Stochastic voyages into uncharted chemical space produce a representative library of all possible drug-like compounds

Versatile Framework for Drug-Target Interaction Prediction by Considering Domain-Specific Features

Predicting drug-target interactions (DTIs) is one of the crucial tasks in drug discovery, but traditional wet-lab experiments are costly and time-consuming. Recently, deep learning has emerged as a promising tool for accelerating DTI prediction due to its powerful performance. However, the models trained on limited known DTI data struggle to generalize effectively to novel drug-target pairs. In this work, we propose a strategy to train an ensemble of models by capturing both domain-generic and domain-specific features (E-DIS) to learn diverse domain features and adapt them to out-of-distribution data. Multiple experts were trained on different domains to capture and align domain-specific information from various distributions without accessing any data from unseen domains. E-DIS provides a comprehensive representation of proteins and ligands by capturing diverse features. Experimental results on four benchmark data sets in both in-domain and cross-domain settings demonstrated that E-DIS significantly improved model performance and domain generalization compared to existing methods. Our approach presents a significant advancement in DTI prediction by combining domain-generic and domain-specific features, enhancing the generalization ability of the DTI prediction model.

Enhancing molecular design efficiency: Uniting language models and generative networks with genetic algorithms

This study examines the effectiveness of generative models in drug discovery, material science, and polymer science, aiming to overcome constraints associated with traditional inverse design methods relying on heuristic rules. Generative models generate synthetic data resembling real data, enabling deep learning model training without extensive labeled datasets. They prove valuable in creating virtual libraries of molecules for material science and facilitating drug discovery by generating molecules with specific properties. While generative adversarial networks (GANs) are explored for these purposes, mode collapse restricts their efficacy, limiting novel structure variability. To address this, we introduce a masked language model (LM) inspired by natural language processing. Although LMs alone can have inherent limitations, we propose a hybrid architecture combining LMs and GANs to efficiently generate new molecules, demonstrating superior performance over standalone masked LMs, particularly for smaller population sizes. This hybrid LM-GAN architecture enhances efficiency in optimizing properties and generating novel samples.

Graph to Activation Energy Models Easily Reach Irreducible Errors but Show Limited Transferability

Activation energy characterization of competing reactions is a costly but crucial step for understanding the kinetic relevance of distinct reaction pathways, product yields, and myriad other properties of reacting systems. The standard methodology for activation energy characterization has historically been a transition state search using the highest level of theory that can be afforded. However, recently, several groups have popularized the idea of predicting activation energies directly based on nothing more than the reactant and product graphs, a sufficiently complex neural network, and a broad enough data set. Here, we have revisited this task using the recently developed Reaction Graph Depth 1 (RGD1) transition state data set and several newly developed graph attention architectures. All of these new architectures achieve similar state-of-the-art results of ∼4 kcal/mol mean absolute error on withheld testing sets of reactions but poor performance on external testing sets composed of reactions with differing mechanisms, reaction molecularity, or reactant size distribution. Limited transferability is also shown to be shared by other contemporary graph to activation energy architectures through a series of case studies. We conclude that an array of standard graph architectures can already achieve results comparable to the irreducible error of available reaction data sets but that out-of-distribution performance remains poor.

PS2MS: A Deep Learning-Based Prediction System for Identifying New Psychoactive Substances Using Mass Spectrometry

The rapid proliferation of new psychoactive substances (NPS) poses significant challenges to conventional mass-spectrometry-based identification methods due to the absence of reference spectra for these emerging substances. This paper introduces PS2MS, an AI-powered predictive system designed specifically to address the limitations of identifying the emergence of unidentified novel illicit drugs. PS2MS builds a synthetic NPS database by enumerating feasible derivatives of known substances and uses deep learning to generate mass spectra and chemical fingerprints. When the mass spectrum of an analyte does not match any known reference, PS2MS simultaneously examines the chemical fingerprint and mass spectrum against the putative NPS database using integrated metrics to deduce possible identities. Experimental results affirm the effectiveness of PS2MS in identifying cathinone derivatives within real evidence specimens, signifying its potential for practical use in identifying emerging drugs of abuse for researchers and forensic experts.

SpaceGrow: efficient shape-based virtual screening of billion-sized combinatorial fragment spaces

The growing size of make-on-demand chemical libraries is posing new challenges to cheminformatics. These ultra-large chemical libraries became too large for exhaustive enumeration. Using a combinatorial approach instead, the resource requirement scales approximately with the number of synthons instead of the number of molecules. This gives access to billions or trillions of compounds as so-called chemical spaces with moderate hardware and in a reasonable time frame. While extremely performant ligand-based 2D methods exist in this context, 3D methods still largely rely on exhaustive enumeration and therefore fail to apply. Here, we present SpaceGrow: a novel shape-based 3D approach for ligand-based virtual screening of billions of compounds within hours on a single CPU. Compared to a conventional superposition tool, SpaceGrow shows comparable pose reproduction capacity based on RMSD and superior ranking performance while being orders of magnitude faster. Result assessment of two differently sized subsets of the eXplore space reveals a higher probability of finding superior results in larger spaces highlighting the potential of searching in ultra-large spaces. Furthermore, the application of SpaceGrow in a drug discovery workflow was investigated in four examples involving G protein-coupled receptors (GPCRs) with the aim to identify compounds with similar binding capabilities and molecular novelty.

Computational Approaches and Drug Discovery: Where Are We Going?

Science is a point of view [...].

