matrix of the sequence using maximum likelihood estimation. From the heatmap of these matrices, we found the presence of active participation by different types of traders during high volatility days. On such days, these traders place limit orders primarily with the intention of deleting the majority of them to influence the market. These findings are supported by high stationary distribution and low mean recurrence values of add and delete orders. Further, we found similar spectral gap and entropy rate values, which indicates that similar trading strategies are employed on both high and low volatility days during the trade war. Among all the sectors considered in this study, we observe that there is a recurring pattern of full execution orders in the Finance & Banking sector. This shows that the banking stocks are resilient during the trade war. Hence, this study may be useful in understanding stock market order dynamics and devise trading strategies accordingly on high and low volatility days during extreme macroeconomic events.

MARS Plus: An Improved Molecular Design Tool for Complex Compounds Involving Ionic, Stereo, and Cis-Trans Isomeric Structures

MARS (Molecular Assembling and Representation Suite) (Hsu et al. J. Chem. Inf. Model. 2019, 59, 3703-3713) is a toolbox for the molecular design of organic molecules. MARS uses integer arrays to represent the elements and connectivity between elements of a molecule. It provides a collection of operations to manipulate the elemental composition and connectivity of a molecule (or a pair of molecules), enabling the creation of novel chemical compounds. In this work, the original MARS is extended to handle complex molecular structures, including geometric (cis-trans) isomers, stereo isomers, cyclic compounds, and ionic species. The extended version of MARS, referred to as MARS+, has a more comprehensive coverage of the chemical space and therefore can explore molecules with a greater chemical and physical diversity. Compared to other molecular design tools, MARS+ is designed to perform all possible manipulations on a given molecule or a pair of molecules. Molecular structure manipulation can be conducted in either a controlled or a random fashion. Furthermore, every structure manipulation has a counterpart so that the operation can be reversed. Nearly any possible chemical structure can be generated with MARS+ via a combination of molecular operations. The capabilities of MARS+ are examined by the design of new ionic liquids (ILs). The results show that MARS+ is a useful tool for computer-aided molecular design (CAMD) and molecular structure enumeration.

A molecule perturbation software library and its application to study the effects of molecular design constraints

Computational molecular design can yield chemically unreasonable compounds when performed carelessly. A popular strategy to mitigate this risk is mimicking reference chemistry. This is commonly achieved by restricting the way in which molecules are constructed or modified. While it is well established that such an approach helps in designing chemically appealing molecules, concerns about these restrictions impacting chemical space exploration negatively linger. In this work we present a software library for constrained graph-based molecule manipulation and showcase its functionality by developing a molecule generator. Said generator designs molecules mimicking reference chemical features of differing granularity. We find that restricting molecular construction lightly, beyond the usual positive effects on drug-likeness and synthesizability of designed molecules, provides guidance to optimization algorithms navigating chemical space. Nonetheless, restricting molecular construction excessively can indeed hinder effective chemical space exploration.

Using deep neural networks to explore chemical space

INTRODUCTION

The popularity and success of advanced AI methods like deep neural networks has led to novel ways for exploring chemical space. Their opaque nature poses challenges for model evaluation regarding novelty, uniqueness, and distribution of the chemical space covered. However, these methods also promise to be able to explore uncharted chemical space in novel ways that do not rely directly on structural similarity.

AREAS COVERED

This review provides an overview of popular deep learning methods for chemical space exploration. Crucial aspects like choice of molecular representation, training for focused chemical space exploration, and criteria for assessing and validating chemical space coverage are discussed.

EXPERT OPINION

Deep learning offers great potential for chemical space exploration beyond conventional fragment-based methods. Given the rarity of prospective applications and considering the difficulty in assessing representativeness and comprehensiveness of chemical space covered, developing criteria for assessing and validating generative models is of great significance. Latent space models like variational autoencoders are conceptually appealing for inverse QSAR/QSPR approaches as neighborhood relationships in latent space can be trained to reflect property similarities. Future research in understanding and interpreting generative models might lead to a better understanding of biologically relevant properties of molecules.

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.

