Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis
Myasthenia gravis (MG) is a neuromuscular junction disease with a complex pathophysiology and clinical variation for which no clear biomarker has been discovered. We hypothesized that because changes in gut microbiome composition often occur in autoimmune diseases, the gut microbiome structures of p...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Microbiology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1227300/full |
| _version_ | 1797671818298916864 |
|---|---|
| author | Che-Cheng Chang Che-Cheng Chang Che-Cheng Chang Tzu-Chi Liu Chi-Jie Lu Chi-Jie Lu Chi-Jie Lu Hou-Chang Chiu Hou-Chang Chiu Wei-Ning Lin |
| author_facet | Che-Cheng Chang Che-Cheng Chang Che-Cheng Chang Tzu-Chi Liu Chi-Jie Lu Chi-Jie Lu Chi-Jie Lu Hou-Chang Chiu Hou-Chang Chiu Wei-Ning Lin |
| author_sort | Che-Cheng Chang |
| collection | DOAJ |
| description | Myasthenia gravis (MG) is a neuromuscular junction disease with a complex pathophysiology and clinical variation for which no clear biomarker has been discovered. We hypothesized that because changes in gut microbiome composition often occur in autoimmune diseases, the gut microbiome structures of patients with MG would differ from those without, and supervised machine learning (ML) analysis strategy could be trained using data from gut microbiota for diagnostic screening of MG. Genomic DNA from the stool samples of MG and those without were collected and established a sequencing library by constructing amplicon sequence variants (ASVs) and completing taxonomic classification of each representative DNA sequence. Four ML methods, namely least absolute shrinkage and selection operator, extreme gradient boosting (XGBoost), random forest, and classification and regression trees with nested leave-one-out cross-validation were trained using ASV taxon–based data and full ASV–based data to identify key ASVs in each data set. The results revealed XGBoost to have the best predicted performance. Overlapping key features extracted when XGBoost was trained using the full ASV–based and ASV taxon–based data were identified, and 31 high-importance ASVs (HIASVs) were obtained, assigned importance scores, and ranked. The most significant difference observed was in the abundance of bacteria in the Lachnospiraceae and Ruminococcaceae families. The 31 HIASVs were used to train the XGBoost algorithm to differentiate individuals with and without MG. The model had high diagnostic classification power and could accurately predict and identify patients with MG. In addition, the abundance of Lachnospiraceae was associated with limb weakness severity. In this study, we discovered that the composition of gut microbiomes differed between MG and non-MG subjects. In addition, the proposed XGBoost model trained using 31 HIASVs had the most favorable performance with respect to analyzing gut microbiomes. These HIASVs selected by the ML model may serve as biomarkers for clinical use and mechanistic study in the future. Our proposed ML model can identify several taxonomic markers and effectively discriminate patients with MG from those without with a high accuracy, the ML strategy can be applied as a benchmark to conduct noninvasive screening of MG. |
| first_indexed | 2024-03-11T21:21:01Z |
| format | Article |
| id | doaj.art-840ae868fcdd4d0084acfde0b99ddbe9 |
| institution | Directory Open Access Journal |
| issn | 1664-302X |
| language | English |
| last_indexed | 2024-03-11T21:21:01Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Microbiology |
| spelling | doaj.art-840ae868fcdd4d0084acfde0b99ddbe92023-09-28T06:05:21ZengFrontiers Media S.A.Frontiers in Microbiology1664-302X2023-09-011410.3389/fmicb.2023.12273001227300Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravisChe-Cheng Chang0Che-Cheng Chang1Che-Cheng Chang2Tzu-Chi Liu3Chi-Jie Lu4Chi-Jie Lu5Chi-Jie Lu6Hou-Chang Chiu7Hou-Chang Chiu8Wei-Ning Lin9PhD Program in Nutrition and Food Science, Fu Jen Catholic University, New Taipei City, TaiwanDepartment of Neurology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City, TaiwanGraduate Institute of Biomedical and Pharmaceutical Science, Fu Jen Catholic University, New Taipei City, TaiwanGraduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City, TaiwanGraduate Institute of Business Administration, Fu Jen Catholic University, New Taipei City, TaiwanArtificial Intelligence Development Center, Fu Jen Catholic University, New Taipei City, TaiwanDepartment of Information Management, Fu Jen Catholic University, New Taipei City, TaiwanSchool of Medicine, Fu Jen Catholic University, New