Streamlining Oncology Research with AI-Powered In Vivo Study Design: ModernVivo at AACR

The American Association for Cancer Research (AACR) was established over a century ago with the mission of advancing scientific discoveries to improve cancer treatment through education, funding, and research. As one of the largest organizations dedicated to cancer research, the AACR plays a vital role in expanding our understanding of cancer and supporting high-quality studies to address its severity and impact. Through funding opportunities, science policy initiatives, and advocacy efforts, the AACR has significantly influenced how we combat cancer1.

AACR 2025

One of the most significant events for global cancer researchers is the AACR Annual Meeting, taking place this year from April 25-30 at the McCormick Place Convention Center in Chicago. This conference serves as a vital platform for collaboration and innovation in oncology research, where attendees reconnect with colleagues, establish new partnerships, and explore the latest advancements in the field. The AACR Annual Meeting fosters knowledge exchange and collaboration to drive progress in cancer research by bringing together researchers, clinicians, and industry leaders.

Meet ModernVivo

ModernVivo is excited to participate in this year’s conference (booth 3839) to share how our AI-driven technology can help simplify and enhance in vivo studies, which remain a critical yet challenging aspect of oncology research. To achieve the goals set out by the AACR, we believe that scientists must leverage all available advantages, such as automated and comprehensive literature searches, to optimize their experimental design. Without embracing new technologies, researchers will likely suffer from the same challenges that have plagued in vivo research for decades.

Current Challenges in Oncology Preclinical Research

Preclinical oncology research faces numerous challenges that hinder discoveries and delay the development of therapies that could improve patient outcomes. A central barrier is the lack of translation from in vivo studies to the clinic. For instance, roughly 95% of drugs entering clinical trials fail to gain approval2. This highlights the disconnect between what appears promising and effective in preclinical studies and what actually translates into human benefit.

Study Timelines

Clinical trials are inherently lengthy and costly3. However, prolonged preclinical study timelines can create unnecessary delays for researchers striving to identify and validate potential therapeutics. A key challenge arises during the experimental design phase, where researchers must navigate extensive literature datasets to determine optimal in vivo study parameters. Traditional methods often lack thoroughness, forcing researchers to spend months developing protocols that may still be suboptimal—ultimately increasing the risk of failure.

Costs

The complexity and error-prone nature of preclinical research means that researchers face mounting costs when performing in vivo work. Each repeated experiment significantly increases expenses and can jeopardize entire projects, leading to unmet commitments to funders and stakeholders. Relying solely on manual literature reviews or outdated protocols may cause researchers to overlook existing solutions that could meet their needs and eliminate the high costs of creating new models from scratch or outsourcing.

Low Predictive Accuracy

A fundamental issue with current methods for designing and conducting in vivo studies is their inability to consistently translate into successful clinical trials2. This limitation amplifies existing challenges, resulting in higher costs, wasted resources, and prolonged study timelines.

When these issues compound, they significantly hinder research efficiency and reduce clinical trial success rates. Ultimately, these setbacks delay the development of life-saving cancer therapies.

How AI-Powered In Vivo Study Design Can Streamline Oncology Research

AI is changing the landscape of biomedical research and clinical practice4. However, researchers have yet to reap the full benefits of AI when designing preclinical in vivo studies.

AI-Driven In Vivo Experimental Design

In vivo experimental design benefits enormously from AI-driven solutions. A key advantage is the ability to instantly scan multiple literature databases, providing researchers with comprehensive insights from the entire body of biomedical literature.

This approach ensures that research strategies are based on a complete dataset, preventing researchers from spending months designing experiments using only a limited subset of available information.

Additionally, AI allows researchers to move beyond outdated or legacy protocols by providing quick access to research methodologies tailored to their needs. This includes the latest disease models and crucial details that might otherwise be hidden in lengthy materials sections or buried deep within extensive literature databases.

These capabilities have direct implications for the most pressing challenges in oncology research:

  • Shortened Timelines: Faster interrogation of databases reduces planning timescales from months to moments, allowing researchers to press ahead with confidence.
  • Reduced Cost: Faster timescales mean reduced expenses in the preparation stages of research. Furthermore, researchers avoid costs associated with optimization steps and repeat experiments by identifying the best parameters the first time around.
  • Improved Design: By drawing from more extensive sets of data and information, researchers ultimately generate improved protocols that generate higher quality and more reliable data.
  • Improved Translational Success: Refining and optimizing preclinical studies by incorporating existing research and recent advancements allows researchers to produce more clinically relevant and translatable results. This is invaluable for bridging the gap between preclinical promise and clinical trial success.

Tackling the Complexity of Pancreatic Cancer

Researchers are already leveraging ModernVivo’s AI-driven platform. By enabling rapid literature reviews to identify the most suitable models, we helped pancreatic cancer researchers reduce their experimental development time by 75%, a crucial advantage for tackling this highly complex and medically urgent disease5.

Read the full case study.

'People Sitting on a Chair Listening to a Man Speaking' by Pavel Danilyuk on Pexels

Visit ModernVivo’s Booth at AACR to Streamline Your Oncology Preclinical Research

ModernVivo will present its AI-driven platform at Booth 3839 during AACR 2025, offering live demonstrations of our in vivo design tools!

We’re excited to connect with researchers leading the development of next-generation cancer therapeutics and to build new partnerships in the pursuit of cancer cures.

Visit the ModernVivo team at Booth 3839 to explore how AI-driven solutions can streamline and improve your in vivo study design.

References

1. Home. American Association for Cancer Research (AACR). Accessed March 10, 2025. https://www.aacr.org/

2. Seyhan AA. Lost in translation: the valley of death across preclinical and clinical divide – identification of problems and overcoming obstacles. Transl Med Commun. 2019;4(1). doi:10.1186/s41231-019-0050-7

3. Sertkaya A, Beleche T, Jessup A, Sommers BD. Costs of Drug Development and Research and Development Intensity in the US, 2000-2018. JAMA Netw Open. 2024;7(6):e2415445. doi:10.1001/jamanetworkopen.2024.15445

4. Zhang K, Yang X, Wang Y, et al. Artificial intelligence in drug development. Nat Med. 2025;31(1):45-59. doi:10.1038/s41591-024-03434-4

5. Halbrook CJ, Lyssiotis CA, Pasca di Magliano M, Maitra A. Pancreatic cancer: Advances and challenges. Cell. 2023;186(8):1729-1754. doi:10.1016/j.cell.2023.02.014

AI Disclosure: Some of this content was generated with assistance from AI tools for copywriting.

Want to Connect?
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.