Language models can learn complex molecular distributions

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.

nach0: multimodal natural and chemical languages foundation model

Large Language Models (LLMs) have substantially driven scientific progress in various domains, and many papers have demonstrated their ability to tackle complex problems with creative solutions. Our paper introduces a new foundation model, nach0, capable of solving various chemical and biological tasks: biomedical question answering, named entity recognition, molecular generation, molecular synthesis, attributes prediction, and others. nach0 is a multi-domain and multi-task encoder-decoder LLM pre-trained on unlabeled text from scientific literature, patents, and molecule strings to incorporate a range of chemical and linguistic knowledge. We employed instruction tuning, where specific task-related instructions are utilized to fine-tune nach0 for the final set of tasks. To train nach0 effectively, we leverage the NeMo framework, enabling efficient parallel optimization of both base and large model versions. Extensive experiments demonstrate that our model outperforms state-of-the-art baselines on single-domain and cross-domain tasks. Furthermore, it can generate high-quality outputs in molecular and textual formats, showcasing its effectiveness in multi-domain setups.

MTMol-GPT: De novo multi-target molecular generation with transformer-based generative adversarial imitation learning

De novo drug design is crucial in advancing drug discovery, which aims to generate new drugs with specific pharmacological properties. Recently, deep generative models have achieved inspiring progress in generating drug-like compounds. However, the models prioritize a single target drug generation for pharmacological intervention, neglecting the complicated inherent mechanisms of diseases, and influenced by multiple factors. Consequently, developing novel multi-target drugs that simultaneously target specific targets can enhance anti-tumor efficacy and address issues related to resistance mechanisms. To address this issue and inspired by Generative Pre-trained Transformers (GPT) models, we propose an upgraded GPT model with generative adversarial imitation learning for multi-target molecular generation called MTMol-GPT. The multi-target molecular generator employs a dual discriminator model using the Inverse Reinforcement Learning (IRL) method for a concurrently multi-target molecular generation. Extensive results show that MTMol-GPT generates various valid, novel, and effective multi-target molecules for various complex diseases, demonstrating robustness and generalization capability. In addition, molecular docking and pharmacophore mapping experiments demonstrate the drug-likeness properties and effectiveness of generated molecules potentially improve neuropsychiatric interventions. Furthermore, our model's generalizability is exemplified by a case study focusing on the multi-targeted drug design for breast cancer. As a broadly applicable solution for multiple targets, MTMol-GPT provides new insight into future directions to enhance potential complex disease therapeutics by generating high-quality multi-target molecules in drug discovery.

Carbon-based molecular properties efficiently predicted by deep learning-based quantum chemical simulation with large language models

The prediction of thermodynamic properties of carbon-based molecules based on their geometrical conformation using fluctuation and density functional theories has achieved great success in the field of energy chemistry, while the excessive computational cost provides both opportunities and challenges for the integration of machine learning. In this work, a deep learning-based quantum chemical prediction model was constructed for efficient prediction of thermodynamic properties of carbon-based molecules. We constructed a novel framework - encoding the 3D information into a large language model (LLM), which in turn generates a 2D SMILES string, while embedding a learnable encoding designed to preserve the integrity of the original 3D information, providing better structural information for the model. Additionally, we have designed an equivariant learning module to encompass representations of conformations and feature learning for conformational sampling. This framework aims to predict thermodynamic properties more accurately than learning from 2D topology alone, while providing faster computational speeds than conventional simulations. By combining machine learning and quantum chemistry, we pioneer efficient practical applications in the field of energy chemistry. Our model advances the integration of data-driven and physics-based modeling to unlock novel insights into carbon-based 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.

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.

Deep Generative Models in De Novo Drug Molecule Generation

The discovery of new drugs has important implications for human health. Traditional methods for drug discovery rely on experiments to optimize the structure of lead molecules, which are time-consuming and high-cost. Recently, artificial intelligence has exhibited promising and efficient performance for drug-like molecule generation. In particular, deep generative models achieve great success in de novo generation of drug-like molecules with desired properties, showing massive potential for novel drug discovery. In this study, we review the recent progress of molecule generation using deep generative models, mainly focusing on molecule representations, public databases, data processing tools, and advanced artificial intelligence based molecule generation frameworks. In particular, we present a comprehensive comparison of state-of-the-art deep generative models for molecule generation and a summary of commonly used molecular design strategies. We identify research gaps and challenges of molecule generation such as the need for better databases, missing 3D information in molecular representation, and the lack of high-precision evaluation metrics. We suggest future directions for molecular generation and drug discovery.

