Dataset Information

Helix Matrix Transformation Combined With Convolutional Neural Network Algorithm for Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry-Based Bacterial Identification.

ABSTRACT: Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) analysis is a rapid and reliable method for bacterial identification. Classification algorithms, as a critical part of the MALDI-TOF MS analysis approach, have been developed using both traditional algorithms and machine learning algorithms. In this study, a method that combined helix matrix transformation with a convolutional neural network (CNN) algorithm was presented for bacterial identification. A total of 14 bacterial species including 58 strains were selected to create an in-house MALDI-TOF MS spectrum dataset. The 1D array-type MALDI-TOF MS spectrum data were transformed through a helix matrix transformation into matrix-type data, which was fitted during the CNN training. Through the parameter optimization, the threshold for binarization was set as 16 and the final size of a matrix-type data was set as 25 × 25 to obtain a clean dataset with a small size. A CNN model with three convolutional layers was well trained using the dataset to predict bacterial species. The filter sizes for the three convolutional layers were 4, 8, and 16. The kernel size was three and the activation function was the rectified linear unit (ReLU). A back propagation neural network (BPNN) model was created without helix matrix transformation and a convolution layer to demonstrate whether the helix matrix transformation combined with CNN algorithm works better. The areas under the receiver operating characteristic (ROC) curve of the CNN and BPNN models were 0.98 and 0.87, respectively. The accuracies of the CNN and BPNN models were 97.78 ± 0.08 and 86.50 ± 0.01, respectively, with a significant statistical difference (p < 0.001). The results suggested that helix matrix transformation combined with the CNN algorithm enabled the feature extraction of the bacterial MALDI-TOF MS spectrum, which might be a proposed solution to identify bacterial species.

SUBMITTER: Ling J

PROVIDER: S-EPMC7693542 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Helix Matrix Transformation Combined With Convolutional Neural Network Algorithm for Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry-Based Bacterial Identification.

Ling Jin J Li Gaomin G Shao Hong H Wang Hong H Yin Hongrui H Zhou Hu H Song Yufei Y Chen Gang G

Frontiers in microbiology 20201112

Matrix-assisted laser desorption ionization-time of flight mass spectrometry (MALDI-TOF MS) analysis is a rapid and reliable method for bacterial identification. Classification algorithms, as a critical part of the MALDI-TOF MS analysis approach, have been developed using both traditional algorithms and machine learning algorithms. In this study, a method that combined helix matrix transformation with a convolutional neural network (CNN) algorithm was presented for bacterial identification. A to ...[more]

PMID: 33304324

Similar Datasets

Project description:Streptococcus suis, particularly S. suis serotype 2 (SS2), is an important zoonotic pathogen causing meningitis in humans worldwide. Although the proper classification of the causative and pathogenic serotype is salutary for the clinical diagnosis, cross-reactions leading to the indistinguishability of serotypes by the current serotyping methods are significant limitations. In the present study, matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF-MS) analysis of extracted peptides was developed to improve the classification of serotype of S. suis. The peptide mass fingerprint (PMFs) database of S. suis was generated from the whole-cell peptides of 32 reference strains of S. suis isolates obtained from pigs. Thirty-two human S. suis isolates from clinical cases in Thailand were used to validate this alternative serotyping method in direct comparison to the multiplex (m)PCR approach. All reference strains, representing 32 serotypes of S. suis, exhibited their individual PMFs patterns, thus allowing differentiation from one another. Highly pathogenic SS2 and SS14 were clearly differentiated from the otherwise serologically closely related SS1/2 and SS1, respectively. The developed MALDI-TOF-MS serotyping method correctly classified the serotype in 68.8% (22/32) of the same serotype isolates generated from the PMFs database; while the validity for the clinical human isolates was 62.5% (20/32). The agreement between the MALDI-TOF-MS and mPCR serotyping was moderate with a Kappa score of 0.522, considering that mPCR could correctly serotype up to 75%. The present study demonstrated that PMFs from the developed MALDI-TOF-MS-based method could successfully discriminate the previously indistinguishable highly pathogenic SS2 and SS14 from SS1/2 and SS1, respectively. Moreover, this serotyping method distinguished pathogenic SS6, and so is an alternative approach of choice to rapidly and reliably serotype clinically pathogenic S. suis isolates.

Dataset Information

Helix Matrix Transformation Combined With Convolutional Neural Network Algorithm for Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry-Based Bacterial Identification.

Publications

Helix Matrix Transformation Combined With Convolutional Neural Network Algorithm for Matrix-Assisted Laser Desorption Ionization-Time of Flight Mass Spectrometry-Based Bacterial Identification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets