AI in Pharma: Transforming Drug Discovery and Strategic Management with MYC-Modulating Compounds and BET Protein Inhibitors

Abstract

The landscape of pharmaceutical R&D is being reshaped by the synergistic integration of Artificial Intelligence (AI) and groundbreaking drug discoveries, mainly focusing on MYC-modulating compounds and BET protein inhibitors. This Patent Highlight delves into this convergence, illustrating a transformative shift in the pharmaceutical industry’s approach to drug development, strategic management, and treating various diseases, from cancer to inflammatory and fibrotic disorders.

Important Compound Classes

Titles

Pyridazinone-Derived Compounds for the Modulation of MYC and for Medical Uses; Pyrroles and Imidazoles as BET Protein Inhibitors; and Method and System for Pharmaceutical Portforlio Strategic Management Decision Support Based on Artificial Intelligence

Patent Publication Numbers

WO 2023/245091 A1 (URL: https://patents.google.com/patent/WO2023245091A1/en?oq=WO+2023%2f245091+A1);

WO 2024/018423 A1 (URL: https://patentscope.wipo.int/search/en/detail.jsf?docId=WO2024018423&_cid=P10-LRVUC3-58424-9); and

WO 2023/245301 A1 (https://patents.google.com/patent/WO2023245301A1/en?oq=WO+2023%2f245301+A1)

Publication Dates

December 21, 2023; January 25, 2024; and December 28, 2023.

Priority Applications

US 63/352,514; US 2302871.5; and US 63/366,875

Priority Dates

June 15, 2022; February 27, 2023; and June 23, 2022

Inventors

Adanve, B.; NG, Y. Z.; Lai, J. (WO 2023/245091 A1); Bell, M.; Foley, D. W.; Woodland, C. A. (WO 2024/018423 A1); and Piffo, E.; Avramioti, D.; Gierschendorf, J.; Raymond, C. (WO 2023/245301 A1)

Assignee Companies

Genetic Intelligence, Inc. [US/US], 142 W 57th Street, 11th Floor, New York, NY 10019, United States (WO 2023/245091 A1); Tay Therapeutics Limited [GB/GB], Dundee University Incubator 3 James Lindsay Place, Dundee DDI 5JJ, U.K. (WO 2024/018423 A1); and Groupe Sorintellis Inc. [CA/CA], 1540-1050 Côte du Beaver Hall, Montreal, Québec H2Z 0A5, Canada (WO 2023/245301 A1)

Disease Area

Cancer

Biological Target

MYC and BET proteins

Summary

The pharmaceutical industry has faced escalating challenges in recent years, including rising R&D costs, complex regulatory environments, and the need for expedited drug development processes. Developments in pyridazine-derived compounds targeting MYC proto-oncogenes for cancer treatment and pyrroles and imidazoles as inhibitors of BET proteins for treating inflammatory and fibrotic diseases are setting new frontiers. Concurrently, AI’s role in strategic decision-making is heralding a new era of precision and efficiency.

Patent application WO 2023/245091 A1 introduces a breakthrough in treating MYC-driven cancers. The MYC family of proto-oncogenes, integral in cell proliferation and oncogenesis, has been notoriously challenging to target therapeutically. Deregulated MYC expression leads to significant cell metabolic changes, termed “metabolic reprogramming”. This reprogramming varies among different tumor types, dependent on oncogene activity, tissue of origin, and interaction with microenvironment components. MYC-induced metabolic stress can sensitize cells toward apoptosis, with implications for therapeutic strategies targeting these metabolic dependencies. The newly developed pyridazine-derived compounds show promise in modulating MYC expression or activity, offering a novel approach to treating various cancers. This innovation represents a significant stride in oncological therapeutics and exemplifies the sophisticated nature of modern drug discovery.

Patent application WO 2024/018423 Al introduces pyrroles and imidazoles as inhibitors of BET proteins, offering potential treatments for diseases involving inflammation and fibrosis. This patent highlights the therapeutic potential of these novel compounds in treating a wide range of disorders, including inflammatory skin disorders, respiratory diseases, gastrointestinal diseases, and fibrotic conditions in various organs.

