Exploring Chemical Space with Machine Learning

When Machine Learning and Deep Learning Come to the Big Data in Food Chemistry

Since the first food database was released over one hundred years ago, food databases have become more diversified, including food composition databases, food flavor databases, and food chemical compound databases. These databases provide detailed information about the nutritional compositions, flavor molecules, and chemical properties of various food compounds. As artificial intelligence (AI) is becoming popular in every field, AI methods can also be applied to food industry research and molecular chemistry. Machine learning and deep learning are valuable tools for analyzing big data sources such as food databases. Studies investigating food compositions, flavors, and chemical compounds with AI concepts and learning methods have emerged in the past few years. This review illustrates several well-known food databases, focusing on their primary contents, interfaces, and other essential features. We also introduce some of the most common machine learning and deep learning methods. Furthermore, a few studies related to food databases are given as examples, demonstrating their applications in food pairing, food-drug interactions, and molecular modeling. Based on the results of these applications, it is expected that the combination of food databases and AI will play an essential role in food science and food chemistry.

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.

Natural product drug discovery in the artificial intelligence era

Natural products (NPs) are primarily recognized as privileged structures to interact with protein drug targets. Their unique characteristics and structural diversity continue to marvel scientists for developing NP-inspired medicines, even though the pharmaceutical industry has largely given up. High-performance computer hardware, extensive storage, accessible software and affordable online education have democratized the use of artificial intelligence (AI) in many sectors and research areas. The last decades have introduced natural language processing and machine learning algorithms, two subfields of AI, to tackle NP drug discovery challenges and open up opportunities. In this article, we review and discuss the rational applications of AI approaches developed to assist in discovering bioactive NPs and capturing the molecular "patterns" of these privileged structures for combinatorial design or target selectivity.

MassGenie: A Transformer-Based Deep Learning Method for Identifying Small Molecules from Their Mass Spectra

The 'inverse problem' of mass spectrometric molecular identification ('given a mass spectrum, calculate/predict the 2D structure of the molecule whence it came') is largely unsolved, and is especially acute in metabolomics where many small molecules remain unidentified. This is largely because the number of experimentally available electrospray mass spectra of small molecules is quite limited. However, the forward problem ('calculate a small molecule's likely fragmentation and hence at least some of its mass spectrum from its structure alone') is much more tractable, because the strengths of different chemical bonds are roughly known. This kind of molecular identification problem may be cast as a language translation problem in which the source language is a list of high-resolution mass spectral peaks and the 'translation' a representation (for instance in SMILES) of the molecule. It is thus suitable for attack using the deep neural networks known as transformers. We here present MassGenie, a method that uses a transformer-based deep neural network, trained on ~6 million chemical structures with augmented SMILES encoding and their paired molecular fragments as generated in silico, explicitly including the protonated molecular ion. This architecture (containing some 400 million elements) is used to predict the structure of a molecule from the various fragments that may be expected to be observed when some of its bonds are broken. Despite being given essentially no detailed nor explicit rules about molecular fragmentation methods, isotope patterns, rearrangements, neutral losses, and the like, MassGenie learns the effective properties of the mass spectral fragment and valency space, and can generate candidate molecular structures that are very close or identical to those of the 'true' molecules. We also use VAE-Sim, a previously published variational autoencoder, to generate candidate molecules that are 'similar' to the top hit. In addition to using the 'top hits' directly, we can produce a rank order of these by 'round-tripping' candidate molecules and comparing them with the true molecules, where known. As a proof of principle, we confine ourselves to positive electrospray mass spectra from molecules with a molecular mass of 500Da or lower, including those in the last CASMI challenge (for which the results are known), getting 49/93 (53%) precisely correct. The transformer method, applied here for the first time to mass spectral interpretation, works extremely effectively both for mass spectra generated in silico and on experimentally obtained mass spectra from pure compounds. It seems to act as a Las Vegas algorithm, in that it either gives the correct answer or simply states that it cannot find one. The ability to create and to 'learn' millions of fragmentation patterns in silico, and therefrom generate candidate structures (that do not have to be in existing libraries) directly, thus opens up entirely the field of de novo small molecule structure prediction from experimental mass spectra.

Diversity and Chemical Library Networks of Large Data Sets

The quantification of chemical diversity has many applications in drug discovery, organic chemistry, food, and natural product chemistry, to name a few. As the size of the chemical space is expanding rapidly, it is imperative to develop efficient methods to quantify the diversity of large and ultralarge chemical libraries and visualize their mutual relationships in chemical space. Herein, we show an application of our recently introduced extended similarity indices to measure the fingerprint-based diversity of 19 chemical libraries typically used in drug discovery and natural products research with over 18 million compounds. Based on this concept, we introduce the Chemical Library Networks (CLNs) as a general and efficient framework to represent visually the chemical space of large chemical libraries providing a global perspective of the relation between the libraries. For the 19 compound libraries explored in this work, it was found that the (extended) Tanimoto index offers the best description of extended similarity in combination with RDKit fingerprints. CLNs are general and can be explored with any structure representation and similarity coefficient for large chemical libraries.

