Chemical language models enable navigation in sparsely populated chemical space

t-SMILES: a fragment-based molecular representation framework for de novo ligand design

Effective representation of molecules is a crucial factor affecting the performance of artificial intelligence models. This study introduces a flexible, fragment-based, multiscale molecular representation framework called t-SMILES (tree-based SMILES) with three code algorithms: TSSA (t-SMILES with shared atom), TSDY (t-SMILES with dummy atom but without ID) and TSID (t-SMILES with ID and dummy atom). It describes molecules using SMILES-type strings obtained by performing a breadth-first search on a full binary tree formed from a fragmented molecular graph. Systematic evaluations using JTVAE, BRICS, MMPA, and Scaffold show the feasibility of constructing a multi-code molecular description system, where various descriptions complement each other, enhancing the overall performance. In addition, it can avoid overfitting and achieve higher novelty scores while maintaining reasonable similarity on labeled low-resource datasets, regardless of whether the model is original, data-augmented, or pre-trained then fine-tuned. Furthermore, it significantly outperforms classical SMILES, DeepSMILES, SELFIES and baseline models in goal-directed tasks. And it surpasses state-of-the-art fragment, graph and SMILES based approaches on ChEMBL, Zinc, and QM9.

Deep learning for low-data drug discovery: Hurdles and opportunities

Deep learning is becoming increasingly relevant in drug discovery, from de novo design to protein structure prediction and synthesis planning. However, it is often challenged by the small data regimes typical of certain drug discovery tasks. In such scenarios, deep learning approaches-which are notoriously 'data-hungry'-might fail to live up to their promise. Developing novel approaches to leverage the power of deep learning in low-data scenarios is sparking great attention, and future developments are expected to propel the field further. This mini-review provides an overview of recent low-data-learning approaches in drug discovery, analyzing their hurdles and advantages. Finally, we venture to provide a forecast of future research directions in low-data learning for drug discovery.

Advances in machine learning with chemical language models in molecular property and reaction outcome predictions

Molecular properties and reactions form the foundation of chemical space. Over the years, innumerable molecules have been synthesized, a smaller fraction of them found immediate applications, while a larger proportion served as a testimony to creative and empirical nature of the domain of chemical science. With increasing emphasis on sustainable practices, it is desirable that a target set of molecules are synthesized preferably through a fewer empirical attempts instead of a larger library, to realize an active candidate. In this front, predictive endeavors using machine learning (ML) models built on available data acquire high timely significance. Prediction of molecular property and reaction outcome remain one of the burgeoning applications of ML in chemical science. Among several methods of encoding molecular samples for ML models, the ones that employ language like representations are gaining steady popularity. Such representations would additionally help adopt well-developed natural language processing (NLP) models for chemical applications. Given this advantageous background, herein we describe several successful chemical applications of NLP focusing on molecular property and reaction outcome predictions. From relatively simpler recurrent neural networks (RNNs) to complex models like transformers, different network architecture have been leveraged for tasks such as de novo drug design, catalyst generation, forward and retro-synthesis predictions. The chemical language model (CLM) provides promising avenues toward a broad range of applications in a time and cost-effective manner. While we showcase an optimistic outlook of CLMs, attention is also placed on the persisting challenges in reaction domain, which would optimistically be addressed by advanced algorithms tailored to chemical language and with increased availability of high-quality datasets.

Exploring Novel Fentanyl Analogues Using a Graph-Based Transformer Model

The structures of fentanyl and its analogues are easy to be modified and few types have been included in database so far, which allow criminals to avoid the supervision of relevant departments. This paper introduces a molecular graph-based transformer model, which is combined with a data augmentation method based on substructure replacement to generate novel fentanyl analogues. 140,000 molecules were generated, and after a set of screening, 36,799 potential fentanyl analogues were finally obtained. We calculated the molecular properties of 36,799 potential fentanyl analogues. The results showed that the model could learn some properties of original fentanyl molecules. We compared the generated molecules from transformer model and data augmentation method based on substructure replacement with those generated by the other two molecular generation models based on deep learning, and found that the model in this paper can generate more novel potential fentanyl analogues. Finally, the findings of the paper indicate that transformer model based on molecular graph helps us explore the structure of potential fentanyl molecules as well as understand distribution of original molecules of fentanyl.

Prospective de novo drug design with deep interactome learning

De novo drug design aims to generate molecules from scratch that possess specific chemical and pharmacological properties. We present a computational approach utilizing interactome-based deep learning for ligand- and structure-based generation of drug-like molecules. This method capitalizes on the unique strengths of both graph neural networks and chemical language models, offering an alternative to the need for application-specific reinforcement, transfer, or few-shot learning. It enables the "zero-shot" construction of compound libraries tailored to possess specific bioactivity, synthesizability, and structural novelty. In order to proactively evaluate the deep interactome learning framework for protein structure-based drug design, potential new ligands targeting the binding site of the human peroxisome proliferator-activated receptor (PPAR) subtype gamma are generated. The top-ranking designs are chemically synthesized and computationally, biophysically, and biochemically characterized. Potent PPAR partial agonists are identified, demonstrating favorable activity and the desired selectivity profiles for both nuclear receptors and off-target interactions. Crystal structure determination of the ligand-receptor complex confirms the anticipated binding mode. This successful outcome positively advocates interactome-based de novo design for application in bioorganic and medicinal chemistry, enabling the creation of innovative bioactive molecules.

Fast and effective molecular property prediction with transferability map

Effective transfer learning for molecular property prediction has shown considerable strength in addressing insufficient labeled molecules. Many existing methods either disregard the quantitative relationship between source and target properties, risking negative transfer, or require intensive training on target tasks. To quantify transferability concerning task-relatedness, we propose Principal Gradient-based Measurement (PGM) for transferring molecular property prediction ability. First, we design an optimization-free scheme to calculate a principal gradient for approximating the direction of model optimization on a molecular property prediction dataset. We have analyzed the close connection between the principal gradient and model optimization through mathematical proof. PGM measures the transferability as the distance between the principal gradient obtained from the source dataset and that derived from the target dataset. Then, we perform PGM on various molecular property prediction datasets to build a quantitative transferability map for source dataset selection. Finally, we evaluate PGM on multiple combinations of transfer learning tasks across 12 benchmark molecular property prediction datasets and demonstrate that it can serve as fast and effective guidance to improve the performance of a target task. This work contributes to more efficient discovery of drugs, materials, and catalysts by offering a task-relatedness quantification prior to transfer learning and understanding the relationship between chemical properties.

NAFLDkb: A Knowledge Base and Platform for Drug Development against Nonalcoholic Fatty Liver Disease

Nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease with a broad spectrum of histologic manifestations. The rapidly growing prevalence and the complex pathologic mechanisms of NAFLD pose great challenges for treatment development. Despite tremendous efforts devoted to drug development, there are no FDA-approved medicines yet. Here, we present NAFLDkb, a specialized knowledge base and platform for computer-aided drug design against NAFLD. With multiperspective information curated from diverse source materials and public databases, NAFLDkb presents the associations of drug-related entities as individual knowledge graphs. Practical drug discovery tools that facilitate the utilization and expansion of NAFLDkb have also been implemented in the web interface, including chemical structure search, drug-likeness screening, knowledge-based repositioning, and research article annotation. Moreover, case studies of a knowledge graph repositioning model and a generative neural network model are presented herein, where three repositioning drug candidates and 137 novel lead-like compounds were newly established as NAFLD pharmacotherapy options reusing data records and machine learning tools in NAFLDkb, suggesting its clinical reliability and great potential in identifying novel drug-disease associations of NAFLD and generating new insights to accelerate NAFLD drug development. NAFLDkb is freely accessible at https://www.biosino.org/nafldkb and will be updated periodically with the latest findings.

Chemoinformatic approaches for navigating large chemical spaces

INTRODUCTION

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

AREAS COVERED

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

EXPERT OPINION

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

Reinvent 4: Modern AI-driven generative molecule design

REINVENT 4 is a modern open-source generative AI framework for the design of small molecules. The software utilizes recurrent neural networks and transformer architectures to drive molecule generation. These generators are seamlessly embedded within the general machine learning optimization algorithms, transfer learning, reinforcement learning and curriculum learning. REINVENT 4 enables and facilitates de novo design, R-group replacement, library design, linker design, scaffold hopping and molecule optimization. This contribution gives an overview of the software and describes its design. Algorithms and their applications are discussed in detail. REINVENT 4 is a command line tool which reads a user configuration in either TOML or JSON format. The aim of this release is to provide reference implementations for some of the most common algorithms in AI based molecule generation. An additional goal with the release is to create a framework for education and future innovation in AI based molecular design. The software is available from https://github.com/MolecularAI/REINVENT4 and released under the permissive Apache 2.0 license. Scientific contribution. The software provides an open-source reference implementation for generative molecular design where the software is also being used in production to support in-house drug discovery projects. The publication of the most common machine learning algorithms in one code and full documentation thereof will increase transparency of AI and foster innovation, collaboration and education.

Generative artificial intelligence in drug discovery: basic framework, recent advances, challenges, and opportunities

There are two main ways to discover or design small drug molecules. The first involves fine-tuning existing molecules or commercially successful drugs through quantitative structure-activity relationships and virtual screening. The second approach involves generating new molecules through de novo drug design or inverse quantitative structure-activity relationship. Both methods aim to get a drug molecule with the best pharmacokinetic and pharmacodynamic profiles. However, bringing a new drug to market is an expensive and time-consuming endeavor, with the average cost being estimated at around $2.5 billion. One of the biggest challenges is screening the vast number of potential drug candidates to find one that is both safe and effective. The development of artificial intelligence in recent years has been phenomenal, ushering in a revolution in many fields. The field of pharmaceutical sciences has also significantly benefited from multiple applications of artificial intelligence, especially drug discovery projects. Artificial intelligence models are finding use in molecular property prediction, molecule generation, virtual screening, synthesis planning, repurposing, among others. Lately, generative artificial intelligence has gained popularity across domains for its ability to generate entirely new data, such as images, sentences, audios, videos, novel chemical molecules, etc. Generative artificial intelligence has also delivered promising results in drug discovery and development. This review article delves into the fundamentals and framework of various generative artificial intelligence models in the context of drug discovery via de novo drug design approach. Various basic and advanced models have been discussed, along with their recent applications. The review also explores recent examples and advances in the generative artificial intelligence approach, as well as the challenges and ongoing efforts to fully harness the potential of generative artificial intelligence in generating novel drug molecules in a faster and more affordable manner. Some clinical-level assets generated form generative artificial intelligence have also been discussed in this review to show the ever-increasing application of artificial intelligence in drug discovery through commercial partnerships.

Chemical language models for molecular design

In drug discovery, chemical language models (CLMs) originating from natural language processing offer new opportunities for molecular design. CLMs have been developed using recurrent neural network (RNN) or transformer architectures. For the predictive performance of RNN-based encoder-decoder frameworks and transformers, attention mechanisms play a central role. Among others, emerging application areas for CLMs include constrained generative modeling and the prediction of chemical reactions or drug-target interactions. Since CLMs are applicable to any compound or target data that can be presented in a sequential format and tokenized, mappings of different types of sequences can be learned. For example, active compounds can be predicted from protein sequence motifs. Novel off-the-beat-path applications can also be considered. For example, analogue series from medicinal chemistry can be perceived and represented as chemical sequences and extended with new compounds using CLMs. Herein, methodological features of CLMs and different applications are discussed.

Deep Learning-Enabled MS/MS Spectrum Prediction Facilitates Automated Identification Of Novel Psychoactive Substances

The market for illicit drugs has been reshaped by the emergence of more than 1100 new psychoactive substances (NPS) over the past decade, posing a major challenge to the forensic and toxicological laboratories tasked with detecting and identifying them. Tandem mass spectrometry (MS/MS) is the primary method used to screen for NPS within seized materials or biological samples. The most contemporary workflows necessitate labor-intensive and expensive MS/MS reference standards, which may not be available for recently emerged NPS on the illicit market. Here, we present NPS-MS, a deep learning method capable of accurately predicting the MS/MS spectra of known and hypothesized NPS from their chemical structures alone. NPS-MS is trained by transfer learning from a generic MS/MS prediction model on a large data set of MS/MS spectra. We show that this approach enables a more accurate identification of NPS from experimentally acquired MS/MS spectra than any existing method. We demonstrate the application of NPS-MS to identify a novel derivative of phencyclidine (PCP) within an unknown powder seized in Denmark without the use of any reference standards. We anticipate that NPS-MS will allow forensic laboratories to identify more rapidly both known and newly emerging NPS. NPS-MS is available as a web server at https://nps-ms.ca/, which provides MS/MS spectra prediction capabilities for given NPS compounds. Additionally, it offers MS/MS spectra identification against a vast database comprising approximately 8.7 million predicted NPS compounds from DarkNPS and 24.5 million predicted ESI-QToF-MS/MS spectra for these compounds.

