GEOM, energy-annotated molecular conformations for property prediction and molecular generation

Structure-based protein and small molecule generation using EGNN and diffusion models: A comprehensive review

Recent breakthroughs in deep learning have revolutionized protein sequence and structure prediction. These advancements are built on decades of protein design efforts, and are overcoming traditional time and cost limitations. Diffusion models, at the forefront of these innovations, significantly enhance design efficiency by automating knowledge acquisition. In the field of de novo protein design, the goal is to create entirely novel proteins with predetermined structures. Given the arbitrary positions of proteins in 3-D space, graph representations and their properties are widely used in protein generation studies. A critical requirement in protein modelling is maintaining spatial relationships under transformations (rotations, translations, and reflections). This property, known as equivariance, ensures that predicted protein characteristics adapt seamlessly to changes in orientation or position. Equivariant graph neural networks offer a solution to this challenge. By incorporating equivariant graph neural networks to learn the score of the probability density function in diffusion models, one can generate proteins with robust 3-D structural representations. This review examines the latest deep learning advancements, specifically focusing on frameworks that combine diffusion models with equivariant graph neural networks for protein generation.

Emerging Conformational-Analysis Protocols from the RTCONF55-16K Reaction Thermochemistry Conformational Benchmark Set

RTCONF55-16K is a new, reactive conformational data set based on cost-efficient methods to assess different conformational analysis protocols. Our reference calculations underpinned the accuracy of the CENSO (Grimme et al. J. Phys. Chem. A, 2021, 125, 4039) procedure and resulted in alternative recipes with different cost-accuracy compromises. Our general-purpose and economical protocols (CENSO-light and zero, respectively) were found to be 10-30 times faster than the original algorithm, adding only 0.4-0.7 kcal/mol absolute error to the relative free energy estimates.

EC-Conf: A ultra-fast diffusion model for molecular conformation generation with equivariant consistency

Despite recent advancement in 3D molecule conformation generation driven by diffusion models, its high computational cost in iterative diffusion/denoising process limits its application. Here, an equivariant consistency model (EC-Conf) was proposed as a fast diffusion method for low-energy conformation generation. In EC-Conf, a modified SE (3)-equivariant transformer model was directly used to encode the Cartesian molecular conformations and a highly efficient consistency diffusion process was carried out to generate molecular conformations. It was demonstrated that, with only one sampling step, it can already achieve comparable quality to other diffusion-based models running with thousands denoising steps. Its performance can be further improved with a few more sampling iterations. The performance of EC-Conf is evaluated on both GEOM-QM9 and GEOM-Drugs sets. Our results demonstrate that the efficiency of EC-Conf for learning the distribution of low energy molecular conformation is at least two magnitudes higher than current SOTA diffusion models and could potentially become a useful tool for conformation generation and sampling. SCIENTIFIC CONTRIBUTIONS: In this work, we proposed an equivariant consistency model that significantly improves the efficiency of conformation generation in diffusion-based models while maintaining high structural quality. This method serves as a general framework and can be further extended to more complex structure generation and prediction tasks, including those involving proteins, in future steps.

Learning Joint 2-D and 3-D Graph Diffusion Models for Complete Molecule Generation

Designing new molecules is essential for drug discovery and material science. Recently, deep generative models that aim to model molecule distribution have made promising progress in narrowing down the chemical research space and generating high-fidelity molecules. However, current generative models only focus on modeling 2-D bonding graphs or 3-D geometries, which are two complementary descriptors for molecules. The lack of ability to jointly model them limits the improvement of generation quality and further downstream applications. In this article, we propose a joint 2-D and 3-D graph diffusion model (JODO) that generates geometric graphs representing complete molecules with atom types, formal charges, bond information, and 3-D coordinates. To capture the correlation between 2-D molecular graphs and 3-D geometries in the diffusion process, we develop a diffusion graph transformer (DGT) to parameterize the data prediction model that recovers the original data from noisy data. The DGT uses a relational attention mechanism that enhances the interaction between node and edge representations. This mechanism operates concurrently with the propagation and update of scalar attributes and geometric vectors. Our model can also be extended for inverse molecular design targeting single or multiple quantum properties. In our comprehensive evaluation pipeline for unconditional joint generation, the experimental results show that JODO remarkably outperforms the baselines on the QM9 and GEOM-Drugs datasets. Furthermore, our model excels in few-step fast sampling, as well as in inverse molecule design and molecular graph generation. Our code is provided in https://github.com/GRAPH-0/JODO.

Unlocking comprehensive molecular design across all scenarios with large language model and unordered chemical language

Molecular generation stands at the forefront of AI-driven technologies, playing a crucial role in accelerating the development of small molecule drugs. The intricate nature of practical drug discovery necessitates the development of a versatile molecular generation framework that can tackle diverse drug design challenges. However, existing methodologies often struggle to encompass all aspects of small molecule drug design, particularly those rooted in language models, especially in tasks like linker design, due to the autoregressive nature of large language model-based approaches. To empower a language model for a wider range of molecular design tasks, we introduce an unordered simplified molecular-input line-entry system based on fragments (FU-SMILES). Building upon this foundation, we propose FragGPT, a universal fragment-based molecular generation model. Initially pretrained on extensive molecular datasets, FragGPT utilizes FU-SMILES to facilitate efficient generation across various practical applications, such as de novo molecule design, linker design, R-group exploration, scaffold hopping, and side chain optimization. Furthermore, we integrate conditional generation and reinforcement learning (RL) methodologies to ensure that the generated molecules possess multiple desired biological and physicochemical properties. Experimental results across diverse scenarios validate FragGPT's superiority in generating molecules with enhanced properties and novel structures, outperforming existing state-of-the-art models. Moreover, its robust drug design capability is further corroborated through real-world drug design cases.