Perspectives on development of optoelectronic materials in artificial intelligence age

Optoelectronic devices, such as light-emitting diodes, have been demonstrated as one of the most demanded forthcoming display and lighting technologies because of their low cost, low power consumption, high brightness, and high contrast. The improvement of device performance relies on advances in precisely designing novelty functional materials, including light-emitting materials, hosts, hole/electron transport materials, and yet which is a time-consuming, laborious and resource-intensive task. Recently, machine learning (ML) has shown great prospects to accelerate material discovery and property enhancement. This review will summarize the workflow of ML in optoelectronic materials discovery, including data collection, feature engineering, model selection, model evaluation and model application. We highlight multiple recent applications of machine-learned potentials in various optoelectronic functional materials, ranging from semiconductor quantum dots (QDs) or perovskite QDs, organic molecules to carbon-based nanomaterials. We furthermore discuss the current challenges to fully realize the potential of ML-assisted materials design for optoelectronics applications. It is anticipated that this review will provide critical insights to inspire new exciting discoveries on ML-guided of high-performance optoelectronic devices with a combined effort from different disciplines.

Machine Learning Prediction of the Experimental Transition Temperature of Fe(II) Spin-Crossover Complexes

Spin-crossover (SCO) complexes are materials that exhibit changes in the spin state in response to external stimuli, with potential applications in molecular electronics. It is challenging to know a priori how to design ligands to achieve the delicate balance of entropic and enthalpic contributions needed to tailor a transition temperature close to room temperature. We leverage the SCO complexes from the previously curated SCO-95 data set [Vennelakanti et al. J. Chem. Phys. 159, 024120 (2023)] to train three machine learning (ML) models for transition temperature (T1/2) prediction using graph-based revised autocorrelations as features. We perform feature selection using random forest-ranked recursive feature addition (RF-RFA) to identify the features essential to model transferability. Of the ML models considered, the full feature set RF and recursive feature addition RF models perform best, achieving moderate correlation to experimental T1/2 values. We then compare ML T1/2 predictions to those from three previously identified best-performing density functional approximations (DFAs) which accurately predict SCO behavior across SCO-95, finding that the ML models predict T1/2 more accurately than the best-performing DFAs. In addition, we study ML model predictions for a set of 18 SCO complexes for which only estimated T1/2 values are available. Upon excluding outliers from this set, the RF-RFA RF model shows a strong correlation to estimated T1/2 values with a Pearson's r of 0.82. In contrast, DFA-predicted T1/2 values have large errors and show no correlation to estimated T1/2 values over the same set of complexes. Overall, our study demonstrates slightly superior performance of ML models in comparison with some of the best-performing DFAs, and we expect ML models to improve further as larger data sets of SCO complexes are curated and become available for model training.

Evolutionary Monte Carlo of QM Properties in Chemical Space: Electrolyte Design

Optimizing a target function over the space of organic molecules is an important problem appearing in many fields of applied science but also a very difficult one due to the vast number of possible molecular systems. We propose an evolutionary Monte Carlo algorithm for solving such problems which is capable of straightforwardly tuning both exploration and exploitation characteristics of an optimization procedure while retaining favorable properties of genetic algorithms. The method, dubbed MOSAiCS (Metropolis Optimization by Sampling Adaptively in Chemical Space), is tested on problems related to optimizing components of battery electrolytes, namely, minimizing solvation energy in water or maximizing dipole moment while enforcing a lower bound on the HOMO-LUMO gap; optimization was carried out over sets of molecular graphs inspired by QM9 and Electrolyte Genome Project (EGP) data sets. MOSAiCS reliably generated molecular candidates with good target quantity values, which were in most cases better than the ones found in QM9 or EGP. While the optimization results presented in this work sometimes required up to 106 QM calculations and were thus feasible only thanks to computationally efficient ab initio approximations of properties of interest, we discuss possible strategies for accelerating MOSAiCS using machine learning approaches.

Art driven by visual representations of chemical space

Science and art have been connected for centuries. With the development of new computational methods, new scientific disciplines have emerged, such as computational chemistry, and related fields, such as cheminformatics. Chemoinformatics is grounded on the chemical space concept: a multi-descriptor space in which chemical structures are described. In several practical applications, visual representations of the chemical space of compound datasets are low-dimensional plots helpful in identifying patterns. However, the authors propose that the plots can also be used as artistic expressions. This manuscript introduces an approach to merging art with chemoinformatics through visual and artistic representations of chemical space. As case studies, we portray the chemical space of food chemicals and other compounds to generate visually appealing graphs with twofold benefits: sharing chemical knowledge and developing pieces of art driven by chemoinformatics. The art driven by chemical space visualization will help increase the application of chemistry and art and contribute to general education and dissemination of chemoinformatics and chemistry through artistic expressions. All the code and data sets to reproduce the visual representation of the chemical space presented in the manuscript are freely available at https://github.com/DIFACQUIM/Art-Driven-by-Visual-Representations-of-Chemical-Space- . Scientific contribution: Chemical space as a concept to create digital art and as a tool to train and introduce students to cheminformatics.

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.

Sampling and Mapping Chemical Space with Extended Similarity Indices

Visualization of the chemical space is useful in many aspects of chemistry, including compound library design, diversity analysis, and exploring structure-property relationships, to name a few. Examples of notable research areas where the visualization of chemical space has strong applications are drug discovery and natural product research. However, the sheer volume of even comparatively small sub-sections of chemical space implies that we need to use approximations at the time of navigating through chemical space. ChemMaps is a visualization methodology that approximates the distribution of compounds in large datasets based on the selection of satellite compounds that yield a similar mapping of the whole dataset when principal component analysis on a similarity matrix is performed. Here, we show how the recently proposed extended similarity indices can help find regions that are relevant to sample satellites and reduce the amount of high-dimensional data needed to describe a library's chemical space.

