AI Identifies Preclinical Cancer Compounds With Potential to Reach the Brain

1. Rakovina Therapeutics Inc. has a consulting relationship with Street Smart an affiliate of Streetwise Reports. Street Smart Clients pay a monthly consulting fee between US$8,000 and US$20,000.
2. As of the date of this article, officers, contractors, shareholders, and/or employees of Streetwise Reports LLC (including members of their household) own securities of  Rakovina Therapeutics Inc.
3. James Guttman wrote this article for Streetwise Reports LLC and provides services to Streetwise Reports as an employee. 
4.  This article does not constitute investment advice and is not a solicitation for any investment. Streetwise Reports does not render general or specific investment advice and the information on Streetwise Reports should not be considered a recommendation to buy or sell any security. Each reader is encouraged to consult with his or her personal financial adviser and perform their own comprehensive investment research. By opening this page, each reader accepts and agrees to Streetwise Reports' terms of use and full legal disclaimer. Streetwise Reports does not endorse or recommend the business, products, services or securities of any company. 
5. This article does not constitute medical advice. Officers, employees and contributors to Streetwise Reports are not licensed medical professionals. Readers should always contact their healthcare professionals for medical advice.

For additional disclosures, please click here.

1. Ownership and Share Structure Information

The information listed above was updated on the date this article was published and was compiled from information from the company and various other data providers.

Rakovina Therapeutics Inc. (RKV:TSX.V) has presented new findings from its AI-enabled drug discovery platform at the 2025 Society for Neuro-Oncology (SNO) Annual Meeting, held November 19–23 in Honolulu, Hawaii. The company's second abstract at the event, developed in collaboration with the Vancouver Prostate Centre and the University of British Columbia, focused on the discovery and development of novel PARP1-selective inhibitors designed to penetrate the central nervous system (CNS).

The presentation detailed Rakovina's use of Deep Docking and generative artificial intelligence (AI) techniques to virtually screen chemical libraries for compounds predicted to inhibit PARP1 selectively, an enzyme involved in repairing damaged DNA, and demonstrate properties consistent with CNS penetration. According to the company, hundreds of compounds have been synthesized and evaluated, with a subset showing both PARP1-selective activity and promising in vitro pharmacokinetic profiles. These early-stage results are being used to inform further optimization and compound selection.

"The data generated to date provide early insight into our AI-driven discovery platform and its ability to prioritize compounds with the features we are seeking, including PARP1 selectivity and properties supportive of CNS penetration," said Prof. Mads Daugaard, President of Rakovina Therapeutics, in a company news release. "These results demonstrate timely progress of our PARP1-selective inhibitor program and validate our iterative AI approach."

Diving Into AI-Enabled Oncology Research

On October 15, Google DeepMind researchers working with Yale University announced that their 27 billion parameter model, C2S-Scale, had helped identify a novel drug interaction capable of converting immunologically "cold" tumors into "hot" ones, making them more visible to the immune system. The report stated, "C2S-Scale had successfully identified a novel, interferon-conditional amplifier, revealing a new potential pathway to make 'cold' tumors 'hot.'" The team further noted that this prediction was later validated in human neuroendocrine cell models, where the AI-guided combination treatment resulted in a 50% increase in antigen presentation. "This result also provides a blueprint for a new kind of biological discovery," the researchers wrote.

By early November, progress in lung cancer applications was also documented. On November 3, Northwestern University's Dr. Mohamed Abazeed introduced iSeg, an AI-based segmentation tool designed to help radiation oncologists more accurately target tumors. "It's about shaping care to match the needs of each patient," Abazeed said. His team's efforts, including prior work on the iGray platform and ongoing clinical trials, aimed to make treatment "individualized, precise, and effective." He added that the broader objective was "a suite of individualized tools that seamlessly integrate into clinical workflows to make radiation oncology faster, safer, and more effective."

