Integrating Everything: The Molecule Selection Toolkit, a System for Compound Prioritization in Drug Discovery

Mothra: Multiobjective de novo Molecular Generation Using Monte Carlo Tree Search

In the field of drug discovery, identifying compounds that satisfy multiple criteria, such as target protein affinity, pharmacokinetics, and membrane permeability, is challenging because of the vast chemical space. Until now, multiobjective optimization via generative models has often involved linear combinations of different reward functions. Linear combinations solve multiobjective optimization problems by turning multiobjective optimization into a single-objective task and causing problems with weighting for each objective. Herein, we propose a scalable multiobjective molecular generative model developed using deep learning techniques. This model integrates the capabilities of recurrent neural networks for molecular generation and Pareto multiobjective Monte Carlo tree search to determine the optimal search direction. Through this integration, our model can generate compounds using enhanced evaluation functions that include important aspects like target protein affinity, drug similarity, and toxicity. The proposed model addresses the limitations of previous linear combination methods, and its effectiveness is demonstrated via extensive experimentation. The improvements achieved in the evaluation metrics underscore the potential utility of our approach toward drug discovery applications. In addition, we provide the source code for our model such that researchers can easily access and use our framework in their own investigations. The source code and pretrained model for Mothra, developed in this study, along with the Docker image for the Pareto front explorer and compound picker, designed to streamline the selection and visualization of optimal chemical compounds, are released under the GNU General Public License v3.0 and available at https://github.com/sekijima-lab/Mothra.

Artificial Intelligence for Drug Discovery: Are We There Yet?

Drug discovery is adapting to novel technologies such as data science, informatics, and artificial intelligence (AI) to accelerate effective treatment development while reducing costs and animal experiments. AI is transforming drug discovery, as indicated by increasing interest from investors, industrial and academic scientists, and legislators. Successful drug discovery requires optimizing properties related to pharmacodynamics, pharmacokinetics, and clinical outcomes. This review discusses the use of AI in the three pillars of drug discovery: diseases, targets, and therapeutic modalities, with a focus on small-molecule drugs. AI technologies, such as generative chemistry, machine learning, and multiproperty optimization, have enabled several compounds to enter clinical trials. The scientific community must carefully vet known information to address the reproducibility crisis. The full potential of AI in drug discovery can only be realized with sufficient ground truth and appropriate human intervention at later pipeline stages.

3D based generative PROTAC linker design with reinforcement learning

Proteolysis targeting chimera (PROTAC), has emerged as an effective modality to selectively degrade disease-related proteins by harnessing the ubiquitin-proteasome system. Due to PROTACs' hetero-bifunctional characteristics, in which a linker joins a warhead binding to a protein of interest (POI), conferring specificity and a E3-ligand binding to an E3 ubiquitin ligase, this could trigger the ubiquitination and transportation of POI to the proteasome, followed by degradation. The rational PROTAC linker design is challenging due to its relatively large molecular weight and the complexity of maintaining the binding mode of warhead and E3-ligand in the binding pockets of counterpart. Conventional linker generation method can only generate linkers in either 1D SMILES or 2D graph, without taking into account the information of ternary structures. Here we propose a novel 3D linker generative model PROTAC-INVENT which can not only generate SMILES of PROTAC but also its 3D putative binding conformation coupled with the target protein and the E3 ligase. The model is trained jointly with the RL approach to bias the generation of PROTAC structures toward pre-defined 2D and 3D based properties. Examples were provided to demonstrate the utility of the model for generating reasonable 3D conformation of PROTACs. On the other hand, our results show that the associated workflow for 3D PROTAC conformation generation can also be used as an efficient docking protocol for PROTACs.

An overview of compound properties, multiparameter optimization, and computational drug design methods for PARP-1 inhibitor drugs

Breast cancer treatment with PARP-1 inhibitors remains challenging due to emerging toxicities, drug resistance, and unaffordable costs of treatment options. How do we invent strategies to design better anti-cancer drugs? A part of the answer is in optimized compound properties, desirability functions, and modern computational drug design methods that drive selectivity and toxicity and have not been reviewed for PARP-1 inhibitors. Nonetheless, comparisons of these compound properties for PARP-1 inhibitors are not available in the literature. In this review, we analyze the physchem, PKPD space to identify inherent desirability functions characteristic of approved drugs that can be valuable for the design of better candidates. Recent literature utilizing ligand, structure-based drug design strategies and matched molecular pair analysis (MMPA) for the discovery of novel PARP-1 inhibitors are also reviewed. Thus, this perspective provides valuable insights into the medchem and multiparameter optimization of PARP-1 inhibitors that might be useful to other medicinal chemists.

