Neural Network Approach for Predicting Infrared Spectra from 3D Molecular Structure

TL;DR

This paper presents a machine learning model that predicts infrared spectra directly from 3D molecular structures, outperforming traditional methods in accuracy and speed, and can be adapted for different spectral types.

Contribution

Introduces a novel ML approach for IR spectra prediction from 3D structures, reducing computational cost and improving accuracy over DFT calculations.

Findings

Model achieves a Spectral Information Similarity Metric of 0.92 on 200 molecules.

Outperforms scaled DFT frequencies with a similarity metric of 0.57.

Offers a fast alternative to anharmonic calculations, applicable to various spectra types.

Abstract

Accurately predicting infrared (IR) spectra in computational chemistry using ab initio methods remains a challenge. Current approaches often rely on an empirical approach or on tedious anharmonic calculations, mainly adapted to semi-rigid molecules. This limitation motivates us to explore alternative methodologies. Previous studies explored machine-learning techniques for potential and dipolar surface generation, followed by IR spectra calculation using classical molecular dynamics. However, these methods are computationally expensive and require molecule-by-molecule processing. Our article introduces a new approach to improve IR spectra prediction accuracy within a significantly reduced computing time. We developed a machine learning (ML) model to directly predict IR spectra from three-dimensional (3D) molecular structures. The spectra predicted by our model significantly outperform those from density functional theory (DFT) calculations, even after scaling. In a test set of 200 molecules, our model achieves a Spectral Information Similarity Metric of 0.92, surpassing the value achieved by DFT scaled frequencies, which is 0.57. Additionally, our model considers anharmonic effects, offering a fast alternative to laborious anharmonic calculations. Moreover, our model can be used to predict various types of spectra (Ultraviolet or Nuclear Magnetic Resonance for example) as a function of molecular structure. All it needs is a database of 3D structures and their associated spectra.