Targeting RNA structures in diseases with small molecules

RNA is crucial for gene expression and regulation. Recent advances in understanding of RNA biochemistry, structure and molecular biology have revealed the importance of RNA structure in cellular processes and diseases. Various approaches to discovering drug-like small molecules that target RNA structure have been developed. This review provides a brief introduction to RNA structural biology and how RNA structures function as disease regulators. We summarize approaches to targeting RNA with small molecules and highlight their advantages, shortcomings and therapeutic potential.

CReM: chemically reasonable mutations framework for structure generation

Structure generators are widely used in de novo design studies and their performance substantially influences an outcome. Approaches based on the deep learning models and conventional atom-based approaches may result in invalid structures and fail to address their synthetic feasibility issues. On the other hand, conventional reaction-based approaches result in synthetically feasible compounds but novelty and diversity of generated compounds may be limited. Fragment-based approaches can provide both better novelty and diversity of generated compounds but the issue of synthetic complexity of generated structure was not explicitly addressed before. Here we developed a new framework of fragment-based structure generation that, by design, results in the chemically valid structures and provides flexible control over diversity, novelty, synthetic complexity and chemotypes of generated compounds. The framework was implemented as an open-source Python module and can be used to create custom workflows for the exploration of chemical space.

Integration of target discovery, drug discovery and drug delivery: A review on computational strategies

Most of the computational tools involved in drug discovery developed during the 1980s were largely based on computational chemistry, quantitative structure-activity relationship (QSAR) and cheminformatics. Subsequently, the advent of genomics in the 2000s gave rise to a huge number of databases and computational tools developed to analyze large quantities of data, through bioinformatics, to obtain valuable information about the genomic regulation of different organisms. Target identification and validation is a long process during which evidence for and against a target is accumulated in the pursuit of developing new drugs. Finally, the drug delivery system appears as a novel approach to improve drug targeting and releasing into the cells, leading to new opportunities to improve drug efficiency and avoid potential secondary effects. In each area: target discovery, drug discovery and drug delivery, different computational strategies are being developed to accelerate the process of selection and discovery of new tools to be applied to different scientific fields. Research on these three topics is growing rapidly, but still requires a global view of this landscape to detect the most challenging bottleneck and how computational tools could be integrated in each topic. This review describes the current state of the art in computational strategies for target discovery, drug discovery and drug delivery and how these fields could be integrated. Finally, we will discuss about the current needs in these fields and how the continuous development of databases and computational tools will impact on the improvement of those areas. This article is categorized under: Therapeutic Approaches and Drug Discovery > Emerging Technologies Therapeutic Approaches and Drug Discovery > Nanomedicine for Infectious Disease Nanotechnology Approaches to Biology > Nanoscale Systems in Biology.

Screening Library Design

Thanks to technological advances and a greater understanding of the biological and chemical natures of targets and related diseases, high-throughput screening (HTS) has been allowed to be faster, cheaper, and more accessible. Yet, despite these increased technologies and understandings, the frequency of novel and drugs are being approved each year has not being increasing over the years. 2017 was considered a "bumper" year with a total of 46 approved drugs, over double that of the previous year. However, it is thought that part of the problem that HTS has not lived up to expectations is because of the contents of current chemical libraries. Therefore, new methods to design screening libraries are of great interest.

Synthesis meets theory: Past, present and future of rational chemistry

Chemical synthesis has its roots in the empirical approach of alchemy. Nonetheless, the birth of the scientific method, the technical and technological advances (exploiting revolutionary discoveries in physics) and the improved management and sharing of growing databases greatly contributed to the evolution of chemistry from an esoteric ground into a mature scientific discipline during these last 400 years. Furthermore, thanks to the evolution of computational resources, platforms and media in the last 40 years, theoretical chemistry has added to the puzzle the final missing tile in the process of “rationalizing” chemistry. The use of mathematical models of chemical properties, behaviors and reactivities is nowadays ubiquitous in literature. Theoretical chemistry has been successful in the difficult task of complementing and explaining synthetic results and providing rigorous insights when these are otherwise unattainable by experiment. The first part of this review walks the reader through a concise historical overview on the evolution of the “model” in chemistry. Salient milestones have been highlighted and briefly discussed. The second part focuses more on the general description of recent state-of-the-art computational techniques currently used worldwide by chemists to produce synergistic models between theory and experiment. Each section is complemented by key-examples taken from the literature that illustrate the application of the technique discussed therein.

