Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies
Therapeutic monoclonal antibodies (mAbs) are a new generation of protein-based medicines that are usually expensive and thus represent a target for counterfeiters. In the present study, a method based on Raman spectroscopy that combined extreme point sort transformation with a long short-term memory...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Chemistry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fchem.2022.887960/full |
| _version_ | 1811329799289831424 |
|---|---|
| author | Jin Ling Luxia Zheng Mingming Xu Gang Chen Xiao Wang Danzhuo Mao Hong Shao |
| author_facet | Jin Ling Luxia Zheng Mingming Xu Gang Chen Xiao Wang Danzhuo Mao Hong Shao |
| author_sort | Jin Ling |
| collection | DOAJ |
| description | Therapeutic monoclonal antibodies (mAbs) are a new generation of protein-based medicines that are usually expensive and thus represent a target for counterfeiters. In the present study, a method based on Raman spectroscopy that combined extreme point sort transformation with a long short-term memory (LSTM) network algorithm was presented for the identification of therapeutic mAbs. A total of 15 therapeutic mAbs were used in this study. An in-house Raman spectrum dataset for model training was created with 1,350 spectra. The characteristic region of the Raman spectrum was reduced in dimension and then transformed through an extreme point sort transformation into a sequence array, which was fitted for the LSTM network. The characteristic array was extracted from the sequence array using a well-trained LSTM network and then compared with standard spectra for identification. To demonstrate whether the present algorithm was better, ThermoFisher OMNIC 8.3 software (Thermo Fisher Scientific Inc., U.S.) with two matching modes was selected for comparison. Finally, the present method was successfully applied to identify 30 samples, including 15 therapeutic mAbs and 15 other injections. The characteristic region was selected from 100 to 1800 cm−1 of the full spectrum. The optimized dimensional values were set from 35 to 53, and the threshold value range was from 0.97 to 0.99 for 15 therapeutic mAbs. The results of the robustness test indicated that the present method had good robustness against spectral peak drift, random noise and fluorescence interference from the measurement. The areas under the curve (AUC) values of the present method that were analysed on the full spectrum and analysed on the characteristic region by the OMNIC 8.3 software’s built-in method were 1.000, 0.678, and 0.613, respectively. The similarity scores for 15 therapeutic mAbs using OMNIC 8.3 software in all groups compared with that of the relative present algorithm group had extremely remarkable differences (p < 0.001). The results suggested that the extreme point sort transformation combined with the LSTM network algorithm enabled the characteristic extraction of the therapeutic mAb Raman spectrum. The present method is a proposed solution to rapidly identify therapeutic mAbs. |
| first_indexed | 2024-04-13T15:50:14Z |
| format | Article |
| id | doaj.art-e160d068e8264a0284c3cd984e6479e9 |
| institution | Directory Open Access Journal |
| issn | 2296-2646 |
| language | English |
| last_indexed | 2024-04-13T15:50:14Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Chemistry |
| spelling | doaj.art-e160d068e8264a0284c3cd984e6479e92022-12-22T02:40:52ZengFrontiers Media S.A.Frontiers in Chemistry2296-26462022-04-011010.3389/fchem.2022.887960887960Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal AntibodiesJin Ling0Luxia Zheng1Mingming Xu2Gang Chen3Xiao Wang4Danzhuo Mao5Hong Shao6NMPA Key Laboratory for Quality Control of Therapeutic Monoclonal Antibodies, Shanghai Institute for Food and Drug Control, Shanghai, ChinaNMPA Key Laboratory for Quality Control of Therapeutic Monoclonal Antibodies, Shanghai Institute for Food and Drug Control, Shanghai, ChinaNMPA Key Laboratory for Quality Control of Therapeutic Monoclonal Antibodies, Shanghai Institute for Food and Drug Control, Shanghai, ChinaNMPA Key Laboratory for Quality Control of Therapeutic Monoclonal Antibodies, Shanghai Institute for Food and Drug Control, Shanghai, ChinaNMPA Key Laboratory for Quality Analysis of Chemical Drug Preparations, Shanghai Institute for Food and Drug Control, Shanghai, ChinaNMPA Key Laboratory for Quality Analysis of Chemical Drug Preparations, Shanghai Institute for Food and Drug Control, Shanghai, ChinaNMPA Key Laboratory for Quality Control of Therapeutic Monoclonal Antibodies, Shanghai Institute for Food and Drug Control, Shanghai, ChinaTherapeutic monoclonal antibodies (mAbs) are a new generation