Abstract
Macromolecular structures can be determined from solution X-ray scattering. Small-angle X-ray scattering (SAXS) provides global structural information on length scales of 10s to 100s of Ångstroms, and many algorithms are available to convert SAXS data into low-resolution structural envelopes. Extension of measurements to wider scattering angles (WAXS or wide-angle X-ray scattering) can sharpen the resolution to below 10 Å, filling in structural details that can be critical for biological function. These WAXS profiles are especially challenging to interpret because of the significant contribution of solvent in addition to solute on these smaller length scales. Based on training with molecular dynamics generated models, the application of extreme gradient boosting (XGBoost) is discussed, which is a supervised machine learning (ML) approach to interpret features in solution scattering profiles. These ML methods are applied to predict key structural parameters of double-stranded ribonucleic acid (dsRNA) duplexes. Duplex conformations vary with salt and sequence and directly impact the foldability of functional RNA molecules. The strong structural periodicities in these duplexes yield scattering profiles with rich sets of features at intermediate-to-wide scattering angles. In the ML models, these profiles are treated as 1D images or features. These ML models identify specific scattering angles, or regions of scattering angles, which correspond with and successfully predict distinct structural parameters. Thus, this work demonstrates that ML strategies can integrate theoretical molecular models with experimental solution scattering data, providing a new framework for extracting highly relevant structural information from solution experiments on biological macromolecules.
Highlights
Ribonucleic acids (RNAs) comprise an important class of biological macromolecules that transfer genetic codes, and signal their response to binding partners through structural changes
874 Chen and Pollack Machine learning deciphers structural features of RNA duplexes noise-free model was trained using the aforementioned dataset with 191 q points, derived from direct computation based on an molecular dynamics (MD) structure
Our goal is to propose machine learning (ML) frameworks for the analysis of solution X-ray scattering data when MD predictions are available
Summary
Ribonucleic acids (RNAs) comprise an important class of biological macromolecules that transfer genetic codes, and signal their response to binding partners through structural changes. Since the discovery of the first catalytically active RNA in the 1980s (Cech et al, 1981), much attention has been focused on how RNA sequence and structure enable its responses to partners, including ions, small ligands and proteins. Two independent studies focused on the structural variation of fully base-paired RNA duplexes, which exhibit sequencedependent (Yesselman et al, 2019) and salt-dependent (Chen & Pollack, 2019) conformations. These works suggest that subtle variations in the RNA stems can affect the precise alignment of contacts that stabilizes tertiary structures, imparting more selectivity to interactions and expanding the. We report a new approach for detecting the small twisting and compression of the RNA duplexes which may dramatically impact the overall molecular structure
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call