Aneta Polewko-Klim

Amyotrophic lateral sclerosis (ALS) is a fatal neurodegenerative disease where substantial heterogeneity in clinical presentation urgently requires a better stratification of patients for the development of drug trials and clinical care. In this study we explored stratification through a crowdsourcing approach, the DREAM Prize4Life ALS Stratification Challenge. Using data from >10,000 patients from ALS clinical trials and 1479 patients from community-based patient registers, more than 30 teams developed new approaches for machine learning and clustering, outperforming the best current predictions of disease outcome. We propose a new method to integrate and analyze patient clusters across methods, showing a clear pattern of consistent and clinically relevant sub-groups of patients that also enabled the reliable classification of new patients. Our analyses reveal novel insights in ALS and describe for the first time the potential of a crowdsourcing to uncover hidden patient sub-populations, and to accelerate disease understanding and therapeutic development.

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 an 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 The computational kernel of the package is implemented in C++. A high-performance version implemented in CUDA C is also available. The application of MDFS is demonstrated using the well-known Madelon dataset, in which a decision variable is generated from synergistic interactions between descriptor variables. It is shown that the application of multidimensional analysis results in better sensitivity and ranking 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.

BACKGROUND: Modern 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. RESULTS: The 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. CONCLUSIONS: We 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. REVIEWERS: This article was reviewed by Lan Hu, Tim Beissbarth and Dimitar Vassilev.

Super learner algorithm was created to combine results of multiple base learners with the use of cross validation. However, in many cases it does not outperform significantly a simple average of the base results. We propose to apply multiple repeats of cross validation to improve the performance of super learning. Two approaches to application of repeated cross validation were tested on artificial data sets and on real-life, biomedical data sets. One of the approaches, MEAN OUTPUT strategy, proved to significantly improve the results. To reduce the computational complexity of the algorithm, we suggest the use of 3-fold, rather than the previously recommended 10-fold validation. The tests showed, that this simplification does not affect the super learning results.