Adaptive language model training for molecular design

The vast size of chemical space necessitates computational approaches to automate and accelerate the design of molecular sequences to guide experimental efforts for drug discovery. Genetic algorithms provide a useful framework to incrementally generate molecules by applying mutations to known chemical structures. Recently, masked language models have been applied to automate the mutation process by leveraging large compound libraries to learn commonly occurring chemical sequences (i.e., using tokenization) and predict rearrangements (i.e., using mask prediction). Here, we consider how language models can be adapted to improve molecule generation for different optimization tasks. We use two different generation strategies for comparison, fixed and adaptive. The fixed strategy uses a pre-trained model to generate mutations; the adaptive strategy trains the language model on each new generation of molecules selected for target properties during optimization. Our results show that the adaptive strategy allows the language model to more closely fit the distribution of molecules in the population. Therefore, for enhanced fitness optimization, we suggest the use of the fixed strategy during an initial phase followed by the use of the adaptive strategy. We demonstrate the impact of adaptive training by searching for molecules that optimize both heuristic metrics, drug-likeness and synthesizability, as well as predicted protein binding affinity from a surrogate model. Our results show that the adaptive strategy provides a significant improvement in fitness optimization compared to the fixed pre-trained model, empowering the application of language models to molecular design tasks.

Insights into the deviation from piecewise linearity in transition metal complexes from supervised machine learning models

Virtual high-throughput screening (VHTS) and machine learning (ML) with density functional theory (DFT) suffer from inaccuracies from the underlying density functional approximation (DFA). Many of these inaccuracies can be traced to the lack of derivative discontinuity that leads to a curvature in the energy with electron addition or removal. Over a dataset of nearly one thousand transition metal complexes typical of VHTS applications, we computed and analyzed the average curvature (i.e., deviation from piecewise linearity) for 23 density functional approximations spanning multiple rungs of "Jacob's ladder". While we observe the expected dependence of the curvatures on Hartree-Fock exchange, we note limited correlation of curvature values between different rungs of "Jacob's ladder". We train ML models (i.e., artificial neural networks or ANNs) to predict the curvature and the associated frontier orbital energies for each of these 23 functionals and then interpret differences in curvature among the different DFAs through analysis of the ML models. Notably, we observe spin to play a much more important role in determining the curvature of range-separated and double hybrids in comparison to semi-local functionals, explaining why curvature values are weakly correlated between these and other families of functionals. Over a space of 187.2k hypothetical compounds, we use our ANNs to pinpoint DFAs for which representative transition metal complexes have near-zero curvature with low uncertainty, demonstrating an approach to accelerate screening of complexes with targeted optical gaps.

Bridging Chemical Knowledge and Machine Learning for Performance Prediction of Organic Synthesis

Recent years have witnessed a boom of machine learning (ML) applications in chemistry, which reveals the potential of data-driven prediction of synthesis performance. Digitalization and ML modelling are the key strategies to fully exploit the unique potential within the synergistic interplay between experimental data and the robust prediction of performance and selectivity. A series of exciting studies have demonstrated the importance of chemical knowledge implementation in ML, which improves the model's capability for making predictions that are challenging and often go beyond the abilities of human beings. This Minireview summarizes the cutting-edge embedding techniques and model designs in synthetic performance prediction, elaborating how chemical knowledge can be incorporated into machine learning until June 2022. By merging organic synthesis tactics and chemical informatics, we hope this Review can provide a guide map and intrigue chemists to revisit the digitalization and computerization of organic chemistry principles.

Towards Decoding Hepatotoxicity of Approved Drugs through Navigation of Multiverse and Consensus Chemical Spaces

Drug-induced liver injury (DILI) is the principal reason for failure in developing drug candidates. It is the most common reason to withdraw from the market after a drug has been approved for clinical use. In this context, data from animal models, liver function tests, and chemical properties could complement each other to understand DILI events better and prevent them. Since the chemical space concept improves decision-making drug design related to the prediction of structure-property relationships, side effects, and polypharmacology drug activity (uniquely mentioning the most recent advances), it is an attractive approach to combining different phenomena influencing DILI events (e.g., individual "chemical spaces") and exploring all events simultaneously in an integrated analysis of the DILI-relevant chemical space. However, currently, no systematic methods allow the fusion of a collection of different chemical spaces to collect different types of data on a unique chemical space representation, namely "consensus chemical space." This study is the first report that implements data fusion to consider different criteria simultaneously to facilitate the analysis of DILI-related events. In particular, the study highlights the importance of analyzing together in vitro and chemical data (e.g., topology, bond order, atom types, presence of rings, ring sizes, and aromaticity of compounds encoded on RDKit fingerprints). These properties could be aimed at improving the understanding of DILI events.

Language models for the prediction of SARS-CoV-2 inhibitors

The COVID-19 pandemic highlights the need for computational tools to automate and accelerate drug design for novel protein targets. We leverage deep learning language models to generate and score drug candidates based on predicted protein binding affinity. We pre-trained a deep learning language model (BERT) on ∼9.6 billion molecules and achieved peak performance of 603 petaflops in mixed precision. Our work reduces pre-training time from days to hours, compared to previous efforts with this architecture, while also increasing the dataset size by nearly an order of magnitude. For scoring, we fine-tuned the language model using an assembled set of thousands of protein targets with binding affinity data and searched for inhibitors of specific protein targets, SARS-CoV-2 Mpro and PLpro. We utilized a genetic algorithm approach for finding optimal candidates using the generation and scoring capabilities of the language model. Our generalizable models accelerate the identification of inhibitors for emerging therapeutic targets.

Chemical Multiverse: An Expanded View of Chemical Space

Technological advances and practical applications of the chemical space concept in drug discovery, natural product research, and other research areas have attracted the scientific community's attention. The large- and ultra-large chemical spaces are associated with the significant increase in the number of compounds that can potentially be made and exist and the increasing number of experimental and calculated descriptors, that are emerging that encode the molecular structure and/or property aspects of the molecules. Due to the importance and continued evolution of compound libraries, herein, we discuss definitions proposed in the literature for chemical space and emphasize the convenience, discussed in the literature to use complementary descriptors to obtain a comprehensive view of the chemical space of compound data sets. In this regard, we introduce the term chemical multiverse to refer to the comprehensive analysis of compound data sets through several chemical spaces, each defined by a different set of chemical representations. The chemical multiverse is contrasted with a related idea: consensus chemical space.