Comprehensive Survey of Recent Drug Discovery Using Deep Learning

Drug discovery based on artificial intelligence has been in the spotlight recently as it significantly reduces the time and cost required for developing novel drugs. With the advancement of deep learning (DL) technology and the growth of drug-related data, numerous deep-learning-based methodologies are emerging at all steps of drug development processes. In particular, pharmaceutical chemists have faced significant issues with regard to selecting and designing potential drugs for a target of interest to enter preclinical testing. The two major challenges are prediction of interactions between drugs and druggable targets and generation of novel molecular structures suitable for a target of interest. Therefore, we reviewed recent deep-learning applications in drug-target interaction (DTI) prediction and de novo drug design. In addition, we introduce a comprehensive summary of a variety of drug and protein representations, DL models, and commonly used benchmark datasets or tools for model training and testing. Finally, we present the remaining challenges for the promising future of DL-based DTI prediction and de novo drug design.

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.

FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space

The question of molecular similarity is core in cheminformatics and is usually assessed via a pairwise comparison based on vectors of properties or molecular fingerprints. We recently exploited variational autoencoders to embed 6M molecules in a chemical space, such that their (Euclidean) distance within the latent space so formed could be assessed within the framework of the entire molecular set. However, the standard objective function used did not seek to manipulate the latent space so as to cluster the molecules based on any perceived similarity. Using a set of some 160,000 molecules of biological relevance, we here bring together three modern elements of deep learning to create a novel and disentangled latent space, viz transformers, contrastive learning, and an embedded autoencoder. The effective dimensionality of the latent space was varied such that clear separation of individual types of molecules could be observed within individual dimensions of the latent space. The capacity of the network was such that many dimensions were not populated at all. As before, we assessed the utility of the representation by comparing clozapine with its near neighbors, and we also did the same for various antibiotics related to flucloxacillin. Transformers, especially when as here coupled with contrastive learning, effectively provide one-shot learning and lead to a successful and disentangled representation of molecular latent spaces that at once uses the entire training set in their construction while allowing "similar" molecules to cluster together in an effective and interpretable way.

Critical benchmarking of popular composite thermochemistry models and density functional approximations on a probabilistically pruned benchmark dataset of formation enthalpies

First-principles calculation of the standard formation enthalpy, ΔH_f° (298 K), in such a large scale as required by chemical space explorations, is amenable only with density functional approximations (DFAs) and certain composite wave function theories (cWFTs). Unfortunately, the accuracies of popular range-separated hybrid, "rung-4" DFAs, and cWFTs that offer the best accuracy-vs-cost trade-off have until now been established only for datasets predominantly comprising small molecules; their transferability to larger systems remains vague. In this study, we present an extended benchmark dataset of ΔH_f° for structurally and electronically diverse molecules. We apply quartile-ranking based on boundary-corrected kernel density estimation to filter outliers and arrive at probabilistically pruned enthalpies of 1694 compounds (PPE1694). For this dataset, we rank the prediction accuracies of G4, G4(MP2), ccCA, CBS-QB3, and 23 popular DFAs using conventional and probabilistic error metrics. We discuss systematic prediction errors and highlight the role an empirical higher-level correction plays in the G4(MP2) model. Furthermore, we comment on uncertainties associated with the reference empirical data for atoms and the systematic errors stemming from these that grow with the molecular size. We believe that these findings will aid in identifying meaningful application domains for quantum thermochemical methods.

Deep learning and generative methods in cheminformatics and chemical biology: navigating small molecule space intelligently

The number of 'small' molecules that may be of interest to chemical biologists - chemical space - is enormous, but the fraction that have ever been made is tiny. Most strategies are discriminative, i.e. have involved 'forward' problems (have molecule, establish properties). However, we normally wish to solve the much harder generative or inverse problem (describe desired properties, find molecule). 'Deep' (machine) learning based on large-scale neural networks underpins technologies such as computer vision, natural language processing, driverless cars, and world-leading performance in games such as Go; it can also be applied to the solution of inverse problems in chemical biology. In particular, recent developments in deep learning admit the in silico generation of candidate molecular structures and the prediction of their properties, thereby allowing one to navigate (bio)chemical space intelligently. These methods are revolutionary but require an understanding of both (bio)chemistry and computer science to be exploited to best advantage. We give a high-level (non-mathematical) background to the deep learning revolution, and set out the crucial issue for chemical biology and informatics as a two-way mapping from the discrete nature of individual molecules to the continuous but high-dimensional latent representation that may best reflect chemical space. A variety of architectures can do this; we focus on a particular type known as variational autoencoders. We then provide some examples of recent successes of these kinds of approach, and a look towards the future.