Customizable de novo design strategies for DOCK: Application to HIVgp41 and other therapeutic targets

De novo design can be used to explore vast areas of chemical space in computational lead discovery. As a complement to virtual screening, from-scratch construction of molecules is not limited to compounds in pre-existing vendor catalogs. Here, we present an iterative fragment growth method, integrated into the program DOCK, in which new molecules are built using rules for allowable connections based on known molecules. The method leverages DOCK's advanced scoring and pruning approaches and users can define very specific criteria in terms of properties or features to customize growth toward a particular region of chemical space. The code was validated using three increasingly difficult classes of calculations: (1) Rebuilding known X-ray ligands taken from 663 complexes using only their component parts (focused libraries), (2) construction of new ligands in 57 drug target sites using a library derived from ∼13M drug-like compounds (generic libraries), and (3) application to a challenging protein-protein interface on the viral drug target HIVgp41. The computational testing confirms that the de novo DOCK routines are robust and working as envisioned, and the compelling results highlight the potential utility for designing new molecules against a wide variety of important protein targets. © 2017 Wiley Periodicals, Inc.

A graph-based approach to construct target-focused libraries for virtual screening

Background

Due to exorbitant costs of high-throughput screening, many drug discovery projects commonly employ inexpensive virtual screening to support experimental efforts. However, the vast majority of compounds in widely used screening libraries, such as the ZINC database, will have a very low probability to exhibit the desired bioactivity for a given protein. Although combinatorial chemistry methods can be used to augment existing compound libraries with novel drug-like compounds, the broad chemical space is often too large to be explored. Consequently, the trend in library design has shifted to produce screening collections specifically tailored to modulate the function of a particular target or a protein family.

Methods

Assuming that organic compounds are composed of sets of rigid fragments connected by flexible linkers, a molecule can be decomposed into its building blocks tracking their atomic connectivity. On this account, we developed eSynth, an exhaustive graph-based search algorithm to computationally synthesize new compounds by reconnecting these building blocks following their connectivity patterns.

Results

We conducted a series of benchmarking calculations against the Directory of Useful Decoys, Enhanced database. First, in a self-benchmarking test, the correctness of the algorithm is validated with the objective to recover a molecule from its building blocks. Encouragingly, eSynth can efficiently rebuild more than 80 % of active molecules from their fragment components. Next, the capability to discover novel scaffolds is assessed in a cross-benchmarking test, where eSynth successfully reconstructed 40 % of the target molecules using fragments extracted from chemically distinct compounds. Despite an enormous chemical space to be explored, eSynth is computationally efficient; half of the molecules are rebuilt in less than a second, whereas 90 % take only about a minute to be generated.

Conclusions

eSynth can successfully reconstruct chemically feasible molecules from molecular fragments. Furthermore, in a procedure mimicking the real application, where one expects to discover novel compounds based on a small set of already developed bioactives, eSynth is capable of generating diverse collections of molecules with the desired activity profiles. Thus, we are very optimistic that our effort will contribute to targeted drug discovery. eSynth is freely available to the academic community at www.brylinski.org/content/molecular-synthesis.Graphical abstract

Chemoinformatics in the New Era: From Molecular Dynamics to Systems Dynamics

Chemoinformatics, due to its power in gathering information at the molecular level, has a wide array of important applications to biology, including fundamental biochemical studies and drug discovery and optimization. As modern "omics" based profiling and network based modeling and simulation techniques grow in sophistication, chemoinformatics now faces a great opportunity to include systems-level control mechanisms as one of its pillar components to extend and refine its various applications. This viewpoint article, through the example of computer aided targeting of the PI3K/Akt/mTOR pathway, outlines major steps of integrating systems dynamics simulations into molecular dynamics simulations to facilitate a higher level of chemoinformatics that would revolutionize drug lead optimization, personalized therapy, and possibly other applications.

Molpher: a software framework for systematic chemical space exploration

BACKGROUND

Chemical space is virtual space occupied by all chemically meaningful organic compounds. It is an important concept in contemporary chemoinformatics research, and its systematic exploration is vital to the discovery of either novel drugs or new tools for chemical biology.

