Dataset Information

Every which way? On predicting tumor evolution using cancer progression models.

ABSTRACT: Successful prediction of the likely paths of tumor progression is valuable for diagnostic, prognostic, and treatment purposes. Cancer progression models (CPMs) use cross-sectional samples to identify restrictions in the order of accumulation of driver mutations and thus CPMs encode the paths of tumor progression. Here we analyze the performance of four CPMs to examine whether they can be used to predict the true distribution of paths of tumor progression and to estimate evolutionary unpredictability. Employing simulations we show that if fitness landscapes are single peaked (have a single fitness maximum) there is good agreement between true and predicted distributions of paths of tumor progression when sample sizes are large, but performance is poor with the currently common much smaller sample sizes. Under multi-peaked fitness landscapes (i.e., those with multiple fitness maxima), performance is poor and improves only slightly with sample size. In all cases, detection regime (when tumors are sampled) is a key determinant of performance. Estimates of evolutionary unpredictability from the best performing CPM, among the four examined, tend to overestimate the true unpredictability and the bias is affected by detection regime; CPMs could be useful for estimating upper bounds to the true evolutionary unpredictability. Analysis of twenty-two cancer data sets shows low evolutionary unpredictability for several of the data sets. But most of the predictions of paths of tumor progression are very unreliable, and unreliability increases with the number of features analyzed. Our results indicate that CPMs could be valuable tools for predicting cancer progression but that, currently, obtaining useful predictions of paths of tumor progression from CPMs is dubious, and emphasize the need for methodological work that can account for the probably multi-peaked fitness landscapes in cancer.

SUBMITTER: Diaz-Uriarte R

PROVIDER: S-EPMC6693785 | biostudies-literature | 2019 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Every which way? On predicting tumor evolution using cancer progression models.

Diaz-Uriarte Ramon R Vasallo Claudia C

PLoS computational biology 20190802 8

Successful prediction of the likely paths of tumor progression is valuable for diagnostic, prognostic, and treatment purposes. Cancer progression models (CPMs) use cross-sectional samples to identify restrictions in the order of accumulation of driver mutations and thus CPMs encode the paths of tumor progression. Here we analyze the performance of four CPMs to examine whether they can be used to predict the true distribution of paths of tumor progression and to estimate evolutionary unpredictabi ...[more]

PMID: 31374072

Similar Datasets

Project description:The diverse clinical outcomes of prostate cancer have led to the development of gene signature assays predicting disease progression. Improved prostate cancer progression biomarkers are needed as current RNA biomarker tests have varying success for intermediate prostate cancer. Interest grows in universal gene signatures for invasive carcinoma progression. Early breast and prostate cancers share characteristics, including hormone dependence and BRCA1/2 mutations. Given the similarities in the pathobiology of breast and prostate cancer, we utilized the NanoString BC360 panel, comprising the validated PAM50 classifier and pathway-specific signatures associated with general tumor progression as well as breast cancer-specific classifiers. This retrospective cohort of primary prostate cancers (n=53) was stratified according to biochemical recurrence (BCR) status and the CAPRA-S to identify genes related to high-risk disease. Two public cohort (TCGA-PRAD and GSE54460) were used to validate the results. Expression profiling of our cohort uncovered associations between PIP and INHBA with BCR and high CAPRA-S score, as well as associations between VCAN, SFRP2, and THBS4 and BCR. Despite low levels of the ESR1 gene compared to AR, we found strong expression of the ER signaling signature, suggesting that BCR may be driven by ER-mediated pathways. Kaplan-Meier and univariate Cox proportional hazards regression analysis indicated the expression of ESR1, PGR, VCAN, and SFRP2 could predict the occurrence of relapse events. This is in keeping with the pathways represented by these genes which contribute to angiogenesis and the epithelial-mesenchymal transition. It is likely that VCAN works by activating the stroma and remodeling the tumor microenvironment. Additionally, SFRP2 overexpression has been associated with increased tumor size and reduced survival rates in breast cancer and among prostate cancer patients who experienced BCR. ESR1 influences disease progression by activating stroma, stimulating stem/progenitor prostate cancer, and inducing TGF-β. Estrogen signaling may therefore serve as a surrogate to AR signaling during progression and in hormone-refractory disease, particularly in prostate cancer patients with stromal-rich tumors. Collectively, the use of agnostic biomarkers developed for breast cancer stratification has facilitated a precise clinical classification of patients undergoing radical prostatectomy and highlighted the therapeutic potential of targeting estrogen signaling in prostate cancer.

Project description:PurposePrior artificial intelligence (AI) models for predicting glaucoma progression have used traditional classifiers that do not consider the longitudinal nature of patients' follow-up. In this study, we developed survival-based AI models for predicting glaucoma patients' progression to surgery, comparing performance of regression-, tree-, and deep learning-based approaches.DesignRetrospective observational study.SubjectsPatients with glaucoma seen at a single academic center from 2008 to 2020 identified from electronic health records (EHRs).MethodsFrom the EHRs, we identified 361 baseline features, including demographics, eye examinations, diagnoses, and medications. We trained AI survival models to predict patients' progression to glaucoma surgery using the following: (1) a penalized Cox proportional hazards (CPH) model with principal component analysis (PCA); (2) random survival forests (RSFs); (3) gradient-boosting survival (GBS); and (4) a deep learning model (DeepSurv). The concordance index (C-index) and mean cumulative/dynamic area under the curve (mean AUC) were used to evaluate model performance on a held-out test set. Explainability was investigated using Shapley values for feature importance and visualization of model-predicted cumulative hazard curves for patients with different treatment trajectories.Main outcome measuresProgression to glaucoma surgery.ResultsOf the 4512 patients with glaucoma, 748 underwent glaucoma surgery, with a median follow-up of 1038 days. The DeepSurv model performed best overall (C-index, 0.775; mean AUC, 0.802) among the models studied in this article (CPH with PCA: C-index, 0.745; mean AUC, 0.780; RSF: C-index, 0.766; mean AUC, 0.804; GBS: C-index, 0.764; mean AUC, 0.791). Predicted cumulative hazard curves demonstrate how models could distinguish between patient who underwent early surgery and patients who underwent surgery after > 3000 days of follow-up or no surgery.ConclusionsArtificial intelligence survival models can predict progression to glaucoma surgery using structured data from EHRs. Tree-based and deep learning-based models performed better at predicting glaucoma progression to surgery than the CPH regression model, potentially because of their better suitability for high-dimensional data sets. Future work predicting ophthalmic outcomes should consider using tree-based and deep learning-based survival AI models. Additional research is needed to develop and evaluate more sophisticated deep learning survival models that can incorporate clinical notes or imaging.Financial disclosuresProprietary or commercial disclosure may be found after the references.

Dataset Information

Every which way? On predicting tumor evolution using cancer progression models.

Publications

Every which way? On predicting tumor evolution using cancer progression models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets