PT  - JOURNAL ARTICLE
AU  - Nitin Kapadia
AU  - Ziad W. El-Hajj
AU  - Rodrigo Reyes-Lamothe
TI  - Bound2Learn: A Machine Learning Approach for Classification of DNA-Bound Proteins from Single-Molecule Tracking Experiments
AID  - 10.1101/2020.02.20.958512
DP  - 2020 Jan 01
TA  - bioRxiv
PG  - 2020.02.20.958512
4099  - http://biorxiv.org/content/early/2020/02/21/2020.02.20.958512.short
4100  - http://biorxiv.org/content/early/2020/02/21/2020.02.20.958512.full
AB  - Many proteins act on DNA for a wide range of processes, including DNA replication, DNA repair, and transcription. Their time spent on DNA can provide insight into these processes and their stability within complexes to which they may belong. Single-particle tracking allows for direct visualization of protein-DNA kinetics, however, identifying whether a molecule is bound to DNA can be non-trivial. Further complications arise with tracking molecules for extended durations in cases of processes with slow kinetics. We developed a machine learning approach, using output from a widely used tracking software, to robustly classify tracks in order to accurately estimate residence times. We validated our approach in silico, and in live-cell data from Escherichia coli and Saccharomyces cerevisiae. Our method has the potential for broad utility and is applicable to other organisms.