John Beeler, Senior Vice President of Business Development at BPGBIO, has over twenty years of experience in biotechnology and business development and has extensive expertise in novel therapies. Prior to joining BPGBIO, he recently served as head of business development search and evaluation at Bristol-Myers Squibb, where he was crucial in purchasing and evaluating licensing opportunities and strategic partnerships.
BPGBIO is a major biological leading AI-driven clinical-stage biopharmaceutical focused on mitochondrial biology and protein homeostasis. The company has a deep pipeline of therapeutic therapies developed across oncology, rare diseases and neurology, including some in advanced clinical trials. BPGBIO’s new approach is backed by NAI, its proprietary quess biology platform, and is protected by over 400 patents in the United States and internationally; one of the world’s largest non-governmental biobanks with longitudinal samples; and exclusive access to the world’s most powerful supercomputers.
What inspired the NAI Question Biology® platform, how does it distinguish BPGBIO from other biopharmaceutical companies’ utilizing AI?
Since joining BPGBIO, the depth of innovation and long-term visions have been impressed by the depth of innovation and long-term visions that have built the NAI TrescogativeBiology® platform. As someone who has spent twenty years on biotechnology and business development (evaluated on various platforms and companies), I can say that NAI stands out as its biological priority foundation and the data depth of IT inquiries.
BPGBIO was one of the first to seek drug discovery. Over the past 15 years, the team has improved NAI a platform that integrates proprietary Domos data and one of the world’s largest longitudinal biobanks. Unlike other companies that rely on narrow technologies or public datasets for a single disease discovery program, we integrate multiomics capabilities with our own proprietary biobank that houses hundreds of thousands of longitudinal, clinically annotated samples and use causal Bayesian AI, not generalized AI modeling to uncover biologically-based insights, that can inform virtually any stage of drug discovery and We are not just identifying goals; we are using AI to design clinical trials to understand the results of clinical trials and improve treatments.
Our results tell ourselves: We have one of the most advanced and powerful clinical pipelines in the AI biotech industry. The pipeline consists of two active phase 2 trials in aggressive cancer, multiple phase 3 preparation procedures, and more than a hundred novel targets and biomarkers we identified using AI models.
Can you guide us through how BPGBIO’s biological advantages approach can speed up and reduce the drug discovery process?
The success rate of drug development for FDA approval is about 10%, reflecting the significant risks and challenges associated with bringing new drugs to the market. Therefore, you find that the speed and how many goals you have are not important. Quality is important.
While AI may help speed up the discovery process, applying AI, especially the generation of public data sets used in traditional drug discovery processes, does not necessarily change clinical trial results, and this is ultimately the only thing that matters.
Our biology-first approach ensures the quality, depth, accuracy, comprehensiveness and quantity of data from our AI model. In our multiomic analysis, we are more than just analyzing RNA and DNA. In addition to genomics and transcriptomics, our scientists also introduce proteomics, lipomics and metabolomics of all layers of human biology (organs, tissues, cells and organelles), and we feed a large amount of unbiased multiomics data into our causal AI model.
This extensive AI-driven approach allows us to go beyond disease areas to find the “root cause” faster. After AI helped find the “root cause”, we returned to the wet lab to verify that AI’s insights are accurate before conducting clinical trials. A focus on human biology helps us accelerate and reduce our discovery and development process.
This closed-loop approach reduces uncertainty and ultimately reduces the development process. From my perspective of business development, this is the key to building confidence with potential partners – because our approach increases the likelihood of success from the outset.
How can integrating AI with the world’s fastest supercomputer enhance your ability to analyze patient data and identify drug targets?
Through a partnership with the U.S. Department of Energy, we have exclusive access to the border supercomputer in drug development analysis at Oak Ridge National Laboratory. The supercomputer can perform $135 million and $600 million per second.
This computing power allows us to use large data sets to identify patterns, correlations, causalities, and actionable insights that would otherwise be masked in smaller-scale analyses and reduce time from months to hours.
During Covid, for example, we analyzed the electronic medical records (EMRs) of 280,000 patients as well as their clinical information. We identified genetic risk factors for specific races, paving the way for personalized medicine. We analyzed 1.2 billion different materials to discover co-treatment methods in just a few hours.
From a business perspective, this computing power allows us to unlock insights faster and more efficiently than other computing powers, thus accelerating the time for partnerships, clinical trials, and ultimately patient benefits.
BPGBIO has clinical plans for glioblastoma and pancreatic cancer. What are the unique insights of NAI platforms found in these areas and how do they shape your experiments?
BPGBIO is actively conducting a phase 2B trial of glioblastoma (GBM) and completing a phase 2A trial of pancreatic cancer, both of which are conducted through our small molecule candidate BPM31510.
