Software System Design to Support Scale in Mammalian Cell Line Engineering

Area of Science:

• Biotechnology
• Bioinformatics
• Genomics

Background:

• Traditional cell line engineering (CLE) workflows are manual and low-throughput.
• Increasing demands in research, development, and bioproduction necessitate higher efficiency.

Purpose of the Study:

• To develop a high-throughput CLE platform by integrating software solutions with wet lab automation.
• To improve the throughput of CLE processes by threefold.

Main Methods:

• Development of a Gene Expression Markup Language (GEML) for e-commerce and manufacturing system integration.
• Creation of a Laboratory Information Management System (LIMS) to track CLE projects.
• Implementation of a machine learning (ML)-based method for analyzing brightfield images of engineered clones.

Main Results:

• Achieved a threefold increase in CLE platform throughput.
• Successfully integrated GEML and LIMS for streamlined cell line manufacturing.
• Developed an ML model for efficient clone analysis without fluorescent staining.

Conclusions:

• Combining wet lab automation with software approaches is crucial for high-throughput CLE.
• The developed platform enhances robustness and meets the growing demands of the field.
• Software-based solutions are essential for unlocking the full potential of CLE workflows.