Machine Learning Methods in Drug Discovery

The advancements of information technology and related processing techniques have created a fertile base for progress in many scientific fields and industries. In the fields of drug discovery and development, machine learning techniques have been used for the development of novel drug candidates. The methods for designing drug targets and novel drug discovery now routinely combine machine learning and deep learning algorithms to enhance the efficiency, efficacy, and quality of developed outputs. The generation and incorporation of big data, through technologies such as high-throughput screening and high through-put computational analysis of databases used for both lead and target discovery, has increased the reliability of the machine learning and deep learning incorporated techniques. The use of these virtual screening and encompassing online information has also been highlighted in developing lead synthesis pathways. In this review, machine learning and deep learning algorithms utilized in drug discovery and associated techniques will be discussed. The applications that produce promising results and methods will be reviewed.

Evaluation of QSAR Equations for Virtual Screening

Quantitative Structure Activity Relationship (QSAR) models can inform on the correlation between activities and structure-based molecular descriptors. This information is important for the understanding of the factors that govern molecular properties and for designing new compounds with favorable properties. Due to the large number of calculate-able descriptors and consequently, the much larger number of descriptors combinations, the derivation of QSAR models could be treated as an optimization problem. For continuous responses, metrics which are typically being optimized in this process are related to model performances on the training set, for example, R2 and QCV2. Similar metrics, calculated on an external set of data (e.g., QF1/F2/F32), are used to evaluate the performances of the final models. A common theme of these metrics is that they are context -” ignorant”. In this work we propose that QSAR models should be evaluated based on their intended usage. More specifically, we argue that QSAR models developed for Virtual Screening (VS) should be derived and evaluated using a virtual screening-aware metric, e.g., an enrichment-based metric. To demonstrate this point, we have developed 21 Multiple Linear Regression (MLR) models for seven targets (three models per target), evaluated them first on validation sets and subsequently tested their performances on two additional test sets constructed to mimic small-scale virtual screening campaigns. As expected, we found no correlation between model performances evaluated by “classical” metrics, e.g., R2 and QF1/F2/F32 and the number of active compounds picked by the models from within a pool of random compounds. In particular, in some cases models with favorable R2 and/or QF1/F2/F32 values were unable to pick a single active compound from within the pool whereas in other cases, models with poor R2 and/or QF1/F2/F32 values performed well in the context of virtual screening. We also found no significant correlation between the number of active compounds correctly identified by the models in the training, validation and test sets. Next, we have developed a new algorithm for the derivation of MLR models by optimizing an enrichment-based metric and tested its performances on the same datasets. We found that the best models derived in this manner showed, in most cases, much more consistent results across the training, validation and test sets and outperformed the corresponding MLR models in most virtual screening tests. Finally, we demonstrated that when tested as binary classifiers, models derived for the same targets by the new algorithm outperformed Random Forest (RF) and Support Vector Machine (SVM)-based models across training/validation/test sets, in most cases. We attribute the better performances of the Enrichment Optimizer Algorithm (EOA) models in VS to better handling of inactive random compounds. Optimizing an enrichment-based metric is therefore a promising strategy for the derivation of QSAR models for classification and virtual screening.

Elevating Chemistry Research with a Modern Electronics Toolkit

With the rapid development of high technology, chemical science is not as it used to be a century ago. Many chemists acquire and utilize skills that are well beyond the traditional definition of chemistry. The digital age has transformed chemistry laboratories. One aspect of this transformation is the progressing implementation of electronics and computer science in chemistry research. In the past decade, numerous chemistry-oriented studies have benefited from the implementation of electronic modules, including microcontroller boards (MCBs), single-board computers (SBCs), professional grade control and data acquisition systems, as well as field-programmable gate arrays (FPGAs). In particular, MCBs and SBCs provide good value for money. The application areas for electronic modules in chemistry research include construction of simple detection systems based on spectrophotometry and spectrofluorometry principles, customizing laboratory devices for automation of common laboratory practices, control of reaction systems (batch- and flow-based), extraction systems, chromatographic and electrophoretic systems, microfluidic systems (classical and nonclassical), custom-built polymerase chain reaction devices, gas-phase analyte detection systems, chemical robots and drones, construction of FPGA-based imaging systems, and the Internet-of-Chemical-Things. The technology is easy to handle, and many chemists have managed to train themselves in its implementation. The only major obstacle in its implementation is probably one's imagination.