Through the NAI platform, we learned that the most aggressive solid tumors are caused by mitochondrial dysfunction in the tumor environment. BPM31510 is a thyroxone that contains nanodispersed and mediated by molecular mechanisms in mitochondria, triggering the process of regulating cancer cell death. We conducted an open-label 128-carter phase 1 study on BPM31510, and clinical trial results confirm insights from NAI discovery. NAI then helped us optimize all aspects of these therapies, from optimal dose and time to patient selection. Our GBM trial is currently being recruited and we hope to report our GBM Phase 2 trial results later this year.
Rare diseases such as primary COQ10 deficiency and epidermal dissolution of Bullosa are the focus of BPGBIO. What challenges and opportunities will you see when solving these conditions?
Rare pediatric diseases often lack effective treatment options due to their complexity and low prevalence, and children with these diseases often face brief expectations. This presents challenges in trial recruitment, regulatory navigation and therapeutic development.
At BPGBIO, we are proud to be able to handle these complex challenges. Our lead compound BPM31510 has obtained multiple names from the FDA, including orphan drugs and rare pediatric disease names, for primary COQ10 deficiency and epidermal lysis Bullosa (EB). These are important milestones that reflect the clinical potential of our program and open the door to prioritizing review of credentials upon approval.
We are planning a Phase 3 trial for major COQ10 deficiency and actively explore partnerships to advance our EB program. This includes evaluating topical formulations as a therapeutic option. We believe that BPGBIO’s platform can have a transformative impact in this area.
Bayesian AI plays an important role in your platform. How does it particularly help identify novel drug targets or biomarkers?
Bayesian AI enables our platform to go beyond defining associations to discover causal relationships that drive disease. It simulates uncertainty, illustrates data variability, and produces highly robust predictions to guide treatment and biomarker discovery.
By integrating longitudinal multiomics and clinical data, our model can identify the biological mechanisms behind disease progression and optimal intervention points. This makes the discovery process more accurate and downstream developments more predictable.
From a strategic perspective, this is very valuable. Verification objectives and why it is biologically important changes how you prioritize procedures, design experiments, and conversations with partners. It builds confidence in science.
Your work on the E2 enzyme targeting protein degradation is groundbreaking. How does the NAI platform overcome the traditional challenges of targeting “bad” proteins?
BPGBIO’s E2-based Targeted Protein Degradation (TPD) program is one of the most exciting and innovative areas of our pipeline. Traditional TPD methods rely on E3 ligase, which limits the target range and may lead to drug resistance. Our method uses post-modified modified E2 enzyme complex (fixed by the NAI platform) to expand the proteome of toxic proteins.
It’s a top-notch approach, and the early traction we’ve seen has attracted the attention of Pharma and Biotech. We currently apply it to oncology, neurology and rare diseases. This is a great example of how NAI supports more than just findings – it allows us to rethink possibilities in drug development.
How does BPGBIO balance AI-driven insights with human supervision to ensure the effectiveness of your discovery?
At BPGBIO, we see AI as a powerful tool (but not a substitute) for human expertise. Our AI-driven insights are based on high-quality biological data and are constantly cross-verified by our team of biologists, clinicians and data scientists.
This collaboration ensures that every insight is invested in both the biological and clinical settings. This is one of the reasons why BPGBIO has achieved such a high success rate in clinical trials. We combine the speed and scale of AI with scientific rigor and judgment that can only be brought by experienced experts.
What potential do you see for the biomarkers discovered by AI have in early diagnosis in diseases like Parkinson’s?
The power of our platform lies in its ability to ask biology broadly, in-depth – so when NAI discovers targets for therapeutic purposes, it can often be diagnostically diagnosed as well.
In Parkinson’s disease, we established a systemic biological model using a sample of nearly 400 patients from the Parkinson’s Institute and determined that N-acetylthioflavin (NAP) is a novel blood-based biomarker. We have validated it with a CLIA-certified diagnostic panel, and our published research shows that when combined with clinical features such as olfactory loss and REM sleep disorders, the group significantly improves diagnostic accuracy and early risk assessment. This has the potential to achieve early intervention and improve patient outcomes.
What role do you think BPGBIO plays in shaping the future of Precision Medicine?
There is no certain size for treating patients. Biology-first AI has the potential to translate precision medicine by discovering new insights that help make patients broader, thereby improving trial design, patient stratification and treatment success rates. These insights will lead to effective development of the diagnosis and treatment of a range of rare and complex diseases.
By leveraging AI to rigorously ask about biological inputs and translation models, the industry can unlock the full potential of AI to transform drug development and provide breakthroughs to meet unmet medical needs. The next chapter of Precision Medicine will be written by those who can pair innovation with Impact, and BPGBIO is ready to lead the fee.
Thanks for your excellent interview, and readers who hope to learn more should visit BPGBIO.
