Martin Selin
30 June 2023, 13:00 CEST
Optical tweezers are powerful tools for manipulating and studying the mechanical properties of single biomolecules, such as DNA. However, conducting such experiments manually is both time-consuming and labor-intensive limiting the amount of data collectable. In this work, we present a method to automate optical tweezers with the use of deep learning applying it to DNA pulling experiments.
A typical DNA pulling experiment can be divided into three main steps, each of which we have automated. The first is positioning of a bead in a micropipette(or secondary optical trap), second is connecting DNA of a another optically trapped bead with the bead in the micropipette and lastly the stretching of the DNA by moving the trapped bead while monitoring the force.
We have used deep learning, in particular a unet, to track beads and identify important features in the sample such as the micropipette. Combining this with realtime feedback allows the system to both trap beads and carefully position trap beads.
We demonstrate the viability of our method by stretching lambda DNA, showing human like reliability in performing the experiments. We expect our method to find use in the study of small biomolecules enabling more and faster data collection as well as longer running experiments.