OU Researchers Use AI to Speed Up Antibody Drug Development
The race to develop life-saving drugs is on, and a team of researchers at the University of Oklahoma (OU) has made a groundbreaking discovery that could revolutionize the process. They've developed a machine learning model that significantly accelerates the manufacturing of monoclonal antibodies, a type of lab-made protein used to treat various conditions, including cancers and autoimmune diseases.
Monoclonal antibodies are a marvel of modern medicine, but their production has been a bottleneck in the drug development process. The market for these therapies is projected to double by 2030, but the current manufacturing timeline is a major hurdle. That's where OU's innovative solution comes in.
In a recent study published in the journal Communications Engineering, Chongle Pan, a professor of computer science and biomedical engineering at OU, and Penghua Wang, a doctoral student in data science and analytics, detail their machine learning model. This model uses growth data from earlier production stages to predict cell productivity, a crucial factor in antibody manufacturing.
The process is similar to brewing beer. Yeast in beer fermentation feeds on sugars, converting them to alcohol. Similarly, Chinese hamster ovary (CHO) cells, the industry standard for producing therapeutic antibodies, feed on nutrients to maximize antibody production. However, not all cloned cell lines produce antibodies at the same rate, and biomanufacturers must screen these samples, a time-consuming process that can take several weeks.
Pan and Wang's model, trained and validated using the Luedeking-Piret model, a mathematical equation describing cell growth and protein production, achieved impressive results. It correctly selected higher-performing clones in 76.2% of its trials and accurately forecasted daily production trajectories from day 10 to day 16, using only data from the first nine days of growth.
This breakthrough has significant implications for the pharmaceutical industry. By reducing the time and cost of drug development, it could make life-saving medicines more accessible to patients. However, the model still requires further testing and training before it can be implemented in Wheeler Bio's production processes.
Despite this, the early results have been encouraging. Patrick Lucy, President and CEO of Wheeler Bio, expressed enthusiasm for the technology, stating their commitment to leveraging AI and machine learning to accelerate cell line development and process development for antibody therapeutic production.
This research is part of a $35 million program funded by the U.S. Economic Development Administration to expand the biotechnology industry cluster in Oklahoma City. The initiative aims to combine academic innovation with industrial application, with OU's Gallogly College of Engineering and the OU Bioprocessing Core Facility playing pivotal roles.
Pan emphasized the importance of applying machine learning and data science expertise to real-world problems, highlighting the collaboration with Wheeler Bio as a unique opportunity to bridge the gap between academia and industry.
The study, titled 'Luedeking-Piret regression for multi-step-ahead forecasting and clone selection in monoclonal antibodies biomanufacturing,' can be accessed at https://doi.org/10.1038/s44172-025-00547-7.
About Wheeler Bio:
Wheeler Bio, a contract development and manufacturing pioneer, has developed the ModularCMC™ platform, which enables the rapid translation of antibody-based therapeutics from discovery to clinical studies while ensuring scalability. Their High Science/High Touch approach combines cutting-edge development and cGMP manufacturing technologies with a highly experienced scientific team, committed to timeline transparency, scientific rigor, and a true partnering mindset.
About the University of Oklahoma:
The University of Oklahoma is a leading research institution, dedicated to advancing knowledge and innovation. Through collaborations like this, OU is making significant contributions to the biotechnology industry, ultimately benefiting patients and society.
