Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration
Early diagnosis of lung cancer to increase the survival rate, which is currently at a low range of mid-30%, remains a critical need. Despite this, multi-omics data have rarely been applied to non-small-cell lung cancer (NSCLC) diagnosis. We developed a multi-omics data-affinitive artificial intellig...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Biomolecules |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2218-273X/12/12/1839 |
| _version_ | 1797461193412050944 |
|---|---|
| author | Min-Koo Park Jin-Muk Lim Jinwoo Jeong Yeongjae Jang Ji-Won Lee Jeong-Chan Lee Hyungyu Kim Euiyul Koh Sung-Joo Hwang Hong-Gee Kim Keun-Cheol Kim |
| author_facet | Min-Koo Park Jin-Muk Lim Jinwoo Jeong Yeongjae Jang Ji-Won Lee Jeong-Chan Lee Hyungyu Kim Euiyul Koh Sung-Joo Hwang Hong-Gee Kim Keun-Cheol Kim |
| author_sort | Min-Koo Park |
| collection | DOAJ |
| description | Early diagnosis of lung cancer to increase the survival rate, which is currently at a low range of mid-30%, remains a critical need. Despite this, multi-omics data have rarely been applied to non-small-cell lung cancer (NSCLC) diagnosis. We developed a multi-omics data-affinitive artificial intelligence algorithm based on the graph convolutional network that integrates mRNA expression, DNA methylation, and DNA sequencing data. This NSCLC prediction model achieved a 93.7% macro F1-score, indicating that values for false positives and negatives were substantially low, which is desirable for accurate classification. Gene ontology enrichment and pathway analysis of features revealed that two major subtypes of NSCLC, lung adenocarcinoma and lung squamous cell carcinoma, have both specific and common GO biological processes. Numerous biomarkers (i.e., microRNA, long non-coding RNA, differentially methylated regions) were newly identified, whereas some biomarkers were consistent with previous findings in NSCLC (e.g., <i>SPRR1B</i>). Thus, using multi-omics data integration, we developed a promising cancer prediction algorithm. |
| first_indexed | 2024-03-09T17:15:54Z |
| format | Article |
| id | doaj.art-0e081868891d403eb15cb39af5c40538 |
| institution | Directory Open Access Journal |
| issn | 2218-273X |
| language | English |
| last_indexed | 2024-03-09T17:15:54Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biomolecules |
| spelling | doaj.art-0e081868891d403eb15cb39af5c405382023-11-24T13:34:14ZengMDPI AGBiomolecules2218-273X2022-12-011212183910.3390/biom12121839Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data IntegrationMin-Koo Park0Jin-Muk Lim1Jinwoo Jeong2Yeongjae Jang3Ji-Won Lee4Jeong-Chan Lee5Hyungyu Kim6Euiyul Koh7Sung-Joo Hwang8Hong-Gee Kim9Keun-Cheol Kim10Department of Biological Sciences, College of Natural Sciences, Kangwon National University, Chuncheon 24341, Republic of KoreaBiomedical Knowledge Engineering Laboratory, School of Dentistry and Dental Research Institute, Seoul National University, Seoul 08826, Republic of KoreaAI Institute, Alopax-Algo, Co., Ltd., Seoul 06978, Republic of KoreaMedical AI Team, Jonathan Wellcare Division, Acryl, Inc., Seoul 06069, Republic of KoreaHugenebio Institute, Bio-Innovation Park, Erom, Inc., Chuncheon 24427, Republic of KoreaHugenebio Institute, Bio-Innovation Park, Erom, Inc., Chuncheon 24427, Republic of KoreaMedical AI Team, Jonathan Wellcare Division, Acryl, Inc., Seoul 06069, Republic of KoreaMedical AI Team, Jonathan Wellcare Division, Acryl, Inc., Seoul 06069, Republic of KoreaIntegrated Medicine Institute, Loving Care Hospital, Seongnam 463400, Republic of KoreaBiomedical Knowledge Engineering Laboratory, School of Dentistry and Dental Research Institute, Seoul National University, Seoul 08826, Republic of KoreaDepartment of Biological Sciences, College of Natural Sciences, Kangwon National University, Chuncheon 24341, Republic of KoreaEarly diagnosis of lung cancer to increase the survival rate, which is currently at a low range of mid-30%, remains a critical need. Despite this, multi-omics data have rarely been applied to non-small-cell lung cancer (NSCLC) diagnosis. We developed a multi-omics data-affinitive artificial intelligence algorithm based on the graph convolutional network that integrates mRNA expression, DNA methylation, and DNA sequencing data. This NSCLC prediction model achieved a 93.7% macro F1-score, indicating that values for false positives and negatives were substantially low, which is desirable for accurate classification. Gene ontology enrichment and pathway analysis of features revealed that two major subtypes of NSCLC, lung adenocarcinoma and lung squamous cell carcinoma, have both specific and common GO biological processes. Numerous biomarkers (i.e., microRNA, long non-coding RNA, differentially methylated regions) were newly identified, whereas some biomarkers were consistent with previous findings in NSCLC (e.g., <i>SPRR1B</i>). Thus, using multi-omics data integration, we developed a promising cancer prediction algorithm.https://www.mdpi.com/2218-273X/12/12/1839non-small-cell lung cancerdeep learninggraph convolutional networkcancer predictionbiomarkergene ontology enrichment |
| spellingShingle | Min-Koo Park Jin-Muk Lim Jinwoo Jeong Yeongjae Jang Ji-Won Lee Jeong-Chan Lee Hyungyu Kim Euiyul Koh Sung-Joo Hwang Hong-Gee Kim Keun-Cheol Kim Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration Biomolecules non-small-cell lung cancer deep learning graph convolutional network cancer prediction biomarker gene ontology enrichment |
| title | Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration |
| title_full | Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration |
| title_fullStr | Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration |
| title_full_unstemmed | Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration |
| title_short | Deep-Learning Algorithm and Concomitant Biomarker Identification for NSCLC Prediction Using Multi-Omics Data Integration |
| title_sort | deep learning algorithm and concomitant biomarker identification for nsclc prediction using multi omics data integration |
| topic | non-small-cell lung cancer deep learning graph convolutional network cancer prediction biomarker gene ontology enrichment |
| url | https://www.mdpi.com/2218-273X/12/12/1839 |
| work_keys_str_mv | AT minkoopark deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT jinmuklim deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT jinwoojeong deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT yeongjaejang deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT jiwonlee deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT jeongchanlee deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT hyungyukim deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT euiyulkoh deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT sungjoohwang deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT honggeekim deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration AT keuncheolkim deeplearningalgorithmandconcomitantbiomarkeridentificationfornsclcpredictionusingmultiomicsdataintegration |