Quantum mechanical electronic and geometric parameters for DNA k-mers as features for machine learning

We are witnessing a steep increase in model development initiatives in genomics that employ high-end machine learning methodologies. Of particular interest are models that predict certain genomic characteristics based solely on DNA sequence. These models, however, treat the DNA as a mere collection of four, A, T, G and C, letters, dismissing the past advancements in science that can enable the use of more intricate information from nucleic acid sequences. Here, we provide a comprehensive database of quantum mechanical (QM) and geometric features for all the permutations of 7-meric DNA in their representative B, A and Z conformations. The database is generated by employing the applicable high-cost and time-consuming QM methodologies. This can thus make it seamless to associate a wealth of novel molecular features to any DNA sequence, by scanning it with a matching k-meric window and pulling the pre-computed values from our database for further use in modelling. We demonstrate the usefulness of our deposited features through their exclusive use in developing a model for A->C mutation rates.

CREMP: Conformer-rotamer ensembles of macrocyclic peptides for machine learning

Computational and machine learning approaches to model the conformational landscape of macrocyclic peptides have the potential to enable rational design and optimization. However, accurate, fast, and scalable methods for modeling macrocycle geometries remain elusive. Recent deep learning approaches have significantly accelerated protein structure prediction and the generation of small-molecule conformational ensembles, yet similar progress has not been made for macrocyclic peptides due to their unique properties. Here, we introduce CREMP, a resource generated for the rapid development and evaluation of machine learning models for macrocyclic peptides. CREMP contains 36,198 unique macrocyclic peptides and their high-quality structural ensembles generated using the Conformer-Rotamer Ensemble Sampling Tool (CREST). Altogether, this new dataset contains nearly 31.3 million unique macrocycle geometries, each annotated with energies derived from semi-empirical extended tight-binding (xTB) DFT calculations. Additionally, we include 3,258 macrocycles with reported passive permeability data to couple conformational ensembles to experiment. We anticipate that this dataset will enable the development of machine learning models that can improve peptide design and optimization for novel therapeutics.

scDrug+: predicting drug-responses using single-cell transcriptomics and molecular structure

Predicting drug responses based on individual transcriptomic profiles holds promise for refining prognosis and advancing precision medicine. Although many studies have endeavored to predict the responses of known drugs to novel transcriptomic profiles, research into predicting responses for newly discovered drugs remains sparse. In this study, we introduce scDrug+, a comprehensive pipeline that seamlessly integrates single-cell analysis with drug-response prediction. Importantly, scDrug+ is equipped to predict the response of new drugs by analyzing their molecular structures. The open-source tool is available as a Docker container, ensuring ease of deployment and reproducibility. It can be accessed at https://github.com/ailabstw/scDrugplus.

Twins in rotational spectroscopy: Does a rotational spectrum uniquely identify a molecule?

Rotational spectroscopy is the most accurate method for determining structures of molecules in the gas phase. It is often assumed that a rotational spectrum is a unique "fingerprint" of a molecule. The availability of large molecular databases and the development of artificial intelligence methods for spectroscopy make the testing of this assumption timely. In this paper, we pose the determination of molecular structures from rotational spectra as an inverse problem. Within this framework, we adopt a funnel-based approach to search for molecular twins, which are two or more molecules, which have similar rotational spectra but distinctly different molecular structures. We demonstrate that there are twins within standard levels of computational accuracy by generating rotational constants for many molecules from several large molecular databases, indicating that the inverse problem is ill-posed. However, some twins can be distinguished by increasing the accuracy of the theoretical methods or by performing additional experiments.

DiffPROTACs is a deep learning-based generator for proteolysis targeting chimeras

PROteolysis TArgeting Chimeras (PROTACs) has recently emerged as a promising technology. However, the design of rational PROTACs, especially the linker component, remains challenging due to the absence of structure-activity relationships and experimental data. Leveraging the structural characteristics of PROTACs, fragment-based drug design (FBDD) provides a feasible approach for PROTAC research. Concurrently, artificial intelligence-generated content has attracted considerable attention, with diffusion models and Transformers emerging as indispensable tools in this field. In response, we present a new diffusion model, DiffPROTACs, harnessing the power of Transformers to learn and generate new PROTAC linkers based on given ligands. To introduce the essential inductive biases required for molecular generation, we propose the O(3) equivariant graph Transformer module, which augments Transformers with graph neural networks (GNNs), using Transformers to update nodes and GNNs to update the coordinates of PROTAC atoms. DiffPROTACs effectively competes with existing models and achieves comparable performance on two traditional FBDD datasets, ZINC and GEOM. To differentiate the molecular characteristics between PROTACs and traditional small molecules, we fine-tuned the model on our self-built PROTACs dataset, achieving a 93.86% validity rate for generated PROTACs. Additionally, we provide a generated PROTAC database for further research, which can be accessed at https://bailab.siais.shanghaitech.edu.cn/service/DiffPROTACs-generated.tgz. The corresponding code is available at https://github.com/Fenglei104/DiffPROTACs and the server is at https://bailab.siais.shanghaitech.edu.cn/services/diffprotacs.

Dataset for quantum-mechanical exploration of conformers and solvent effects in large drug-like molecules

We here introduce the Aquamarine (AQM) dataset, an extensive quantum-mechanical (QM) dataset that contains the structural and electronic information of 59,783 low-and high-energy conformers of 1,653 molecules with a total number of atoms ranging from 2 to 92 (mean: 50.9), and containing up to 54 (mean: 28.2) non-hydrogen atoms. To gain insights into the solvent effects as well as collective dispersion interactions for drug-like molecules, we have performed QM calculations supplemented with a treatment of many-body dispersion (MBD) interactions of structures and properties in the gas phase and implicit water. Thus, AQM contains over 40 global and local physicochemical properties (including ground-state and response properties) per conformer computed at the tightly converged PBE0+MBD level of theory for gas-phase molecules, whereas PBE0+MBD with the modified Poisson-Boltzmann (MPB) model of water was used for solvated molecules. By addressing both molecule-solvent and dispersion interactions, AQM dataset can serve as a challenging benchmark for state-of-the-art machine learning methods for property modeling and de novo generation of large (solvated) molecules with pharmaceutical and biological relevance.