Artificial intelligence-driven design of fuel mixtures

High-performance fuel design is imperative to achieve cleaner burning and high-efficiency engine systems. We introduce a data-driven artificial intelligence (AI) framework to design liquid fuels exhibiting tailor-made properties for combustion engine applications to improve efficiency and lower carbon emissions. The fuel design approach is a constrained optimization task integrating two parts: (i) a deep learning (DL) model to predict the properties of pure components and mixtures and (ii) search algorithms to efficiently navigate in the chemical space. Our approach presents the mixture-hidden vector as a linear combination of each single component's vectors in each blend and incorporates it into the network architecture (the mixing operator (MO)). We demonstrate that the DL model exhibits similar accuracy as competing computational techniques in predicting the properties for pure components, while the search tool can generate multiple candidate fuel mixtures. The integrated framework was evaluated to showcase the design of high-octane and low-sooting tendency fuel that is subject to gasoline specification constraints. This AI fuel design methodology enables rapidly developing fuel formulations to optimize engine efficiency and lower emissions.

A pocket-based 3D molecule generative model fueled by experimental electron density

We report for the first time the use of experimental electron density (ED) as training data for the generation of drug-like three-dimensional molecules based on the structure of a target protein pocket. Similar to a structural biologist building molecules based on their ED, our model functions with two main components: a generative adversarial network (GAN) to generate the ligand ED in the input pocket and an ED interpretation module for molecule generation. The model was tested on three targets: a kinase (hematopoietic progenitor kinase 1), protease (SARS-CoV-2 main protease), and nuclear receptor (vitamin D receptor), and evaluated with a reference dataset composed of over 8000 compounds that have their activities reported in the literature. The evaluation considered the chemical validity, chemical space distribution-based diversity, and similarity with reference active compounds concerning the molecular structure and pocket-binding mode. Our model can generate molecules with similar structures to classical active compounds and novel compounds sharing similar binding modes with active compounds, making it a promising tool for library generation supporting high-throughput virtual screening. The ligand ED generated can also be used to support fragment-based drug design. Our model is available as an online service to academic users via https://edmg.stonewise.cn/#/create .

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

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

Approaches for enhancing the analysis of chemical space for drug discovery

INTRODUCTION

Chemical space is a powerful, general, and practical conceptual framework in drug discovery and other areas in chemistry that addresses the diversity of molecules and it has various applications. Moreover, chemical space is a cornerstone of chemoinformatics as a scientific discipline. In response to the increase in the set of chemical compounds in databases, generators of chemical structures, and tools to calculate molecular descriptors, novel approaches to generate visual representations of chemical space in low dimensions are emerging and evolving. Such approaches include a wide range of commercial and free applications, software, and open-source methods.

AREAS COVERED

The current state of chemical space in drug design and discovery is reviewed. The topics discussed herein include advances for efficient navigation in chemical space, the use of this concept in assessing the diversity of different data sets, exploring structure-property/activity relationships for one or multiple endpoints, and compound library design. Recent advances in methodologies for generating visual representations of chemical space have been highlighted, thereby emphasizing open-source methods.

EXPERT OPINION

Quantitative and qualitative generation and analysis of chemical space require novel approaches for handling the increasing number of molecules and their information available in chemical databases (including emerging ultra-large libraries). In addition, it is of utmost importance to note that chemical space is a conceptual framework that goes beyond visual representation in low dimensions. However, the graphical representation of chemical space has several practical applications in drug discovery and beyond.

Modeling of the Crystallization Conditions for Organic Synthesis Product Purification Using Deep Learning

Crystallization is an important purification technique for solid products in a chemical laboratory. However, the correct selection of a solvent is important for the success of the procedure. In order to accelerate the solvent or solvent mixture search process, we offer an in silico alternative, i.e., a never previously demonstrated approach that can model the reaction mixture crystallization conditions which are invariant to the reaction type. The offered deep learning-based method is trained to directly predict the solvent labels used in the crystallization steps of the synthetic procedure. Our solvent label prediction task is a multi-label multi-class classification task during which the method must correctly choose one or several solvents from 13 possible examples. During the experimental investigation, we tested two multi-label classifiers (i.e., Feed-Forward and Long Short-Term Memory neural networks) applied on top of vectors. For the vectorization, we used two methods (i.e., extended-connectivity fingerprints and autoencoders) with various parameters. Our optimized technique was able to reach the accuracy of 0.870 ± 0.004 (which is 0.693 above the baseline) on the testing dataset. This allows us to assume that the proposed approach can help to accelerate manual R&D processes in chemical laboratories.

Machine Learning for the Discovery, Design, and Engineering of Materials

Machine learning (ML) has become a part of the fabric of high-throughput screening and computational discovery of materials. Despite its increasingly central role, challenges remain in fully realizing the promise of ML. This is especially true for the practical acceleration of the engineering of robust materials and the development of design strategies that surpass trial and error or high-throughput screening alone. Depending on the quantity being predicted and the experimental data available, ML can either outperform physics-based modes, be used to accelerate such models, or be integrated with them to improve their performance. We cover recent advances in algorithms and in their application that are starting to make inroads toward (a) the discovery of new materials through large-scale enumerative screening, (b) the design of materials through identification of rules and principles that govern materials properties, and (c) the engineering of practical materials by satisfying multiple objectives. We conclude with opportunities for further advancement to realize ML as a widespread tool for practical computational materials design. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

A Survey of Datasets, Preprocessing, Modeling Mechanisms, and Simulation Tools Based on AI for Material Analysis and Discovery