of protein-based medicines that are usually expensive and thus represent a target for counterfeiters. In the present study, a method based on Raman spectroscopy that combined extreme point sort transformation with a long short-term memory (LSTM) network algorithm was presented for the identification of therapeutic mAbs. A total of 15 therapeutic mAbs were used in this study. An in-house Raman spectrum dataset for model training was created with 1,350 spectra. The characteristic region of the Raman spectrum was reduced in dimension and then transformed through an extreme point sort transformation into a sequence array, which was fitted for the LSTM network. The characteristic array was extracted from the sequence array using a well-trained LSTM network and then compared with standard spectra for identification. To demonstrate whether the present algorithm was better, ThermoFisher OMNIC 8.3 software (Thermo Fisher Scientific Inc., U.S.) with two matching modes was selected for comparison. Finally, the present method was successfully applied to identify 30 samples, including 15 therapeutic mAbs and 15 other injections. The characteristic region was selected from 100 to 1800 cm−1 of the full spectrum. The optimized dimensional values were set from 35 to 53, and the threshold value range was from 0.97 to 0.99 for 15 therapeutic mAbs. The results of the robustness test indicated that the present method had good robustness against spectral peak drift, random noise and fluorescence interference from the measurement. The areas under the curve (AUC) values of the present method that were analysed on the full spectrum and analysed on the characteristic region by the OMNIC 8.3 software’s built-in method were 1.000, 0.678, and 0.613, respectively. The similarity scores for 15 therapeutic mAbs using OMNIC 8.3 software in all groups compared with that of the relative present algorithm group had extremely remarkable differences (p < 0.001). The results suggested that the extreme point sort transformation combined with the LSTM network algorithm enabled the characteristic extraction of the therapeutic mAb Raman spectrum. The present method is a proposed solution to rapidly identify therapeutic mAbs.https://www.frontiersin.org/articles/10.3389/fchem.2022.887960/fullRaman spectroscopylong-short term memory networktherapeutic monoclonal antibodyextreme point sort transformationalgorithm study |
| spellingShingle | Jin Ling Luxia Zheng Mingming Xu Gang Chen Xiao Wang Danzhuo Mao Hong Shao Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies Frontiers in Chemistry Raman spectroscopy long-short term memory network therapeutic monoclonal antibody extreme point sort transformation algorithm study |
| title | Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies |
| title_full | Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies |
| title_fullStr | Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies |
| title_full_unstemmed | Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies |
| title_short | Extreme Point Sort Transformation Combined With a Long Short-Term Memory Network Algorithm for the Raman-Based Identification of Therapeutic Monoclonal Antibodies |
| title_sort | extreme point sort transformation combined with a long short term memory network algorithm for the raman based identification of therapeutic monoclonal antibodies |
| topic | Raman spectroscopy long-short term memory network therapeutic monoclonal antibody extreme point sort transformation algorithm study |
| url | https://www.frontiersin.org/articles/10.3389/fchem.2022.887960/full |
| work_keys_str_mv | AT jinling extremepointsorttransformationcombinedwithalongshorttermmemorynetworkalgorithmfortheramanbasedidentificationoftherapeuticmonoclonalantibodies AT luxiazheng extremepointsorttransformationcombinedwithalongshorttermmemorynetworkalgorithmfortheramanbasedidentificationoftherapeuticmonoclonalantibodies AT mingmingxu extremepointsorttransformationcombinedwithalongshorttermmemorynetworkalgorithmfortheramanbasedidentificationoftherapeuticmonoclonalantibodies AT gangchen extremepointsorttransformationcombinedwithalongshorttermmemorynetworkalgorithmfortheramanbasedidentificationoftherapeuticmonoclonalantibodies AT xiaowang extremepointsorttransformationcombinedwithalongshorttermmemorynetworkalgorithmfortheramanbasedidentificationoftherapeuticmonoclonalantibodies AT danzhuomao extremepointsorttransformationcombinedwithalongshorttermmemorynetworkalgorithmfortheramanbasedidentificationoftherapeuticmonoclonalantibodies AT hongshao extremepointsorttransformationcombinedwithalongshorttermmemorynetworkalgorithmfortheramanbasedidentificationoftherapeuticmonoclonalantibodies |