Identification of Emerging Novel Psychoactive Substances by Retrospective Analysis of Population-Scale Mass Spectrometry Data Sets

Over the last two decades, hundreds of new psychoactive substances (NPSs), also known as "designer drugs", have emerged on the illicit drug market. The toxic and potentially fatal effects of these compounds oblige laboratories around the world to screen for NPS in seized materials and biological samples, commonly using high-resolution mass spectrometry. However, unambiguous identification of a NPS by mass spectrometry requires comparison to data from analytical reference materials, acquired on the same instrument. The sheer number of NPSs that are available on the illicit market, and the pace at which new compounds are introduced, means that forensic laboratories must make difficult decisions about which reference materials to acquire. Here, we asked whether retrospective suspect screening of population-scale mass spectrometry data could provide a data-driven platform to prioritize emerging NPSs for assay development. We curated a suspect database of precursor and diagnostic fragment ion masses for 83 emerging NPSs and used this database to retrospectively screen mass spectrometry data from 12,727 urine drug screens from one Canadian province. We developed integrative computational strategies to prioritize the most reliable identifications and tracked the frequency of these identifications over a 3 year study period between August 2019 and August 2022. The resulting data were used to guide the acquisition of new reference materials, which were in turn used to validate a subset of the retrospective identifications. Last, we took advantage of matching clinical reports for all 12,727 samples to systematically benchmark the accuracy of our retrospective data analysis approach. Our work opens up new avenues to enable the rapid detection of emerging illicit drugs through large-scale reanalysis of mass spectrometry data.

Variational autoencoder-based chemical latent space for large molecular structures with 3D complexity

The structural diversity of chemical libraries, which are systematic collections of compounds that have potential to bind to biomolecules, can be represented by chemical latent space. A chemical latent space is a projection of a compound structure into a mathematical space based on several molecular features, and it can express structural diversity within a compound library in order to explore a broader chemical space and generate novel compound structures for drug candidates. In this study, we developed a deep-learning method, called NP-VAE (Natural Product-oriented Variational Autoencoder), based on variational autoencoder for managing hard-to-analyze datasets from DrugBank and large molecular structures such as natural compounds with chirality, an essential factor in the 3D complexity of compounds. NP-VAE was successful in constructing the chemical latent space from large-sized compounds that were unable to be handled in existing methods, achieving higher reconstruction accuracy, and demonstrating stable performance as a generative model across various indices. Furthermore, by exploring the acquired latent space, we succeeded in comprehensively analyzing a compound library containing natural compounds and generating novel compound structures with optimized functions.

Integrated Molecular Modeling and Machine Learning for Drug Design

Modern therapeutic development often involves several stages that are interconnected, and multiple iterations are usually required to bring a new drug to the market. Computational approaches have increasingly become an indispensable part of helping reduce the time and cost of the research and development of new drugs. In this Perspective, we summarize our recent efforts on integrating molecular modeling and machine learning to develop computational tools for modulator design, including a pocket-guided rational design approach based on AlphaSpace to target protein-protein interactions, delta machine learning scoring functions for protein-ligand docking as well as virtual screening, and state-of-the-art deep learning models to predict calculated and experimental molecular properties based on molecular mechanics optimized geometries. Meanwhile, we discuss remaining challenges and promising directions for further development and use a retrospective example of FDA approved kinase inhibitor Erlotinib to demonstrate the use of these newly developed computational tools.