Small molecules and their impact in drug discovery: A perspective on the occasion of the 125th anniversary of the Bayer Chemical Research Laboratory

The year 2021 marks the 125th anniversary of the Bayer Chemical Research Laboratory in Wuppertal, Germany. A significant number of prominent small-molecule drugs, from aspirin to Xarelto, have emerged from this research site. In this review, we shed light on historic cornerstones of small-molecule drug research, discussing current and future trends in drug discovery as well as providing a personal outlook on the future of drug research with a focus on small molecules.

CACHE (Critical Assessment of Computational Hit-finding Experiments): A public–private partnership benchmarking initiative to enable the development of computational methods for hit-finding

One aspirational goal of computational chemistry is to predict potent and drug-like binders for any protein, such that only those that bind are synthesized. In this Roadmap, we describe the launch of Critical Assessment of Computational Hit-finding Experiments (CACHE), a public benchmarking project to compare and improve small molecule hit-finding algorithms through cycles of prediction and experimental testing. Participants will predict small molecule binders for new and biologically relevant protein targets representing different prediction scenarios. Predicted compounds will be tested rigorously in an experimental hub, and all predicted binders as well as all experimental screening data, including the chemical structures of experimentally tested compounds, will be made publicly available, and not subject to any intellectual property restrictions. The ability of a range of computational approaches to find novel binders will be evaluated, compared, and openly published. CACHE will launch 3 new benchmarking exercises every year. The outcomes will be better prediction methods, new small molecule binders for target proteins of importance for fundamental biology or drug discovery, and a major technological step towards achieving the goal of Target 2035, a global initiative to identify pharmacological probes for all human proteins.

Screening of antibacterial compounds with novel structure from the FDA approved drugs using machine learning methods

Bacterial infection is one of the most important factors affecting the human life span. Elderly people are more harmed by bacterial infections due to their deficits in immunity. Because of the lack of new antibiotics in recent years, bacterial resistance has increasingly become a serious problem globally. In this study, an antibacterial compound predictor was constructed using the support vector machines and random forest methods and the data of the active and inactive antibacterial compounds from the ChEMBL database. The results showed that both models have excellent prediction performance (mean accuracy >0.9 and mean AUC >0.9 for the two models). We used the predictor to screen potential antibacterial compounds from FDA-approved drugs in the DrugBank database. The screening results showed that 1087 small-molecule drugs have potential antibacterial activity and 154 of them are FDA-approved antibacterial drugs, which accounts for 76.2% of the approved antibacterial drugs collected in this study. Through molecular fingerprint similarity analysis and common substructure analysis, we screened 8 predicted antibacterial small-molecule compounds with novel structures compared with known antibacterial drugs, and 5 of them are widely used in the treatment of various tumors. This study provides a new insight for predicting antibacterial compounds by using approved drugs, the predicted compounds might be used to treat bacterial infections and extend lifespan.

Bayesian optimization for goal-oriented multi-objective inverse material design

Bayesian optimization (BO) can accelerate material design requiring time-consuming experiments. However, although most material designs require tuning of multiple properties, the efficiency of multi-objective (MO) BO in time-consuming experimental material design remains unclear, due to the complexity of handling multiple objectives. This study introduces MO BO method that efficiently achieves predefined goals and shows that by focusing on achieving the goals, BO can efficiently accelerate realistic MO design problems with small efforts. Benchmarks showed that the proposed BO method dramatically reduced the number of experiments needed to achieve goals relative to a baseline method. Virtual MO inverse design experiments with realistic material design problems were also performed, during which the proposed method could achieve goals within only around ten experiments in average and showed over 1000-fold acceleration relative to the random sampling for the most difficult case. The introduction of goal-oriented BO will precede real-world application of BO.

Derivatization Design of Synthetically Accessible Space for Optimization: In Silico Synthesis vs Deep Generative Design

Molecular design is of utmost importance in lead optimization programs ultimately determining the fate of the project and the speed to reach preclinical stage. Newly designed lead analogues or new chemotypes must successfully address the challenges in the multidimensional optimization process throughout several optimization cycles. The speed, quality, and creativity of the designs can have a major impact on the cycle time, the number of required cycles, and the number of compounds needed to be synthesized and evaluated that in combination affect the overall timeline and cost of the lead optimization phase. Recently, a new concept, generative design with deep learning, has become popular for de novo design of project relevant analogue sets. We have developed a de novo design technology called "derivatization design" that applies artificial-intelligence-assisted forward in silico synthesis for the generation of near neighbor lead analogues as well as scaffold variations. The several attractive features of the methodology include synthetic feasibility, reagent availability and cost data associated with each new molecule; thus, detailed synthetic assessment is automatically generated during the design. As a result, these practically important data types can become an early part of the ranking and selection process for cycle time reduction. The power of derivatization design is demonstrated in a simple design study of DDR1 inhibitors and comparison of the produced molecules to a recently published data set obtained with deep generative design.

