Artificial Intelligence for Autonomous Molecular Design: A Perspective

CACTUS: Chemistry Agent Connecting Tool Usage to Science

Large language models (LLMs) have shown remarkable potential in various domains but often lack the ability to access and reason over domain-specific knowledge and tools. In this article, we introduce Chemistry Agent Connecting Tool-Usage to Science (CACTUS), an LLM-based agent that integrates existing cheminformatics tools to enable accurate and advanced reasoning and problem-solving in chemistry and molecular discovery. We evaluate the performance of CACTUS using a diverse set of open-source LLMs, including Gemma-7b, Falcon-7b, MPT-7b, Llama3-8b, and Mistral-7b, on a benchmark of thousands of chemistry questions. Our results demonstrate that CACTUS significantly outperforms baseline LLMs, with the Gemma-7b, Mistral-7b, and Llama3-8b models achieving the highest accuracy regardless of the prompting strategy used. Moreover, we explore the impact of domain-specific prompting and hardware configurations on model performance, highlighting the importance of prompt engineering and the potential for deploying smaller models on consumer-grade hardware without a significant loss in accuracy. By combining the cognitive capabilities of open-source LLMs with widely used domain-specific tools provided by RDKit, CACTUS can assist researchers in tasks such as molecular property prediction, similarity searching, and drug-likeness assessment.

Leveraging Numerical Simulation Technology to Advance Drug Preparation: A Comprehensive Review of Application Scenarios and Cases

BACKGROUND/OBJECTIVES

Numerical simulation plays an important role in pharmaceutical preparation recently. Mechanistic models, as a type of numerical model, are widely used in the study of pharmaceutical preparations. Mechanistic models are based on a priori knowledge, i.e., laws of physics, chemistry, and biology. However, due to interdisciplinary reasons, pharmacy researchers have greater difficulties in using computer models.

METHODS

In this paper, we highlight the application scenarios and examples of mechanistic modelling in pharmacy research and provide a reference for drug researchers to get started.

RESULTS

By establishing a suitable model and inputting preparation parameters, researchers can analyze the drug preparation process. Therefore, mechanistic models are effective tools to optimize the preparation parameters and predict potential quality problems of the product. With product quality parameters as the ultimate goal, the experiment design is optimized by mechanistic models. This process emphasizes the concept of quality by design.

CONCLUSIONS

The use of numerical simulation saves experimental cost and time, and speeds up the experimental process. In pharmacy experiments, part of the physical information and the change processes are difficult to obtain, such as the mechanical phenomena during tablet compression and the airflow details in the nasal cavity. Therefore, it is necessary to predict the information and guide the formulation with the help of mechanistic models.

The changing scenario of drug discovery using AI to deep learning: Recent advancement, success stories, collaborations, and challenges

Due to the transformation of artificial intelligence (AI) tools and technologies, AI-driven drug discovery has come to the forefront. It reduces the time and expenditure. Due to these advantages, pharmaceutical industries are concentrating on AI-driven drug discovery. Several drug molecules have been discovered using AI-based techniques and tools, and several newly AI-discovered drug molecules have already entered clinical trials. In this review, we first present the data and their resources in the pharmaceutical sector for AI-driven drug discovery and illustrated some significant algorithms or techniques used for AI and ML which are used in this field. We gave an overview of the deep neural network (NN) models and compared them with artificial NNs. Then, we illustrate the recent advancement of the landscape of drug discovery using AI to deep learning, such as the identification of drug targets, prediction of their structure, estimation of drug-target interaction, estimation of drug-target binding affinity, design of de novo drug, prediction of drug toxicity, estimation of absorption, distribution, metabolism, excretion, toxicity; and estimation of drug-drug interaction. Moreover, we highlighted the success stories of AI-driven drug discovery and discussed several collaboration and the challenges in this area. The discussions in the article will enrich the pharmaceutical industry.

Native Mass Spectrometry Dissects the Structural Dynamics of an Allosteric Heterodimer of SARS-CoV-2 Nonstructural Proteins

Structure-based drug design, which relies on precise understanding of the target protein and its interaction with the drug candidate, is dramatically expedited by advances in computational methods for candidate prediction. Yet, the accuracy needs to be improved with more structural data from high throughput experiments, which are challenging to generate, especially for dynamic and weak associations. Herein, we applied native mass spectrometry (native MS) to rapidly characterize ligand binding of an allosteric heterodimeric complex of SARS-CoV-2 nonstructural proteins (nsp) nsp10 and nsp16 (nsp10/16), a complex essential for virus survival in the host and thus a desirable drug target. Native MS showed that the dimer is in equilibrium with monomeric states in solution. Consistent with the literature, well characterized small cosubstrate, RNA substrate, and product bind with high specificity and affinity to the dimer but not the free monomers. Unsuccessfully designed ligands bind indiscriminately to all forms. Using neutral gas collision, the nsp16 monomer with bound cosubstrate can be released from the holo dimer complex, confirming the binding to nsp16 as revealed by the crystal structure. However, we observed an unusual migration of the endogenous zinc ions bound to nsp10 to nsp16 after collisional dissociation. The metal migration can be suppressed by using surface collision with reduced precursor charge states, which presumably resulted in minimal gas-phase structural rearrangement and highlighted the importance of complementary techniques. With minimal sample input (∼μg), native MS can rapidly detect ligand binding affinities and locations in dynamic multisubunit protein complexes, demonstrating the potential of an "all-in-one" native MS assay for rapid structural profiling of protein-to-AI-based compound systems to expedite drug discovery.