Functional annotation of enzyme-encoding genes using deep learning with transformer layers

Functional annotation of open reading frames in microbial genomes remains substantially incomplete. Enzymes constitute the most prevalent functional gene class in microbial genomes and can be described by their specific catalytic functions using the Enzyme Commission (EC) number. Consequently, the ability to predict EC numbers could substantially reduce the number of un-annotated genes. Here we present a deep learning model, DeepECtransformer, which utilizes transformer layers as a neural network architecture to predict EC numbers. Using the extensively studied Escherichia coli K-12 MG1655 genome, DeepECtransformer predicted EC numbers for 464 un-annotated genes. We experimentally validated the enzymatic activities predicted for three proteins (YgfF, YciO, and YjdM). Further examination of the neural network's reasoning process revealed that the trained neural network relies on functional motifs of enzymes to predict EC numbers. Thus, DeepECtransformer is a method that facilitates the functional annotation of uncharacterized genes.

Hallucinating hallucinogens

Fighting the designer drug epidemic with generative AI.

Scientific discovery in the age of artificial intelligence

Artificial intelligence (AI) is being increasingly integrated into scientific discovery to augment and accelerate research, helping scientists to generate hypotheses, design experiments, collect and interpret large datasets, and gain insights that might not have been possible using traditional scientific methods alone. Here we examine breakthroughs over the past decade that include self-supervised learning, which allows models to be trained on vast amounts of unlabelled data, and geometric deep learning, which leverages knowledge about the structure of scientific data to enhance model accuracy and efficiency. Generative AI methods can create designs, such as small-molecule drugs and proteins, by analysing diverse data modalities, including images and sequences. We discuss how these methods can help scientists throughout the scientific process and the central issues that remain despite such advances. Both developers and users of AI toolsneed a better understanding of when such approaches need improvement, and challenges posed by poor data quality and stewardship remain. These issues cut across scientific disciplines and require developing foundational algorithmic approaches that can contribute to scientific understanding or acquire it autonomously, making them critical areas of focus for AI innovation.

67 million natural product-like compound database generated via molecular language processing

Natural products are a rich resource of bioactive compounds for valuable applications across multiple fields such as food, agriculture, and medicine. For natural product discovery, high throughput in silico screening offers a cost-effective alternative to traditional resource-heavy assay-guided exploration of structurally novel chemical space. In this data descriptor, we report a characterized database of 67,064,204 natural product-like molecules generated using a recurrent neural network trained on known natural products, demonstrating a significant 165-fold expansion in library size over the approximately 400,000 known natural products. This study highlights the potential of using deep generative models to explore novel natural product chemical space for high throughput in silico discovery.

Motif2Mol: Prediction of New Active Compounds Based on Sequence Motifs of Ligand Binding Sites in Proteins Using a Biochemical Language Model

In drug design, the prediction of new active compounds from protein sequence data has only been attempted in a few studies thus far. This prediction task is principally challenging because global protein sequence similarity has strong evolutional and structural implications, but is often only vaguely related to ligand binding. Deep language models adapted from natural language processing offer new opportunities to attempt such predictions via machine translation by directly relating amino acid sequences and chemical structures to each based on textual molecular representations. Herein, we introduce a biochemical language model with transformer architecture for the prediction of new active compounds from sequence motifs of ligand binding sites. In a proof-of-concept application on inhibitors of more than 200 human kinases, the Motif2Mol model revealed promising learning characteristics and an unprecedented ability to consistently reproduce known inhibitors of different kinases.

Designing highly potent compounds using a chemical language model

Compound potency prediction is a major task in medicinal chemistry and drug design. Inspired by the concept of activity cliffs (which encode large differences in potency between similar active compounds), we have devised a new methodology for predicting potent compounds from weakly potent input molecules. Therefore, a chemical language model was implemented consisting of a conditional transformer architecture for compound design guided by observed potency differences. The model was evaluated using a newly generated compound test system enabling a rigorous assessment of its performance. It was shown to predict known potent compounds from different activity classes not encountered during training. Moreover, the model was capable of creating highly potent compounds that were structurally distinct from input molecules. It also produced many novel candidate compounds not included in test sets. Taken together, the findings confirmed the ability of the new methodology to generate structurally diverse highly potent compounds.

