Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach
Epidermal growth factor receptor (EGFR) inhibitors have benefitted cancer patients worldwide, but resistance inevitably develops over time, resulting in treatment failures. An accurate prediction model for acquired resistance (AR) to EGFR inhibitors is critical for early diagnosis and according inte...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-01-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | http://www.mdpi.com/2072-6694/11/1/45 |
| _version_ | 1797765533519577088 |
|---|---|
| author | Young Rae Kim Yong Wan Kim Suh Eun Lee Hye Won Yang Sung Young Kim |
| author_facet | Young Rae Kim Yong Wan Kim Suh Eun Lee Hye Won Yang Sung Young Kim |
| author_sort | Young Rae Kim |
| collection | DOAJ |
| description | Epidermal growth factor receptor (EGFR) inhibitors have benefitted cancer patients worldwide, but resistance inevitably develops over time, resulting in treatment failures. An accurate prediction model for acquired resistance (AR) to EGFR inhibitors is critical for early diagnosis and according intervention, but is not yet available due to personal variations and the complex mechanisms of AR. Here, we have developed a novel pipeline to build a meta-analysis-based, multivariate model for personalized pathways in AR to EGFR inhibitors, using sophisticated machine learning algorithms. Surprisingly, the model achieved excellent predictive performance, with a cross-study validation area under curve (AUC) of over 0.9, and generalization performance on independent cohorts of samples, with a perfect AUC score of 1. Furthermore, the model showed excellent transferability across different cancer cell lines and EGFR inhibitors, including gefitinib, erlotinib, afatinib, and cetuximab. In conclusion, our model achieved high predictive accuracy through robust cross study validation, and enabled individualized prediction on newly introduced data. We also discovered common pathway alteration signatures for AR to EGFR inhibitors, which can provide directions for other follow-up studies. |
| first_indexed | 2024-03-12T20:11:29Z |
| format | Article |
| id | doaj.art-44d542e08375483095ef560ebf4ba3df |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-12T20:11:29Z |
| publishDate | 2019-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-44d542e08375483095ef560ebf4ba3df2023-08-02T01:38:56ZengMDPI AGCancers2072-66942019-01-011114510.3390/cancers11010045cancers11010045Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning ApproachYoung Rae Kim0Yong Wan Kim1Suh Eun Lee2Hye Won Yang3Sung Young Kim4Department of Biochemistry, School of Medicine, Konkuk University, 120, Neungdong-ro, Gwangjin-gu, Seoul 05029, KoreaDepartment of Biochemistry, School of Medicine, Konkuk University, 120, Neungdong-ro, Gwangjin-gu, Seoul 05029, KoreaDepartment of Biochemistry, School of Medicine, Konkuk University, 120, Neungdong-ro, Gwangjin-gu, Seoul 05029, KoreaSchool of Medicine, Trinity Biomedical Sciences Institute, Trinity College Dublin, 152-160 Pearse Street, D02 R590 Dublin, IrelandDepartment of Biochemistry, School of Medicine, Konkuk University, 120, Neungdong-ro, Gwangjin-gu, Seoul 05029, KoreaEpidermal growth factor receptor (EGFR) inhibitors have benefitted cancer patients worldwide, but resistance inevitably develops over time, resulting in treatment failures. An accurate prediction model for acquired resistance (AR) to EGFR inhibitors is critical for early diagnosis and according intervention, but is not yet available due to personal variations and the complex mechanisms of AR. Here, we have developed a novel pipeline to build a meta-analysis-based, multivariate model for personalized pathways in AR to EGFR inhibitors, using sophisticated machine learning algorithms. Surprisingly, the model achieved excellent predictive performance, with a cross-study validation area under curve (AUC) of over 0.9, and generalization performance on independent cohorts of samples, with a perfect AUC score of 1. Furthermore, the model showed excellent transferability across different cancer cell lines and EGFR inhibitors, including gefitinib, erlotinib, afatinib, and cetuximab. In conclusion, our model achieved high predictive accuracy through robust cross study validation, and enabled individualized prediction on newly introduced data. We also discovered common pathway alteration signatures for AR to EGFR inhibitors, which can provide directions for other follow-up studies.http://www.mdpi.com/2072-6694/11/1/45drug resistancegefitiniberlotinibbiostatisticsbioinformatics |
| spellingShingle | Young Rae Kim Yong Wan Kim Suh Eun Lee Hye Won Yang Sung Young Kim Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach Cancers drug resistance gefitinib erlotinib biostatistics bioinformatics |
| title | Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach |
| title_full | Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach |
| title_fullStr | Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach |
| title_full_unstemmed | Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach |
| title_short | Personalized Prediction of Acquired Resistance to EGFR-Targeted Inhibitors Using a Pathway-Based Machine Learning Approach |
| title_sort | personalized prediction of acquired resistance to egfr targeted inhibitors using a pathway based machine learning approach |
| topic | drug resistance gefitinib erlotinib biostatistics bioinformatics |
| url | http://www.mdpi.com/2072-6694/11/1/45 |
| work_keys_str_mv | AT youngraekim personalizedpredictionofacquiredresistancetoegfrtargetedinhibitorsusingapathwaybasedmachinelearningapproach AT yongwankim personalizedpredictionofacquiredresistancetoegfrtargetedinhibitorsusingapathwaybasedmachinelearningapproach AT suheunlee personalizedpredictionofacquiredresistancetoegfrtargetedinhibitorsusingapathwaybasedmachinelearningapproach AT hyewonyang personalizedpredictionofacquiredresistancetoegfrtargetedinhibitorsusingapathwaybasedmachinelearningapproach AT sungyoungkim personalizedpredictionofacquiredresistancetoegfrtargetedinhibitorsusingapathwaybasedmachinelearningapproach |