Research has become increasingly more interdisciplinary over the past few years. Artificial intelligence and its sub-fields have proven valuable for interdisciplinary research applications, especially physical sciences. Recently, machine learning-based mechanisms have been adapted for material science applications, meeting traditional experiments' challenges in a time and cost-efficient manner. The scientific community focuses on harnessing varying mechanisms to process big data sets extracted from material databases to derive hidden knowledge that can successfully be employed in technical frameworks of material screening, selection, and recommendation. However, a plethora of underlying aspects of the existing material discovery methods needs to be critically assessed to have a precise and collective analysis that can serve as a baseline for various forthcoming material discovery problems. This study presents a comprehensive survey of state-of-the-art benchmark data sets, detailed pre-processing and analysis, appropriate learning model mechanisms, and simulation techniques for material discovery. We believe that such an in-depth analysis of the mentioned aspects provides promising directions to the young interdisciplinary researchers from computing and material science fields. This study will help devise useful modeling in the materials discovery to positively contribute to the material industry, reducing the manual effort involved in the traditional material discovery. Moreover, we also present a detailed analysis of experimental and computation-based artificial intelligence mechanisms suggested by the existing literature.

On the Investigation of Effective Factors on Electronic Structure Properties of Transition Metal Complexes: Robust Modeling Using GPR Approach

Materials discovery is usually done using high-throughput computational screening. The use of costly and complex direct density functional theory (DFT) simulation methods has been commonly used to determine subtle trends in spin-state ordering and inorganic bonding of inorganic materials and, in general, to predict the electronic structure properties of transition metal complexes. A Gaussian process regression (GPR) framework consisting of four kernel functions is introduced for spin-state splitting estimation through inorganic chemistry-appropriate empirical inputs. To this end, the present study reviewed an extensive range of data values from earlier works. According to statistical analysis, the GPR model showed very good performance. The coefficients of determination were calculated to be 0.986 for the exponential and Matern kernel functions, suggesting the highest predictive power of these methods. Moreover, the sensitivity of output to inputs was measured. Artificial intelligence (AI) helped accurately predict the target values through various input ranges.

LEADD: Lamarckian evolutionary algorithm for de novo drug design

Given an objective function that predicts key properties of a molecule, goal-directed de novo molecular design is a useful tool to identify molecules that maximize or minimize said objective function. Nonetheless, a common drawback of these methods is that they tend to design synthetically unfeasible molecules. In this paper we describe a Lamarckian evolutionary algorithm for de novo drug design (LEADD). LEADD attempts to strike a balance between optimization power, synthetic accessibility of designed molecules and computational efficiency. To increase the likelihood of designing synthetically accessible molecules, LEADD represents molecules as graphs of molecular fragments, and limits the bonds that can be formed between them through knowledge-based pairwise atom type compatibility rules. A reference library of drug-like molecules is used to extract fragments, fragment preferences and compatibility rules. A novel set of genetic operators that enforce these rules in a computationally efficient manner is presented. To sample chemical space more efficiently we also explore a Lamarckian evolutionary mechanism that adapts the reproductive behavior of molecules. LEADD has been compared to both standard virtual screening and a comparable evolutionary algorithm using a standardized benchmark suite and was shown to be able to identify fitter molecules more efficiently. Moreover, the designed molecules are predicted to be easier to synthesize than those designed by other evolutionary algorithms.

Has Artificial Intelligence Impacted Drug Discovery?

Artificial intelligence (AI) tools find increasing application in drug discovery supporting every stage of the Design-Make-Test-Analyse (DMTA) cycle. The main focus of this chapter is the application in molecular generation with the aid of deep neural networks (DNN). We present a historical overview of the main advances in the field. We analyze the concepts of distribution and goal-directed learning and then highlight some of the recent applications of generative models in drug design with a focus into research work from the biopharmaceutical industry. We present in some more detail REINVENT which is an open-source software developed within our group in AstraZeneca and the main platform for AI molecular design support for a number of medicinal chemistry projects in the company and we also demonstrate some of our work in library design. Finally, we present some of the main challenges in the application of AI in Drug Discovery and different approaches to respond to these challenges which define areas for current and future work.

Generative Chemical Transformer: Neural Machine Learning of Molecular Geometric Structures from Chemical Language via Attention

Discovering new materials better suited to specific purposes is an important issue in improving the quality of human life. Here, a neural network that creates molecules that meet some desired multiple target conditions based on a deep understanding of chemical language is proposed (generative chemical Transformer, GCT). The attention mechanism in GCT allows a deeper understanding of molecular structures beyond the limitations of chemical language itself which cause semantic discontinuity by paying attention to characters sparsely. The significance of language models for inverse molecular design problems is investigated by quantitatively evaluating the quality of the generated molecules. GCT generates highly realistic chemical strings that satisfy both chemical and linguistic grammar rules. Molecules parsed from the generated strings simultaneously satisfy the multiple target properties and vary for a single condition set. These advances will contribute to improving the quality of human life by accelerating the process of desired material discovery.

Synthesis of sp3-rich chiral bicyclo[3.3.1]nonanes for chemical space expansion and study of biological activities

Chiral sp³-rich bicyclo[3.3.1]nonane scaffolds 10-12 were synthesized as single diastereomers from aldehyde 9, which was prepared from 4,4-dimethoxycyclohexa-2,5-dienone through a copper-catalyzed enantioselective reduction. Three different types of intramolecular addition reactions were studied: SmI₂-mediated reductive cyclization, base-promoted aldol reaction, and one-pot Mannich reaction. We succeeded in introducing three side-chains to scaffold 11 and construct an sp³-rich compound library in both enantiomeric variants by simply changing the chirality of the ligands. The biological evaluation revealed that all synthesized compounds exhibited a concentration-dependent inhibition of hypoxia-inducible factor-1 (HIF-1) transcriptional activity, with IC₅₀ values in the range of 17.2-31.7 µM, whereas their effects on cell viability were varied (IC₅₀ = 3.5 to > 100 µM). The most active compound 16f inhibits the accumulation of HIF-1α protein and mRNA in hypoxia, indicating that it has a mechanism of action distinctly different from other known compounds bearing the common bicyclo[3.3.1]nonane skeleton.