Chemical language models for de novo drug design: Challenges and opportunities

Generative deep learning is accelerating de novo drug design, by allowing the generation of molecules with desired properties on demand. Chemical language models - which generate new molecules in the form of strings using deep learning - have been particularly successful in this endeavour. Thanks to advances in natural language processing methods and interdisciplinary collaborations, chemical language models are expected to become increasingly relevant in drug discovery. This minireview provides an overview of the current state-of-the-art of chemical language models for de novo design, and analyses current limitations, challenges, and advantages. Finally, a perspective on future opportunities is provided.

Molecular Generative Model via Retrosynthetically Prepared Chemical Building Block Assembly

Deep generative models are attracting attention as a smart molecular design strategy. However, previous models often render molecules with low synthesizability, hindering their real-world applications. Here, a novel graph-based conditional generative model which makes molecules by tailoring retrosynthetically prepared chemical building blocks until achieving target properties in an auto-regressive fashion is proposed. This strategy improves the synthesizability and property control of the resulting molecules and also helps learn how to select appropriate building blocks and bind them together to achieve target properties. By applying a negative sampling method to the selection process of building blocks, this model overcame a critical limitation of previous fragment-based models, which can only use molecules from the training set during generation. As a result, the model works equally well with unseen building blocks without sacrificing computational efficiency. It is demonstrated that the model can generate potential inhibitors with high docking scores against the 3CL protease of SARS-COV-2.

Molecular Blueprinting by Word Processing

In this work, computer-assisted writing techniques for linear expressions of the structure of polycyclic molecules, branched molecules and clusters, based on formal languages, are tested. The techniques used only require the ability to process written texts, even just using a text editor, and one of the many available molecular drawing/optimization programs that accept input in the form of a SMILES string. A few specific syntactic operators acting on strings are characterized in terms of their effect on the corresponding structure, and although they are simply examples, they are already capable of producing non-trivial structures. The aim of this work is to encourage experiments that may lead to potentially interesting molecular schemata, in view of their symmetry and stereochemistry, as revealed by optimization, and to develop insight into the connection between formal expressions and structures. Given the simplicity and availability of the required tools, it can also be useful for education.

Leveraging molecular structure and bioactivity with chemical language models for de novo drug design

Generative chemical language models (CLMs) can be used for de novo molecular structure generation by learning from a textual representation of molecules. Here, we show that hybrid CLMs can additionally leverage the bioactivity information available for the training compounds. To computationally design ligands of phosphoinositide 3-kinase gamma (PI3Kγ), a collection of virtual molecules was created with a generative CLM. This virtual compound library was refined using a CLM-based classifier for bioactivity prediction. This second hybrid CLM was pretrained with patented molecular structures and fine-tuned with known PI3Kγ ligands. Several of the computer-generated molecular designs were commercially available, enabling fast prescreening and preliminary experimental validation. A new PI3Kγ ligand with sub-micromolar activity was identified, highlighting the method's scaffold-hopping potential. Chemical synthesis and biochemical testing of two of the top-ranked de novo designed molecules and their derivatives corroborated the model's ability to generate PI3Kγ ligands with medium to low nanomolar activity for hit-to-lead expansion. The most potent compounds led to pronounced inhibition of PI3K-dependent Akt phosphorylation in a medulloblastoma cell model, demonstrating efficacy of PI3Kγ ligands in PI3K/Akt pathway repression in human tumor cells. The results positively advocate hybrid CLMs for virtual compound screening and activity-focused molecular design.

Machine Learning and Computational Chemistry for the Endocannabinoid System

Computational methods in medicinal chemistry facilitate drug discovery and design. In particular, machine learning methodologies have recently gained increasing attention. This chapter provides a structured overview of the current state of computational chemistry and its applications for the interrogation of the endocannabinoid system (ECS), highlighting methods in structure-based drug design, virtual screening, ligand-based quantitative structure-activity relationship (QSAR) modeling, and de novo molecular design. We emphasize emerging methods in machine learning and anticipate a forecast of future opportunities of computational medicinal chemistry for the ECS.

