3.8 Proceedings Paper

Identifying Structural Properties of Proteins from X-ray Free Electron Laser Diffraction Patterns

Publisher

IEEE
DOI: 10.1109/eScience55777.2022.00017

Keywords

machine learning; diffraction patterns; proteins; autoencoder

Funding

  1. NSF [1741057, 1841758, 2028923, 2138811, 2223704]
  2. IBM Shared University (SUR) Award
  3. JSPS KAKENHI [JP20H05453]
  4. FOCUS for Establishing Super-computing Center of Excellence
  5. JLESC Consortium
  6. JDRD Program at UTK
  7. Direct For Computer & Info Scie & Enginr
  8. Division of Computing and Communication Foundations [2028923] Funding Source: National Science Foundation
  9. Direct For Computer & Info Scie & Enginr
  10. Div Of Information & Intelligent Systems [1841758, 1741057] Funding Source: National Science Foundation
  11. Office of Advanced Cyberinfrastructure (OAC)
  12. Direct For Computer & Info Scie & Enginr [2138811] Funding Source: National Science Foundation

Ask authors/readers for more resources

Capturing the structural information of biological molecules is crucial for understanding their function and mechanism. This research presents a framework, XPSI, which utilizes X-ray Free Electron Lasers to accurately predict the orientation, conformation, and protein type of molecules from their diffraction patterns. Compared to other machine learning methods, XPSI shows low computational cost and high prediction accuracy.
Capturing structural information of a biological molecule is crucial to determine its function and understand its mechanics. X-ray Free Electron Lasers (XFEL) are an experimental method used to create diffraction patterns (images) that can reveal structural information. In this work we design, implement, and evaluate XPSI (X-ray Free Electron Laser-based Protein Structure Identifier), a framework capable of predicting three structural properties in molecules (i.e., orientation, conformation, and protein type) from their diffraction patterns. XPSI predicts these properties with high accuracy in challenging scenarios, such as recognizing orientations despite symmetries in diffraction patterns, distinguishing conformations even when they have similar structures, and identifying protein types under different noise conditions. Our framework shows low computational cost and high prediction accuracy compared to other machine learning methods such as random forest and neural networks.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.8
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available