Artificial Intelligence for Autonomous Molecular Design: A Perspective

Domain-aware artificial intelligence has been increasingly adopted in recent years to expedite molecular design in various applications, including drug design and discovery. Recent advances in areas such as physics-informed machine learning and reasoning, software engineering, high-end hardware development, and computing infrastructures are providing opportunities to build scalable and explainable AI molecular discovery systems. This could improve a design hypothesis through feedback analysis, data integration that can provide a basis for the introduction of end-to-end automation for compound discovery and optimization, and enable more intelligent searches of chemical space. Several state-of-the-art ML architectures are predominantly and independently used for predicting the properties of small molecules, their high throughput synthesis, and screening, iteratively identifying and optimizing lead therapeutic candidates. However, such deep learning and ML approaches also raise considerable conceptual, technical, scalability, and end-to-end error quantification challenges, as well as skepticism about the current AI hype to build automated tools. To this end, synergistically and intelligently using these individual components along with robust quantum physics-based molecular representation and data generation tools in a closed-loop holds enormous promise for accelerated therapeutic design to critically analyze the opportunities and challenges for their more widespread application. This article aims to identify the most recent technology and breakthrough achieved by each of the components and discusses how such autonomous AI and ML workflows can be integrated to radically accelerate the protein target or disease model-based probe design that can be iteratively validated experimentally. Taken together, this could significantly reduce the timeline for end-to-end therapeutic discovery and optimization upon the arrival of any novel zoonotic transmission event. Our article serves as a guide for medicinal, computational chemistry and biology, analytical chemistry, and the ML community to practice autonomous molecular design in precision medicine and drug discovery.

Analysis of the uncharted, druglike property space by self-organizing maps

Physicochemical properties are fundamental to predict the pharmacokinetic and pharmacodynamic behavior of drug candidates. Easily calculated descriptors such as molecular weight and logP have been found to correlate with the success rate of clinical trials. These properties have been previously shown to highlight a sweet-spot in the chemical space associated with favorable pharmacokinetics, which is superior against other regions during hit identification and optimization. In this study, we applied self-organizing maps (SOMs) trained on sixteen calculated properties of a subset of known drugs for the analysis of commercially available compound databases, as well as public biological and chemical databases frequently used for drug discovery. Interestingly, several regions of the property space have been identified that are highly overrepresented by commercially available chemical libraries, while we found almost completely unoccupied regions of the maps (commercially neglected chemical space resembling the properties of known drugs). Moreover, these underrepresented portions of the chemical space are compatible with most rigorous property filters applied by the pharma industry in medicinal chemistry optimization programs. Our results suggest that SOMs may be directly utilized in the strategy of library design for drug discovery to sample previously unexplored parts of the chemical space to aim at yet-undruggable targets.

Deciphering Cryptic Behavior in Bimetallic Transition-Metal Complexes with Machine Learning

We demonstrate an alternative, data-driven approach to uncovering structure-property relationships for the rational design of heterobimetallic transition-metal complexes that exhibit metal-metal bonding. We tailor graph-based representations of the metal-local environment for these complexes for use in multiple linear regression and kernel ridge regression (KRR) models. We curate a set of 28 experimentally characterized complexes to develop a multiple linear regression model for oxidation potentials. We achieve good accuracy (mean absolute error of 0.25 V) and preserve transferability to unseen experimental data with a new ligand structure. We also train a KRR model on a subset of 330 structurally characterized heterobimetallics to predict the degree of metal-metal bonding. This KRR model predicts relative metal-metal bond lengths in the test set to within 5%, and analysis of key features reveals the fundamental atomic contributions (e.g., the valence electron configuration) that most strongly influence the behavior of these complexes. Our work provides guidance for rational bimetallic design, suggesting that properties, including the formal shortness ratio, should be transferable from one period to another.

Machine learning to tame divergent density functional approximations: a new path to consensus materials design principles

Virtual high-throughput screening (VHTS) with density functional theory (DFT) and machine-learning (ML)-acceleration is essential in rapid materials discovery. By necessity, efficient DFT-based workflows are carried out with a single density functional approximation (DFA). Nevertheless, properties evaluated with different DFAs can be expected to disagree for cases with challenging electronic structure (e.g., open-shell transition-metal complexes, TMCs) for which rapid screening is most needed and accurate benchmarks are often unavailable. To quantify the effect of DFA bias, we introduce an approach to rapidly obtain property predictions from 23 representative DFAs spanning multiple families, “rungs” (e.g., semi-local to double hybrid) and basis sets on over 2000 TMCs. Although computed property values (e.g., spin state splitting and frontier orbital gap) differ by DFA, high linear correlations persist across all DFAs. We train independent ML models for each DFA and observe convergent trends in feature importance, providing DFA-invariant, universal design rules. We devise a strategy to train artificial neural network (ANN) models informed by all 23 DFAs and use them to predict properties (e.g., spin-splitting energy) of over 187k TMCs. By requiring consensus of the ANN-predicted DFA properties, we improve correspondence of computational lead compounds with literature-mined, experimental compounds over the typically employed single-DFA approach.

Machine learning (ML)-based feature analysis reveals universal design rules regardless of density functional choices. Using the consensus among multiple functionals, we identify robust lead complexes in ML-accelerated chemical discovery.