Leveraging Artificial Intelligence to Expedite Antibody Design and Enhance Antibody-Antigen Interactions

This perspective sheds light on the transformative impact of recent computational advancements in the field of protein therapeutics, with a particular focus on the design and development of antibodies. Cutting-edge computational methods have revolutionized our understanding of protein-protein interactions (PPIs), enhancing the efficacy of protein therapeutics in preclinical and clinical settings. Central to these advancements is the application of machine learning and deep learning, which offers unprecedented insights into the intricate mechanisms of PPIs and facilitates precise control over protein functions. Despite these advancements, the complex structural nuances of antibodies pose ongoing challenges in their design and optimization. Our review provides a comprehensive exploration of the latest deep learning approaches, including language models and diffusion techniques, and their role in surmounting these challenges. We also present a critical analysis of these methods, offering insights to drive further progress in this rapidly evolving field. The paper includes practical recommendations for the application of these computational techniques, supplemented with independent benchmark studies. These studies focus on key performance metrics such as accuracy and the ease of program execution, providing a valuable resource for researchers engaged in antibody design and development. Through this detailed perspective, we aim to contribute to the advancement of antibody design, equipping researchers with the tools and knowledge to navigate the complexities of this field.

Integrated data-driven and experimental approaches to accelerate lead optimization targeting SARS-CoV-2 main protease

Identification of potential therapeutic candidates can be expedited by integrating computational modeling with domain aware machine learning (ML) models followed by experimental validation in an iterative manner. Generative deep learning models can generate thousands of new candidates, however, their physiochemical and biochemical properties are typically not fully optimized. Using our recently developed deep learning models and a scaffold as a starting point, we generated tens of thousands of compounds for SARS-CoV-2 M^pro that preserve the core scaffold. We utilized and implemented several computational tools such as structural alert and toxicity analysis, high throughput virtual screening, ML-based 3D quantitative structure-activity relationships, multi-parameter optimization, and graph neural networks on generated candidates to predict biological activity and binding affinity in advance. As a result of these combined computational endeavors, eight promising candidates were singled out and put through experimental testing using Native Mass Spectrometry and FRET-based functional assays. Two of the tested compounds with quinazoline-2-thiol and acetylpiperidine core moieties showed IC[Formula: see text] values in the low micromolar range: [Formula: see text] [Formula: see text]M and 3.41±0.0015 [Formula: see text]M, respectively. Molecular dynamics simulations further highlight that binding of these compounds results in allosteric modulations within the chain B and the interface domains of the M^pro. Our integrated approach provides a platform for data driven lead optimization with rapid characterization and experimental validation in a closed loop that could be applied to other potential protein targets.

AI-Accelerated Design of Targeted Covalent Inhibitors for SARS-CoV-2

Direct-acting antivirals for the treatment of the COVID-19 pandemic caused by the SARS-CoV-2 virus are needed to complement vaccination efforts. Given the ongoing emergence of new variants, automated experimentation, and active learning based fast workflows for antiviral lead discovery remain critical to our ability to address the pandemic's evolution in a timely manner. While several such pipelines have been introduced to discover candidates with noncovalent interactions with the main protease (Mpro), here we developed a closed-loop artificial intelligence pipeline to design electrophilic warhead-based covalent candidates. This work introduces a deep learning-assisted automated computational workflow to introduce linkers and an electrophilic "warhead" to design covalent candidates and incorporates cutting-edge experimental techniques for validation. Using this process, promising candidates in the library were screened, and several potential hits were identified and tested experimentally using native mass spectrometry and fluorescence resonance energy transfer (FRET)-based screening assays. We identified four chloroacetamide-based covalent inhibitors of Mpro with micromolar affinities (KI of 5.27 μM) using our pipeline. Experimentally resolved binding modes for each compound were determined using room-temperature X-ray crystallography, which is consistent with the predicted poses. The induced conformational changes based on molecular dynamics simulations further suggest that the dynamics may be an important factor to further improve selectivity, thereby effectively lowering KI and reducing toxicity. These results demonstrate the utility of our modular and data-driven approach for potent and selective covalent inhibitor discovery and provide a platform to apply it to other emerging targets.

Analyte Interactions with Oxoporphyrinogen Derivatives: Computational Aspects

Abstract:

The binding of anions by highly-coloured chromophore compounds is of interest from the point-of-view of the development of optical sensors for analyte species. In this review, we have summarised our work on the interactions between oxoporphyrinogen type host compounds and different analyte species using computational methods. The origin of our interest in sensing using oxoporphyrinogens stems from an initial finding involving anion-host interactions involving a conjugated oxoporphyrinogen molecule. This review starts from that point, introducing some additional exemplary anion binding data, which is then elaborated to include descriptions of our synthesis work towards multitopic and ion pair interactions. In all the projects, we have consulted computational data on host structure and host-guest complexes in order to obtain information about the interactions occurring during complexation. Density functional theory and molecular dynamics simulations have been extensively used for these purposes. Oxoporphyrinogens are highly colored synthetically flexible compounds whose interactions with anions, ion pairs, and other species have been modelled using computational methods.