Boehringer Ingelheim & IBM Collaborate on Antibody Discovery Platform

The collaboration involves Boehringer utilising an IBM-developed, pre-trained AI model, which will undergo further refinement using additional proprietary data from Boehringer.

Boehringer Ingelheim and IBM have strategically collaborated, utilising IBM's foundation model technologies to expedite the discovery of novel candidate antibodies. This partnership aims to pave the way for developing highly efficient therapeutics.

Speaking on the collaboration, Andrew Nixon, global head of Biotherapeutics Discovery at Boehringer Ingelheim, said, "We are very excited to collaborate with the research team at IBM, who share our vision of making in silico biologic drug discovery a reality."

He anticipates that this collaboration will lead to an unprecedented platform for accelerated antibody discovery, enabling Boehringer to develop and deliver new treatments for patients with high unmet needs.

The collaboration involves Boehringer utilising an IBM-developed, pre-trained AI model, which will undergo further refinement using additional proprietary data from Boehringer.

Alessandro Curioni, vice president of Accelerated Discovery at IBM Research, highlighted IBM's role in extending the impact of generative AI models beyond language domains. He stated, "We are thrilled to now bring IBM's multimodal foundation model technologies to Boehringer, a leader in the development and manufacturing of antibody-based therapies, to help accelerate the pace at which Boehringer can create new therapeutics."

Therapeutic antibodies play a central role in treating various diseases, including cancer, autoimmune disorders, and infectious diseases. Despite technological advancements, the discovery and development of therapeutic antibodies covering diverse epitopes remain complex and time-consuming.

Boehringer and IBM researchers aim to streamline the antibody discovery process through in-silico methods. The collaboration aims to accelerate the generation of new human antibody sequences by utilising information on sequence, structure, and molecular profiles of disease-relevant targets, along with success criteria for antibody molecules.

IBM's foundation model technologies will play a crucial role in enhancing the speed and efficiency of antibody discovery, improving the quality of predicted candidates.

The process involves using IBM's foundation model technologies to design antibody candidates for defined targets, followed by AI-enhanced simulation screening to select and refine the best binders for the target.

Boehringer Ingelheim will then produce these candidates in mini-scales for experimental assessment. The results from laboratory experiments will feed back into the in-silico methods, contributing to continuous improvement.

Boehringer's collaboration with IBM aligns with its broader strategy of building a leading digital ecosystem, collaborating with academic and industry partners to accelerate drug discovery and development.

IBM, a global leader in hybrid cloud and AI, continues its efforts to harness generative AI and foundation models for accelerating the discovery and creation of new biologics and small molecules. Earlier this year, the company's generative AI model efficiently predicted the physicochemical properties of drug-like small molecules.

IBM's biomedical foundation model technologies leverage diverse publicly available datasets, including protein-protein and drug-target interactions. These pre-trained models are then fine-tuned using specific proprietary data from IBM's partners, resulting in newly designed proteins and small molecules with desired properties.

As a research-driven biopharmaceutical company, Boehringer Ingelheim is committed to developing breakthrough therapies that address high unmet medical needs and transform lives.