Individual and collective human intelligence in drug design: evaluating the search strategy

In recent years, individual and collective human intelligence, defined as the knowledge, skills, reasoning and intuition of individuals and groups, have been used in combination with computer algorithms to solve complex scientific problems. Such approach was successfully used in different research fields such as: structural biology, comparative genomics, macromolecular crystallography and RNA design. Herein we describe an attempt to use a similar approach in small-molecule drug discovery, specifically to drive search strategies of de novo drug design. This is assessed with a case study that consists of a series of public experiments in which participants had to explore the huge chemical space in silico to find predefined compounds by designing molecules and analyzing the score associate with them. Such a process may be seen as an instantaneous surrogate of the classical design-make-test cycles carried out by medicinal chemists during the drug discovery hit to lead phase but not hindered by long synthesis and testing times. We present first findings on (1) assessing human intelligence in chemical space exploration, (2) comparing individual and collective human intelligence performance in this task and (3) contrasting some human and artificial intelligence achievements in de novo drug design.

Synthesis and Evaluation of Novel 1,2,6-Thiadiazinone Kinase Inhibitors as Potent Inhibitors of Solid Tumors

A focused series of substituted 4H-1,2,6-thiadiazin-4-ones was designed and synthesized to probe the anti-cancer properties of this scaffold. Insights from previous kinase inhibitor programs were used to carefully select several different substitution patterns. Compounds were tested on bladder, prostate, pancreatic, breast, chordoma, and lung cancer cell lines with an additional skin fibroblast cell line as a toxicity control. This resulted in the identification of several low single digit micro molar compounds with promising therapeutic windows, particularly for bladder and prostate cancer. A number of key structural features of the 4H-1,2,6-thiadiazin-4-one scaffold are discussed that show promising scope for future improvement.

Exploring and mapping chemical space with molecular assembly trees

The rule-based search of chemical space can generate an almost infinite number of molecules, but exploration of known molecules as a function of the minimum number of steps needed to build up the target graphs promises to uncover new motifs and transformations. Assembly theory is an approach to compare the intrinsic complexity and properties of molecules by the minimum number of steps needed to build up the target graphs. Here, we apply this approach to prebiotic chemistry, gene sequences, plasticizers, and opiates. This allows us to explore molecules connected to the assembly tree, rather than the entire space of molecules possible. Last, by developing a reassembly method, based on assembly trees, we found that in the case of the opiates, a new set of drug candidates could be generated that would not be accessible via conventional fragment-based drug design, thereby demonstrating how this approach might find application in drug discovery.

Potential Applications of Artificial Intelligence and Machine Learning in Radiochemistry and Radiochemical Engineering

Artificial intelligence and machine learning are poised to disrupt PET imaging from bench to clinic. In this perspective, the authors offer insights into how the technology could be applied to improve the radiosynthesis of new radiopharmaceuticals for PET imaging, including identification of an optimal labeling approach as well as strategies for radiolabeling reaction optimization.

Data-driven algorithms for inverse design of polymers

The ever-increasing demand for novel polymers with superior properties requires a deeper understanding and exploration of the chemical space. Recently, data-driven approaches to explore the chemical space for polymer design have emerged. Among them, inverse design strategies for designing polymers with specific properties have evolved to be a significant materials informatics platform by learning hidden knowledge from materials data as well as smartly navigating the chemical space in an optimized way. In this review, we first summarize the progress in the representation of polymers, a prerequisite step for the inverse design of polymers. Then, we systematically introduce three data-driven strategies implemented for the inverse design of polymers, i.e., high-throughput virtual screening, global optimization, and generative models. Finally, we discuss the challenges and opportunities of the data-driven strategies as well as optimization algorithms employed in the inverse design of polymers.

Ab Initio Machine Learning in Chemical Compound Space

Chemical compound space (CCS), the set of all theoretically conceivable combinations of chemical elements and (meta-)stable geometries that make up matter, is colossal. The first-principles based virtual sampling of this space, for example, in search of novel molecules or materials which exhibit desirable properties, is therefore prohibitive for all but the smallest subsets and simplest properties. We review studies aimed at tackling this challenge using modern machine learning techniques based on (i) synthetic data, typically generated using quantum mechanics based methods, and (ii) model architectures inspired by quantum mechanics. Such Quantum mechanics based Machine Learning (QML) approaches combine the numerical efficiency of statistical surrogate models with an ab initio view on matter. They rigorously reflect the underlying physics in order to reach universality and transferability across CCS. While state-of-the-art approximations to quantum problems impose severe computational bottlenecks, recent QML based developments indicate the possibility of substantial acceleration without sacrificing the predictive power of quantum mechanics.

Computational Discovery of Transition-metal Complexes: From High-throughput Screening to Machine Learning

Transition-metal complexes are attractive targets for the design of catalysts and functional materials. The behavior of the metal-organic bond, while very tunable for achieving target properties, is challenging to predict and necessitates searching a wide and complex space to identify needles in haystacks for target applications. This review will focus on the techniques that make high-throughput search of transition-metal chemical space feasible for the discovery of complexes with desirable properties. The review will cover the development, promise, and limitations of "traditional" computational chemistry (i.e., force field, semiempirical, and density functional theory methods) as it pertains to data generation for inorganic molecular discovery. The review will also discuss the opportunities and limitations in leveraging experimental data sources. We will focus on how advances in statistical modeling, artificial intelligence, multiobjective optimization, and automation accelerate discovery of lead compounds and design rules. The overall objective of this review is to showcase how bringing together advances from diverse areas of computational chemistry and computer science have enabled the rapid uncovering of structure-property relationships in transition-metal chemistry. We aim to highlight how unique considerations in motifs of metal-organic bonding (e.g., variable spin and oxidation state, and bonding strength/nature) set them and their discovery apart from more commonly considered organic molecules. We will also highlight how uncertainty and relative data scarcity in transition-metal chemistry motivate specific developments in machine learning representations, model training, and in computational chemistry. Finally, we will conclude with an outlook of areas of opportunity for the accelerated discovery of transition-metal complexes.

