MetaphysicalCells

MetaphysicalCells

Share this post

MetaphysicalCells
MetaphysicalCells
AI For Drug Discovery: Weekly News 💟

AI For Drug Discovery: Weekly News 💟

Marina T Alamanou's avatar
Marina T Alamanou
Jul 08, 2025
∙ Paid
3

Share this post

MetaphysicalCells
MetaphysicalCells
AI For Drug Discovery: Weekly News 💟
Share
👾AI For Drug Discovery: Weekly News👾

👾 ImmunoPrecise’s LENSai Platform Maps 🆕 Proteins with Crystal-Clear Accuracy

New benchmark confirms LENSai’s ability to accurately predict binding on 1️⃣7️⃣ previously unseen antibody-antigen complexes, achieving near-crystallography precision without prior training data.

ImmunoPrecise Antibodies Ltd. (NASDAQ: IPA) announced on July 03, 2025 a 🆕 validation study supporting the generalizability of its proprietary epitope mapping platform, LENSai, powered by IPA’s patented HYFT® technology (AI Drug Discovery Breakthrough: ImmunoPrecise LENSai Platform Maps New Proteins with Crystal-Clear Accuracy).

LENSai Epitope Mapping uses AI to pinpoint where antibodies are most likely to attach to disease-related proteins. Unlike traditional methods that take months and require lab work, LENSai delivers results in hours, by using just the digital sequences, and cutting timeliness as well as eliminating the need to produce expensive materials.

In the 🆕 benchmark study, LENSai was tested on 3️⃣0️⃣ antibody-protein pairs, 1️⃣7️⃣ of which the platform had never seen before. Despite having no prior exposure to these molecules, LENSai achieved prediction scores nearly identical to those from its original training data. This score, known as AUC (Area Under the Curve), is a widely accepted measure of accuracy in computational biology. The consistent performance on entirely new, unseen complexes confirms that LENSai’s AI can reliably analyze and predict antibody binding - even for molecules outside its training set.

💬 “LENSai accurately mapped antibody binding sites on entirely new antibody - protein complexes-none of which were used in training. Not the antibodies. Not the targets. Not the complexes. And the predictions aligned with wet-lab results. This is a major breakthrough in generalizing AI for therapeutic discovery, made possible by our proprietary technology, which captures functional meaning instead of memorizing shapes. It shows that AI doesn’t always need massive data to be powerful and accurate - it just needs the right kind”

said Dr. Jennifer Bath, CEO of ImmunoPrecise.

Moreover on June 12, 2025, ImmunoPrecise Antibodies announced compelling in vitro 🧫 results demonstrating that its AI-designed GLP-1 receptor agonist (GLP-1RA) peptide sequences achieved comparable or superior receptor activation to Semaglutide, a benchmark GLP-1 therapy and one of the most commercially successful drugs in the world. The in vitro analysis was conducted by an independent third party, further strengthening the objectivity and reliability of the findings (AI-Designed GLP-1 Peptides from ImmunoPrecise Antibodies Surpass Semaglutide in Receptor Activation Studies).

The results validate the power 🚀 of IPA’s LENSai™ platform and its proprietary HYFT™ technology, which enables first-principles-based in silico peptide discovery and optimization. 5️⃣ rationally engineered peptide sequences—AI-optimized for improved stability and peptidase resistance—were tested against benchmark GLP-1 analogs in receptor activation assays, and 2️⃣ lead candidates outperformed or matched Semaglutide under controlled assay conditions.

IPA (1983, Canada) is a progressive, scientific Contract Research Organization (CRO) that represents a HUB of biotherapeutic intelligence that includes a hybrid of experts and technologies. They provide highly specialized full-continuum therapeutic antibody discovery, development, and out-licensing services (Talem)—with advanced omics and complex intelligence technology (LENSᵃⁱ) that provide greater efficiency and accuracy than ever before.

  • 🖇️ LENSai™ Integrated Intelligence Technology powered by HYFTs® (Universal FingerprintsTM)—that seamlessly integrates massive data from diverse data sources to enhance LLMs and accelerate antibody discovery—was developed by BioStrand, founded in Belgium in 2019, and is an independently operating subsidiary of IPA at the intersection of biotech discovery, biotherapeutics and AI. For more:

    BioStrand: The Ultimate Convenience in Multi-Omics Data Search and Analysis 🔝

    BioStrand: The Ultimate Convenience in Multi-Omics Data Search and Analysis 🔝

    Marina T Alamanou
    ·
    September 5, 2024
    Read full story
  • 🖇️ Talem Therapeutics LLC is also a subsidiary of IPA and is focused on the discovery and development of next-generation, human, monoclonal, therapeutic antibodies. For more about Talem’s pipeline:

    AI-powered drug discovery: update (X)

    AI-powered drug discovery: update (X)

    Marina T Alamanou
    ·
    October 3, 2024
    Read full story
  • For more about IPA:

    Un-locking 🔐 Data to Transform Biology (part III)

    Un-locking 🔐 Data to Transform Biology (part III)

    Marina T Alamanou
    ·
    September 19, 2024
    Read full story

MetaphysicalCells is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2025 Marina T Alamanou
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture

Share