Polygenic risk modeling of tumor stage and survival in bladder cancer

Abstract

Introduction Bladder cancer assessment with non-invasive gene expression signatures facilitates the detection of patients at risk and surveillance of their status, bypassing the discomforts given by cystoscopy. To achieve accurate cancer estimation, analysis pipelines for gene expression data (GED) may integrate a sequence of several machine learning and bio-statistical techniques to model complex characteristics of pathological patterns. Methods Numerical experiments tested the combination of GED preprocessing by discretization with tree ensemble embeddings and nonlinear dimensionality reductions to categorize oncological patients comprehensively. Modeling aimed to identify tumor stage and distinguish survival outcomes in two situations: complete and partial data embedding. This latter experimental condition simulates the addition of new patients to an existing model for rapid monitoring of disease progression. Machine learning procedures were employed to identify the most relevant genes involved in patient prognosis and test the performance of preprocessed GED compared to untransformed data in predicting patient conditions. Results Data embedding paired with dimensionality reduction produced prognostic maps with well-defined clusters of patients, suitable for medical decision support. A second experiment simulated the addition of new patients to an existing model (partial data embedding): Uniform Manifold Approximation and Projection (UMAP) methodology with uniform data discretization led to better outcomes than other analyzed pipelines. Further exploration of parameter space for UMAP and t-distributed stochastic neighbor embedding (t-SNE) underlined the importance of tuning a higher number of parameters for UMAP rather than t-SNE. Moreover, two different machine learning experiments identified a group of genes valuable for partitioning patients (gene relevance analysis) and showed the higher precision obtained by preprocessed data in predicting tumor outcomes for cancer stage and survival rate (six classes prediction). Conclusions The present investigation proposed new analysis pipelines for disease outcome modeling from bladder cancer-related biomarkers. Complete and partial data embedding experiments suggested that pipelines employing UMAP had a more accurate predictive ability, supporting the recent literature trends on this methodology. However, it was also found that several UMAP parameters influence experimental results, therefore deriving a recommendation for researchers to pay attention to this aspect of the UMAP technique. Machine learning procedures further demonstrated the effectiveness of the proposed preprocessing in predicting patients’ conditions and determined a sub-group of biomarkers significant for forecasting bladder cancer prognosis.

Algorithm-Based Risk Identification in Patients with Breast Cancer-Related Lymphedema: A Cross-Sectional Study

“…UMAP tries to preserve the local and global information contained in the input variables by capturing the latent structures of the initial high-dimensional dataset and representing them as a visualizable graph. This feature is one fundamental difference between UMAP and another well-known dimensionality reduction technique, Barnes-Hut-SNE, that preserves only the local data structure, as previously investigated by the same authors [41]. Preserving the entire initial data structure allows for adding new data to a learned representation.…”

Benchmarking the use of Dimensional Reduction Techniques: A Case Study of Oesophageal Cancer Image Analysis

“…Previous work of UMAP by Nascimben et. al [33] exploring different combinations of parameters like min_distance, n_neighbour and distance metric of UMAP are also relevant. Hence, our extended analysis including n_neighbors, min_dist, and distance metric, results in variation in the plot outcome (Supporting Information S1 C to H).…”