Progress on open chemoinformatic tools for expanding and exploring the chemical space

The concept of chemical space is a cornerstone in chemoinformatics, and it has broad conceptual and practical applicability in many areas of chemistry, including drug design and discovery. One of the most considerable impacts is in the study of structure-property relationships where the property can be a biological activity or any other characteristic of interest to a particular chemistry discipline. The chemical space is highly dependent on the molecular representation that is also a cornerstone concept in computational chemistry. Herein, we discuss the recent progress on chemoinformatic tools developed to expand and characterize the chemical space of compound data sets using different types of molecular representations, generate visual representations of such spaces, and explore structure-property relationships in the context of chemical spaces. We emphasize the development of methods and freely available tools focusing on drug discovery applications. We also comment on the general advantages and shortcomings of using freely available and easy-to-use tools and discuss the value of using such open resources for research, education, and scientific dissemination.

Fragment-Based Ligand Discovery Using Protein-Observed 19F NMR: A Second Semester Organic Chemistry CURE Project

Curriculum-based undergraduate research experiences (CUREs) have been shown to increase student retention in STEM fields and are starting to become more widely adopted in chemistry curricula. Here we describe a 10-week CURE that is suitable for a second-semester organic chemistry laboratory course. Students synthesize small molecules and use protein-observed ¹⁹F (PrOF) NMR to assess the small molecule's binding affinity to a target protein. The research project introduced students to multistep organic synthesis, structure-activity relationship studies, quantitative biophysical measurements (measuring K_d from PrOF NMR experiments), and scientific literacy. Docking experiments could be added to help students understand how changes in a ligand structure may affect binding to a protein. Assessment using the CURE survey indicates self-perceived skill gains from the course that exceed gains measured in a traditional and an inquiry-based laboratory experience. Given the speed of the binding experiment and the alignment of the synthetic methods with a second-semester organic chemistry laboratory course, a PrOF NMR fragment-based ligand discovery lab can be readily implemented in the undergraduate chemistry curriculum.

Data Science in Chemical Engineering: Applications to Molecular Science

Chemical engineering is being rapidly transformed by the tools of data science. On the horizon, artificial intelligence (AI) applications will impact a huge swath of our work, ranging from the discovery and design of new molecules to operations and manufacturing and many areas in between. Early adoption of data science, machine learning, and early examples of AI in chemical engineering has been rich with examples of molecular data science-the application tools for molecular discovery and property optimization at the atomic scale. We summarize key advances in this nascent subfield while introducing molecular data science for a broad chemical engineering readership. We introduce the field through the concept of a molecular data science life cycle and discuss relevant aspects of five distinct phases of this process: creation of curated data sets, molecular representations, data-driven property prediction, generation of new molecules, and feasibility and synthesizability considerations.

Putting Density Functional Theory to the Test in Machine-Learning-Accelerated Materials Discovery

Accelerated discovery with machine learning (ML) has begun to provide the advances in efficiency needed to overcome the combinatorial challenge of computational materials design. Nevertheless, ML-accelerated discovery both inherits the biases of training data derived from density functional theory (DFT) and leads to many attempted calculations that are doomed to fail. Many compelling functional materials and catalytic processes involve strained chemical bonds, open-shell radicals and diradicals, or metal-organic bonds to open-shell transition-metal centers. Although promising targets, these materials present unique challenges for electronic structure methods and combinatorial challenges for their discovery. In this Perspective, we describe the advances needed in accuracy, efficiency, and approach beyond what is typical in conventional DFT-based ML workflows. These challenges have begun to be addressed through ML models trained to predict the results of multiple methods or the differences between them, enabling quantitative sensitivity analysis. For DFT to be trusted for a given data point in a high-throughput screen, it must pass a series of tests. ML models that predict the likelihood of calculation success and detect the presence of strong correlation will enable rapid diagnoses and adaptation strategies. These "decision engines" represent the first steps toward autonomous workflows that avoid the need for expert determination of the robustness of DFT-based materials discoveries.

Prediction of Chromatography Conditions for Purification in Organic Synthesis Using Deep Learning

In this research, a process for developing normal-phase liquid chromatography solvent systems has been proposed. In contrast to the development of conditions via thin-layer chromatography (TLC), this process is based on the architecture of two hierarchically connected neural network-based components. Using a large database of reaction procedures allows those two components to perform an essential role in the machine-learning-based prediction of chromatographic purification conditions, i.e., solvents and the ratio between solvents. In our paper, we build two datasets and test various molecular vectorization approaches, such as extended-connectivity fingerprints, learned embedding, and auto-encoders along with different types of deep neural networks to demonstrate a novel method for modeling chromatographic solvent systems employing two neural networks in sequence. Afterward, we present our findings and provide insights on the most effective methods for solving prediction tasks. Our approach results in a system of two neural networks with long short-term memory (LSTM)-based auto-encoders, where the first predicts solvent labels (by reaching the classification accuracy of 0.950 ± 0.001) and in the case of two solvents, the second one predicts the ratio between two solvents (R2 metric equal to 0.982 ± 0.001). Our approach can be used as a guidance instrument in laboratories to accelerate scouting for suitable chromatography conditions.

MolFinder: an evolutionary algorithm for the global optimization of molecular properties and the extensive exploration of chemical space using SMILES

Here, we introduce a new molecule optimization method, MolFinder, based on an efficient global optimization algorithm, the conformational space annealing algorithm, and the SMILES representation. MolFinder finds diverse molecules with desired properties efficiently without any training and a large molecular database. Compared with recently proposed reinforcement-learning-based molecule optimization algorithms, MolFinder consistently outperforms in terms of both the optimization of a given target property and the generation of a set of diverse and novel molecules. The efficiency of MolFinder demonstrates that combinatorial optimization using the SMILES representation is a promising approach for molecule optimization, which has not been well investigated despite its simplicity. We believe that our results shed light on new possibilities for advances in molecule optimization methods.