Exploring data-driven chemical SMILES tokenization approaches to identify key protein-ligand binding moieties

Machine learning models have found numerous successful applications in computational drug discovery. A large body of these models represents molecules as sequences since molecular sequences are easily available, simple, and informative. The sequence-based models often segment molecular sequences into pieces called chemical words, analogous to the words that make up sentences in human languages, and then apply advanced natural language processing techniques for tasks such as de novo drug design, property prediction, and binding affinity prediction. However, the chemical characteristics and significance of these building blocks, chemical words, remain unexplored. To address this gap, we employ data-driven SMILES tokenization techniques such as Byte Pair Encoding, WordPiece, and Unigram to identify chemical words and compare the resulting vocabularies. To understand the chemical significance of these words, we build a language-inspired pipeline that treats high affinity ligands of protein targets as documents and selects key chemical words making up those ligands based on tf-idf weighting. The experiments on multiple protein-ligand affinity datasets show that despite differences in words, lengths, and validity among the vocabularies generated by different subword tokenization algorithms, the identified key chemical words exhibit similarity. Further, we conduct case studies on a number of target to analyze the impact of key chemical words on binding. We find that these key chemical words are specific to protein targets and correspond to known pharmacophores and functional groups. Our approach elucidates chemical properties of the words identified by machine learning models and can be used in drug discovery studies to determine significant chemical moieties.

Predicting the formation of NADES using a transformer-based model

The application of natural deep eutectic solvents (NADES) in the pharmaceutical, agricultural, and food industries represents one of the fastest growing fields of green chemistry, as these mixtures can potentially replace traditional organic solvents. These advances are, however, limited by the development of new NADES which is today, almost exclusively empirically driven and often derivative from known mixtures. To overcome this limitation, we propose the use of a transformer-based machine learning approach. Here, the transformer-based neural network model was first pre-trained to recognize chemical patterns from SMILES representations (unlabeled general chemical data) and then fine-tuned to recognize the patterns in strings that lead to the formation of either stable NADES or simple mixtures of compounds not leading to the formation of stable NADES (binary classification). Because this strategy was adapted from language learning, it allows the use of relatively small datasets and relatively low computational resources. The resulting algorithm is capable of predicting the formation of multiple new stable eutectic mixtures (n = 337) from a general database of natural compounds. More importantly, the system is also able to predict the components and molar ratios needed to render NADES with new molecules (not present in the training database), an aspect that was validated using previously reported NADES as well as by developing multiple novel solvents containing ibuprofen. We believe this strategy has the potential to transform the screening process for NADES as well as the pharmaceutical industry, streamlining the use of bioactive compounds as functional components of liquid formulations, rather than simple solutes.

ChatGPT in the Material Design: Selected Case Studies to Assess the Potential of ChatGPT

The pursuit of designing smart and functional materials is of paramount importance across various domains, such as material science, engineering, chemical technology, electronics, biomedicine, energy, and numerous others. Consequently, researchers are actively involved in the development of innovative models and strategies for material design. Recent advancements in analytical tools, experimentation, and computer technology additionally enhance the material design possibilities. Notably, data-driven techniques like artificial intelligence and machine learning have achieved substantial progress in exploring various applications within material science. One such approach, ChatGPT, a large language model, holds transformative potential for addressing complex queries. In this article, we explore ChatGPT's understanding of material science by assigning some simple tasks across various subareas of computational material science. The findings indicate that while ChatGPT may make some minor errors in accomplishing general tasks, it demonstrates the capability to learn and adapt through human interactions. However, issues like output consistency, probable hidden errors, and ethical consequences should be addressed.

The Future of Molecular Studies through the Lens of Large Language Models

The rapid advancement of large language models is reshaping research across various fields, offering a novel approach to the complex realm of molecular studies. Our evaluation of GPT-4 and GPT-3.5, focusing on their performance in generating and optimizing molecular structures, highlights GPT-4's strengths in certain aspects of molecular optimization. However, it also revealed challenges in accurately creating complex molecules. Addressing these issues, we propose possible directions for future molecular science research. These suggestions aim to forge new paths for exploring the intricacies of molecular structures, potentially bringing new efficiencies and innovations in the field.

