Artificial Intelligence and Computational Statistics Platform for Biosimilar Subvisible Characterization
Overview
Buyer
Place of Performance
NAICS
PSC
Set Aside
Original Source
Timeline
Qualification Details
Fit reasons
- NAICS alignment with historical contract wins in similar service areas.
- Scope strongly matches core technical capabilities and delivery model.
Risks
- Past performance thresholds may require one additional teaming partner.
- Potential clarification needed on staffing minimums before bid/no-bid.
Next steps
Validate eligibility requirements, assign capture owner, and schedule partner outreach to confirm teaming strategy before submission planning.
Quick Summary
The Food and Drug Administration (FDA), specifically the Office of Product Quality Research (OPQR), is seeking an Artificial Intelligence and Computational Statistics Platform with associated services for biosimilar subvisible characterization. This platform will detect and classify protein aggregates in biosimilar drug products to support feasibility studies. The contract will be a Firm Fixed-Price Purchase Order awarded via the Lowest Price Technically Acceptable (LPTA) method. Quotes are due by May 26, 2026, at 1:00 PM EST.
Scope of Work
The required platform must combine machine learning and computational statistics to characterize heterogeneous suspensions of subvisible particles (<100 microns) in biologic and biosimilar drug products. Key capabilities include:
- Generating morphological fingerprints of protein aggregates specific to product, stress, or aggregation mechanism.
- Differentiating particles from various stress types, the product, and container closure systems.
- Compatibility with Flow Imaging and Backgrounded Membrane Imaging data without prior image processing.
- Providing quantitative data on aggregate and particle populations, moving beyond simple size and count methods.
- Employing statistical analysis tools such as Euclidean distance or Kolmogorov-Smirnov test-based similarity scores.
- Being a trusted, industry-acceptable model with demonstrable experience and publications in applying supervised and unsupervised ML for classifying visible and subvisible particle images in biologics.
- Compensating for optical phenomena at different length scales and allowing visual examination of nearest images to any fingerprint point.
- Providing training to OPQR staff on AI/ML application for particle classification and interpretation of results.
Contract & Timeline
- Contract Type: Firm Fixed-Price (FFP) Purchase Order
- Period of Performance: 12 months from the date of award
- Place of Performance: Silver Spring, MD
- Set-Aside: Full and Open Competition
- Questions Due: May 18, 2026, 1:00 PM EST
- Quotes Due: May 26, 2026, 1:00 PM EST
- Published: May 11, 2026
Evaluation
Award will be made to the responsible quoter offering the Lowest Price Technically Acceptable (LPTA). Evaluation factors include:
- Total Price
- Technical features meeting/exceeding specified requirements. Failure to meet any requirement will result in a technically unacceptable rating.
Additional Notes
This is a combined synopsis/solicitation (RFQ) under solicitation number FDA-75F40126Q00142. Offerors must submit electronic documents without macros. The Government is not obligated to make an award.