Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example
Kidney cancer has a high metastatic potential with up to 30% of patients developing distant metastasis after surgery. We assessed the value of AI models in predicting the metastatic potential of clear cell renal cell carcinoma (ccRCC), based on the genetic data. Tissue samples from patients with bot...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2024-01-01
|
| Series: | BIO Web of Conferences |
| Online Access: | https://www.bio-conferences.org/articles/bioconf/pdf/2024/19/bioconf_ifbioscfu2024_01009.pdf |
| _version_ | 1827287279643656192 |
|---|---|
| author | Boyko Maria Antipushina Ekaterina Bernstein Alexander Sharaev Maxim Apanovich Natalya Matveev Vsevolod Alferova Vera Matveev Alexey |
| author_facet | Boyko Maria Antipushina Ekaterina Bernstein Alexander Sharaev Maxim Apanovich Natalya Matveev Vsevolod Alferova Vera Matveev Alexey |
| author_sort | Boyko Maria |
| collection | DOAJ |
| description | Kidney cancer has a high metastatic potential with up to 30% of patients developing distant metastasis after surgery. We assessed the value of AI models in predicting the metastatic potential of clear cell renal cell carcinoma (ccRCC), based on the genetic data. Tissue samples from patients with both metastatic and non-metastatic squamous cell carcinoma were analyzed, focusing on the expression and methylation levels of specific protein-coding (PC) and microRNA (miRNA) genes. Using quantitative PCR and data classification techniques, we found a correlation between metastasis and reduced expression of PC-genes CA9, NDUFA4L2, EGLN3, and BHLHE41, as well as increased methylation in miRNA genes MIR125B-1, MIR137, MIR375, MIR193A, and MIR34B. AI models were built for predicting distant metastases based on the expression values and methylation status of selected genes. One model is based on solving a regression problem and is non-interpretable, while another one is based on proposed decision rules and is interpretable. The quality of the models was assessed using sensitivity and specificity metrics, and cross-validation technology was used to ensure the reliability of the results. |
| first_indexed | 2024-04-24T10:55:41Z |
| format | Article |
| id | doaj.art-bd492b02e3d44d59b39f086d7511086d |
| institution | Directory Open Access Journal |
| issn | 2117-4458 |
| language | English |
| last_indexed | 2024-04-24T10:55:41Z |
| publishDate | 2024-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | BIO Web of Conferences |
| spelling | doaj.art-bd492b02e3d44d59b39f086d7511086d2024-04-12T07:36:42ZengEDP SciencesBIO Web of Conferences2117-44582024-01-011000100910.1051/bioconf/202410001009bioconf_ifbioscfu2024_01009Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer exampleBoyko Maria0Antipushina Ekaterina1Bernstein Alexander2Sharaev Maxim3Apanovich Natalya4Matveev Vsevolod5Alferova Vera6Matveev Alexey7BIMAI-Lab, Biomedically Informed Artificial Intelligence Laboratory, University of SharjahBIMAI-Lab, Biomedically Informed Artificial Intelligence Laboratory, University of SharjahBIMAI-Lab, Biomedically Informed Artificial Intelligence Laboratory, University of SharjahBIMAI-Lab, Biomedically Informed Artificial Intelligence Laboratory, University of SharjahResearch Center for Medical Genetics (RCMG)National Medical Research Center of Oncology named after N.N. BlokhinPirogov Russian National Research Medical UniversityNational Medical Research Center of Oncology named after N.N. BlokhinKidney cancer has a high metastatic potential with up to 30% of patients developing distant metastasis after surgery. We assessed the value of AI models in predicting the metastatic potential of clear cell renal cell carcinoma (ccRCC), based on the genetic data. Tissue samples from patients with both metastatic and non-metastatic squamous cell carcinoma were analyzed, focusing on the expression and methylation levels of specific protein-coding (PC) and microRNA (miRNA) genes. Using quantitative PCR and data classification techniques, we found a correlation between metastasis and reduced expression of PC-genes CA9, NDUFA4L2, EGLN3, and BHLHE41, as well as increased methylation in miRNA genes MIR125B-1, MIR137, MIR375, MIR193A, and MIR34B. AI models were built for predicting distant metastases based on the expression values and methylation status of selected genes. One model is based on solving a regression problem and is non-interpretable, while another one is based on proposed decision rules and is interpretable. The quality of the models was assessed using sensitivity and specificity metrics, and cross-validation technology was used to ensure the reliability of the results.https://www.bio-conferences.org/articles/bioconf/pdf/2024/19/bioconf_ifbioscfu2024_01009.pdf |
| spellingShingle | Boyko Maria Antipushina Ekaterina Bernstein Alexander Sharaev Maxim Apanovich Natalya Matveev Vsevolod Alferova Vera Matveev Alexey Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example BIO Web of Conferences |
| title | Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example |
| title_full | Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example |
| title_fullStr | Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example |
| title_full_unstemmed | Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example |
| title_short | Interpretable AI models for predicting distant metastasis development based on genetic data: Kidney cancer example |
| title_sort | interpretable ai models for predicting distant metastasis development based on genetic data kidney cancer example |
| url | https://www.bio-conferences.org/articles/bioconf/pdf/2024/19/bioconf_ifbioscfu2024_01009.pdf |
| work_keys_str_mv | AT boykomaria interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample AT antipushinaekaterina interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample AT bernsteinalexander interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample AT sharaevmaxim interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample AT apanovichnatalya interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample AT matveevvsevolod interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample AT alferovavera interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample AT matveevalexey interpretableaimodelsforpredictingdistantmetastasisdevelopmentbasedongeneticdatakidneycancerexample |