Software Infrastructure for Next-Generation QM/MM-ΔMLP Force Fields

We present software infrastructure for the design and testing of new quantum mechanical/molecular mechanical and machine-learning potential (QM/MM-ΔMLP) force fields for a wide range of applications. The software integrates Amber's molecular dynamics simulation capabilities with fast, approximate quantum models in the xtb package and machine-learning potential corrections in DeePMD-kit. The xtb package implements the recently developed density-functional tight-binding QM models with multipolar electrostatics and density-dependent dispersion (GFN2-xTB), and the interface with Amber enables their use in periodic boundary QM/MM simulations with linear-scaling QM/MM particle-mesh Ewald electrostatics. The accuracy of the semiempirical models is enhanced by including machine-learning correction potentials (ΔMLPs) enabled through an interface with the DeePMD-kit software. The goal of this paper is to present and validate the implementation of this software infrastructure in molecular dynamics and free energy simulations. The utility of the new infrastructure is demonstrated in proof-of-concept example applications. The software elements presented here are open source and freely available. Their interface provides a powerful enabling technology for the design of new QM/MM-ΔMLP models for studying a wide range of problems, including biomolecular reactivity and protein-ligand binding.

Geometry-complete diffusion for 3D molecule generation and optimization

Generative deep learning methods have recently been proposed for generating 3D molecules using equivariant graph neural networks (GNNs) within a denoising diffusion framework. However, such methods are unable to learn important geometric properties of 3D molecules, as they adopt molecule-agnostic and non-geometric GNNs as their 3D graph denoising networks, which notably hinders their ability to generate valid large 3D molecules. In this work, we address these gaps by introducing the Geometry-Complete Diffusion Model (GCDM) for 3D molecule generation, which outperforms existing 3D molecular diffusion models by significant margins across conditional and unconditional settings for the QM9 dataset and the larger GEOM-Drugs dataset, respectively. Importantly, we demonstrate that GCDM's generative denoising process enables the model to generate a significant proportion of valid and energetically-stable large molecules at the scale of GEOM-Drugs, whereas previous methods fail to do so with the features they learn. Additionally, we show that extensions of GCDM can not only effectively design 3D molecules for specific protein pockets but can be repurposed to consistently optimize the geometry and chemical composition of existing 3D molecules for molecular stability and property specificity, demonstrating new versatility of molecular diffusion models. Code and data are freely available on GitHub .

A variant on the CREST iMTD algorithm for noncovalent clusters of flexible molecules

Conformational ensemble generation and the search for the global minimum conformation are important problems in computational chemistry. In this work, a variant on the conformer-rotamer ensemble sampling tool (CREST) iterative metadynamics (iMTD) algorithm designed for determining structural ensembles and energetics of noncovalent clusters of flexible molecules is presented. We term this new algorithm a low-energy diversity-enhanced variant on CREST, or LEDE-CREST. As with CREST, the energies are evaluated using the semiempirical GFN2-xTB extended tight binding approach. The utility of the algorithm is highlighted by generating ensembles for a variety of noncovalent clusters of flexible or rigid monomers using both CREST and LEDE-CREST.

MolPLA: a molecular pretraining framework for learning cores, R-groups and their linker joints

MOTIVATION

Molecular core structures and R-groups are essential concepts in drug development. Integration of these concepts with conventional graph pre-training approaches can promote deeper understanding in molecules. We propose MolPLA, a novel pre-training framework that employs masked graph contrastive learning in understanding the underlying decomposable parts in molecules that implicate their core structure and peripheral R-groups. Furthermore, we formulate an additional framework that grants MolPLA the ability to help chemists find replaceable R-groups in lead optimization scenarios.

RESULTS

Experimental results on molecular property prediction show that MolPLA exhibits predictability comparable to current state-of-the-art models. Qualitative analysis implicate that MolPLA is capable of distinguishing core and R-group sub-structures, identifying decomposable regions in molecules and contributing to lead optimization scenarios by rationally suggesting R-group replacements given various query core templates.

AVAILABILITY AND IMPLEMENTATION

The code implementation for MolPLA and its pre-trained model checkpoint is available at https://github.com/dmis-lab/MolPLA.

A survey of generative AI for de novo drug design: new frontiers in molecule and protein generation

Artificial intelligence (AI)-driven methods can vastly improve the historically costly drug design process, with various generative models already in widespread use. Generative models for de novo drug design, in particular, focus on the creation of novel biological compounds entirely from scratch, representing a promising future direction. Rapid development in the field, combined with the inherent complexity of the drug design process, creates a difficult landscape for new researchers to enter. In this survey, we organize de novo drug design into two overarching themes: small molecule and protein generation. Within each theme, we identify a variety of subtasks and applications, highlighting important datasets, benchmarks, and model architectures and comparing the performance of top models. We take a broad approach to AI-driven drug design, allowing for both micro-level comparisons of various methods within each subtask and macro-level observations across different fields. We discuss parallel challenges and approaches between the two applications and highlight future directions for AI-driven de novo drug design as a whole. An organized repository of all covered sources is available at https://github.com/gersteinlab/GenAI4Drug.

Gram matrix: an efficient representation of molecular conformation and learning objective for molecular pretraining

Accurate prediction of molecular properties is fundamental in drug discovery and development, providing crucial guidance for effective drug design. A critical factor in achieving accurate molecular property prediction lies in the appropriate representation of molecular structures. Presently, prevalent deep learning-based molecular representations rely on 2D structure information as the primary molecular representation, often overlooking essential three-dimensional (3D) conformational information due to the inherent limitations of 2D structures in conveying atomic spatial relationships. In this study, we propose employing the Gram matrix as a condensed representation of 3D molecular structures and for efficient pretraining objectives. Subsequently, we leverage this matrix to construct a novel molecular representation model, Pre-GTM, which inherently encapsulates 3D information. The model accurately predicts the 3D structure of a molecule by estimating the Gram matrix. Our findings demonstrate that Pre-GTM model outperforms the baseline Graphormer model and other pretrained models in the QM9 and MoleculeNet quantitative property prediction task. The integration of the Gram matrix as a condensed representation of 3D molecular structure, incorporated into the Pre-GTM model, opens up promising avenues for its potential application across various domains of molecular research, including drug design, materials science, and chemical engineering.

