• Corpus ID: 208637363

Accurate Prediction of Chemical Shifts for Aqueous Protein Structure for "Real World" Cases using Machine Learning

  title={Accurate Prediction of Chemical Shifts for Aqueous Protein Structure for "Real World" Cases using Machine Learning},
  author={J. Li and Kochise Bennett and Yuchen Liu and Michael V. Martin and Teresa Head-Gordon},
  journal={arXiv: Chemical Physics},
Accurate prediction of NMR chemical shifts can in principle help refine aqueous solution structure of proteins to the quality of X-ray structures. We report a new machine learning algorithm for protein chemical shift prediction that outperforms existing chemical shift calculators on realistic NMR solution data. Our UCBShift predictor implements two modules: a transfer prediction module that employs both sequence and structural alignment to select reference candidates for experimental chemical… 
2 Citations

Figures and Tables from this paper

Learning to Make Chemical Predictions: the Interplay of Feature Representation, Data, and Machine Learning Algorithms

This Perspective focuses on the interplay of machine learning algorithm with the chemically motivated descriptors and the size and type of data sets needed for molecular property prediction, and demonstrates that success is predicated on the choice of feature extracted or real-space representations of chemical structures.



SPARTA+: a modest improvement in empirical NMR chemical shift prediction by means of an artificial neural network

A new chemical shift prediction program, SPARTA+, is described, based on artificial neural networking, which appears to be approaching the limit at which empirical approaches can predict chemical shifts.

RefDB: A database of uniformly referenced protein chemical shifts

It is evident that protein NMR spectroscopists are increasingly adhering to recommended IUPAC 13C and 15N chemical shift referencing conventions, however, approximately 20% of newly deposited protein entries in the BMRB are still being incorrectly referenced, cause for some concern.

SHIFTX2: significantly improved protein chemical shift prediction

A new computer program, called SHIFTX2, is described which is capable of rapidly and accurately calculating diamagnetic 1H, 13C and 15N chemical shifts from protein coordinate data and will open the door to many long-anticipated applications of chemical shift prediction to protein structure determination, refinement and validation.

A Multi-Resolution 3D-DenseNet for Chemical Shift Prediction in NMR Crystallography.

Principal Component analysis (PCA) is used to both understand and indicate that chemical shift prediction for 1H, which has far fewer training environments than the 1H atom type, will improve once more unique training samples are made available to exploit the deep network architecture.

Automated 1H and 13C chemical shift prediction using the BioMagResBank

It is believed that SHIFTY may have widespread utility in assigning individual members in families of related proteins, an endeavor that accounts for a growing portion of the protein NMR work being done today.

Rapid and accurate calculation of protein 1 H , 13 C and 15 N chemical shifts

A computer program (SHIFTX) is described which rapidly and accurately calculates the diamagnetic 1H, 13C and 15N chemical shifts of both backbone and sidechain atoms in proteins. The program uses a

Protein backbone chemical shifts predicted from searching a database for torsion angle and sequence homology

A computer program is described that uses this correlation with local structure to predict protein backbone chemical shifts, given an input three-dimensional structure, by searching a newly generated database for triplets of adjacent residues that provide the best match in ϕ/ψ/χ1 torsion angles and sequence similarity to the query triplet of interest.

A simple method to predict protein flexibility using secondary chemical shifts.

This chemical shift method is able to quantitatively predict per-residue RMSD values (from both MD simulations and NMR structural ensembles) as well as model-free backbone order parameters.

Protein chemical shift analysis: a practical guide.

  • D. WishartA. Nip
  • Chemistry
    Biochemistry and cell biology = Biochimie et biologie cellulaire
  • 1998
This article outlines procedures for identifying secondary structure elements through heteronuclear chemical shift analysis and demonstrates how empirical shift contour maps can actually be used to refine, and more importantly generate, reasonably good three-dimensional protein structures.

A probabilistic approach for validating protein NMR chemical shift assignments

A new structure-independent protocol is presented, which is based on using residue-specific and secondary structure-specific chemical shift distributions calculated over small residue fragments to identify mis-assigned resonances and is able to identify and re-reference mis-referenced chemical shift assignments.