Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration
Identifying the cell of origin of cancer is important to guide treatment decisions. Machine learning approaches have been proposed to classify the cell of origin based on somatic mutation profiles from solid biopsies. However, solid biopsies can cause complications and certain tumors are not accessi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Life |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1729/12/1/1 |
| _version_ | 1818062722265251840 |
|---|---|
| author | Alexandra Danyi Myrthe Jager Jeroen de Ridder |
| author_facet | Alexandra Danyi Myrthe Jager Jeroen de Ridder |
| author_sort | Alexandra Danyi |
| collection | DOAJ |
| description | Identifying the cell of origin of cancer is important to guide treatment decisions. Machine learning approaches have been proposed to classify the cell of origin based on somatic mutation profiles from solid biopsies. However, solid biopsies can cause complications and certain tumors are not accessible. Liquid biopsies are promising alternatives but their somatic mutation profile is sparse and current machine learning models fail to perform in this setting. We propose an improved method to deal with sparsity in liquid biopsy data. Firstly, data augmentation is performed on sparse data to enhance model robustness. Secondly, we employ data integration to merge information from: (i) SNV density; (ii) SNVs in driver genes and (iii) trinucleotide motifs. Our adapted method achieves an average accuracy of 0.88 and 0.65 on data where only 70% and 2% of SNVs are retained, compared to 0.83 and 0.41 with the original model, respectively. The method and results presented here open the way for application of machine learning in the detection of the cell of origin of cancer from liquid biopsy data. |
| first_indexed | 2024-12-10T14:08:43Z |
| format | Article |
| id | doaj.art-65fd0467d5884c749b7a7a2633ce13d7 |
| institution | Directory Open Access Journal |
| issn | 2075-1729 |
| language | English |
| last_indexed | 2024-12-10T14:08:43Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Life |
| spelling | doaj.art-65fd0467d5884c749b7a7a2633ce13d72022-12-22T01:45:34ZengMDPI AGLife2075-17292021-12-01121110.3390/life12010001Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and IntegrationAlexandra Danyi0Myrthe Jager1Jeroen de Ridder2Center for Molecular Medicine, University Medical Center Utrecht, 3584 CX Utrecht, The NetherlandsCenter for Molecular Medicine, University Medical Center Utrecht, 3584 CX Utrecht, The NetherlandsCenter for Molecular Medicine, University Medical Center Utrecht, 3584 CX Utrecht, The NetherlandsIdentifying the cell of origin of cancer is important to guide treatment decisions. Machine learning approaches have been proposed to classify the cell of origin based on somatic mutation profiles from solid biopsies. However, solid biopsies can cause complications and certain tumors are not accessible. Liquid biopsies are promising alternatives but their somatic mutation profile is sparse and current machine learning models fail to perform in this setting. We propose an improved method to deal with sparsity in liquid biopsy data. Firstly, data augmentation is performed on sparse data to enhance model robustness. Secondly, we employ data integration to merge information from: (i) SNV density; (ii) SNVs in driver genes and (iii) trinucleotide motifs. Our adapted method achieves an average accuracy of 0.88 and 0.65 on data where only 70% and 2% of SNVs are retained, compared to 0.83 and 0.41 with the original model, respectively. The method and results presented here open the way for application of machine learning in the detection of the cell of origin of cancer from liquid biopsy data.https://www.mdpi.com/2075-1729/12/1/1deep learninggenomicsgenetic variabilitybioinformatics |
| spellingShingle | Alexandra Danyi Myrthe Jager Jeroen de Ridder Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration Life deep learning genomics genetic variability bioinformatics |
| title | Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration |
| title_full | Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration |
| title_fullStr | Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration |
| title_full_unstemmed | Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration |
| title_short | Cancer Type Classification in Liquid Biopsies Based on Sparse Mutational Profiles Enabled through Data Augmentation and Integration |
| title_sort | cancer type classification in liquid biopsies based on sparse mutational profiles enabled through data augmentation and integration |
| topic | deep learning genomics genetic variability bioinformatics |
| url | https://www.mdpi.com/2075-1729/12/1/1 |
| work_keys_str_mv | AT alexandradanyi cancertypeclassificationinliquidbiopsiesbasedonsparsemutationalprofilesenabledthroughdataaugmentationandintegration AT myrthejager cancertypeclassificationinliquidbiopsiesbasedonsparsemutationalprofilesenabledthroughdataaugmentationandintegration AT jeroenderidder cancertypeclassificationinliquidbiopsiesbasedonsparsemutationalprofilesenabledthroughdataaugmentationandintegration |