Tapping into AI and ML to accelerate the next generation of drug discovery
atai Life Sciences
Healing mental health disorders so that everyone, everywhere can live a more fulfilled life.
At?atai Life Sciences, we are committed to bringing the next generation of mental health treatments to patients as efficiently and effectively as possible. Glenn Short , Senior Vice President, Early Development, discusses how we are using artificial intelligence (AI) and machine learning (ML) with the aim to speed up the drug development journey.
Drug development is a complex process which can take anywhere between 10-15 years until a drug is approved and available to patients.[i] Often, more than five years of this process is spent solely on the discovery phase involving the identification of molecules that have the desired pharmacology to impact disease.[ii] Traditional approaches to finding suitable molecules are woefully inefficient and typically employ brute force methods such as high-throughput screening of large compound libraries or random assembly of smaller building blocks to generate large combinatorial libraries which are then screened. Given the recent advancements and increased sophistication of artificial intelligence (AI) approaches, we’ve held the belief since atai was founded that AI and machine learning (ML) have the potential to transform the way we go about drug discovery – making it more cost and time efficient in delivering new medicines to patients living with mental health disorders. ?
Understanding the possibilities of AI/ML
While computational techniques have been employed successfully allowing in silico drug screening, drug design and optimization, advanced AI/ML approaches could leapfrog over much of the early discovery process allowing us to land at a more advanced starting point to initiate drug discovery efforts.
Anyone who has used OpenAI’s ChatGPT will recognize that it is trained to go beyond the limitations of a traditional search engine – not only serving information, but processing and contextualizing vast amounts of data to answer specific questions. Similarly, in drug discovery, AI/ML can greatly speed-up and refine the process of identifying drug-like compounds with improved specificity, selectivity and efficacy.
To give you a real-world example: we can think of the traditional drug discovery process as a mail carrier trying to find the correct address to deliver an unaddressed letter to. The process is typically uninformed – like the mail carrier wondering if the intended recipient of the letter is even on their mail route. It is only by knocking on various doors that the mail carrier will know if they have found the letter’s correct recipient. However, the AI/ML approach to drug discovery is analogous to?analyzing details of the letter (the return address, the names associated with addresses in each location making associations, correlations and assessing probabilities) to adjust the route to get to the right street or neighborhood, increasing the likelihood of delivery. While AI/ML may not allow us to identify the exact address at which the intended recipient lives, it does help us know the town and street of the recipient which increases the odds and improves the efficiency of correctly delivering the letter. ??????
Although AI/ML can accelerate and enhance the early drug discovery process, it does not replace the need for experimental follow up and validation. One of our drug discovery engines was founded in 2019 in partnership with Recursion, and is based on a AI/ML strategy which uses computational strategies to make highly informed decisions to help prioritize those molecules that have the greatest likelihood of being drug-like, selective and efficacious. By focusing medicinal chemistry efforts on the most promising molecules first, the use of AI/ML early in the drug discovery process creates time and cost efficiencies.
Engineering novel treatments for mental health disorders
atai is already leveraging AI/ML technologies to great effect to design new chemical entities (NCEs) with the potential for enhanced effectiveness and safety in both in vitro and in vivo assays relevant to mental health disorders. For example, our drug discovery engines can utilize available biological data to rapidly design novel molecules that mimic the activities of psychedelics, but with improved properties. This has been most evident in the generation of non-tryptamine NCEs that maintain the overall activity fingerprint of N,N-Dimethyltryptamine (DMT) while increasing 5-HT2A receptor selectivity over the 5-HT2B receptor which has been associated with cardiac valvulopathy. ?AI/ML approaches have also provided us an opportunity to design novel compounds with reduced hallucinogenic potential, while maintaining other neuroplastigen-like biological activities presumed relevant to therapeutic efficacy. Such modifications may expedite development of the molecule because of less complex safety considerations and greater flexibility with dosing frequency and its relative beneficial impact to patients.
The future of AI powered clinical development
Our approach is putting atai at the forefront of groundbreaking drug discovery: it brings us a deeper level of understanding and an ability to tailor our future treatments to specific patient needs. Not only does this potentially reduce the time from discovery to clinical study, but it may significantly improve our ability to reach more patients with treatment-resistant mental health disorder, taking us closer to our mission to deliver mental health treatments and care for everyone everywhere.
领英推荐
Forward-Looking Statements:
Please note that the information provided above contains forward-looking statements.?We have based these forward-looking statements largely on our current expectations and projections about future events and trends that we believe may affect our financial condition, results of operations, business strategy, short-term and long-term business operations and objectives, and financial needs. These forward-looking statements are subject to a number of important factors that could cause actual results to differ materially from those in the forward-looking statements, including the risks, uncertainties, and assumptions described under "Summary Risk Factors" below, “Risk Factors” in Item 1A of Part I, “Management’s Discussion and Analysis of Financial Condition and Results of Operations” in Item 7 of Part II and elsewhere in our Form 10-K for the year ended December 31, 2022, filed with the Securities and Exchange Commission (“SEC”), as may be updated by other filings we file with or furnish to the SEC.
Any forward-looking statements made herein speak only as of the date of this communication, and you should not rely on forward-looking statements as predictions of future events. Although we believe that the expectations reflected in the forward-looking statements are reasonable, we cannot guarantee that the future results, performance, or achievements reflected in the forward-looking statements will be achieved or will occur. Except as required by applicable law, we undertake no obligation to update any of these forward-looking statements for any reason after the date hereof or to conform these statements to actual results or revised expectations.
Background on atai Life Sciences AG:
atai Life Sciences (Nasdaq: ATAI), is a clinical-stage biopharmaceutical company aiming to accelerate the development of new medicines across its companies to achieve clinically meaningful and sustained behavioral change in mental health patients.?
We have a pipeline of five clinical-stage drug development programs, several of which are envisioned to be paired with a proprietary, internally developed digital therapeutics platform. Of these five clinical drug candidates, three are psychedelic and two are non-psychedelic in nature. In addition, we use AI-based computational and medicinal chemistry approaches as part of our drug discovery efforts to generate the next generation of psychedelic and related molecules. As of our latest publicly filed report, we also have a 22.4% stake in COMPASS Pathways (separately listed on Nasdaq; CMPS).
References
So thrilled to start my journey towards a healthier lifestyle! Just enrolled in a yoga class and picked up some fresh produce for the week. Here’s to making positive changes! ??? That's fantastic to hear! Remember, as Aristotle once said, 'We are what we repeatedly do. Excellence, then, is not an act, but a habit'. Keep nurturing those positive changes and watch as your life transforms. ????????