Detection and Identification of Macromolecular Complexes in Cryo-Electron Tomograms Using Support Vector Machines

Detection and identification of macromolecular complexes in cryo-electron tomograms is challenging due to the extremely low signal-to-noise ratio (SNR). While the state-of-the-art method is template matching with a single template, we propose a supervised learning approach in 3 steps: (i) pre-detection of candidates, (ii) feature calculation and (iii) final decision using support vector machine (SVM). We use two types of features for SVM: (i) correlation coefficients from multiple templates, and (ii) rotation invariant features derived from spherical harmonics. Experiments conducted on both simulated and experimental tomograms show that our approach outperforms the state-of-the-art method.     «

Detection and identification of macromolecular complexes in cryo-electron tomograms is challenging due to the extremely low signal-to-noise ratio (SNR). While the state-of-the-art method is template matching with a single template, we propose a supervised learning approach in 3 steps: (i) pre-detection of candidates, (ii) feature calculation and (iii) final decision using support vector machine (SVM). We use two types of features for SVM: (i) correlation coefficients from multiple templates, an...     »