AB Initio Tomography With Object Heterogeneity and Unknown Viewing Paramete

In this paper, we present an algorithm to automatically construct all the conformations of a heterogeneous planar object from their tomographic projections at random unknown view angles. Our statistically motivated approach can reveal and analyze the heterogeneity in the projection dataset and segregate the projections belonging to different structures without requiring prior structural information or templates, expert human intervention or even the knowledge of the number of conformations present in the sample. Even in the presence of high noise variance (low SNR) and a large number of conformations, our algorithm can estimate the structures of each conformation to a high degree of accuracy. We demonstrate the broad applicability of our algorithm by evaluating its performance on synthetic 2D datasets of well-known protein complexes such as Lipase under varying levels of noise and different number of conformations.