Detecting 2D NMR Signals Using Mask RCNN

Hadeel Saad Alghamdi; Alexei Lisitsa; Igor Barsukov; Rudi Grosman

doi:10.5220/0011804700003393

Detecting 2D NMR Signals Using Mask RCNN

Hadeel Saad Alghamdi
, Alexei Lisitsa
, Igor Barsukov
, Rudi Grosman

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

Picking peaks in two-dimensional Nuclear Magnetic Resonance (NMR) spectra has been a critical research problem and a very time-consuming important step in further analyses of NMR biological molecular systems. Here, we implemented machine learning approach for peak detection and segmentation using machine learning framework Mask R-CNN.The model was trained on a large number of synthetic spectra of known configurations, and we show that our model demonstrates promising results up to 0.93 accuracy. We implemented uniform scaling on the data matrix during training to further improve detection to achieve 10.17% FPs and 1.7% FNs rate. We show the utility of Mask R-CNN on NMR spectra where the data range plays an important role in peak detection.

Original language	English
Pages (from-to)	940-947
Number of pages	8
Journal	International Conference on Agents and Artificial Intelligence
Volume	3
DOIs	https://doi.org/10.5220/0011804700003393
State	Published - 2023
Externally published	Yes
Event	15th International Conference on Agents and Artificial Intelligence, ICAART 2023 - Lisbon, Portugal Duration: 22 Feb 2023 → 24 Feb 2023

Bibliographical note

Publisher Copyright:
© 2023 by SCITEPRESS – Science and Technology Publications, Lda.

Keywords

Mask R-CNN
NMR Spectre Analysis
Peak Detection

ASJC Scopus subject areas

Artificial Intelligence

Access to Document

10.5220/0011804700003393

Cite this

@article{d39ec548e9a549f2b6940b798b35678d,

title = "Detecting 2D NMR Signals Using Mask RCNN",

abstract = "Picking peaks in two-dimensional Nuclear Magnetic Resonance (NMR) spectra has been a critical research problem and a very time-consuming important step in further analyses of NMR biological molecular systems. Here, we implemented machine learning approach for peak detection and segmentation using machine learning framework Mask R-CNN.The model was trained on a large number of synthetic spectra of known configurations, and we show that our model demonstrates promising results up to 0.93 accuracy. We implemented uniform scaling on the data matrix during training to further improve detection to achieve 10.17\% FPs and 1.7\% FNs rate. We show the utility of Mask R-CNN on NMR spectra where the data range plays an important role in peak detection.",

keywords = "Mask R-CNN, NMR Spectre Analysis, Peak Detection",

author = "Alghamdi, \{Hadeel Saad\} and Alexei Lisitsa and Igor Barsukov and Rudi Grosman",

note = "Publisher Copyright: {\textcopyright} 2023 by SCITEPRESS {\textendash} Science and Technology Publications, Lda.; 15th International Conference on Agents and Artificial Intelligence, ICAART 2023 ; Conference date: 22-02-2023 Through 24-02-2023",

year = "2023",

doi = "10.5220/0011804700003393",

language = "English",

volume = "3",

pages = "940--947",

journal = "International Conference on Agents and Artificial Intelligence",

issn = "2184-3589",

publisher = "Science and Technology Publications, Lda",

}

TY - JOUR

T1 - Detecting 2D NMR Signals Using Mask RCNN

AU - Alghamdi, Hadeel Saad

AU - Lisitsa, Alexei

AU - Barsukov, Igor

AU - Grosman, Rudi

PY - 2023

Y1 - 2023

N2 - Picking peaks in two-dimensional Nuclear Magnetic Resonance (NMR) spectra has been a critical research problem and a very time-consuming important step in further analyses of NMR biological molecular systems. Here, we implemented machine learning approach for peak detection and segmentation using machine learning framework Mask R-CNN.The model was trained on a large number of synthetic spectra of known configurations, and we show that our model demonstrates promising results up to 0.93 accuracy. We implemented uniform scaling on the data matrix during training to further improve detection to achieve 10.17% FPs and 1.7% FNs rate. We show the utility of Mask R-CNN on NMR spectra where the data range plays an important role in peak detection.

AB - Picking peaks in two-dimensional Nuclear Magnetic Resonance (NMR) spectra has been a critical research problem and a very time-consuming important step in further analyses of NMR biological molecular systems. Here, we implemented machine learning approach for peak detection and segmentation using machine learning framework Mask R-CNN.The model was trained on a large number of synthetic spectra of known configurations, and we show that our model demonstrates promising results up to 0.93 accuracy. We implemented uniform scaling on the data matrix during training to further improve detection to achieve 10.17% FPs and 1.7% FNs rate. We show the utility of Mask R-CNN on NMR spectra where the data range plays an important role in peak detection.

KW - Mask R-CNN

KW - NMR Spectre Analysis

KW - Peak Detection

UR - https://www.scopus.com/pages/publications/85184963053

U2 - 10.5220/0011804700003393

DO - 10.5220/0011804700003393

M3 - Conference article

AN - SCOPUS:85184963053

SN - 2184-3589

VL - 3

SP - 940

EP - 947

JO - International Conference on Agents and Artificial Intelligence

JF - International Conference on Agents and Artificial Intelligence

T2 - 15th International Conference on Agents and Artificial Intelligence, ICAART 2023

Y2 - 22 February 2023 through 24 February 2023

ER -

Detecting 2D NMR Signals Using Mask RCNN

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this