The trend toward personalized treatment continued with work out of University College London. In a study published on November 18, UCL researchers applied AI to standard rectal cancer pathology slides to analyze immune response patterns. "We found that AI can pick up important immune signals from these slides," said Dr. Charles-Antoine Collins-Fekete. The research highlighted how AI tools could help identify tumor immune environments and potentially guide treatment options based on image-derived immune signatures. Dr. Zhuoyan Shen of UCL added, "By combining immune cell data with genetic information, we can get a clearer picture of how each patient's cancer will behave before and after treatment."

Endorsements Highlight AI-Driven Preclinical Strength

According to a November 7 report from Dr. Douglas Loe of Leede Financial Inc., Rakovina Therapeutics' AI-derived ATR inhibitors outperformed existing clinical-stage drugs in preclinical testing. "Preclinical data showed that all three [Rakovina] compounds needed significantly lower drug concentrations to block ATR activity versus existing, clinical-stage drugs," Loe wrote. The compounds — referred to as Compound A, B, and C — achieved ATR enzyme inhibition at concentrations of 119 nanomolars, 167 nanomolars, and 175 nanomolars, respectively. Each figure was substantially below that of comparator drugs, which ranged from 420 to 4,680 nanomolars.

Loe also emphasized that Rakovina's compounds demonstrated dual-targeting activity against ATR and mTOR kinases, which could be relevant for further anti-cancer applications. Of particular note was the ability of these compounds to penetrate the central nervous system (CNS), a challenge for many existing ATR inhibitors. "This is a significant advancement as no other ATR inhibitor in clinical development has demonstrated meaningful brain exposure," Loe stated. Compound B, for example, achieved brain concentrations equivalent to 51.4% of plasma levels following a 5 mg/kg dose.

The analyst further noted the broader implications of Rakovina's discovery model. "Rakovina uses two externally validated AI platforms, one being Variational AI's Enki. The other is the Deep Docking platform out of UBC, which produced compounds licensed to Roche Holding AG for US$140M," Loe reported. He pointed to the validation of the Enki platform through a separate Merck partnership involving milestone-based payments of up to US$349 million as evidence of the technology's standing within the AI-driven drug discovery sector.

AI Meets Oncology: Advancing a New Class of Brain-Penetrant Cancer Therapies

Rakovina's AI-discovered PARP1 inhibitor program, known as kt-2000AI, represents a focused effort to develop CNS-penetrant, PARP1-selective small molecules. According to the company's Q4 2025 investor presentation, the initial screening phase involved 1.6 billion compounds, from which 389 were synthesized and tested. Nine potential candidates have been identified to date, and an additional 30 compounds are currently undergoing assessment.

The kt-2000AI program is part of a broader pipeline that includes the kt-5000AI ATR inhibitor series and kt-3283, a PARP/HDAC dual-function candidate, all aimed at targeting solid tumors with DDR deficiencies. Upcoming milestones for the PARP1 program include the synthesis of lead compounds for additional preclinical studies and pre-IND (Investigational New Drug) preparation. 

Rakovina's AI-enabled approach is built on well-validated platforms such as Deep Docking and Enki, which allow for accelerated identification of drug candidates with optimized biological and pharmacological characteristics. The company retains ownership of all drug candidates generated through these collaborations.

With increasing interest from pharmaceutical partners in AI-derived oncology candidates, Rakovina continues to engage in discussions and aims to advance its programs through internal development and strategic collaboration. 

Ownership and Share Structure ¹

Edison Oncology owns 12% of Rakovina Therapeutics.  

Management and Reporting Insiders own 4%, with the top two being Jeffrey Bacha and Alfredo De Lucrezia. 

The rest is friends/family and retail.   

Rakovina Therapeutics recently announced a 10:1 share consolidation, effective on  June 24, 2025.

This means that for every 10 pre-consolidation common shares, shareholders now hold one post-consolidation common share.  

Rakovina Therapeutics Inc. has approximately 21.15 million shares outstanding. Its market capitalization is approximately CA$6.34 million. Over the past 52 weeks, its stock price ranged between approximately CA$0.40 and CA$2.30.