COSMIC: Molecular Conformation Space Modeling in Internal Coordinates with an Adversarial Framework

The fast and accurate conformation space modeling is an essential part of computational approaches for solving ligand and structure-based drug discovery problems. Recent state-of-the-art diffusion models for molecular conformation generation show promising distribution coverage and physical plausibility metrics but suffer from a slow sampling procedure. We propose a novel adversarial generative framework, COSMIC, that shows comparable generative performance but provides a time-efficient sampling and training procedure. Given a molecular graph and random noise, the generator produces a conformation in two stages. First, it constructs a conformation in a rotation and translation invariant representation─internal coordinates. In the second step, the model predicts the distances between neighboring atoms and performs a few fast optimization steps to refine the initial conformation. The proposed model considers conformation energy, achieving comparable space coverage, and diversity metrics results.

A Multi-view Molecular Pre-training with Generative Contrastive Learning

Molecular representation learning can preserve meaningful molecular structures as embedding vectors, which is a necessary prerequisite for molecular property prediction. Yet, learning how to accurately represent molecules remains challenging. Previous approaches to learning molecular representations in an end-to-end manner potentially suffered information loss while neglecting the utilization of molecular generative representations. To obtain rich molecular feature information, the pre-training molecular representation model utilized different molecular representations to reduce information loss caused by a single molecular representation. Therefore, we provide the MVGC, a unique multi-view generative contrastive learning pre-training model. Our pre-training framework specifically acquires knowledge of three fundamental feature representations of molecules and effectively integrates them to predict molecular properties on benchmark datasets. Comprehensive experiments on seven classification tasks and three regression tasks demonstrate that our proposed MVGC model surpasses the majority of state-of-the-art approaches. Moreover, we explore the potential of the MVGC model to learn the representation of molecules with chemical significance.

Mixed Continuous and Categorical Flow Matching for 3D De Novo Molecule Generation

Deep generative models that produce novel molecular structures have the potential to facilitate chemical discovery. Diffusion models currently achieve state of the art performance for 3D molecule generation. In this work, we explore the use of flow matching, a recently proposed generative modeling framework that generalizes diffusion models, for the task of de novo molecule generation. Flow matching provides flexibility in model design; however, the framework is predicated on the assumption of continuously-valued data. 3D de novo molecule generation requires jointly sampling continuous and categorical variables such as atom position and atom type. We extend the flow matching framework to categorical data by constructing flows that are constrained to exist on a continuous representation of categorical data known as the probability simplex. We call this extension SimplexFlow. We explore the use of SimplexFlow for de novo molecule generation. However, we find that, in practice, a simpler approach that makes no accommodations for the categorical nature of the data yields equivalent or superior performance. As a result of these experiments, we present FlowMol, a flow matching model for 3D de novo generative model that achieves improved performance over prior flow matching methods, and we raise important questions about the design of prior distributions for achieving strong performance in flow matching models. Code and trained models for reproducing this work are available at https://github.com/dunni3/FlowMol.

QuanDB: a quantum chemical property database towards enhancing 3D molecular representation learning

Previous studies have shown that the three-dimensional (3D) geometric and electronic structure of molecules play a crucial role in determining their key properties and intermolecular interactions. Therefore, it is necessary to establish a quantum chemical (QC) property database containing the most stable 3D geometric conformations and electronic structures of molecules. In this study, a high-quality QC property database, called QuanDB, was developed, which included structurally diverse molecular entities and featured a user-friendly interface. Currently, QuanDB contains 154,610 compounds sourced from public databases and scientific literature, with 10,125 scaffolds. The elemental composition comprises nine elements: H, C, O, N, P, S, F, Cl, and Br. For each molecule, QuanDB provides 53 global and 5 local QC properties and the most stable 3D conformation. These properties are divided into three categories: geometric structure, electronic structure, and thermodynamics. Geometric structure optimization and single point energy calculation at the theoretical level of B3LYP-D3(BJ)/6-311G(d)/SMD/water and B3LYP-D3(BJ)/def2-TZVP/SMD/water, respectively, were applied to ensure highly accurate calculations of QC properties, with the computational cost exceeding 107 core-hours. QuanDB provides high-value geometric and electronic structure information for use in molecular representation models, which are critical for machine-learning-based molecular design, thereby contributing to a comprehensive description of the chemical compound space. As a new high-quality dataset for QC properties, QuanDB is expected to become a benchmark tool for the training and optimization of machine learning models, thus further advancing the development of novel drugs and materials. QuanDB is freely available, without registration, at https://quandb.cmdrg.com/ .

Exploring Chemical Reaction Space with Machine Learning Models: Representation and Feature Perspective

Chemical reactions serve as foundational building blocks for organic chemistry and drug design. In the era of large AI models, data-driven approaches have emerged to innovate the design of novel reactions, optimize existing ones for higher yields, and discover new pathways for synthesizing chemical structures comprehensively. To effectively address these challenges with machine learning models, it is imperative to derive robust and informative representations or engage in feature engineering using extensive data sets of reactions. This work aims to provide a comprehensive review of established reaction featurization approaches, offering insights into the selection of representations and the design of features for a wide array of tasks. The advantages and limitations of employing SMILES, molecular fingerprints, molecular graphs, and physics-based properties are meticulously elaborated. Solutions to bridge the gap between different representations will also be critically evaluated. Additionally, we introduce a new frontier in chemical reaction pretraining, holding promise as an innovative yet unexplored avenue.

Physics-Informed Generative Model for Drug-like Molecule Conformers

We present a diffusion-based generative model for conformer generation. Our model is focused on the reproduction of the bonded structure and is constructed from the associated terms traditionally found in classical force fields to ensure a physically relevant representation. Techniques in deep learning are used to infer atom typing and geometric parameters from a training set. Conformer sampling is achieved by taking advantage of recent advancements in diffusion-based generation. By training on large, synthetic data sets of diverse, drug-like molecules optimized with the semiempirical GFN2-xTB method, high accuracy is achieved for bonded parameters, exceeding that of conventional, knowledge-based methods. Results are also compared to experimental structures from the Protein Databank and the Cambridge Structural Database.

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.

