By Alexandra Urman, Analyst

As proposed in our previous research, investment analysts using outdated debit rates to determine futures could undervalue clinical assets at every stage of development. Next Generation Sequencing (NGS), Artificial Intelligence (AI), CRISPR and other gene therapies should increase the efficiency of clinical trials, shorten development times and reduce failure rates. As a result, the return on investment could improve significantly.

Recent advances in protein modeling of neural networks could reduce clinical pipeline costs and increase drug R&D returns beyond what we initially modeled. Based on our ongoing research in this area, we now believe that preclinical development could become even cheaper and deliver results faster: a marketable therapy costs only $50 million in preclinical investment, half the number that we had previously estimated.

What changed?

Alphabet subsidiary DeepMind has announced AlphaFold, a neural network-based algorithm that can predict protein folding, as well as an open source database of protein structures powered by AlphaFold2. Based on their amino acid sequences, the database predicts the 3D structure of almost all known human proteins, around 350,000.

Essential to life on earth, proteins consist of thousands of linked amino acids that determine their shape and their interaction with other molecules, including drugs. To understand these relationships, drug developers typically use X-ray crystallography – a common experimental method that is tedious, slow and expensive. Over the past few decades, scientists have used computational biology to overcome these hurdles, but none of the algorithms have proven to be accurate enough.

According to our research, innovative algorithms based on neural networks can accurately predict protein structures in laboratory experiments and could boost human therapies and agricultural breakthroughs. DeepMind’s AlphaFold2 has predictive accuracy that meets and sometimes exceeds high-fidelity experimental approaches[1] and could apply to all proteins and protein-protein interactions.

Neural network-based algorithms could reduce preclinical trials Costs and boosting drug candidate pipelines

Knowing the shape of a protein structure early in research could cut the cost and time from discovery to approval of an Investigational New Drug (IND) by 50%. An AlphaFold-like algorithm that quickly determines the shape of proteins could improve economics more than our previous model suggested. For example, using throughput rates from past clinical trials (“Status Quo” in the table below), we estimated preclinical costs per marketed drug at $243 million. If technologies such as NGS and AI were to improve throughput rates, however, preclinical costs per marketed drug could be more than halved to $103 million (“NGS and AI” in the table below), and new predictive neural network AlphaFold-based algorithms could halve those costs at $52 million.

Assumptions: 15% discount rate in all phases except registration, which has a 3% discount rate, estimated peak sales of $1 billion for non-curative therapies, net margin of 70 %, 20% tax. Forecasts are inherently limited and unreliable.

Source: ARK Investment Management LLC, 2022

Our research suggests that neural network-based algorithms could reduce R&D costs, increase the value of clinical trial assets, and increase the likelihood of clinical trial phase transition. For example, enabling technologies could shorten the average time spent on preclinical experimentation. Historically, the duration of preclinical testing, from discovery to phase 1, has averaged four years. Based on our model assumptions, this number drops to three years and, with neural network-based algorithms, to two years, as shown below. Across the entire pipeline – from discovery to registration of a therapeutic drug – the technology could improve efficiency, reduce costs and eliminate 3.5 years of research and development time.

Assumptions: 15% discount rate in all phases, except for registration, which has a 3% discount rate; Maximum sales estimated at $1 billion for non-curative therapies; 70% net margin; 20% tax. Forecasts are inherently limited and unreliable.

Source: ARK Investment Management LLC, 2022

In our opinion, AlphaFold or similar technologies could increase the net present value (NPV) of a discovery asset from $30 million to approximately $170 million, as shown below. The old drug developers might have spent $120,000 and a year of experimentation to figure out a new protein structure. Today, this information is accessible in databases, and globally, which should increase the pace and success rate of experimentation at an early stage, implying both that the net present value of an early stage asset should be higher and that more of these assets will enter the pipeline. In other words, the cost savings are unlikely to reduce overall R&D expenditures for early-stage experimentation, but rather should increase the number of drug candidates entering the pipeline.

Assumptions: 15% discount rate in all phases, except for registration, which has a 3% discount rate; Maximum sales estimated at $1 billion for non-curative therapies; 70% net margin, 20% taxes. Forecasts are inherently limited and unreliable.

Source: ARK Investment Management LLC, 2022

The mass adoption and scaling of NGS, AI, neural network-based algorithms, and healing therapies could narrow the gap between the net present values ​​of preclinical and clinical assets. In other words, we think the current early-stage pipelines, which growth stock investors often overlook, will be far more valuable than many realize.

Footnote:

• 1 https://alphafold.ebi.ac.uk/entry/P02088?utm_campaign=Sunday%20Newsletter&utm_medium=email&_hsmi=145809075&_hsenc=p2ANqtz-_tEuJqOJK3tW6xxkC-F2eOQDg3OzSPywVI1AfEeCacnTxM__gADzGG1tqjI5XGGXKxRa29buLtloed6YaKWUf0fssN-w&utm_content=145809075&utm_source=hs_email

  The 3D structure of hemoglobin (a well-known protein in red blood cells that transports oxygen through the body) is characterized in the AlphaFold2 database, as shown in the link above.

Warning:

©2021-2026, ARK Investment Management LLC (“ARK” ® “ARK Invest”). All content is original and was researched and produced by ARK, unless otherwise stated. No part of ARK’s original content may be reproduced in any form, or referred to in any other publication, without the express written permission of ARK. The Content is for informational and educational purposes only and should not be construed as investment advice or an offer or solicitation regarding products or services to anyone who is prohibited from receiving such information. under the laws applicable to their place of citizenship, domicile or residence. Some of the statements contained on this website may be statements of future expectations and other forward-looking statements based on ARK’s current opinions and assumptions, and involve known and unknown risks and uncertainties that could cause actual results, performance or events to differ materially from those expressed or implied by such statements. All content is subject to change without notice. All statements made regarding companies or securities or other financial information on this site or any site linked to ARK are strictly beliefs and views held by ARK or the third party making such statement and are not endorsements. by ARK of a company or title or recommendations. by ARK to buy, sell or hold securities. The content presented does not constitute investment advice, should not be used as the basis for any investment decision, and does not purport to provide legal, tax or accounting advice. Remember that there are inherent risks in investing in the markets and that your investments may be worth more or less than your original investment when redeemed. There is no guarantee that ARK’s objectives will be achieved. Further, there can be no assurance that the investment strategies, methods, sectors or programs herein have been or will prove profitable, or that any investment recommendations or decisions made by us in the future will be profitable for any investor or customer. Professional money management is not suitable for all investors. For complete information, please see our Terms and Conditions page. The Advisor did not pay any fees at the granting of the Awards for the right to promote the Advisor’s receipt of the Awards and the Advisor was not required to be a member of any organization to be eligible for the Awards. For full reward disclosure, please see our Terms and Conditions page. Past performance is not indicative of future performance.

Original post

Editor’s note: The summary bullet points for this article were chosen by the Seeking Alpha editors.