Correlated RNN Framework to Quickly Generate Molecules with Desired Properties for Energetic Materials in the Low Data Regime

Motivated by the challenging of deep learning on the low data regime and the urgent demand for intelligent design on highly energetic materials, we explore a correlated deep learning framework, which consists of three recurrent neural networks (RNNs) correlated by the transfer learning strategy, to efficiently generate new energetic molecules with a high detonation velocity in the case of very limited data available. To avoid the dependence on the external big data set, data augmentation by fragment shuffling of 303 energetic compounds is utilized to produce 500,000 molecules to pretrain RNN, through which the model can learn sufficient structure knowledge. Then the pretrained RNN is fine-tuned by focusing on the 303 energetic compounds to generate 7153 molecules similar to the energetic compounds. In order to more reliably screen the molecules with a high detonation velocity, the SMILE enumeration augmentation coupled with the pretrained knowledge is utilized to build an RNN-based prediction model, through which R² is boosted from 0.4446 to 0.9572. The comparable performance with the transfer learning strategy based on an existing big database (ChEMBL) to produce the energetic molecules and drug-like ones further supports the effectiveness and generality of our strategy in the low data regime. High-precision quantum mechanics calculations further confirm that 35 new molecules present a higher detonation velocity and lower synthetic accessibility than the classic explosive RDX, along with good thermal stability. In particular, three new molecules are comparable to caged CL-20 in the detonation velocity. All the source codes and the data set are freely available at https://github.com/wangchenghuidream/RNNMGM.

Coverage Score: A Model Agnostic Method to Efficiently Explore Chemical Space

Selecting the most appropriate compounds to synthesize and test is a vital aspect of drug discovery. Methods like clustering and diversity present weaknesses in selecting the optimal sets for information gain. Active learning techniques often rely on an initial model and computationally expensive semi-supervised batch selection. Herein, we describe a new subset-based selection method, Coverage Score, that combines Bayesian statistics and information entropy to balance representation and diversity to select a maximally informative subset. Coverage Score can be influenced by prior selections and desirable properties. In this paper, subsets selected through Coverage Score are compared against subsets selected through model-independent and model-dependent techniques for several datasets. In drug-like chemical space, Coverage Score consistently selects subsets that lead to more accurate predictions compared to other selection methods. Subsets selected through Coverage Score produced Random Forest models that have a root-mean-square-error up to 12.8% lower than subsets selected at random and can retain up to 99% of the structural dissimilarity of a diversity selection.

MACAW: An Accessible Tool for Molecular Embedding and Inverse Molecular Design

The growing capabilities of synthetic biology and organic chemistry demand tools to guide syntheses toward useful molecules. Here, we present Molecular AutoenCoding Auto-Workaround (MACAW), a tool that uses a novel approach to generate molecules predicted to meet a desired property specification (e.g., a binding affinity of 50 nM or an octane number of 90). MACAW describes molecules by embedding them into a smooth multidimensional numerical space, avoiding uninformative dimensions that previous methods often introduce. The coordinates in this embedding provide a natural choice of features for accurately predicting molecular properties, which we demonstrate with examples for cetane and octane numbers, flash points, and histamine H1 receptor binding affinity. The approach is computationally efficient and well-suited to the small- and medium-size datasets commonly used in biosciences. We showcase the utility of MACAW for virtual screening by identifying molecules with high predicted binding affinity to the histamine H1 receptor and limited affinity to the muscarinic M2 receptor, which are targets of medicinal relevance. Combining these predictive capabilities with a novel generative algorithm for molecules allows us to recommend molecules with a desired property value (i.e., inverse molecular design). We demonstrate this capability by recommending molecules with predicted octane numbers of 40, 80, and 120, which is an important characteristic of biofuels. Thus, MACAW augments classical retrosynthesis tools by providing recommendations for molecules on specification.

DeepAS - Chemical language model for the extension of active analogue series

In medicinal chemistry, hit-to-lead and lead optimization efforts produce analogue series (ASs), the analysis of which is of central relevance for the exploration and exploitation of structure-activity relationships (SARs) and generation of candidate compounds. The key question in any chemical optimization effort is which analogue(s) to generate next, for which computational support is typically provided through QSAR analysis and compound potency predictions. In this study, we introduce a new chemical language model for analogue design via deep learning. For this purpose, ASs comprising active compounds are ordered according to increasing potency and the chemical language model predicts preferred R-groups for new analogues on the basis of ordered R-group sequences. Hence, consistent with the principles of deep models for natural language processing, analogues with new R-groups are predicted based upon conditional probabilities taking preceding groups into account. This implicitly accounts for the potency gradient captured by an AS and detectable SAR trends, providing a new concept for analogue design. Herein, we report the AS-based chemical language model, its initial evaluation, and exemplary applications.

