An automatic particle pickup method using a neural network applicable to low-contrast electron micrographs.

摘要: Three-dimensional reconstruction from electron micrographs requires the selection of many single-particle projection images; more than 10 000 are generally required to obtain 5- 10-A structural resolution. Consequently, various automatic detection algorithms have been developed and successfully applied large symmetric protein complexes. This paper presents a new automated particle recognition pickup procedure based on three-layer neural network that has application range other procedures. Its use for both faint noisy is demonstrated. The method only 200 selected particles as learning data able detect images proteins small kDa.