Uncertainty quantification in drug design

Machine learning and artificial intelligence are increasingly being applied to the drug-design process as a result of the development of novel algorithms, growing access, the falling cost of computation and the development of novel technologies for generating chemically and biologically relevant data. There has been recent progress in fields such as molecular de novo generation, synthetic route prediction and, to some extent, property predictions. Despite this, most research in these fields has focused on improving the accuracy of the technologies, rather than on quantifying the uncertainty in the predictions. Uncertainty quantification will become a key component in autonomous decision making and will be crucial for integrating machine learning and chemistry automation to create an autonomous design-make-test-analyse cycle. This review covers the empirical, frequentist and Bayesian approaches to uncertainty quantification, and outlines how they can be used for drug design. We also outline the impact of uncertainty quantification on decision making.

REINVENT 2.0: An AI Tool for De Novo Drug Design

In the past few years, we have witnessed a renaissance of the field of molecular de novo drug design. The advancements in deep learning and artificial intelligence (AI) have triggered an avalanche of ideas on how to translate such techniques to a variety of domains including the field of drug design. A range of architectures have been devised to find the optimal way of generating chemical compounds by using either graph- or string (SMILES)-based representations. With this application note, we aim to offer the community a production-ready tool for de novo design, called REINVENT. It can be effectively applied on drug discovery projects that are striving to resolve either exploration or exploitation problems while navigating the chemical space. It can facilitate the idea generation process by bringing to the researcher's attention the most promising compounds. REINVENT's code is publicly available at https://github.com/MolecularAI/Reinvent.

EvoMol: a flexible and interpretable evolutionary algorithm for unbiased de novo molecular generation

The objective of this work is to design a molecular generator capable of exploring known as well as unfamiliar areas of the chemical space. Our method must be flexible to adapt to very different problems. Therefore, it has to be able to work with or without the influence of prior data and knowledge. Moreover, regardless of the success, it should be as interpretable as possible to allow for diagnosis and improvement. We propose here a new open source generation method using an evolutionary algorithm to sequentially build molecular graphs. It is independent of starting data and can generate totally unseen compounds. To be able to search a large part of the chemical space, we define an original set of 7 generic mutations close to the atomic level. Our method achieves excellent performances and even records on the QED, penalised logP, SAscore, CLscore as well as the set of goal-directed functions defined in GuacaMol. To demonstrate its flexibility, we tackle a very different objective issued from the organic molecular materials domain. We show that EvoMol can generate sets of optimised molecules having high energy HOMO or low energy LUMO, starting only from methane. We can also set constraints on a synthesizability score and structural features. Finally, the interpretability of EvoMol allows for the visualisation of its exploration process as a chemically relevant tree.

grünifai: interactive multiparameter optimization of molecules in a continuous vector space

SUMMARY

Optimizing small molecules in a drug discovery project is a notoriously difficult task as multiple molecular properties have to be considered and balanced at the same time. In this work, we present our novel interactive in silico compound optimization platform termed grünifai to support the ideation of the next generation of compounds under the constraints of a multiparameter objective. grünifai integrates adjustable in silico models, a continuous representation of the chemical space, a scalable particle swarm optimization algorithm and the possibility to actively steer the compound optimization through providing feedback on generated intermediate structures.

AVAILABILITY AND IMPLEMENTATION

Source code and documentation are freely available under an MIT license and are openly available on GitHub (https://github.com/jrwnter/gruenifai). The backend, including the optimization method and distribution on multiple GPU nodes is written in Python 3. The frontend is written in ReactJS.

Efficient multi-objective molecular optimization in a continuous latent space

One of the main challenges in small molecule drug discovery is finding novel chemical compounds with desirable properties. In this work, we propose a novel method that combines in silico prediction of molecular properties such as biological activity or pharmacokinetics with an in silico optimization algorithm, namely Particle Swarm Optimization. Our method takes a starting compound as input and proposes new molecules with more desirable (predicted) properties. It navigates a machine-learned continuous representation of a drug-like chemical space guided by a defined objective function. The objective function combines multiple in silico prediction models, defined desirability ranges and substructure constraints. We demonstrate that our proposed method is able to consistently find more desirable molecules for the studied tasks in relatively short time. We hope that our method can support medicinal chemists in accelerating and improving the lead optimization process.

Overview of Recent Strategic Advances in Medicinal Chemistry

Introducing novel strategies, concepts, and technologies that speed up drug discovery and the drug development cycle is of great importance both in the highly competitive pharmaceutical industry as well as in academia. This Perspective aims to present a "big-picture" overview of recent strategic innovations in medicinal chemistry and drug discovery.