A Transfer Learning Approach for Reaction Discovery in Small Data Situations Using Generative Model

Sustainable practices in chemical sciences can be better realized by adopting interdisciplinary approaches that combine the advantages of machine learning (ML) on the initially acquired small data in reaction discovery. Developing new reactions generally remains heuristic and even time and resource intensive. For instance, synthesis of fluorine-containing compounds, which constitute ∼20% of the marketed drugs, relies on deoxyfluorination of abundantly available alcohols. Herein, we demonstrate the use of a recurrent neural network-based deep generative model built on a library of just 37 alcohols for effective learning and exploration of the chemical space. The proof-of-concept ML model is able to generate good quality, synthetically accessible, higher-yielding novel alcohol molecules. This protocol would have superior utility for deployment into a practical reaction discovery pipeline.

•

Dual pronged transfer learning, both to generate and predict yields of new molecules

•

Demonstrated the utility for an important family of deoxyfluorination of alcohols

•

Applicable for practically more likely situations with relatively smaller data

•

Extendable to other reaction manifolds to facilitate expedited reaction discovery

Perplexity-Based Molecule Ranking and Bias Estimation of Chemical Language Models

Chemical language models (CLMs) can be employed to design molecules with desired properties. CLMs generate new chemical structures in the form of textual representations, such as the simplified molecular input line entry system (SMILES) strings. However, the quality of these de novo generated molecules is difficult to assess a priori. In this study, we apply the perplexity metric to determine the degree to which the molecules generated by a CLM match the desired design objectives. This model-intrinsic score allows identifying and ranking the most promising molecular designs based on the probabilities learned by the CLM. Using perplexity to compare "greedy" (beam search) with "explorative" (multinomial sampling) methods for SMILES generation, certain advantages of multinomial sampling become apparent. Additionally, perplexity scoring is performed to identify undesired model biases introduced during model training and allows the development of a new ranking system to remove those undesired biases.

High-confidence structural annotation of metabolites absent from spectral libraries

Untargeted metabolomics experiments rely on spectral libraries for structure annotation, but, typically, only a small fraction of spectra can be matched. Previous in silico methods search in structure databases but cannot distinguish between correct and incorrect annotations. Here we introduce the COSMIC workflow that combines in silico structure database generation and annotation with a confidence score consisting of kernel density P value estimation and a support vector machine with enforced directionality of features. On diverse datasets, COSMIC annotates a substantial number of hits at low false discovery rates and outperforms spectral library search. To demonstrate that COSMIC can annotate structures never reported before, we annotated 12 natural bile acids. The annotation of nine structures was confirmed by manual evaluation and two structures using synthetic standards. In human samples, we annotated and manually validated 315 molecular structures currently absent from the Human Metabolome Database. Application of COSMIC to data from 17,400 metabolomics experiments led to 1,715 high-confidence structural annotations that were absent from spectral libraries.

Fear in a Handful of Dust: The Epidemiological, Environmental, and Economic Drivers of Death by PM2.5 Pollution

This study evaluates numerous epidemiological, environmental, and economic factors affecting morbidity and mortality from PM2.5 exposure in the 27 member states of the European Union. This form of air pollution inflicts considerable social and economic damage in addition to loss of life and well-being. This study creates and deploys a comprehensive data pipeline. The first step consists of conventional linear models and supervised machine learning alternatives. Those regression methods do more than predict health outcomes in the EU-27 and relate those predictions to independent variables. Linear regression and its machine learning equivalents also inform unsupervised machine learning methods such as clustering and manifold learning. Lower-dimension manifolds of this dataset's feature space reveal the relationship among EU-27 countries and their success (or failure) in managing PM2.5 morbidity and mortality. Principal component analysis informs further interpretation of variables along economic and health-based lines. A nonlinear environmental Kuznets curve may describe the fuller relationship between economic activity and premature death from PM2.5 exposure. The European Union should bridge the historical, cultural, and economic gaps that impair these countries' collective response to PM2.5 pollution.