This cooperation allows Boehringer Ingelheim to use IBM's foundation model technologies to help discover new antibodies for developing better therapeutics. The collaboration was officially announced on November 28th.
Speaking on the joint venture, Alessandro Curioni, Vice President Accelerated Discovery at IBM Research expressed his enthusiasm. According to Alessandro Curioni, Vice President Accelerated Discovery, IBM Research, "IBM has been at the forefront of creating generative AI models that extend AI’s impact beyond the domain of language. 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."
Andrew Nixon, Global Head of Biotherapeutics Discovery at Boehringer Ingelheim also voiced his confidence about the partnership. According to Andrew Nixon, Global Head of Biotherapeutics Discovery at Boehringer Ingelheim, "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. 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."
In their official statement, IBM elaborated on their biomedical foundation model technologies being used in this venture. According to an article from IBM, the IBM biomedical foundation model technologies utilize diverse publicly available datasets, encompassing protein-protein interactions and drug-target interactions, for the development of pre-trained models. These pre-trained models undergo fine-tuning using proprietary data from IBM's partners, resulting in the creation of newly designed proteins and small molecules with specified properties. Antibodies play a pivotal role in treating various diseases such as cancer, autoimmune, and infectious diseases. Despite significant technological progress, the intricate and time-consuming process of discovering and developing therapeutic antibodies that target diverse epitopes poses a substantial challenge.
Meanwhile, an article from Microsoft also discussed the goals of this collaboration. According to an article from Microsoft, the goal of the collaboration is to speed up development of new antibody therapeutics. The AI model can help by conducting simulations by inputting data related to certain diseases. The data targets sequence, structure, and molecular profiles. These simulations assist in pinpointing antibody molecules with the greatest likelihood of success. Subsequently, these promising molecules undergo testing in laboratory environments, and the results are employed to further enhance the AI model.