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.

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.

Using alternative SMILES representations to identify novel functional analogues in chemical similarity vector searches

Chemical similarity searches are a widely used family of in silico methods for identifying pharmaceutical leads. These methods historically relied on structure-based comparisons to compute similarity. Here, we use a chemical language model to create a vector-based chemical search. We extend previous implementations by creating a prompt engineering strategy that utilizes two different chemical string representation algorithms: one for the query and the other for the database. We explore this method by reviewing search results from nine queries with diverse targets. We find that the method identifies molecules with similar patent-derived functionality to the query, as determined by our validated LLM-assisted patent summarization pipeline. Further, many of these functionally similar molecules have different structures and scaffolds from the query, making them unlikely to be found with traditional chemical similarity searches. This method may serve as a new tool for the discovery of novel molecular structural classes that achieve target functionality.

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.

Molecular Property Diagnostic Suite Compound Library (MPDS-CL): a structure-based classification of the chemical space

Molecular Property Diagnostic Suite Compound Library (MPDS-CL) is an open-source Galaxy-based cheminformatics web portal which presents a structure-based classification of the molecules. A structure-based classification of nearly 150 million unique compounds, obtained from 42 publicly available databases and curated for redundancy removal through 97 hierarchically well-defined atom composition-based portions, has been done. These are further subjected to 56-bit fingerprint-based classification algorithm which led to the formation of 56 structurally well-defined classes. The classes thus obtained were further divided into clusters based on their molecular weight. Thus, the entire set of molecules was put into 56 different classes and 625 clusters. This led to the assignment of a unique ID, named as MPDS-AadharID, for each of these 149,169,443 molecules. MPDS-AadharID is akin to the unique number given to citizens in India (similar to SSN in the US and NINO in the UK). The unique features of MPDS-CL are (a) several search options, such as exact structure search, substructure search, property-based search, fingerprint-based search, using SMILES, InChIKey and key-in; (b) automatic generation of information for the processing for MPDS and other galaxy tools; (c) providing the class and cluster of a molecule which makes it easier and fast to search for similar molecules and (d) information related to the presence of the molecules in multiple databases. The MPDS-CL can be accessed at https://mpds.neist.res.in:8086/ .

Probabilistic generative transformer language models for generative design of molecules

Self-supervised neural language models have recently found wide applications in the generative design of organic molecules and protein sequences as well as representation learning for downstream structure classification and functional prediction. However, most of the existing deep learning models for molecule design usually require a big dataset and have a black-box architecture, which makes it difficult to interpret their design logic. Here we propose the Generative Molecular Transformer (GMTransformer), a probabilistic neural network model for generative design of molecules. Our model is built on the blank filling language model originally developed for text processing, which has demonstrated unique advantages in learning the "molecules grammars" with high-quality generation, interpretability, and data efficiency. Benchmarked on the MOSES datasets, our models achieve high novelty and Scaf compared to other baselines. The probabilistic generation steps have the potential in tinkering with molecule design due to their capability of recommending how to modify existing molecules with explanation, guided by the learned implicit molecule chemistry. The source code and datasets can be accessed freely at https://github.com/usccolumbia/GMTransformer.

Efficient 3D Molecular Design with an E(3) Invariant Transformer VAE

This work introduces a three-dimensional (3D) invariant graph-to-string transformer variational autoencoders (VAE) (Vagrant) for generating molecules with accurate density functional theory (DFT)-level properties. Vagrant learns to model the joint probability distribution of a 3D molecular structure and its properties by encoding molecular structures into a 3D-aware latent space. Directed navigation through this latent space implicitly optimizes the 3D structure of a molecule, and the latent embedding can be used to condition a generative transformer to predict the candidate structure as a one-dimensional (1D) sequence. Additionally, we introduce two novel sampling methods that exploit the latent characteristics of a VAE to improve performance. We show that our method outperforms comparable 3D autoregressive and diffusion methods for predicting quantum chemical property values of novel molecules in terms of both sample quality and computational efficiency.

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.