Patent application WO 2023/245301 A1 marks a paradigm shift in pharmaceutical R&D, moving from molecular-level focus to artificial intelligence (AI)-driven strategic management and decision-making across various aspects of the industry. It proposes an AI-driven system for risk management and decision support across various facets of pharmaceutical operations, including strategic portfolio management, clinical drug development, and investment strategy optimization. By leveraging AI, the system processes vast amounts of data from diverse sources, providing predictive and prescriptive insights that significantly enhance decision-making efficiency and efficacy.

Introducing AI technologies into the drug discovery pipeline, especially in synthesizing, formulating, and clinically evaluating compounds that modulate the MYC oncogene, can fundamentally transform conventional pharmaceutical research and development approaches.

The use of AI in this context may manifest in several transformative ways

AI algorithms, utilizing advanced machine-learning techniques, may predict the efficacy and safety of new MYC-modulating compounds by analyzing large datasets from preclinical studies. They can also assess safety profiles by analyzing historical data and identifying patterns or correlations with adverse events, thereby mitigating risks early in the drug development.

AI can be instrumental in designing clinical trials for MYC-targeted therapies. By analyzing data from previous trials, including patient demographics, disease progression rates, and responses to treatment, AI can help identify the most suitable patient population for a given trial. It can also predict optimal dosing regimens and anticipate potential dropouts or adverse effects, enabling more efficient and cost-effective trials.

AI technologies, especially those involving genomic data analysis, can identify patients most likely to benefit from MYC-modulating therapies. This personalized approach can significantly improve treatment outcomes. By integrating genomic data with clinical data, AI can uncover subgroups within the cancer patient population that share unique genetic mutations or expression patterns, potentially opening new avenues for targeted therapies.

AI can forecast challenges in the market and regulatory landscapes. By analyzing trends in drug approvals, market acceptance, and regulatory changes, AI can provide insights into the potential hurdles a new drug might face. This forecasting ability enables pharmaceutical companies to develop proactive strategies for market entry, regulatory compliance, and postmarket surveillance.

By analyzing vast chemical libraries and biological datasets, AI can identify novel compounds that could modulate MYC effectively, accelerating the early stages of drug discovery. AI-driven structure–activity relationship models can predict the activity of new compounds, thereby enhancing the efficiency of the drug screening process.

AI facilitates greater collaboration across the pharmaceutical industry by enabling the sharing and analysis of data from different sources. This collaborative environment can lead to more robust and diverse datasets, improving the accuracy and reliability of AI predictions. Cloud computing and secure data-sharing platforms are pivotal in this aspect, allowing researchers across the globe to contribute to and benefit from AI-driven insights.

Challenges and Future Directions

While the potential of AI in pharmaceutical R&D is immense, it has challenges. Issues such as data privacy, algorithm bias, and the need for robust, interpretable AI models require careful consideration. Integrating AI into highly regulated environments like pharmaceuticals necessitates stringent validation and regulatory compliance.

Key Structures

Biological Assay

NanoBRET assay, plasma stability assay, intrinsic clearance in liver microsomes assay, thermodynamic stability assay, and in vivo pharmacokinetics.

Biological Data

Inhibitors of BET proteins have demonstrated potential as oral therapeutic agents, exhibiting extended half-lives and favorable oral bioavailability according to in vivo drug metabolism and pharmacokinetics (DMPK) metrics. The table below shows the pharmacokinetic parameters observed in Sprague–Dawley rats following intravenous (IV) administration at a dosage of 1 mg/kg and oral (PO) administration at a dosage of 5 mg/kg for selected exemplary compounds.

Recent Review Articles

See refs (1−6).

The author declares no competing financial interest.

Special Issue

Published as part of ACS Medicinal Chemistry Lettersvirtual special issue “Exploring the Use of AI/ML Technologies in Medicinal Chemistry and Drug Discovery”.