Using Mechanistic Models and Machine Learning to Design Single-Color Multiplexed Nascent Chain Tracking Experiments.

Area of Science:

• Molecular Biology
• Cell Biology
• Biophysics

Background:

• mRNA translation is a fundamental cellular process, crucial for protein synthesis.
• Nascent chain tracking (NCT) offers single-molecule resolution for observing translation dynamics in live cells.
• Current NCT methods are limited to tracking only one or two mRNA species simultaneously due to fluorescent tag constraints.

Approach:

• Developed a hybrid computational pipeline combining mechanistic simulations and machine learning (ML).
• Simulated realistic NCT videos to evaluate experimental designs for resolving multiple mRNA species.
• Utilized ML to assess the potential of using a single fluorescent color for multiple species.

Key Points:

• Demonstrated that a hybrid design strategy can extend the number of simultaneously trackable mRNA species.
• Presented a simulated NCT experiment tracking seven mRNA species in one cell.
• Achieved 90% accuracy in identifying mRNA spots using ML with only two distinct fluorescent tags.

Conclusions:

• The proposed extension to NCT's color palette significantly enhances experimental design possibilities.
• This approach enables simultaneous study of multiple mRNAs, particularly valuable for cell signaling research.
• Facilitates deeper insights into complex cellular dynamics and gene expression regulation.