Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine Learning
Wilms’ tumors are pediatric malignancies that are thought to arise from faulty kidney development. They contain a wide range of poorly differentiated cell states resembling various distorted developmental stages of the fetal kidney, and as a result, differ between patients in a continuous manner tha...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | International Journal of Molecular Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1422-0067/24/4/3532 |
| _version_ | 1797620539394621440 |
|---|---|
| author | Yaron Trink Achia Urbach Benjamin Dekel Peter Hohenstein Jacob Goldberger Tomer Kalisky |
| author_facet | Yaron Trink Achia Urbach Benjamin Dekel Peter Hohenstein Jacob Goldberger Tomer Kalisky |
| author_sort | Yaron Trink |
| collection | DOAJ |
| description | Wilms’ tumors are pediatric malignancies that are thought to arise from faulty kidney development. They contain a wide range of poorly differentiated cell states resembling various distorted developmental stages of the fetal kidney, and as a result, differ between patients in a continuous manner that is not well understood. Here, we used three computational approaches to characterize this continuous heterogeneity in high-risk blastemal-type Wilms’ tumors. Using Pareto task inference, we show that the tumors form a triangle-shaped continuum in latent space that is bounded by three tumor archetypes with “stromal”, “blastemal”, and “epithelial” characteristics, which resemble the un-induced mesenchyme, the cap mesenchyme, and early epithelial structures of the fetal kidney. By fitting a generative probabilistic “grade of membership” model, we show that each tumor can be represented as a unique mixture of three hidden “topics” with blastemal, stromal, and epithelial characteristics. Likewise, cellular deconvolution allows us to represent each tumor in the continuum as a unique combination of fetal kidney-like cell states. These results highlight the relationship between Wilms’ tumors and kidney development, and we anticipate that they will pave the way for more quantitative strategies for tumor stratification and classification. |
| first_indexed | 2024-03-11T08:42:59Z |
| format | Article |
| id | doaj.art-6f087ecfe57f4510854bfb26377fd0e1 |
| institution | Directory Open Access Journal |
| issn | 1661-6596 1422-0067 |
| language | English |
| last_indexed | 2024-03-11T08:42:59Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Molecular Sciences |
| spelling | doaj.art-6f087ecfe57f4510854bfb26377fd0e12023-11-16T21:01:22ZengMDPI AGInternational Journal of Molecular Sciences1661-65961422-00672023-02-01244353210.3390/ijms24043532Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine LearningYaron Trink0Achia Urbach1Benjamin Dekel2Peter Hohenstein3Jacob Goldberger4Tomer Kalisky5Faculty of Engineering and Bar-Ilan Institute of Nanotechnology and Advanced Materials (BINA), Bar-Ilan University, Ramat Gan 5290002, IsraelThe Mina and Everard Goodman Faculty of Life Sciences, Bar-Ilan University, Ramat Gan 5290002, IsraelPediatric Stem Cell Research Institute and Division of Pediatric Nephrology, Edmond and Lily Safra Children’s Hospital, Sheba Medical Center, Tel-Hashomer 5262000, IsraelDepartment of Human Genetics, Leiden University Medical Center, 2300 RC Leiden, The NetherlandsFaculty of Engineering and Bar-Ilan Institute of Nanotechnology and Advanced Materials (BINA), Bar-Ilan University, Ramat Gan 5290002, IsraelFaculty of Engineering and Bar-Ilan Institute of Nanotechnology and Advanced Materials (BINA), Bar-Ilan University, Ramat Gan 5290002, IsraelWilms’ tumors are pediatric malignancies that are thought to arise from faulty kidney development. They contain a wide range of poorly differentiated cell states resembling various distorted developmental stages of the fetal kidney, and as a result, differ between patients in a continuous manner that is not well understood. Here, we used three computational approaches to characterize this continuous heterogeneity in high-risk blastemal-type Wilms’ tumors. Using Pareto task inference, we show that the tumors form a triangle-shaped continuum in latent space that is bounded by three tumor archetypes with “stromal”, “blastemal”, and “epithelial” characteristics, which resemble the un-induced mesenchyme, the cap mesenchyme, and early epithelial structures of the fetal kidney. By fitting a generative probabilistic “grade of membership” model, we show that each tumor can be represented as a unique mixture of three hidden “topics” with blastemal, stromal, and epithelial characteristics. Likewise, cellular deconvolution allows us to represent each tumor in the continuum as a unique combination of fetal kidney-like cell states. These results highlight the relationship between Wilms’ tumors and kidney development, and we anticipate that they will pave the way for more quantitative strategies for tumor stratification and classification.https://www.mdpi.com/1422-0067/24/4/3532Wilms’ tumorspareto task inferencetopic modelingcellular deconvolution |
| spellingShingle | Yaron Trink Achia Urbach Benjamin Dekel Peter Hohenstein Jacob Goldberger Tomer Kalisky Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine Learning International Journal of Molecular Sciences Wilms’ tumors pareto task inference topic modeling cellular deconvolution |
| title | Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine Learning |
| title_full | Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine Learning |
| title_fullStr | Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine Learning |
| title_full_unstemmed | Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine Learning |
| title_short | Characterization of Continuous Transcriptional Heterogeneity in High-Risk Blastemal-Type Wilms’ Tumors Using Unsupervised Machine Learning |
| title_sort | characterization of continuous transcriptional heterogeneity in high risk blastemal type wilms tumors using unsupervised machine learning |
| topic | Wilms’ tumors pareto task inference topic modeling cellular deconvolution |
| url | https://www.mdpi.com/1422-0067/24/4/3532 |
| work_keys_str_mv | AT yarontrink characterizationofcontinuoustranscriptionalheterogeneityinhighriskblastemaltypewilmstumorsusingunsupervisedmachinelearning AT achiaurbach characterizationofcontinuoustranscriptionalheterogeneityinhighriskblastemaltypewilmstumorsusingunsupervisedmachinelearning AT benjamindekel characterizationofcontinuoustranscriptionalheterogeneityinhighriskblastemaltypewilmstumorsusingunsupervisedmachinelearning AT peterhohenstein characterizationofcontinuoustranscriptionalheterogeneityinhighriskblastemaltypewilmstumorsusingunsupervisedmachinelearning AT jacobgoldberger characterizationofcontinuoustranscriptionalheterogeneityinhighriskblastemaltypewilmstumorsusingunsupervisedmachinelearning AT tomerkalisky characterizationofcontinuoustranscriptionalheterogeneityinhighriskblastemaltypewilmstumorsusingunsupervisedmachinelearning |