Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods
Abstract Classification of adenocarcinoma (AC) and squamous cell carcinoma (SCC) poses significant challenges for cytopathologists, often necessitating clinical tests and biopsies that delay treatment initiation. To address this, we developed a machine learning-based approach utilizing resected lung...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | npj Systems Biology and Applications |
| Online Access: | https://doi.org/10.1038/s41540-025-00491-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594623040585728 |
|---|---|
| author | Pragya Kashyap Kalbhavi Vadhi Raj Jyoti Sharma Naveen Dutt Pankaj Yadav |
| author_facet | Pragya Kashyap Kalbhavi Vadhi Raj Jyoti Sharma Naveen Dutt Pankaj Yadav |
| author_sort | Pragya Kashyap |
| collection | DOAJ |
| description | Abstract Classification of adenocarcinoma (AC) and squamous cell carcinoma (SCC) poses significant challenges for cytopathologists, often necessitating clinical tests and biopsies that delay treatment initiation. To address this, we developed a machine learning-based approach utilizing resected lung-tissue microbiome of AC and SCC patients for subtype classification. Differentially enriched taxa were identified using LEfSe, revealing ten potential microbial markers. Linear discriminant analysis (LDA) was subsequently applied to enhance inter-class separability. Next, benchmarking was performed across six different supervised-classification algorithms viz. logistic-regression, naïve-bayes, random-forest, extreme-gradient-boost (XGBoost), k-nearest neighbor, and deep neural network. Noteworthy, XGBoost, with an accuracy of 76.25%, and AUROC (area-under-receiver-operating-characteristic) of 0.81 with 69% specificity and 76% sensitivity, outperform the other five classification algorithms using LDA-transformed features. Validation on an independent dataset confirmed its robustness with an AUROC of 0.71, with minimal false positives and negatives. This study is the first to classify AC and SCC subtypes using lung-tissue microbiome. |
| format | Article |
| id | doaj-art-641d748f844d43ecbcb378e0c6adc3c7 |
| institution | Kabale University |
| issn | 2056-7189 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Systems Biology and Applications |
| spelling | doaj-art-641d748f844d43ecbcb378e0c6adc3c72025-01-19T12:28:17ZengNature Portfolionpj Systems Biology and Applications2056-71892025-01-0111111310.1038/s41540-025-00491-4Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methodsPragya Kashyap0Kalbhavi Vadhi Raj1Jyoti Sharma2Naveen Dutt3Pankaj Yadav4Department of Bioscience & Bioengineering, Indian Institute of TechnologyDepartment of Electrical Engineering, Indian Institute of TechnologyDepartment of Bioscience & Bioengineering, Indian Institute of TechnologyDepartment of Pulmonary Medicine, All India Institute of Medical SciencesDepartment of Bioscience & Bioengineering, Indian Institute of TechnologyAbstract Classification of adenocarcinoma (AC) and squamous cell carcinoma (SCC) poses significant challenges for cytopathologists, often necessitating clinical tests and biopsies that delay treatment initiation. To address this, we developed a machine learning-based approach utilizing resected lung-tissue microbiome of AC and SCC patients for subtype classification. Differentially enriched taxa were identified using LEfSe, revealing ten potential microbial markers. Linear discriminant analysis (LDA) was subsequently applied to enhance inter-class separability. Next, benchmarking was performed across six different supervised-classification algorithms viz. logistic-regression, naïve-bayes, random-forest, extreme-gradient-boost (XGBoost), k-nearest neighbor, and deep neural network. Noteworthy, XGBoost, with an accuracy of 76.25%, and AUROC (area-under-receiver-operating-characteristic) of 0.81 with 69% specificity and 76% sensitivity, outperform the other five classification algorithms using LDA-transformed features. Validation on an independent dataset confirmed its robustness with an AUROC of 0.71, with minimal false positives and negatives. This study is the first to classify AC and SCC subtypes using lung-tissue microbiome.https://doi.org/10.1038/s41540-025-00491-4 |
| spellingShingle | Pragya Kashyap Kalbhavi Vadhi Raj Jyoti Sharma Naveen Dutt Pankaj Yadav Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods npj Systems Biology and Applications |
| title | Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods |
| title_full | Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods |
| title_fullStr | Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods |
| title_full_unstemmed | Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods |
| title_short | Classification of NSCLC subtypes using lung microbiome from resected tissue based on machine learning methods |
| title_sort | classification of nsclc subtypes using lung microbiome from resected tissue based on machine learning methods |
| url | https://doi.org/10.1038/s41540-025-00491-4 |
| work_keys_str_mv | AT pragyakashyap classificationofnsclcsubtypesusinglungmicrobiomefromresectedtissuebasedonmachinelearningmethods AT kalbhavivadhiraj classificationofnsclcsubtypesusinglungmicrobiomefromresectedtissuebasedonmachinelearningmethods AT jyotisharma classificationofnsclcsubtypesusinglungmicrobiomefromresectedtissuebasedonmachinelearningmethods AT naveendutt classificationofnsclcsubtypesusinglungmicrobiomefromresectedtissuebasedonmachinelearningmethods AT pankajyadav classificationofnsclcsubtypesusinglungmicrobiomefromresectedtissuebasedonmachinelearningmethods |