A simple model to solve a complex drug toxicity problem

Linear drug toxicity models like therapeutic index (TI), physicochemical rules (rule of five, 3/75), ligand efficiency indices (LEI), ideal pharmacokinetic (PK) and pharmacodynamic (PD) profiles are widely used in drug discovery and development. In spite of this, predicting drug toxicity at various stages remains challenging and the overall productivity (<20%) and ultimate benefit to the patients remain low. A simple drug toxicity model, "Drug Toxicity Index" (DTI), is developed here using 711 oral drugs. DTI redefines drug toxicity as scaled biphasic and exponential functions of PD, PK and physicochemical parameters. PD, PK and physicochemical toxicity contributions were estimated from the on and off target IC₅₀, maximum unbound plasma drug concentration (free C _max), and log D values, respectively. These contributions are then scaled by molar dose and oral bioavailability and the logarithm of the sum of scaled contributions is DTI. Drugs with DTI above the WHO ATC drug category specific average values consistently have toxic profiles, while drugs with DTI below this average are relatively safe. DTI performs better than standard rules for lead optimization, LEI and exposure based TIs in identifying safe and toxic drugs. DTI classifies 392 drugs reported in the US-FDA's Liver Toxicity Knowledge Base (LTKB) with an AUC for ROC curves of 0.91-0.64 for different WHO ATC categories. DTI has been used to predict network meta-analysis results on relative toxicity within/across eight different therapeutic areas. It is useful in understanding PD, PK and physicochemical toxicity contributions and identifying potentially toxic drugs and the toxicity of recently approved drugs. Decision trees are proposed for applying the DTI concept in preclinical drug discovery and clinical trial settings. DTI can potentially reduce failure in drug discovery and might be useful in therapeutic drug monitoring and in xenobiotic and environmental toxicity studies.

Does Size Really Matter? Probing the Efficacy of Structural Reduction in the Optimization of Bioderived Compounds - A Computational "Proof-of-Concept"

Over the years, numerous synthetic approaches have been utilized in drug design to improve the pharmacological properties of naturally derived compounds and most importantly, minimize toxic effects associated with their transition to drugs. The reduction of complex bioderived compounds to simpler bioactive fragments has been identified as a viable strategy to develop lead compounds with improved activities and minimal toxicities. Although this ‘reductive’ strategy has been widely exemplified, underlying biological events remain unresolved, hence the unanswered question remains how does the fragmentation of a natural compound improve its bioactivity and reduce toxicities? Herein, using a combinatorial approach, we initialize a computational “proof-of- concept” to expound the differential pharmacological and antagonistic activities of a natural compound, Anguinomycin D, and its synthetic fragment, SB640 towards Exportin Chromosome Region Maintenance 1 (CRM1). Interestingly, our findings revealed that in comparison with the parent compound, SB640 exhibited improved pharmacological attributes, while toxicities and off-target activities were relatively minimal. Moreover, we observed that the reduced size of SB640 allowed ‘deep access’ at the Nuclear Export Signals (NES) binding groove of CRM1, which favored optimal and proximal positioning towards crucial residues while the presence of the long polyketide tail in Anguinomycin D constrained its burial at the hydrophobic groove. Furthermore, with regards to their antagonistic functions, structural inactivation (rigidity) was more pronounced in CRM1 when bound by SB640 as compared to Anguinomycin D. These findings provide essential insights that portray synthetic fragmentation of natural compounds as a feasible approach towards the discovery of potential leads in disease treatment.

From flamingo dance to (desirable) drug discovery: a nature-inspired approach

The therapeutic effects of drugs are well known to result from their interaction with multiple intracellular targets. Accordingly, the pharma industry is currently moving from a reductionist approach based on a 'one-target fixation' to a holistic multitarget approach. However, many drug discovery practices are still procedural abstractions resulting from the attempt to understand and address the action of biologically active compounds while preventing adverse effects. Here, we discuss how drug discovery can benefit from the principles of evolutionary biology and report two real-life case studies. We do so by focusing on the desirability principle, and its many features and applications, such as machine learning-based multicriteria virtual screening.

Automatically updating predictive modeling workflows support decision-making in drug design

Using predictive models for early decision-making in drug discovery has become standard practice. We suggest that model building needs to be automated with minimum input and low technical maintenance requirements. Models perform best when tailored to answering specific compound optimization related questions. If qualitative answers are required, 2-bin classification models are preferred. Integrating predictive modeling results with structural information stimulates better decision making. For in silico models supporting rapid structure–activity relationship cycles the performance deteriorates within weeks. Frequent automated updates of predictive models ensure best predictions. Consensus between multiple modeling approaches increases the prediction confidence. Combining qualified and nonqualified data optimally uses all available information. Dose predictions provide a holistic alternative to multiple individual property predictions for reaching complex decisions.