CREST-A program for the exploration of low-energy molecular chemical space

Conformer-rotamer sampling tool (CREST) is an open-source program for the efficient and automated exploration of molecular chemical space. Originally developed in Pracht et al. [Phys. Chem. Chem. Phys. 22, 7169 (2020)] as an automated driver for calculations at the extended tight-binding level (xTB), it offers a variety of molecular- and metadynamics simulations, geometry optimization, and molecular structure analysis capabilities. Implemented algorithms include automated procedures for conformational sampling, explicit solvation studies, the calculation of absolute molecular entropy, and the identification of molecular protonation and deprotonation sites. Calculations are set up to run concurrently, providing efficient single-node parallelization. CREST is designed to require minimal user input and comes with an implementation of the GFNn-xTB Hamiltonians and the GFN-FF force-field. Furthermore, interfaces to any quantum chemistry and force-field software can easily be created. In this article, we present recent developments in the CREST code and show a selection of applications for the most important features of the program. An important novelty is the refactored calculation backend, which provides significant speed-up for sampling of small or medium-sized drug molecules and allows for more sophisticated setups, for example, quantum mechanics/molecular mechanics and minimum energy crossing point calculations.

COATI: Multimodal Contrastive Pretraining for Representing and Traversing Chemical Space

Creating a successful small molecule drug is a challenging multiparameter optimization problem in an effectively infinite space of possible molecules. Generative models have emerged as powerful tools for traversing data manifolds composed of images, sounds, and text and offer an opportunity to dramatically improve the drug discovery and design process. To create generative optimization methods that are more useful than brute-force molecular generation and filtering via virtual screening, we propose that four integrated features are necessary: large, quantitative data sets of molecular structure and activity, an invertible vector representation of realistic accessible molecules, smooth and differentiable regressors that quantify uncertainty, and algorithms to simultaneously optimize properties of interest. Over the course of 12 months, Terray Therapeutics has collected a data set of 2 billion quantitative binding measurements of small molecules to therapeutic targets, which directly motivates multiparameter generative optimization of molecules conditioned on these data. To this end, we present contrastive optimization for accelerated therapeutic inference (COATI), a pretrained, multimodal encoder-decoder model of druglike chemical space. COATI is constructed without any human biasing of features, using contrastive learning from text and 3D representations of molecules to allow for downstream use with structural models. We demonstrate that COATI possesses many of the desired properties of universal molecular embedding: fixed-dimension, invertibility, autoencoding, accurate regression, and low computation cost. Finally, we present a novel metadynamics algorithm for generative optimization using a small subset of our proprietary data collected for a model protein, carbonic anhydrase, designing molecules that satisfy the multiparameter optimization task of potency, solubility, and drug likeness. This work sets the stage for fully integrated generative molecular design and optimization for small molecules.

Molecular Contrastive Pretraining with Collaborative Featurizations

Molecular pretraining, which learns molecular representations over massive unlabeled data, has become a prominent paradigm to solve a variety of tasks in computational chemistry and drug discovery. Recently, prosperous progress has been made in molecular pretraining with different molecular featurizations, including 1D SMILES strings, 2D graphs, and 3D geometries. However, the role of molecular featurizations with their corresponding neural architectures in molecular pretraining remains largely unexamined. In this paper, through two case studies─chirality classification and aromatic ring counting─we first demonstrate that different featurization techniques convey chemical information differently. In light of this observation, we propose a simple and effective MOlecular pretraining framework with COllaborative featurizations (MOCO). MOCO comprehensively leverages multiple featurizations that complement each other and outperforms existing state-of-the-art models that solely rely on one or two featurizations on a wide range of molecular property prediction tasks.

A generative artificial intelligence framework based on a molecular diffusion model for the design of metal-organic frameworks for carbon capture

Metal-organic frameworks (MOFs) exhibit great promise for CO2 capture. However, finding the best performing materials poses computational and experimental grand challenges in view of the vast chemical space of potential building blocks. Here, we introduce GHP-MOFassemble, a generative artificial intelligence (AI), high performance framework for the rational and accelerated design of MOFs with high CO2 adsorption capacity and synthesizable linkers. GHP-MOFassemble generates novel linkers, assembled with one of three pre-selected metal nodes (Cu paddlewheel, Zn paddlewheel, Zn tetramer) into MOFs in a primitive cubic topology. GHP-MOFassemble screens and validates AI-generated MOFs for uniqueness, synthesizability, structural validity, uses molecular dynamics simulations to study their stability and chemical consistency, and crystal graph neural networks and Grand Canonical Monte Carlo simulations to quantify their CO2 adsorption capacities. We present the top six AI-generated MOFs with CO2 capacities greater than 2m mol g-1, i.e., higher than 96.9% of structures in the hypothetical MOF dataset.

Diff-AMP: tailored designed antimicrobial peptide framework with all-in-one generation, identification, prediction and optimization

Antimicrobial peptides (AMPs), short peptides with diverse functions, effectively target and combat various organisms. The widespread misuse of chemical antibiotics has led to increasing microbial resistance. Due to their low drug resistance and toxicity, AMPs are considered promising substitutes for traditional antibiotics. While existing deep learning technology enhances AMP generation, it also presents certain challenges. Firstly, AMP generation overlooks the complex interdependencies among amino acids. Secondly, current models fail to integrate crucial tasks like screening, attribute prediction and iterative optimization. Consequently, we develop a integrated deep learning framework, Diff-AMP, that automates AMP generation, identification, attribute prediction and iterative optimization. We innovatively integrate kinetic diffusion and attention mechanisms into the reinforcement learning framework for efficient AMP generation. Additionally, our prediction module incorporates pre-training and transfer learning strategies for precise AMP identification and screening. We employ a convolutional neural network for multi-attribute prediction and a reinforcement learning-based iterative optimization strategy to produce diverse AMPs. This framework automates molecule generation, screening, attribute prediction and optimization, thereby advancing AMP research. We have also deployed Diff-AMP on a web server, with code, data and server details available in the Data Availability section.

