Affiliation:
1. Department of Biochemistry, Brandeis University
Abstract
Multi-wavelength single-molecule fluorescence colocalization (CoSMoS) methods allow elucidation of complex biochemical reaction mechanisms. However, analysis of CoSMoS data is intrinsically challenging because of low image signal-to-noise ratios, non-specific surface binding of the fluorescent molecules, and analysis methods that require subjective inputs to achieve accurate results. Here, we use Bayesian probabilistic programming to implement Tapqir, an unsupervised machine learning method that incorporates a holistic, physics-based causal model of CoSMoS data. This method accounts for uncertainties in image analysis due to photon and camera noise, optical non-uniformities, non-specific binding, and spot detection. Rather than merely producing a binary ‘spot/no spot’ classification of unspecified reliability, Tapqir objectively assigns spot classification probabilities that allow accurate downstream analysis of molecular dynamics, thermodynamics, and kinetics. We both quantitatively validate Tapqir performance against simulated CoSMoS image data with known properties and also demonstrate that it implements fully objective, automated analysis of experiment-derived data sets with a wide range of signal, noise, and non-specific binding characteristics.
Funder
National Institute of General Medical Sciences
Publisher
eLife Sciences Publications, Ltd
Subject
General Immunology and Microbiology,General Biochemistry, Genetics and Molecular Biology,General Medicine,General Neuroscience
Reference47 articles.
1. Pyro: Deep universal probabilistic programming;Bingham;Journal of Machine Learning Research: JMLR,2019
2. Rocket launcher mechanism of collaborative actin assembly defined by single-molecule imaging;Breitsprecher;Science (New York, N.Y.),2012
3. Kernel operations on the GPU, with autodiff, without memory overflows;Charlier;Journal of Machine Learning Research: JMLR,2021
4. High-throughput platform for real-time monitoring of biological processes by multicolor single-molecule fluorescence;Chen;PNAS,2014
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献