The goal is that these foundation models will enable the discovery of novel candidate antibodies for the development of efficient therapeutics. Training on billions of proteins, both companies are hoping that the AI will speed up health discoveries by generating hypotheses faster and in a more effective way.
IBM’s models are trained on data in a self-supervised environment and aims to support healthcare workers by speeding up antibody discoveries from three years to one year.
Leveraging multimodal LLMs at scale
Boehringer Ingelheim is a leading research-driven biopharmaceutical company that aims to create value through innovation in areas of high unmet medical need. It works to achieve breakthrough therapies that seek to transform lives.
The organisation will be using an IBM-developed, pre-trained AI model that will continue to be fine-tuned on additional data from the company. Using foundation models for antibody discovery in this way is a ground-breaking solution that could improve patient outcomes worldwide, in addition to speeding up work for scientists.
Therapeutic antibodies are integral to the treatment of many diseases, including cancer, autoimmune and infectious diseases. Despite major advances in AI and technology, the discovery and development of therapeutic antibodies is still a highly complex and time-consuming process.
Typically, this type of antibody discovery takes an average timeframe of three years and then must be repeated. AI has the ability to speed up this type of discovery, given that it can generate a hypothesis faster and in a more effective way, shaving the length of time down to one year.
“IBM has been at the forefront of creating generative AI models that extend AI’s impact beyond the domain of language,” said Alessandro Curioni, Vice President Accelerated Discovery at IBM Research.
“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.”
Molecular dynamics + AI = simulation data
Boehringer Ingelheim, alongside IBM researchers, aims to accelerate discovery processes through in-silico methods. The sequence, structure and molecular profile information of disease-relevant targets, as well as success criteria for therapeutically relevant antibody molecules, will form the basis for the in-silico generation of new human antibody sequences.
This process can create unique datasets to train foundation models. IBM’s foundation model technologies have already demonstrated success in generating biologics and small molecules with relevant target affinities and are used to design antibody targets. These are then screened with A-enhanced simulation to select and refine the best binders for the target.
Moving forward, the results from the laboratory experiments will be used to improve the in-silico methods via feedback loops.
This collaboration is ultimately helping Boehringer Ingelheim to build a leading digital ecosystem and enable greater acceleration of drug discovery and development, as well as creating new opportunities to transform patients’ lives.
It also serves as a testament to IBM’s efforts to use generative AI and foundation models to accelerate discovery within healthcare contexts. IBM researchers announced at their media event in Zurich earlier in the week that model fine-tuning should be faster, to the point where the first set of models are set to be tested within a couple of months.
“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,” said Andrew Nixon, Global Head of Biotherapeutics Discovery at Boehringer Ingelheim.
“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.”
Please also check out our upcoming event - Sustainability LIVE Net Zero on 6 and 7 March 2024.
BizClik is a global provider of B2B digital media platforms that cover Executive Communities for CEOs, CFOs, CMOs, Sustainability leaders, Procurement & Supply Chain leaders, Technology & AI leaders, Cyber leaders, FinTech & InsurTech leaders as well as covering industries such as Manufacturing, Mining, Energy, EV, Construction, Healthcare and Food.
BizClik – based in London, Dubai, and New York – offers services such as content creation, advertising & sponsorship solutions, webinars & events.
- Upskilling Global Workers in AI with EY’s Beatriz Sanz SaizAI Strategy
- Intuitive Machines: NASA's Odysseus bets on Private CompanyData & Analytics
- The Impact of AI on Cybersecurity: A Need for PreparednessAI Strategy
- Salesforce: Businesses Must Better Prepare for AI RevolutionData & Analytics