OU, Industry Team Use AI to Speed Antibody Drug Output

New machine learning model dramatically accelerates the manufacturing timeline of monoclonal antibodies.

Published on Feb. 9, 2026

Got story updates? Submit your updates here. ›

Researchers at the University of Oklahoma have developed a machine learning model that can dramatically speed up the manufacturing process for monoclonal antibodies, a key class of modern medical treatments. The model, developed in partnership with Oklahoma City-based contract manufacturer Wheeler Bio, can accurately predict the productivity of different cell lines used to produce the antibodies, reducing the time-consuming screening process by weeks.

Why it matters

The market for monoclonal antibody therapies is forecast to double by 2030, but the manufacturing process has been a bottleneck. This new AI-powered approach could help drug companies get these important treatments to patients faster and at lower cost.

The details

The researchers combined an established mathematical model for cell growth and protein production with machine learning tools to analyze data from Wheeler Bio's antibody manufacturing process. This allowed them to accurately predict the productivity of different cloned cell lines, which is normally a weeks-long screening process. Their model correctly selected higher-performing clones 76.2% of the time and accurately forecast daily production trajectories from day 10 through day 16, using only the first 9 days of growth data.

  • The research was published in February 2026 in the journal Communications Engineering.
  • The project is part of a $35 million program funded by the U.S. Economic Development Administration to expand the biotechnology industry in the Oklahoma City region.

The players

Chongle Pan

An OU professor of computer science and biomedical engineering who co-authored the study.

Penghua Wang

A doctoral student in data science and analytics at OU who co-authored the study.

Wheeler Bio

An Oklahoma City-based contract development and manufacturing organization (CDMO) that focuses on antibody therapies and provided production data for the study.

Patrick Lucy

The President and CEO of Wheeler Bio.

University of Oklahoma

The academic institution where the research was conducted, including the Gallogly College of Engineering and the OU Bioprocessing Core Facility.

Got photos? Submit your photos here. ›

What they’re saying

“We're trying to solve a key bottleneck in the biomanufacturing production process. It's all about getting to market faster.”

— Penghua Wang, Doctoral student in data science and analytics (Mirage News)

“Wheeler Bio is committed to leveraging artificial intelligence and machine learning to accelerate our approach to cell line development and process development for antibody therapeutic production.”

— Patrick Lucy, President and CEO of Wheeler Bio (Mirage News)

“In academia, we tend to pursue theoretical research. But this study, and our partnership with Wheeler Bio, gave us an opportunity to apply machine learning and data science expertise to a real-world problem that the industry faces.”

— Chongle Pan, OU professor of computer science and biomedical engineering (Mirage News)

What’s next

More testing and model training is needed before the AI-powered clone selection model could be put into Wheeler Bio's production processes, according to the researchers.

The takeaway

This new machine learning approach has the potential to dramatically speed up the manufacturing of monoclonal antibodies, a critical class of modern medical treatments. By reducing the timeline for identifying high-performing cell lines, drug companies could get these important therapies to patients faster and at lower cost.