Augmenting Polymer Datasets by Iterative Rearrangement

One of the biggest obstacles to successful polymer property prediction is an effective representation that accurately captures the sequence of repeat units in a polymer. Motivated by the success of data augmentation in computer vision and natural language processing, we explore augmenting polymer data by iteratively rearranging the molecular representation while preserving the correct connectivity, revealing additional substructural information that is not present in a single representation. We evaluate the effects of this technique on the performance of machine learning models trained on three polymer datasets and compare them to common molecular representations. Data augmentation does not yield significant improvements in machine learning property prediction performance compared to equivalent (non-augmented) representations. In datasets where the target property is primarily influenced by the polymer sequence rather than experimental parameters, this data augmentation technique provides molecular embedding with more information to improve property prediction accuracy.

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.

Magicmol: a light-weighted pipeline for drug-like molecule evolution and quick chemical space exploration

The flourishment of machine learning and deep learning methods has boosted the development of cheminformatics, especially regarding the application of drug discovery and new material exploration. Lower time and space expenses make it possible for scientists to search the enormous chemical space. Recently, some work combined reinforcement learning strategies with recurrent neural network (RNN)-based models to optimize the property of generated small molecules, which notably improved a batch of critical factors for these candidates. However, a common problem among these RNN-based methods is that several generated molecules have difficulty in synthesizing despite owning higher desired properties such as binding affinity. However, RNN-based framework better reproduces the molecule distribution among the training set than other categories of models during molecule exploration tasks. Thus, to optimize the whole exploration process and make it contribute to the optimization of specified molecules, we devised a light-weighted pipeline called Magicmol; this pipeline has a re-mastered RNN network and utilize SELFIES presentation instead of SMILES. Our backbone model achieved extraordinary performance while reducing the training cost; moreover, we devised reward truncate strategies to eliminate the model collapse problem. Additionally, adopting SELFIES presentation made it possible to combine STONED-SELFIES as a post-processing procedure for specified molecule optimization and quick chemical space exploration.

Assessment of chemistry knowledge in large language models that generate code

In this work, we investigate the question: do code-generating large language models know chemistry? Our results indicate, mostly yes. To evaluate this, we introduce an expandable framework for evaluating chemistry knowledge in these models, through prompting models to solve chemistry problems posed as coding tasks. To do so, we produce a benchmark set of problems, and evaluate these models based on correctness of code by automated testing and evaluation by experts. We find that recent LLMs are able to write correct code across a variety of topics in chemistry and their accuracy can be increased by 30 percentage points via prompt engineering strategies, like putting copyright notices at the top of files. Our dataset and evaluation tools are open source which can be contributed to or built upon by future researchers, and will serve as a community resource for evaluating the performance of new models as they emerge. We also describe some good practices for employing LLMs in chemistry. The general success of these models demonstrates that their impact on chemistry teaching and research is poised to be enormous.

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.

Deep generative model for drug design from protein target sequence

Drug discovery for a protein target is a laborious and costly process. Deep learning (DL) methods have been applied to drug discovery and successfully generated novel molecular structures, and they can substantially reduce development time and costs. However, most of them rely on prior knowledge, either by drawing on the structure and properties of known molecules to generate similar candidate molecules or extracting information on the binding sites of protein pockets to obtain molecules that can bind to them. In this paper, DeepTarget, an end-to-end DL model, was proposed to generate novel molecules solely relying on the amino acid sequence of the target protein to reduce the heavy reliance on prior knowledge. DeepTarget includes three modules: Amino Acid Sequence Embedding (AASE), Structural Feature Inference (SFI), and Molecule Generation (MG). AASE generates embeddings from the amino acid sequence of the target protein. SFI inferences the potential structural features of the synthesized molecule, and MG seeks to construct the eventual molecule. The validity of the generated molecules was demonstrated by a benchmark platform of molecular generation models. The interaction between the generated molecules and the target proteins was also verified on the basis of two metrics, drug-target affinity and molecular docking. The results of the experiments indicated the efficacy of the model for direct molecule generation solely conditioned on amino acid sequence.

Do Large Language Models Understand Chemistry? A Conversation with ChatGPT

Large language models (LLMs) have promised a revolution in answering complex questions using the ChatGPT model. Its application in chemistry is still in its infancy. This viewpoint addresses the question of how well ChatGPT understands chemistry by posing five simple tasks in different subareas of chemistry.

