Accurate Prediction of NMR Chemical Shifts: Integrating DFT Calculations with Three-Dimensional Graph Neural Networks

Journal of Chemical Theory and Computation, Journal Year: 2024, Volume and Issue: 20(12), P. 5250 - 5258

Published: June 6, 2024

Computer prediction of NMR chemical shifts plays an increasingly important role in molecular structure assignment and elucidation for organic molecule studies. Density functional theory (DFT) gauge-including atomic orbital (GIAO) have established a framework to predict but often at significant computational expense with limited accuracy. Recent advancements deep learning methods, especially graph neural networks (GNNs), shown promise improving the accuracy predicting experimental shifts, either by using 2D topological features or 3D conformational representation. This study presents new GNN model 1H 13C CSTShift, that combines DFT-calculated shielding tensor descriptors, capturing both isotropic anisotropic effects. Utilizing NMRShiftDB2 data set conducting DFT optimization GIAO calculations B3LYP/6-31G(d) level, we prepared NMRShiftDB2-DFT high-quality structures tensors corresponding experimentally measured shifts. The developed CSTShift models achieve state-of-the-art performance on test external CHESHIRE set. Further case studies identifying correct from two groups constitutional isomers show its capability elucidation. source code are accessible https://yzhang.hpc.nyu.edu/IMA.

Language: Английский

---

Quantum chemical package Jaguar: A survey of recent developments and unique features

The Journal of Chemical Physics, Journal Year: 2024, Volume and Issue: 161(5)

Published: Aug. 2, 2024

This paper is dedicated to the quantum chemical package Jaguar, which commercial software developed and distributed by Schrödinger, Inc. We discuss Jaguar’s scientific features that are relevant research as well describe those aspects of program pertinent user interface, organization computer code, its maintenance testing. Among topics feature prominently in this methods grounded pseudospectral approach. A number multistep workflows dependent on Jaguar covered: prediction protonation equilibria aqueous solutions (particularly calculations tautomeric stability pKa), reactivity predictions based automated transition state search, assembly Boltzmann-averaged spectra such vibrational electronic circular dichroism, nuclear magnetic resonance. Discussed also oriented toward materials science applications, particular, properties optoelectronic organic semiconductors, molecular catalyst design. The topic treatment conformations inevitably comes up real world projects considered part all mentioned above. In addition, we examine role machine learning performed from auxiliary functions return approximate calculation runtime a actual properties. current work second series reviews first having been published more than ten years ago. Thus, serves rare milestone path being traversed development thirty existence.

Language: Английский

---

Accurate and Efficient Structure Elucidation from Routine One-Dimensional NMR Spectra Using Multitask Machine Learning

ACS Central Science, Journal Year: 2024, Volume and Issue: 10(11), P. 2162 - 2170

Published: Nov. 13, 2024

Rapid determination of molecular structures can greatly accelerate workflows across many chemical disciplines. However, elucidating structure using only one-dimensional (1D) NMR spectra, the most readily accessible data, remains an extremely challenging problem because combinatorial explosion number possible molecules as constituent atoms is increased. Here, we introduce a multitask machine learning framework that predicts (formula and connectivity) unknown compound solely based on its 1D 1H and/or 13C spectra. First, show how transformer architecture be constructed to efficiently solve task, traditionally performed by chemists, assembling large numbers fragments into structures. Integrating this capability with convolutional neural network, build end-to-end model for predicting from spectra fast accurate. We demonstrate effectiveness up 19 heavy (non-hydrogen) atoms, size which there are trillions Without relying any prior knowledge such formula, our approach exact molecule 69.6% time within first 15 predictions, reducing search space 11 orders magnitude.

Language: Английский

---

Rapid and accurate identification and quantification of Lycium barbarum L. components: Integrating deep lemarning and NMR for nutritional assessment

Food Research International, Journal Year: 2025, Volume and Issue: unknown, P. 116246 - 116246

Published: March 1, 2025

Language: Английский

---

NMR Crystallography Structure Determinations with ¹H Chemical Shifts. GIPAW DFT Calculation Quality Can Be Substantially Degraded, but Nearly Identical Outputs Relative to Benchmark Computations Are Obtained: Why and So What?

The Journal of Physical Chemistry A, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

Nuclear magnetic resonance (NMR) crystallography may be used in various solid-state structural characterization tasks. For organic compounds this context, proton isotropic chemical shifts [δiso(1H)] are routinely used. It is typical to pair experimentally measured δiso values with that were computationally generated from crystal structure models. This can yield a δiso(1H) root-mean-squared deviation (RMSD) value for each model. In study, we monitor the way which gauge including projector augmented wave (GIPAW) density functional theory (DFT) computations of 1H influenced by quality computational input parameters. We consider 126 (using prediction, CSP) structures three molecules: cocaine (30 structures), flutamide (21 and ampicillin (75 structures). The parameters selected plane energy cutoff (Ecut), k-point grid sample reciprocal (i.e., momentum) space. also probe utility performing one-parameter two-parameter linear mappings transforming computed hydrogen shielding (σiso) into values. find both Ecut degraded substantially (e.g., ∼ 25 Ry) yet still produce very similar mechanisms under GIPAW DFT contribute σiso help understand robustness: many contributions zero or cancel out when converting via mapping. robust nature leads consistent estimates RMSD then demonstrated using NMR tasks such as selection/determination, computation severely identical outcomes those more intensive protocol. Ampicillin practical example how our findings might reasonably applied determination complex molecule. propose relatively modest = 35 Ry 1 × grid) first filter obviously poor candidates. Subsequently, slightly higher selection/determination. Our indicate it should possible to, on average, reduce resources required approximately factor 3-4 terms CPU time.

Language: Английский

---

The interplay of density functional selection and crystal structure for accurate NMR chemical shift predictions

Faraday Discussions, Journal Year: 2024, Volume and Issue: unknown

Published: May 17, 2024

This study has investigated the impact improving quality of molecular crystal geometries can have on accuracy predicted 13 C and 15 N chemical shifts in organic crystals.

Language: Английский

---

UCBShift 2.0: Bridging the Gap from Backbone to Side Chain Protein Chemical Shift Prediction for Protein Structures

Journal of the American Chemical Society, Journal Year: 2024, Volume and Issue: 146(46), P. 31733 - 31745

Published: Nov. 12, 2024

Chemical shifts are a readily obtainable NMR observable that can be measured with high accuracy, and because they sensitive to conformational averages the local molecular environment, yield detailed information about protein structure in solution. To predict chemical of structures, we introduced UCBShift method uniquely fuses transfer prediction module, which employs sequence alignments select reference from an experimental database, machine learning model uses carefully curated physics-inspired features derived X-ray crystal structures backbone for proteins. In this work, extend 1.0 side chain shift perform whole analysis, which, when validated against well-defined test data shows higher accuracy better reliability compared popular SHIFTX2 method. With greater abundance cleaned shift-structure modularity general algorithms, users gain insight into different important residue-specific stabilizing interactions prediction. We suggest several backward forward applications 2.0 help validate AlphaFold probe dynamics.

Language: Английский

---

Bent naphthodithiophenes: synthesis and characterization of isomeric fluorophores

RSC Advances, Journal Year: 2024, Volume and Issue: 14(35), P. 25120 - 25129

Published: Jan. 1, 2024

Thiophene-containing heteroarenes are one of the most well-known classes π-conjugated building blocks for photoactive molecules. Isomeric naphthodithiophenes (NDTs) at forefront this research area due to their straightforward synthesis and derivatization. Notably, NDT geometries that bent - such as naphtho[2,1-

Language: Английский

---