RESULTS

In this paper, we describe Molpher, an open-source framework for the systematic exploration of chemical space. Through a process we term 'molecular morphing', Molpher produces a path of structurally-related compounds. This path is generated by the iterative application of so-called 'morphing operators' that represent simple structural changes, such as the addition or removal of an atom or a bond. Molpher incorporates an optimized parallel exploration algorithm, compound logging and a two-dimensional visualization of the exploration process. Its feature set can be easily extended by implementing additional morphing operators, chemical fingerprints, similarity measures and visualization methods. Molpher not only offers an intuitive graphical user interface, but also can be run in batch mode. This enables users to easily incorporate molecular morphing into their existing drug discovery pipelines.

CONCLUSIONS

Molpher is an open-source software framework for the design of virtual chemical libraries focused on a particular mechanistic class of compounds. These libraries, represented by a morphing path and its surroundings, provide valuable starting data for future in silico and in vitro experiments. Molpher is highly extensible and can be easily incorporated into any existing computational drug design pipeline.

Mining electronic laboratory notebooks: analysis, retrosynthesis, and reaction based enumeration

An approach to automatically analyze and use the knowledge contained in electronic laboratory notebooks (ELNs) has been developed. Reactions were reduced to their reactive center and converted to a string representation (SMIRKS) which formed the basis for reaction classification and in silico (retro-)synthesis. Of the SMIRKS that occurred at least five times, 98% successfully regenerated the original product. The extracted reaction rules (SMIRKS) and corresponding reactants span a virtual chemical space which showed a strong dependence on the size of the reactive center. Whereas relatively few robust reaction types were sufficient to describe a large part of all reactions, considerably more reaction rules were necessary to cover all reactions in the ELN. Furthermore, reaction sequences were extracted to identify frequent combinations and diversifying reaction steps. Based on the extracted knowledge a (retro-)synthesis tool was built allowing for de novo design of compounds which have a high chance of being synthetically accessible. In an example application of the de novo design tool, various feasible retrosynthetic routes to the query molecule were obtained. Reaction based enumeration along the top ranked route yielded a library of 29 920 compounds with diverse properties, 99.9% of which are novel in the sense that they are unknown to the public domain.

DOGS: reaction-driven de novo design of bioactive compounds

We present a computational method for the reaction-based de novo design of drug-like molecules. The software DOGS (Design of Genuine Structures) features a ligand-based strategy for automated ‘in silico’ assembly of potentially novel bioactive compounds. The quality of the designed compounds is assessed by a graph kernel method measuring their similarity to known bioactive reference ligands in terms of structural and pharmacophoric features. We implemented a deterministic compound construction procedure that explicitly considers compound synthesizability, based on a compilation of 25'144 readily available synthetic building blocks and 58 established reaction principles. This enables the software to suggest a synthesis route for each designed compound. Two prospective case studies are presented together with details on the algorithm and its implementation. De novo designed ligand candidates for the human histamine H₄ receptor and γ-secretase were synthesized as suggested by the software. The computational approach proved to be suitable for scaffold-hopping from known ligands to novel chemotypes, and for generating bioactive molecules with drug-like properties.

The computer program DOGS aims at the automated generation of new bioactive compounds. Only a single known reference compound is required to have the computer come up with suggestions for potentially isofunctional molecules. A specific feature of the algorithm is its capability to propose a synthesis plan for each designed compound, based on a large set of readily available molecular building blocks and established reaction protocols. The de novo design software provides rapid access to tool compounds and starting points for the development of a lead candidate structure. The manuscript gives a detailed description of the algorithm. Theoretical analysis and prospective case studies demonstrate its ability to propose bioactive, plausible and chemically accessible compounds.

ChemT, an open-source software for building template-based chemical libraries

In computational chemistry, vast quantities of compounds are generated, and there is a need for cheminformatic tools to efficiently build chemical compound libraries. Several software tools for drawing and editing compound structures are available, but they lack options for automatic generation of chemical libraries. We have implemented ChemT, an easy-to-use open-source software tool that automates the process of preparing custom-made template-based chemical libraries. ChemT automatically generates three-dimensional chemical libraries by inputting a chemical template and the functional groups of interest. The graphical user interface of ChemT is self-explanatory, and a complete tutorial is provided. Several file formats are accepted by ChemT, and it is possible to filter the generated compounds according to different physicochemical properties. The compounds can be subject to force field minimization, and the resulting three-dimensional structures recorded on commonly used file formats. ChemT may be a valuable tool for investigators interested in using in silico virtual screening tools, such as quantitative structure-activity relationship modelling or molecular docking, in order to prioritize compounds for further chemical synthesis. To demonstrate the usefulness of ChemT, we describe an example based on a thieno[3,2-b]pyridine template. ChemT is available free of charge from our website at http://www.esa.ipb.pt/~ruiabreu/chemt .