ReBADD-SE: Multi-objective molecular optimisation using SELFIES fragment and off-policy self-critical sequence training

The discovery of drugs to selectively remove disease-related cells is challenging in computer-aided drug design. Many studies have proposed multi-objective molecular generation methods and demonstrated their superiority using the public benchmark dataset for kinase inhibitor generation tasks. However, the dataset does not contain many molecules that violate Lipinski's rule of five. Thus, it remains unclear whether existing methods are effective in generating molecules violating the rule, such as navitoclax. To address this, we analysed the limitations of existing methods and propose a multi-objective molecular generation method with a novel parsing algorithm for molecular string representation and a modified reinforcement learning method for the efficient training of multi-objective molecular optimisation. The proposed model had success rates of 84% in GSK3b+JNK3 inhibitor generation and 99% in Bcl-2 family inhibitor generation tasks.

Computer-aided multi-objective optimization in small molecule discovery

Molecular discovery is a multi-objective optimization problem that requires identifying a molecule or set of molecules that balance multiple, often competing, properties. Multi-objective molecular design is commonly addressed by combining properties of interest into a single objective function using scalarization, which imposes assumptions about relative importance and uncovers little about the trade-offs between objectives. In contrast to scalarization, Pareto optimization does not require knowledge of relative importance and reveals the trade-offs between objectives. However, it introduces additional considerations in algorithm design. In this review, we describe pool-based and de novo generative approaches to multi-objective molecular discovery with a focus on Pareto optimization algorithms. We show how pool-based molecular discovery is a relatively direct extension of multi-objective Bayesian optimization and how the plethora of different generative models extend from single-objective to multi-objective optimization in similar ways using non-dominated sorting in the reward function (reinforcement learning) or to select molecules for retraining (distribution learning) or propagation (genetic algorithms). Finally, we discuss some remaining challenges and opportunities in the field, emphasizing the opportunity to adopt Bayesian optimization techniques into multi-objective de novo design.

Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence

Only around 20% of the human proteome is considered to be druggable with small-molecule antagonists. This leaves some of the most compelling therapeutic targets outside the reach of ligand discovery. The concept of targeted protein degradation (TPD) promises to overcome some of these limitations. In brief, TPD is dependent on small molecules that induce the proximity between a protein of interest (POI) and an E3 ubiquitin ligase, causing ubiquitination and degradation of the POI. In this perspective, we want to reflect on current challenges in the field, and discuss how advances in multiomics profiling, artificial intelligence, and machine learning (AI/ML) will be vital in overcoming them. The presented roadmap is discussed in the context of small-molecule degraders but is equally applicable for other emerging proximity-inducing modalities.

Exploration of Chemical Space Guided by PixelCNN for Fragment-Based De Novo Drug Discovery

We report a novel framework for achieving fragment-based molecular design using pixel convolutional neural network (PixelCNN) combined with the simplified molecular input line entry system (SMILES) as molecular representation. While a widely used recurrent neural network (RNN) assumes monotonically decaying correlations in strings, PixelCNN captures a periodicity among characters of SMILES. Thus, PixelCNN provides us with a novel solution for the analysis of chemical space by extracting the periodicity of molecular structures that will be buried in SMILES. Moreover, this characteristic enables us to generate molecules by combining several simple building blocks, such as a benzene ring and side-chain structures, which contributes to the effective exploration of chemical space by step-by-step searching for molecules from a target fragment. In conclusion, PixelCNN could be a powerful approach focusing on the periodicity of molecules to explore chemical space for the fragment-based molecular design.

Application of Computational Biology and Artificial Intelligence in Drug Design

Traditional drug design requires a great amount of research time and developmental expense. Booming computational approaches, including computational biology, computer-aided drug design, and artificial intelligence, have the potential to expedite the efficiency of drug discovery by minimizing the time and financial cost. In recent years, computational approaches are being widely used to improve the efficacy and effectiveness of drug discovery and pipeline, leading to the approval of plenty of new drugs for marketing. The present review emphasizes on the applications of these indispensable computational approaches in aiding target identification, lead discovery, and lead optimization. Some challenges of using these approaches for drug design are also discussed. Moreover, we propose a methodology for integrating various computational techniques into new drug discovery and design.

