Summary Background Improvements to prognostic models in metastatic castration-resistant prostate cancer have the potential to augment clinical trial design and guide treatment strategies. In partnership with Project Data Sphere, a not-for-profit initiative allowing data from cancer clinical trials to be shared broadly with researchers, we designed an open-data, crowdsourced, DREAM (Dialogue for Reverse Engineering Assessments and Methods) challenge to not only identify a better prognostic model for prediction of survival in patients with metastatic castration-resistant prostate cancer but also engage a community of international data scientists to study this disease. Methods Data from the comparator arms of four phase 3 clinical trials in first-line metastatic castration-resistant prostate cancer were obtained from Project Data Sphere, comprising 476 patients treated with docetaxel and prednisone from the ASCENT2 trial, 526 patients treated with docetaxel, prednisone, and placebo in the MAINSAIL trial, 598 patients treated with docetaxel, prednisone or prednisolone, and placebo in the VENICE trial, and 470 patients treated with docetaxel and placebo in the ENTHUSE 33 trial. Datasets consisting of more than 150 clinical variables were curated centrally, including demographics, laboratory values, medical history, lesion sites, and previous treatments. Data from ASCENT2, MAINSAIL, and VENICE were released publicly to be used as training data to predict the outcome of interest—namely, overall survival. Clinical data were also released for ENTHUSE 33, but data for outcome variables (overall survival and event status) were hidden from the challenge participants so that ENTHUSE 33 could be used for independent validation. Methods were evaluated using the integrated time-dependent area under the curve (iAUC). The reference model, based on eight clinical variables and a penalised Cox proportional-hazards model, was used to compare method performance. Further validation was done using data from a fifth trial—ENTHUSE M1—in which 266 patients with metastatic castration-resistant prostate cancer were treated with placebo alone. Findings 50 independent methods were developed to predict overall survival and were evaluated through the DREAM challenge. The top performer was based on an ensemble of penalised Cox regression models (ePCR), which uniquely identified predictive interaction effects with immune biomarkers and markers of hepatic and renal function. Overall, ePCR outperformed all other methods (iAUC 0·791; Bayes factor >5) and surpassed the reference model (iAUC 0·743; Bayes factor >20). Both the ePCR model and reference models stratified patients in the ENTHUSE 33 trial into high-risk and low-risk groups with significantly different overall survival (ePCR: hazard ratio 3·32, 95% CI 2·39–4·62, p<0·0001; reference model: 2·56, 1·85–3·53, p<0·0001). The new model was validated further on the ENTHUSE M1 cohort with similarly high performance (iAUC 0·768). Meta-analysis across all methods confirmed previously identified...

Identification of informative variables in an information system is often performed using simple one-dimensional filtering procedures that discard information about interactions between variables. Such approach may result in removing some relevant variables from consideration. Here we present an R package MDFS (MultiDimensional Feature Selection) that performs identification of informative variables taking into account synergistic interactions between multiple descriptors and the decision variable. MDFS is an implementation of an algorithm based on information theory (Mnich and Rudnicki, 2017). Computational kernel of the package is implemented in C++. A high-performance version implemented in CUDA C is also available. The applications of MDFS are demonstrated using the well-known Madelon dataset that has synergistic variables by design. The dataset comes from the UCI Machine Learning Repository (Dheeru and Karra Taniskidou, 2017). It is shown that multidimensional analysis is more sensitive than one-dimensional tests and returns more reliable rankings of importance.

Two categories of immune responses—innate and adaptive immunity—have both polygenic backgrounds and a significant environmental component. The goal of the reported study was to define candidate genes and mutations for the immune traits of interest in chickens using machine learning–based sensitivity analysis for single-nucleotide polymorphisms ( SNPs ) located in candidate genes defined in quantitative trait loci regions. Here the adaptive immunity is represented by the specific antibody response toward keyhole limpet hemocyanin ( KLH ), whereas the innate immunity was represented by natural antibodies toward lipopolysaccharide ( LPS ) and lipoteichoic acid ( LTA ). The analysis consisted of 3 basic steps: an identification of candidate SNPs via feature selection, an optimisation of the feature set using recursive feature elimination, and finally a gene-level sensitivity analysis for final selection of models. The predictive model based on 5 genes (MAPK8IP3 CRLF3, UNC13D, ILR9, and PRCKB) explains 14.9% of variance for KLH adaptive response. The models obtained for LTA and LPS use more genes and have lower predictive power, explaining respectively 7.8 and 4.5% of total variance. In comparison, the linear models built on genes identified by a standard statistical analysis explain 1.5, 0.5, and 0.3% of variance for KLH, LTA, and LPS response, respectively. The present study shows that machine learning methods applied to systems with a complex interaction network can discover phenotype-genotype associations with much higher sensitivity than traditional statistical models. It adds contribution to evidence suggesting a role of MAPK8IP3 in the adaptive immune response. It also indicates that CRLF3 is involved in this process as well. Both findings need additional verification.

BackgroundModern experimental techniques deliver data sets containing profiles of tens of thousands of potential molecular and genetic markers that can be used to improve medical diagnostics. Previous studies performed with three different experimental methods for the same set of neuroblastoma patients create opportunity to examine whether augmenting gene expression profiles with information on copy number variation can lead to improved predictions of patients survival. We propose methodology based on comprehensive cross-validation protocol, that includes feature selection within cross-validation loop and classification using machine learning. We also test dependence of results on the feature selection process using four different feature selection methods.ResultsThe models utilising features selected based on information entropy are slightly, but significantly, better than those using features obtained with t-test. The synergy between data on genetic variation and gene expression is possible, but not confirmed. A slight, but statistically significant, increase of the predictive power of machine learning models has been observed for models built on combined data sets. It was found while using both out of bag estimate and in cross-validation performed on a single set of variables. However, the improvement was smaller and non-significant when models were built within full cross-validation procedure that included feature selection within cross-validation loop. Good correlation between performance of the models in the internal and external cross-validation was observed, confirming the robustness of the proposed protocol and results.ConclusionsWe have developed a protocol for building predictive machine learning models. The protocol can provide robust estimates of the model performance on unseen data. It is particularly well-suited for small data sets. We have applied this protocol to develop prognostic models for neuroblastoma, using data on copy number variation and gene expression. We have shown that combining these two sources of information may increase the quality of the models. Nevertheless, the increase is small and larger samples are required to reduce noise and bias arising due to overfitting.ReviewersThis article was reviewed by Lan Hu, Tim Beissbarth and Dimitar Vassilev.