Atom type preferences, structural diversity, and property profiles of known drugs, leads, and nondrugs: a comparative assessment

A new characterization of known drug, lead, and representative nondrug databases was performed taking into account several properties at the atomic and molecular levels. This characterization included atom type preferences, intrinsic structural diversity (Atom Type Diversity, ATD), and other well-known physicochemical properties, as an approach for rapid assessment of druglikeness for small molecule libraries. To characterize ATD, an elaborate united atom classification, UALOGP (United Atom Log P), with 148 atom types, was developed along with associated atomic physicochemical parameters. This classification also enabled an analysis of atom type and physicochemical property distributions (for calculated log P, molar refractivity, molecular weight, total atom count, and ATD) of drug, lead, and nondrug databases, a reassessment of the Ro5 (Rule of Five) and GVW (Ghose−Viswanadhan−Wendoloski) criteria, and development of new criteria and ranges more accurately reflecting the chemical space occupied by small molecule drugs. A relative druglikeness parameter was defined for atom types in drugs, identifying the most preferred types. The present work demonstrates that drug molecules are constitutionally more diverse relative to nondrugs, while being less diverse than leads.

The role of computational methods in the identification of bioactive compounds

Computational methods play an ever increasing role in lead finding. A vast repertoire of molecular design and virtual screening methods emerged in the past two decades and are today routinely used. There is increasing awareness that there is no single best computational protocol and correspondingly there is a shift recommending the combination of complementary methods. A promising trend for the application of computational methods in lead finding is to take advantage of the vast amounts of HTS (High Throughput Screening) data to allow lead assessment by detailed systems-based data analysis, especially for phenotypic screens where the identification of compound-target pairs is the primary goal. Herein, we review trends and provide examples of successful applications of computational methods in lead finding.

De novo drug design

Computer-assisted molecular design supports drug discovery by suggesting novel chemotypes and compound modifications for lead structure optimization. While the aspect of synthetic feasibility of the automatically designed compounds has been neglected for a long time, we are currently witnessing an increased interest in this topic. Here, we review state-of-the-art software for de novo drug design with a special emphasis on fragment-based techniques that generate druglike, synthetically accessible compounds. The importance of scoring functions that can be used to predict compound reactivity and potency is highlighted, and several promising solutions are discussed. Recent practical validation studies are presented that have already demonstrated that rule-based fragment assembly can result in novel synthesizable compounds with druglike properties and a desired biological activity.

Generative models for chemical structures

We apply recently developed techniques for pattern recognition to construct a generative model for chemical structure. This approach can be viewed as ligand-based de novo design. We construct a statistical model describing the structural variations present in a set of molecules which may be sampled to generate new structurally similar examples. We prevent the possibility of generating chemically invalid molecules, according to our implicit hydrogen model, by projecting samples onto the nearest chemically valid molecule. By populating the input set with molecules that are active against a target, we show how new molecules may be generated that will likely also be active against the target.

De novo design: balancing novelty and confined chemical space

IMPORTANCE OF THE FIELD

De novo drug design serves as a tool for the discovery of new ligands for macromolecular targets as well as optimization of known ligands. Recently developed tools aim to address the multi-objective nature of drug design in an unprecedented manner.

AREAS COVERED IN THIS REVIEW

This article discusses recent advances in de novo drug design programs and accessory programs used to evaluate compounds post-generation.

WHAT THE READER WILL GAIN

The reader is introduced to the challenges inherent in de novo drug design and will become familiar with current trends in de novo design. Furthermore, the reader will be better prepared to assess the value of a tool, and be equipped to design more elegant tools in the future.

TAKE HOME MESSAGE

De novo drug design can assist in the efficient discovery of new compounds with a high affinity for a given target. The inclusion of existing chemoinformatic methods with current structure-based de novo design tools provides a means of enhancing the therapeutic value of these generated compounds.