Taipei City, TaiwanDepartment of Neurology, Taipei Medical University, Shuang-Ho Hospital, New Taipei City, TaiwanGraduate Institute of Biomedical and Pharmaceutical Science, Fu Jen Catholic University, New Taipei City, TaiwanMyasthenia gravis (MG) is a neuromuscular junction disease with a complex pathophysiology and clinical variation for which no clear biomarker has been discovered. We hypothesized that because changes in gut microbiome composition often occur in autoimmune diseases, the gut microbiome structures of patients with MG would differ from those without, and supervised machine learning (ML) analysis strategy could be trained using data from gut microbiota for diagnostic screening of MG. Genomic DNA from the stool samples of MG and those without were collected and established a sequencing library by constructing amplicon sequence variants (ASVs) and completing taxonomic classification of each representative DNA sequence. Four ML methods, namely least absolute shrinkage and selection operator, extreme gradient boosting (XGBoost), random forest, and classification and regression trees with nested leave-one-out cross-validation were trained using ASV taxon–based data and full ASV–based data to identify key ASVs in each data set. The results revealed XGBoost to have the best predicted performance. Overlapping key features extracted when XGBoost was trained using the full ASV–based and ASV taxon–based data were identified, and 31 high-importance ASVs (HIASVs) were obtained, assigned importance scores, and ranked. The most significant difference observed was in the abundance of bacteria in the Lachnospiraceae and Ruminococcaceae families. The 31 HIASVs were used to train the XGBoost algorithm to differentiate individuals with and without MG. The model had high diagnostic classification power and could accurately predict and identify patients with MG. In addition, the abundance of Lachnospiraceae was associated with limb weakness severity. In this study, we discovered that the composition of gut microbiomes differed between MG and non-MG subjects. In addition, the proposed XGBoost model trained using 31 HIASVs had the most favorable performance with respect to analyzing gut microbiomes. These HIASVs selected by the ML model may serve as biomarkers for clinical use and mechanistic study in the future. Our proposed ML model can identify several taxonomic markers and effectively discriminate patients with MG from those without with a high accuracy, the ML strategy can be applied as a benchmark to conduct noninvasive screening of MG.https://www.frontiersin.org/articles/10.3389/fmicb.2023.1227300/fullmyasthenia gravisamplicon sequence variantsgut microbiotamachine learningextreme gradient boostingleave one out cross validation |
| spellingShingle | Che-Cheng Chang Che-Cheng Chang Che-Cheng Chang Tzu-Chi Liu Chi-Jie Lu Chi-Jie Lu Chi-Jie Lu Hou-Chang Chiu Hou-Chang Chiu Wei-Ning Lin Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis Frontiers in Microbiology myasthenia gravis amplicon sequence variants gut microbiota machine learning extreme gradient boosting leave one out cross validation |
| title | Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis |
| title_full | Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis |
| title_fullStr | Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis |
| title_full_unstemmed | Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis |
| title_short | Machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis |
| title_sort | machine learning strategy for identifying altered gut microbiomes for diagnostic screening in myasthenia gravis |
| topic | myasthenia gravis amplicon sequence variants gut microbiota machine learning extreme gradient boosting leave one out cross validation |
| url | https://www.frontiersin.org/articles/10.3389/fmicb.2023.1227300/full |
| work_keys_str_mv | AT chechengchang machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT chechengchang machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT chechengchang machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT tzuchiliu machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT chijielu machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT chijielu machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT chijielu machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT houchangchiu machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT houchangchiu machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis AT weininglin machinelearningstrategyforidentifyingalteredgutmicrobiomesfordiagnosticscreeninginmyastheniagravis |