A machine learning approach for the identification of protein secondary structure elements from electron cryo-microscopy density maps

摘要

The accuracy of the secondary structure element (SSE) identification from volumetric protein density maps is critical for de-novo backbone structure derivation in electron cryo-microscopy (cryoEM). It is still challenging to detect the SSE automatically, accurately from the density maps at medium resolutions (～5-10 ?). We present a machine learning approach, SSELearner, to automatically identify helices, β-sheets by using the knowledge from existing volumetric maps in the Electron Microscopy Data Bank. We tested our approach using 10 simulated density maps. The averaged specificity, sensitivity for the helix detection are 94.9%, 95.8%, respectively, those for the β-sheet detection are 86.7%, 96.4%, respectively. We have developed a secondary structure annotator, SSID, to predict the helices, β-strands from the backbone Cα trace. With the help of SSID, we tested our SSELearner using 13 experimentally derived cryo-EM density maps. The machine learning approach shows the specificity, sensitivity of 91.8%, 74.5%, respectively, for the helix detection, 85.2%, 86.5% respectively for the β-sheet detection in cryoEM maps of Electron Microscopy Data Bank. The reduced detection accuracy reveals the challenges in SSE detection when the cryoEM maps are used instead of the simulated maps. Our results suggest that it is effective to use one cryoEM map for learning to detect the SSE in another cryoEM map of similar quality.