Amino Acid Classification in 2D NMR Spectra via Acoustic Signal Embeddings

TL;DR

This paper introduces a novel approach using acoustic signal embeddings from speaker verification models to classify amino acids in 2D NMR spectra, achieving high accuracy and outperforming existing models.

Contribution

It demonstrates that acoustic signal processing techniques can be effectively applied to NMR data for amino acid classification, with a trainable convolutional encoder improving performance.

Findings

97.7% classification accuracy on 20 amino acids

23% improvement over existing NMR models

Effective use of speaker verification embeddings for NMR analysis

Abstract

Nuclear Magnetic Resonance (NMR) is used in structural biology to experimentally determine the structure of proteins, which is used in many areas of biology and is an important part of drug development. Unfortunately, NMR data can cost thousands of dollars per sample to collect and it can take a specialist weeks to assign the observed resonances to specific chemical groups. There has thus been growing interest in the NMR community to use deep learning to automate NMR data annotation. Due to similarities between NMR and audio data, we propose that methods used in acoustic signal processing can be applied to NMR as well. Using a simulated amino acid dataset, we show that by swapping out filter banks with a trainable convolutional encoder, acoustic signal embeddings from speaker verification models can be used for amino acid classification in 2D NMR spectra by treating each amino acid as a unique speaker. On an NMR dataset comparable in size with of 46 hours of audio, we achieve a classification performance of 97.7% on a 20-class problem. We also achieve a 23% relative improvement by using an acoustic embedding model compared to an existing NMR-based model.