IBM, Boehringer partner on genAI, foundation models for therapeutic antibody research

The partners will leverage IBM’s foundation model technologies to help identify antibodies designed to target and neutralize various disease-causing agents or cells.
By Nathan Eddy
04:31 pm

Photo: sanjeri/Getty Images

German pharmaceutical company Boehringer Ingelheim and tech giant IBM are teaming up to harness the power of genAI and foundation models to further biologic drug discovery.

The partnership leverages IBM’s foundation model technologies, consisting of pre-trained, large-scale neural network architectures, to accelerate the identification of novel antibodies vital for therapeutic development.

These antibodies will be created with properties such as high specificity and affinity to address various diseases, including cancer, autoimmune disorders, infectious diseases and other medical conditions.

The initiative is underpinned by IBM’s advanced AI models, which aim to streamline the complex process of discovering therapeutic antibodies by determining molecular profile data of disease-specific targets to generate human antibody sequences through in-silico techniques.

IBM's foundation models rely on diverse publicly available datasets. The pretrained models are tailored to IBM’s partners' proprietary data, which facilitates the creation of custom-designed proteins and small molecules with desired properties.

Boehringer Ingelheim plans to produce and experimentally assess the refined antibody candidates in mini-scales, thereby validating the in-silico methods. The feedback loop is designed to enhance the efficiency and accuracy of antibody discovery techniques.

"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," Andrew Nixon, global head of biotherapeutics discovery at Boehringer Ingelheim, said in a statement. "I am confident that by joining forces with IBM scientists we will develop an unprecedented platform for accelerated antibody discovery which will enable Boehringer to develop and deliver new treatments for patients with high unmet need."


Earlier this year, IBM announced its AI model dubbed MoLFormer-XL, which aims to create new molecules from scratch or screen molecules for new applications.

Multinational pharmaceutical and biotech company Pfizer and AI-powered data company Tempus announced a multiyear strategic alliance to utilize AI and machine learning to inform drug discovery and development in oncology.

Fellow pharma giant AstraZeneca recently created a separate health tech company called Evinova, which will scale the company's already established digital technologies to enhance clinical trials.

The new company will use established digital technology solutions to streamline clinical trial design and delivery to reduce time and costs in medicine development. The venture will also dive into digital remote patient monitoring and therapeutics.

Startup Scala Biodesign, launched with $5.5 million in funding, uses AI-based computational solutions with modeling and data analysis of naturally occurring proteins to generate superior antibodies, enzymes and vaccine immunogens.