Dual-target function validation of single-particle selection from low-contrast cryo-electron micrographs

Weak-signal detection and single-particle selection from low-contrast micrographs of frozen hydrated biomolecules by cryo-electron microscopy (cryo-EM) presents a practical challenge. Cryo-EM image contrast degrades as the size of biomolecules of structural interest decreases. When the image contrast falls into a range where the location or presence of single particles becomes ambiguous, a need arises for objective computational approaches to detect weak signal and to select and verify particles from these low-contrast micrographs. Here we propose an objective validation scheme for low-contrast particle selection using a combination of two different target functions. In an implementation of this dual-target function (DTF) validation, a first target function of fast local correlation was used to select particles through template matching, followed by signal validation through a second target function of maximum likelihood. By a systematic study of simulated data, we found that such an implementation of DTF validation is capable of selecting and verifying particles from cryo-EM micrographs with a signal-to-noise ratio as low as 0.002. Importantly, we demonstrated that DTF validation can robustly evade over-fitting or reference bias from the particle-picking template, allowing true signal to emerge from amidst heavy noise in an objective fashion. The DTF approach allows efficient assembly of a large number of single-particle cryo-EM images of smaller biomolecules or specimens containing contrast-degrading agents like detergents in a semi-automatic manner.