Search
Close this search box.

Protein A Chromatography Multi-scale Data Driven/Mechanistic Modeling (Phase 2)

Develop a hybrid modeling infrastructure for simulating protein A chromatography performance and predicting process/product related impurities in the manufacture of monoclonal antibodies
Categories
Proteins/ Antibodies
Drug substance
Process control
Data
Project status
84% Completed

Industry Need

Laboratory experiments increase new product development cost. Special experiments for predictive model calibration reduces benefits of models.

Solution

Use Protein A modeling to reduce laboratory experimentation. Calibrate predictive model using AI/ML rather than experiments.

Outputs/Deliverables

  • Modelling Software in Open-Source platform (2Q2024)
  • Model Use Training documentation (2Q2024)

Impacts

Reduce process development time and cost of Antibody products

Additional Project Information (Members Only)

Login to the NIIMBL member portal to access more, including: 

  • Updates
  • Value Proposition
  • Related Publications
  • Deliverables

Not yet a member? Learn more about which level of NIIMBL membership is right for you and your organization.

Project Lead

Rensselaer Polytechnic Institute

Rensselaer Polytechnic Institute

Participating Organizations

AstraZeneca

AstraZeneca

Boehringer Ingelheim

Boehringer Ingelheim

Bristol-Myers Squibb

Bristol-Myers Squibb

Cytiva

Cytiva

Federal Stakeholder: National Institute of Standards and Technology

Federal Stakeholder: National Institute of Standards and Technology

Genentech, Inc.

Genentech, Inc.

Merck Sharp & Dohme LLC

Merck Sharp & Dohme LLC

MilliporeSigma/EMD Serono

MilliporeSigma/EMD Serono

NIIMBL

NIIMBL

Pfizer, Inc.

Pfizer, Inc.

Sanofi

Sanofi