Autoencoder techniques for survival analysis on renal cell carcinoma.
Survival is the gold standard in oncology when determining the real impact of therapies in patients outcome. Thus, identifying molecular predictors of survival (like genetic alterations or transcriptomic patterns of gene expression) is one of the most relevant fields in current research. Statistical...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0321045 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849762439929790464 |
|---|---|
| author | Iñigo Sanz Ilundain Laura Hernández-Lorenzo Cristina Rodríguez-Antona Jesús García-Donas José L Ayala |
| author_facet | Iñigo Sanz Ilundain Laura Hernández-Lorenzo Cristina Rodríguez-Antona Jesús García-Donas José L Ayala |
| author_sort | Iñigo Sanz Ilundain |
| collection | DOAJ |
| description | Survival is the gold standard in oncology when determining the real impact of therapies in patients outcome. Thus, identifying molecular predictors of survival (like genetic alterations or transcriptomic patterns of gene expression) is one of the most relevant fields in current research. Statistical methods and metrics to analyze time-to-event data are crucial in understanding disease progression and the effectiveness of treatments. However, in the medical field, data is often high-dimensional, complicating the application of such methodologies. In this study, we addressed this challenge by compressing the high-dimensional transcriptomic data of patients treated with immunotherapy (avelumab + axitinib) and a TKI (sunitinib) into latent, meaningful features using autoencoders. We applied a semi-parametric statistical approach based on the COX Proportional Hazards model, coupled with Breslow's estimator, to predict each patient's Progression-Free Survival (PFS) and determine survival functions. Our analysis explored various penalty configurations and their combinations. Given the complexity of transcriptomic data, we extended our model to incorporate both tabular data and its graph variant, where edges represent protein-protein interactions between genes, offering a more insightful approach. Recognizing the interpretability challenges inherent in neural networks, particularly autoencoders, we analyzed the mutual information between genes in the original data and their latent feature representations to clarify which genes are most associated with specific latent variables. The results indicate that different types of autoencoders are better suited for different tasks: denoising autoencoders excel at accurate reconstruction, while the sparse variant is more effective at producing meaningful representations. Additionally, combining these penalties enhances both reconstruction quality and the interpretability of latent features. The interpretable models identified genes such as LRP2 and ACE2 as highly relevant to renal cell carcinoma. This research underscores the utility of autoencoders in managing high-dimensional data problems. |
| format | Article |
| id | doaj-art-c157389d3da948fcb39e1e97b04db993 |
| institution | DOAJ |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-c157389d3da948fcb39e1e97b04db9932025-08-20T03:05:44ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032104510.1371/journal.pone.0321045Autoencoder techniques for survival analysis on renal cell carcinoma.Iñigo Sanz IlundainLaura Hernández-LorenzoCristina Rodríguez-AntonaJesús García-DonasJosé L AyalaSurvival is the gold standard in oncology when determining the real impact of therapies in patients outcome. Thus, identifying molecular predictors of survival (like genetic alterations or transcriptomic patterns of gene expression) is one of the most relevant fields in current research. Statistical methods and metrics to analyze time-to-event data are crucial in understanding disease progression and the effectiveness of treatments. However, in the medical field, data is often high-dimensional, complicating the application of such methodologies. In this study, we addressed this challenge by compressing the high-dimensional transcriptomic data of patients treated with immunotherapy (avelumab + axitinib) and a TKI (sunitinib) into latent, meaningful features using autoencoders. We applied a semi-parametric statistical approach based on the COX Proportional Hazards model, coupled with Breslow's estimator, to predict each patient's Progression-Free Survival (PFS) and determine survival functions. Our analysis explored various penalty configurations and their combinations. Given the complexity of transcriptomic data, we extended our model to incorporate both tabular data and its graph variant, where edges represent protein-protein interactions between genes, offering a more insightful approach. Recognizing the interpretability challenges inherent in neural networks, particularly autoencoders, we analyzed the mutual information between genes in the original data and their latent feature representations to clarify which genes are most associated with specific latent variables. The results indicate that different types of autoencoders are better suited for different tasks: denoising autoencoders excel at accurate reconstruction, while the sparse variant is more effective at producing meaningful representations. Additionally, combining these penalties enhances both reconstruction quality and the interpretability of latent features. The interpretable models identified genes such as LRP2 and ACE2 as highly relevant to renal cell carcinoma. This research underscores the utility of autoencoders in managing high-dimensional data problems.https://doi.org/10.1371/journal.pone.0321045 |
| spellingShingle | Iñigo Sanz Ilundain Laura Hernández-Lorenzo Cristina Rodríguez-Antona Jesús García-Donas José L Ayala Autoencoder techniques for survival analysis on renal cell carcinoma. PLoS ONE |
| title | Autoencoder techniques for survival analysis on renal cell carcinoma. |
| title_full | Autoencoder techniques for survival analysis on renal cell carcinoma. |
| title_fullStr | Autoencoder techniques for survival analysis on renal cell carcinoma. |
| title_full_unstemmed | Autoencoder techniques for survival analysis on renal cell carcinoma. |
| title_short | Autoencoder techniques for survival analysis on renal cell carcinoma. |
| title_sort | autoencoder techniques for survival analysis on renal cell carcinoma |
| url | https://doi.org/10.1371/journal.pone.0321045 |
| work_keys_str_mv | AT inigosanzilundain autoencodertechniquesforsurvivalanalysisonrenalcellcarcinoma AT laurahernandezlorenzo autoencodertechniquesforsurvivalanalysisonrenalcellcarcinoma AT cristinarodriguezantona autoencodertechniquesforsurvivalanalysisonrenalcellcarcinoma AT jesusgarciadonas autoencodertechniquesforsurvivalanalysisonrenalcellcarcinoma AT joselayala autoencodertechniquesforsurvivalanalysisonrenalcellcarcinoma |