ImmunoPrecise Antibodies Ltd. (IPA) (NASDAQ: IPA) a leader in AI-driven biotherapeutics, is pleased to announce today new benchmarking results that validate the accuracy and utility of its in silico epitope mapping application, part of the LENS^ai™ platform, with a direct comparison to gold-standard wet-lab methods.

The results represent a notable advancement in computational biology, particularly in the field of antibody discovery, where high failure rates and costly, time-intensive experiments remain common industry challenges. LENS^ai’s AI-powered platform was able to match the performance of x-ray crystallography—the industry’s most precise but slowest and most expensive method—using sequence data alone.

"In an industry where over 95% of drug candidates fail before reaching the clinic, accelerating decisions earlier in the discovery pipeline isn’t a luxury—it’s a necessity," said Dr. Jennifer Bath, CEO of IPA. "With LENS^ai, we’re demonstrating that AI is designed to deliver accurate, scalable, and human-relevant biological predictions that were previously only accessible through months of experimental work."

In the benchmarking study, LENS^ai’s in silico epitope mapping application was tested across five known antibody-antigen pairs and against multiple experimental techniques, including HDX-MS, alanine scanning, and x-ray crystallography. The AI system produced predictive scores (AUC 0.79–0.89) comparable to or exceeding those achieved by leading wet-lab methods, while reducing turnaround time from weeks to hours.

Epitope mapping is a cornerstone of antibody development, informing everything from IP strategy to candidate selection. Traditionally, this requires expensive, time-consuming lab work using scarce protein samples. LENS^ai transforms this by delivering early-stage epitope insights from sequence alone, reducing both cost and risk.

This breakthrough aligns with growing regulatory and industry momentum around New Approach Methodologies (NAMs), including the FDA’s recent decision to phase out animal testing requirements for biologics. By eliminating the need for physical materials and enabling near–x-ray-level precision, LENS^ai advances ethical, scalable, and high-resolution approaches to biotherapeutic discovery

We view this achievement as a meaningful advancement that enhances the capabilities of drug discovery platforms" added Dr. Bath. "LENS^ai is now capable of providing pharma and biotech partners with validated, in silico answers to questions that once required months of wet-lab commitment."

This latest achievement marks a major step in the broader development of LENS^ai, IPA’s AI-driven discovery platform. Building on previous releases, including in silico antibody engineering, epitope prediction, and multi-omics integration, LENS^ai continues to demonstrate its ability to deliver high-resolution, scalable insights across key stages of biotherapeutic discovery. Today’s advancement in epitope mapping reflects the growing power of the platform we have been strategically building — connecting sequence-based precision, accelerated timelines, and deep scientific insight to transform the future of therapeutic development.

To read the full case study: LENSai Epitope Mapping Matches X-ray Crystallography

About ImmunoPrecise Antibodies Ltd.

ImmunoPrecise Antibodies Ltd. is a techbio company that leverages multi-omics modeling and complex artificial intelligence through a series of proprietary and patented technologies. The Company owns an integrated end-to-end suite of capabilities to support the discovery and development of therapeutic antibodies and is known for solving complex industry challenges. IPA has several subsidiaries in North America and Europe including entities such as Talem Therapeutics LLC, BioStrand BV, ImmunoPrecise Antibodies (Canada) Ltd. and ImmunoPrecise Antibodies (Europe) B.V. (collectively, the “IPA Family”).

Forward-Looking Statements

This press release contains forward-looking statements within the meaning of applicable United States and Canadian securities laws. Forward-looking statements often include words such as "expects," "intends," "anticipates," "believes," or variations thereof, or state that certain actions, events, or results "may," "will," "could," or "might" occur. These statements relate to, among other things, the anticipated benefits, scalability, and adoption of the LENSai platform, the broader application of HYFT®-based tools, the advancement of AI-native drug discovery methods, and the Company’s ability to maintain regulatory alignment and commercial traction.

Although the Company believes it has a reasonable basis for these forward-looking statements, they are based on current expectations, assumptions, and projections about future events that involve risks and uncertainties. Actual results may differ materially from those expressed or implied due to factors largely beyond the Company’s control, including but not limited to scientific and technological developments, regulatory changes and acceptance, competitive dynamics, IP protection, platform integration challenges, and financial and operational risks.

Forward-looking statements involve known and unknown risks, uncertainties, and other factors that may cause actual results, performance, or achievements to differ materially from those expressed or implied herein. Additional information on risks and uncertainties can be found in the Company’s Annual Report on Form 20-F, as amended, for the year ended April 30, 2024 (available on the Company’s SEDAR+ profile at www.sedarplus.ca and EDGAR profile at www.sec.gov/edgar). Should any of these risks materialize, actual results could vary significantly.

Readers are cautioned not to place undue reliance on forward-looking statements, which reflect the Company’s expectations only as of the date of this release. The Company assumes no obligation to update or revise these statements, except as required by law.

View source version on businesswire.com: https://www.businesswire.com/news/home/20250512248898/en/

LENSai’s AI-powered platform was able to match the performance of x-ray crystallography—the industry’s most precise but slowest and most expensive method—using sequence data alone