SELFIES and the future of molecular string representations

Artificial intelligence (AI) and machine learning (ML) are expanding in popularity for broad applications to challenging tasks in chemistry and materials science. Examples include the prediction of properties, the discovery of new reaction pathways, or the design of new molecules. The machine needs to read and write fluently in a chemical language for each of these tasks. Strings are a common tool to represent molecular graphs, and the most popular molecular string representation, Smiles, has powered cheminformatics since the late 1980s. However, in the context of AI and ML in chemistry, Smiles has several shortcomings-most pertinently, most combinations of symbols lead to invalid results with no valid chemical interpretation. To overcome this issue, a new language for molecules was introduced in 2020 that guarantees 100% robustness: SELF-referencing embedded string (Selfies). Selfies has since simplified and enabled numerous new applications in chemistry. In this perspective, we look to the future and discuss molecular string representations, along with their respective opportunities and challenges. We propose 16 concrete future projects for robust molecular representations. These involve the extension toward new chemical domains, exciting questions at the interface of AI and robust languages, and interpretability for both humans and machines. We hope that these proposals will inspire several follow-up works exploiting the full potential of molecular string representations for the future of AI in chemistry and materials science.

Augmented Hill-Climb increases reinforcement learning efficiency for language-based de novo molecule generation

A plethora of AI-based techniques now exists to conduct de novo molecule generation that can devise molecules conditioned towards a particular endpoint in the context of drug design. One popular approach is using reinforcement learning to update a recurrent neural network or language-based de novo molecule generator. However, reinforcement learning can be inefficient, sometimes requiring up to 10⁵ molecules to be sampled to optimize more complex objectives, which poses a limitation when using computationally expensive scoring functions like docking or computer-aided synthesis planning models. In this work, we propose a reinforcement learning strategy called Augmented Hill-Climb based on a simple, hypothesis-driven hybrid between REINVENT and Hill-Climb that improves sample-efficiency by addressing the limitations of both currently used strategies. We compare its ability to optimize several docking tasks with REINVENT and benchmark this strategy against other commonly used reinforcement learning strategies including REINFORCE, REINVENT (version 1 and 2), Hill-Climb and best agent reminder. We find that optimization ability is improved ~ 1.5-fold and sample-efficiency is improved ~ 45-fold compared to REINVENT while still delivering appealing chemistry as output. Diversity filters were used, and their parameters were tuned to overcome observed failure modes that take advantage of certain diversity filter configurations. We find that Augmented Hill-Climb outperforms the other reinforcement learning strategies used on six tasks, especially in the early stages of training or for more difficult objectives. Lastly, we show improved performance not only on recurrent neural networks but also on a reinforcement learning stabilized transformer architecture. Overall, we show that Augmented Hill-Climb improves sample-efficiency for language-based de novo molecule generation conditioning via reinforcement learning, compared to the current state-of-the-art. This makes more computationally expensive scoring functions, such as docking, more accessible on a relevant timescale.

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.

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.

Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast

Deep learning has been a prevalence in computational chemistry and widely implemented in molecular property predictions. Recently, self-supervised learning (SSL), especially contrastive learning (CL), has gathered growing attention for the potential to learn molecular representations that generalize to the gigantic chemical space. Unlike supervised learning, SSL can directly leverage large unlabeled data, which greatly reduces the effort to acquire molecular property labels through costly and time-consuming simulations or experiments. However, most molecular SSL methods borrow the insights from the machine learning community but neglect the unique cheminformatics (e.g., molecular fingerprints) and multilevel graphical structures (e.g., functional groups) of molecules. In this work, we propose iMolCLR, improvement of Molecular Contrastive Learning of Representations with graph neural networks (GNNs) in two aspects: (1) mitigating faulty negative contrastive instances via considering cheminformatics similarities between molecule pairs and (2) fragment-level contrasting between intramolecule and intermolecule substructures decomposed from molecules. Experiments have shown that the proposed strategies significantly improve the performance of GNN models on various challenging molecular property predictions. In comparison to the previous CL framework, iMolCLR demonstrates an averaged 1.2% improvement of ROC-AUC on eight classification benchmarks and an averaged 10.1% decrease of the error on six regression benchmarks. On most benchmarks, the generic GNN pretrained by iMolCLR rivals or even surpasses supervised learning models with sophisticated architectures and engineered features. Further investigations demonstrate that representations learned through iMolCLR intrinsically embed scaffolds and functional groups that can reason molecule similarities.