IPA’s Subsidiary, BioStrand, Provides an Update on LENSai

ImmunoPrecise Antibodies Ltd. (NASDAQ: IPA) (“ImmunoPrecise” or “IPA” or the “Company”), an AI-driven biotherapeutic research and technology company, announces that its subsidiary, BioStrand, has commercially launched its state-of-the-art Retrieval Augmented Generation (RAG)-based Large Language Model (LLM) platform. This pioneering platform seamlessly integrates with the Company’s patented HYFT technology and LENS^ai platform, signifying a noteworthy leap in the market as the Company aims at ensuring unparalleled accuracy, interpretability, and data-centric design in generative AI tools.

BioStrand's innovative approach to solving the Information Integration Dilemma (IID) has led to the development of a unique technology design that encapsulates and unifies diverse data modalities. This includes syntactical (sequence) data, 3D structural data, unstructured scientific information (e.g., scientific literature), all integrated within a singular framework, the LENS^ai Knowledge Graph. This breakthrough facilitates efficient data fusion, enabling a comprehensive analysis and interpretation of complex biological data.

Knowledge Graphs and LLMs have been recognized for their superior performance over conventional approaches in drug discovery. BioStrand’s integration of their proprietary and patented technologies with LLM synergizes strengths and addresses limitations, leading to a more efficient drug discovery platform. Biomedical LLMs, specifically those pre-trained on domain-specific vocabulary, outperform traditional tools in many biological data-based tasks. For instance, for the important step of identifying drug targets, AI-powered language models have demonstrated superiority over even the most state-of-the-art approaches. Furthermore, AI-enabled LLMs are now being utilized across the drug discovery and development pipeline for predicting drug-target interactions, molecular properties, and even potential drug withdrawals due to safety concerns.

Key Features of BioStrand’s LENS^ai Platform:

1. Holistic Integration of Data: LENS^ai offers a unified approach, linking sequence, structure, function, and literature information from the entire biosphere, providing a comprehensive view of life sciences data.
2. Expansive Knowledge Graph: At its core, LENS^ai boasts a knowledge graph that maps 25 billion relationships across 660 million data objects, ensuring a deep and interconnected understanding of genes, proteins, and biological pathways.
3. Neuro Symbolic Methodology: A fusion of deep learning and symbolic logic techniques, a branch of mathematics and philosophical logic that uses symbols to represent logical expressions, rather than using words. This approach harnesses the data-driven strengths of LLMs and the reasoning capabilities of symbolic systems, offering both adaptability from LLM methods and transparency from symbolic logic, ensuring comprehensive and interpretable outcomes for inquiries.
4. Retrieval-Augmented Generation (RAG) Integration: LENS^ai utilizes RAG to enhance the accuracy of the generated responses of LLMs. By integrating with the HYFTs technology as its proprietary knowledge graph, RAG ensures that the platform provides up-to-date and factual information, reducing the chances of generating inaccurate or "hallucinated" content. This synergy is designed to allow LENS^ai to deliver more informed and precise answers, bridging the gap between the vast generative capabilities of LLMs and the concrete data from HYFTs technology.
5. Traceability and Credibility: All results generated by LENS^ai can be referenced back to their original sources, ensuring authenticity and reliability in research outcomes.

"I am pleased to share that BioStrand's advanced AI platform has now integrated a Retrieval Augmented Generation plugin with a Large Language Model, marking a significant technological advancement. This integration, viewed through the prism of our patented HYFTs, not only simplifies complex information but opens a new dimension of predictive analysis. It notably enhances the platform's ability to delineate the structure, function, and potential applications of large molecules, representing a meaningful step towards more intuitive and insightful data analysis in the life sciences sector.