A community effort in SARS-CoV-2 drug discovery

The COVID-19 pandemic continues to pose a substantial threat to human lives and is likely to do so for years to come. Despite the availability of vaccines, searching for efficient small-molecule drugs that are widely available, including in low- and middle-income countries, is an ongoing challenge. In this work, we report the results of an open science community effort, the "Billion molecules against COVID-19 challenge", to identify small-molecule inhibitors against SARS-CoV-2 or relevant human receptors. Participating teams used a wide variety of computational methods to screen a minimum of 1 billion virtual molecules against 6 protein targets. Overall, 31 teams participated, and they suggested a total of 639,024 molecules, which were subsequently ranked to find 'consensus compounds'. The organizing team coordinated with various contract research organizations (CROs) and collaborating institutions to synthesize and test 878 compounds for biological activity against proteases (Nsp5, Nsp3, TMPRSS2), nucleocapsid N, RdRP (only the Nsp12 domain), and (alpha) spike protein S. Overall, 27 compounds with weak inhibition/binding were experimentally identified by binding-, cleavage-, and/or viral suppression assays and are presented here. Open science approaches such as the one presented here contribute to the knowledge base of future drug discovery efforts in finding better SARS-CoV-2 treatments.

A Multimodal Deep Learning Framework for Predicting PPI-Modulator Interactions

Protein-protein interactions (PPIs) are essential for various biological processes and diseases. However, most existing computational methods for identifying PPI modulators require either target structure or reference modulators, which restricts their applicability to novel PPI targets. To address this challenge, we propose MultiPPIMI, a sequence-based deep learning framework that predicts the interaction between any given PPI target and modulator. MultiPPIMI integrates multimodal representations of PPI targets and modulators and uses a bilinear attention network to capture intermolecular interactions. Experimental results on our curated benchmark data set show that MultiPPIMI achieves an average AUROC of 0.837 in three cold-start scenarios and an AUROC of 0.994 in the random-split scenario. Furthermore, the case study shows that MultiPPIMI can assist molecular docking simulations in screening inhibitors of Keap1/Nrf2 PPI interactions. We believe that the proposed method provides a promising way to screen PPI-targeted modulators.

Systematic Comparison of Experimental Crystallographic Geometries and Gas-Phase Computed Conformers for Torsion Preferences

We performed exhaustive torsion sampling on more than 3 million compounds using the GFN2-xTB method and performed a comparison of experimental crystallographic and gas-phase conformers. Many conformer sampling methods derive torsional angle distributions from experimental crystallographic data, limiting the torsion preferences to molecules that must be stable, synthetically accessible, and able to be crystallized. In this work, we evaluate the differences in torsional preferences of experimental crystallographic geometries and gas-phase computed conformers from a broad selection of compounds to determine whether torsional angle distributions obtained from semiempirical methods are suitable priors for conformer sampling. We find that differences in torsion preferences can be mostly attributed to a lack of available experimental crystallographic data with small deviations derived from gas-phase geometry differences. GFN2 demonstrates the ability to provide accurate and reliable torsional preferences that can provide a basis for new methods free from the limitations of experimental data collection. We provide Gaussian-based fits and sampling distributions suitable for torsion sampling and propose an alternative to the widely used "experimental torsion and knowledge distance geometry" (ETKDG) method using quantum torsion-derived distance geometry (QTDG) methods.

Conformer Generation for Structure-Based Drug Design: How Many and How Good?

Conformer generation, the assignment of realistic 3D coordinates to a small molecule, is fundamental to structure-based drug design. Conformational ensembles are required for rigid-body matching algorithms, such as shape-based or pharmacophore approaches, and even methods that treat the ligand flexibly, such as docking, are dependent on the quality of the provided conformations due to not sampling all degrees of freedom (e.g., only sampling torsions). Here, we empirically elucidate some general principles about the size, diversity, and quality of the conformational ensembles needed to get the best performance in common structure-based drug discovery tasks. In many cases, our findings may parallel "common knowledge" well-known to practitioners of the field. Nonetheless, we feel that it is valuable to quantify these conformational effects while reproducing and expanding upon previous studies. Specifically, we investigate the performance of a state-of-the-art generative deep learning approach versus a more classical geometry-based approach, the effect of energy minimization as a postprocessing step, the effect of ensemble size (maximum number of conformers), and construction (filtering by root-mean-square deviation for diversity) and how these choices influence the ability to recapitulate bioactive conformations and perform pharmacophore screening and molecular docking.

Small-Molecule Conformer Generators: Evaluation of Traditional Methods and AI Models on High-Quality Data Sets

Small-molecule conformer generation (SMCG) is an extremely important task in both ligand- and structure-based computer-aided drug design, especially during the hit discovery phase. Recently, a multitude of artificial intelligence (AI) models tailored for SMCG have emerged. Despite developers typically furnishing performance evaluation data upon releasing their AI models, a comprehensive and equitable performance comparison between AI models and conventional methods is still lacking. In this study, we curated a new benchmarking data set comprising 3354 high-quality ligand bioactive conformations. Subsequently, we conducted a systematic assessment of the performance of four widely adopted traditional methods (i.e., ConfGenX, Conformator, OMEGA, and RDKit ETKDG) and five AI models (i.e., ConfGF, DMCG, GeoDiff, GeoMol, and torsional diffusion) in the tasks of reproducing bioactive and low-energy conformations of small molecules. In the former task, the AI models have no advantage, particularly with a maximum ensemble size of 1. Even the best-performing AI model GeoMol is still worse than any of the tested traditional methods. Conversely, in the latter task, the torsional diffusion model shows obvious advantages, surpassing the best-performing traditional method ConfGenX by 26.09 and 12.97% on the COV-R and COV-P metrics, respectively. Furthermore, the influence of force field-based fine-tuning on the quality of the generated conformers was also discussed. Finally, a user-friendly Web server called fastSMCG was developed to enable researchers to rapidly and flexibly generate small-molecule conformers using both traditional and AI methods. We anticipate that our work will offer valuable practical assistance to the scientific community in this field.

SILVR: Guided Diffusion for Molecule Generation

Computationally generating new synthetically accessible compounds with high affinity and low toxicity is a great challenge in drug design. Machine learning models beyond conventional pharmacophoric methods have shown promise in the generation of novel small-molecule compounds but require significant tuning for a specific protein target. Here, we introduce a method called selective iterative latent variable refinement (SILVR) for conditioning an existing diffusion-based equivariant generative model without retraining. The model allows the generation of new molecules that fit into a binding site of a protein based on fragment hits. We use the SARS-CoV-2 main protease fragments from Diamond XChem that form part of the COVID Moonshot project as a reference dataset for conditioning the molecule generation. The SILVR rate controls the extent of conditioning, and we show that moderate SILVR rates make it possible to generate new molecules of similar shape to the original fragments, meaning that the new molecules fit the binding site without knowledge of the protein. We can also merge up to 3 fragments into a new molecule without affecting the quality of molecules generated by the underlying generative model. Our method is generalizable to any protein target with known fragments and any diffusion-based model for molecule generation.

Mapping the Space of Photoswitchable Ligands and Photodruggable Proteins with Computational Modeling

Light-activated drugs are a promising way to localize biological activity and minimize side effects. However, their development is complicated by the numerous photophysical and biological properties that must be simultaneously optimized. To accelerate the design of photoactive drugs, we describe a procedure that combines ligand-protein docking with chemical property prediction based on machine learning (ML). We apply this procedure to 58 proteins and 9000 photo-drug candidates based on azobenzene cis-trans isomerism. We find that most proteins display a preference for trans isomers over cis and that the binding affinities of nominally active/inactive pairs are in fact highly correlated. These findings have significant value for photopharmacology research, and reinforce the need for virtual screening to identify compounds with rare desirable properties. Further, we combine our procedure with quantum chemical validation to identify promising candidates for the photoactive inhibition of PARP1, an enzyme that is over-expressed in cancer cells. The top compounds are predicted to have long-lived active forms, differential bioactivity, and absorption in the near-infrared therapeutic window.

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.

Equivariant Graph Neural Networks for Toxicity Prediction

Predictive modeling of toxicity is a crucial step in the drug discovery pipeline. It can help filter out molecules with a high probability of failing in the early stages of de novo drug design. Thus, several machine learning (ML) models have been developed to predict the toxicity of molecules by combining classical ML techniques or deep neural networks with well-known molecular representations such as fingerprints or 2D graphs. But the more natural, accurate representation of molecules is expected to be defined in physical 3D space like in ab initio methods. Recent studies successfully used equivariant graph neural networks (EGNNs) for representation learning based on 3D structures to predict quantum-mechanical properties of molecules. Inspired by this, we investigated the performance of EGNNs to construct reliable ML models for toxicity prediction. We used the equivariant transformer (ET) model in TorchMD-NET for this. Eleven toxicity data sets taken from MoleculeNet, TDCommons, and ToxBenchmark have been considered to evaluate the capability of ET for toxicity prediction. Our results show that ET adequately learns 3D representations of molecules that can successfully correlate with toxicity activity, achieving good accuracies on most data sets comparable to state-of-the-art models. We also test a physicochemical property, namely, the total energy of a molecule, to inform the toxicity prediction with a physical prior. However, our work suggests that these two properties can not be related. We also provide an attention weight analysis for helping to understand the toxicity prediction in 3D space and thus increase the explainability of the ML model. In summary, our findings offer promising insights considering 3D geometry information via EGNNs and provide a straightforward way to integrate molecular conformers into ML-based pipelines for predicting and investigating toxicity prediction in physical space. We expect that in the future, especially for larger, more diverse data sets, EGNNs will be an essential tool in this domain.

An equivariant generative framework for molecular graph-structure Co-design

Designing molecules with desirable physiochemical properties and functionalities is a long-standing challenge in chemistry, material science, and drug discovery. Recently, machine learning-based generative models have emerged as promising approaches for de novo molecule design. However, further refinement of methodology is highly desired as most existing methods lack unified modeling of 2D topology and 3D geometry information and fail to effectively learn the structure-property relationship for molecule design. Here we present MolCode, a roto-translation equivariant generative framework for molecular graph-structure Co-design. In MolCode, 3D geometric information empowers the molecular 2D graph generation, which in turn helps guide the prediction of molecular 3D structure. Extensive experimental results show that MolCode outperforms previous methods on a series of challenging tasks including de novo molecule design, targeted molecule discovery, and structure-based drug design. Particularly, MolCode not only consistently generates valid (99.95% validity) and diverse (98.75% uniqueness) molecular graphs/structures with desirable properties, but also generates drug-like molecules with high affinity to target proteins (61.8% high affinity ratio), which demonstrates MolCode's potential applications in material design and drug discovery. Our extensive investigation reveals that the 2D topology and 3D geometry contain intrinsically complementary information in molecule design, and provide new insights into machine learning-based molecule representation and generation.

Enhancing drug property prediction with dual-channel transfer learning based on molecular fragment

BACKGROUND

Accurate prediction of molecular property holds significance in contemporary drug discovery and medical research. Recent advances in AI-driven molecular property prediction have shown promising results. Due to the costly annotation of in vitro and in vivo experiments, transfer learning paradigm has been gaining momentum in extracting general self-supervised information to facilitate neural network learning. However, prior pretraining strategies have overlooked the necessity of explicitly incorporating domain knowledge, especially the molecular fragments, into model design, resulting in the under-exploration of the molecular semantic space.

RESULTS

We propose an effective model with FRagment-based dual-channEL pretraining (FREL). Equipped with molecular fragments, FREL comprehensively employs masked autoencoder and contrastive learning to learn intra- and inter-molecule agreement, respectively. We further conduct extensive experiments on ten public datasets to demonstrate its superiority over state-of-the-art models. Further investigations and interpretations manifest the underlying relationship between molecular representations and molecular properties.

CONCLUSIONS

Our proposed model FREL achieves state-of-the-art performance on the benchmark datasets, emphasizing the importance of incorporating molecular fragments into model design. The expressiveness of learned molecular representations is also investigated by visualization and correlation analysis. Case studies indicate that the learned molecular representations better capture the drug property variation and fragment semantics.

Tora3D: an autoregressive torsion angle prediction model for molecular 3D conformation generation

Three-dimensional (3D) conformations of a small molecule profoundly affect its binding to the target of interest, the resulting biological effects, and its disposition in living organisms, but it is challenging to accurately characterize the conformational ensemble experimentally. Here, we proposed an autoregressive torsion angle prediction model Tora3D for molecular 3D conformer generation. Rather than directly predicting the conformations in an end-to-end way, Tora3D predicts a set of torsion angles of rotatable bonds by an interpretable autoregressive method and reconstructs the 3D conformations from them, which keeps structural validity during reconstruction. Another advancement of our method over other conformational generation methods is the ability to use energy to guide the conformation generation. In addition, we propose a new message-passing mechanism that applies the Transformer to the graph to solve the difficulty of remote message passing. Tora3D shows superior performance to prior computational models in the trade-off between accuracy and efficiency, and ensures conformational validity, accuracy, and diversity in an interpretable way. Overall, Tora3D can be used for the quick generation of diverse molecular conformations and 3D-based molecular representation, contributing to a wide range of downstream drug design tasks.

An Ecosystem for Digital Reticular Chemistry

The vastness of the materials design space makes it impractical to explore using traditional brute-force methods, particularly in reticular chemistry. However, machine learning has shown promise in expediting and guiding materials design. Despite numerous successful applications of machine learning to reticular materials, progress in the field has stagnated, possibly because digital chemistry is more an art than a science and its limited accessibility to inexperienced researchers. To address this issue, we present mofdscribe, a software ecosystem tailored to novice and seasoned digital chemists that streamlines the ideation, modeling, and publication process. Though optimized for reticular chemistry, our tools are versatile and can be used in nonreticular materials research. We believe that mofdscribe will enable a more reliable, efficient, and comparable field of digital chemistry.

Algorithmic Graph Theory, Reinforcement Learning and Game Theory in MD Simulations: From 3D Structures to Topological 2D-Molecular Graphs (2D-MolGraphs) and Vice Versa

This paper reviews graph-theory-based methods that were recently developed in our group for post-processing molecular dynamics trajectories. We show that the use of algorithmic graph theory not only provides a direct and fast methodology to identify conformers sampled over time but also allows to follow the interconversions between the conformers through graphs of transitions in time. Examples of gas phase molecules and inhomogeneous aqueous solid interfaces are presented to demonstrate the power of topological 2D graphs and their versatility for post-processing molecular dynamics trajectories. An even more complex challenge is to predict 3D structures from topological 2D graphs. Our first attempts to tackle such a challenge are presented with the development of game theory and reinforcement learning methods for predicting the 3D structure of a gas-phase peptide.

Thermal Half-Lives of Azobenzene Derivatives: Virtual Screening Based on Intersystem Crossing Using a Machine Learning Potential

Molecular photoswitches are the foundation of light-activated drugs. A key photoswitch is azobenzene, which exhibits trans-cis isomerism in response to light. The thermal half-life of the cis isomer is of crucial importance, since it controls the duration of the light-induced biological effect. Here we introduce a computational tool for predicting the thermal half-lives of azobenzene derivatives. Our automated approach uses a fast and accurate machine learning potential trained on quantum chemistry data. Building on well-established earlier evidence, we argue that thermal isomerization proceeds through rotation mediated by intersystem crossing, and incorporate this mechanism into our automated workflow. We use our approach to predict the thermal half-lives of 19,000 azobenzene derivatives. We explore trends and trade-offs between barriers and absorption wavelengths, and open-source our data and software to accelerate research in photopharmacology.

New avenues in artificial-intelligence-assisted drug discovery

Over the past decade, the amount of biomedical data available has grown at unprecedented rates. Increased automation technology and larger data volumes have encouraged the use of machine learning (ML) or artificial intelligence (AI) techniques for mining such data and extracting useful patterns. Because the identification of chemical entities with desired biological activity is a crucial task in drug discovery, AI technologies have the potential to accelerate this process and support decision making. In addition, the advent of deep learning (DL) has shown great promise in addressing diverse problems in drug discovery, such as de novo molecular design. Herein, we will appraise the current state-of-the-art in AI-assisted drug discovery, discussing the recent applications covering generative models for chemical structure generation, scoring functions to improve binding affinity and pose prediction, and molecular dynamics to assist in the parametrization, featurization and generalization tasks. Finally, we will discuss current hurdles and the strategies to overcome them, as well as potential future directions.

High-throughput property-driven generative design of functional organic molecules

The design of molecules and materials with tailored properties is challenging, as candidate molecules must satisfy multiple competing requirements that are often difficult to measure or compute. While molecular structures produced through generative deep learning will satisfy these patterns, they often only possess specific target properties by chance and not by design, which makes molecular discovery via this route inefficient. In this work, we predict molecules with (Pareto-)optimal properties by combining a generative deep learning model that predicts three-dimensional conformations of molecules with a supervised deep learning model that takes these as inputs and predicts their electronic structure. Optimization of (multiple) molecular properties is achieved by screening newly generated molecules for desirable electronic properties and reusing hit molecules to retrain the generative model with a bias. The approach is demonstrated to find optimal molecules for organic electronics applications. Our method is generally applicable and eliminates the need for quantum chemical calculations during predictions, making it suitable for high-throughput screening in materials and catalyst design.

An Efficient Approach to Large-Scale Ab Initio Conformational Energy Profiles of Small Molecules

Accurate conformational energetics of molecules are of great significance to understand maby chemical properties. They are also fundamental for high-quality parameterization of force fields. Traditionally, accurate conformational profiles are obtained with density functional theory (DFT) methods. However, obtaining a reliable energy profile can be time-consuming when the molecular sizes are relatively large or when there are many molecules of interest. Furthermore, incorporation of data-driven deep learning methods into force field development has great requirements for high-quality geometry and energy data. To this end, we compared several possible alternatives to the traditional DFT methods for conformational scans, including the semi-empirical method GFN2-xTB and the neural network potential ANI-2x. It was found that a sequential protocol of geometry optimization with the semi-empirical method and single-point energy calculation with high-level DFT methods can provide satisfactory conformational energy profiles hundreds of times faster in terms of optimization.

Deep generative molecular design reshapes drug discovery

Recent advances and accomplishments of artificial intelligence (AI) and deep generative models have established their usefulness in medicinal applications, especially in drug discovery and development. To correctly apply AI, the developer and user face questions such as which protocols to consider, which factors to scrutinize, and how the deep generative models can integrate the relevant disciplines. This review summarizes classical and newly developed AI approaches, providing an updated and accessible guide to the broad computational drug discovery and development community. We introduce deep generative models from different standpoints and describe the theoretical frameworks for representing chemical and biological structures and their applications. We discuss the data and technical challenges and highlight future directions of multimodal deep generative models for accelerating drug discovery.