Abstract Background We introduce Iterative Feature Removal (IFR) as an unbiased approach for selecting features with diagnostic capacity from large data sets. The algorithm is based on recently developed tools in machine learning that are driven by sparse feature selection goals. When applied to genomic data, our method is designed to identify genes that can provide deeper insight into complex interactions while remaining directly connected to diagnostic utility. We contrast this approach with the search for a minimal best set of discriminative genes, which can provide only an incomplete picture of the biological complexity. Results Microarray data sets typically contain far more features (genes) than samples. For this type of data, we demonstrate that there are many equivalently-predictive subsets of genes. We iteratively train a classifier using features identified via a sparse support vector machine. At each iteration, we remove all the features that were previously selected. We found that we could iterate many times before a sustained drop in accuracy occurs, with each iteration removing approximately 30 genes from consideration. The classification accuracy on test data remains essentially flat even as hundreds of top-genes are removed. Our method identifies sets of genes that are highly predictive, even when comprised of genes that individually are not. Through automated and manual analysis of the selected genes, we demonstrate that the selected features expose relevant pathways that other approaches would have missed. Conclusions Our results challenge the paradigm of using feature selection techniques to design parsimonious classifiers from microarray and similar high-dimensional, small-sample-size data sets. The fact that there are many subsets of genes that work equally well to classify the data provides a strong counter-result to the notion that there is a small number of “top genes” that should be used to build classifiers. In our results, the best classifiers were formed using genes with limited univariate power, thus illustrating that deeper mining of features using multivariate techniques is important.

Clinical diagnosis of acute infectious diseases during the early stages of infection is critical to administering the appropriate treatment to improve the disease outcome. We present a data driven analysis of the human cellular response to respiratory viruses including influenza, respiratory syncytia virus, and human rhinovirus, and compared this with the response to the bacterial endotoxin, Lipopolysaccharides (LPS). Using an anomaly detection framework we identified pathways that clearly distinguish between asymptomatic and symptomatic patients infected with the four different respiratory viruses and that accurately diagnosed patients exposed to a bacterial infection. Connectivity pathway analysis comparing the viral and bacterial diagnostic signatures identified host cellular pathways that were unique to patients exposed to LPS endotoxin indicating this type of analysis could be used to identify host biomarkers that can differentiate clinical etiologies of acute infection. We applied the Multivariate State Estimation Technique (MSET) on two human influenza (H1N1 and H3N2) gene expression data sets to define host networks perturbed in the asymptomatic phase of infection. Our analysis identified pathways in the respiratory virus diagnostic signature as prognostic biomarkers that triggered prior to clinical presentation of acute symptoms. These early warning pathways correctly predicted that almost half of the subjects would become symptomatic in less than forty hours post-infection and that three of the 18 subjects would become symptomatic after only 8 hours. These results provide a proof-of-concept for utility of anomaly detection algorithms to classify host pathway signatures that can identify presymptomatic signatures of acute diseases and differentiate between etiologies of infection. On a global scale, acute respiratory infections cause a significant proportion of human co-morbidities and account for 4.25 million deaths annually. The development of clinical diagnostic tools to distinguish between acute viral and bacterial respiratory infections is critical to improve patient care and limit the overuse of antibiotics in the medical community. The identification of prognostic respiratory virus biomarkers provides an early warning system that is capable of predicting which subjects will become symptomatic to expand our medical diagnostic capabilities and treatment options for acute infectious diseases. The host response to acute infection may be viewed as a deterministic signaling network responsible for maintaining the health of the host organism. We identify pathway signatures that reflect the very earliest perturbations in the host response to acute infection. These pathways provide a monitor the health state of the host using anomaly detection to quantify and predict health outcomes to pathogens.

Today's world of scientific software for High Energy Physics (HEP) is powered by x86 code, while the future will be much more reliant on accelerators like GPUs and FPGAs. The portable parallelization strategies (PPS) project of the High Energy Physics Center for Computational Excellence (HEP/CCE) is investigating solutions for portability techniques that will allow the coding of an algorithm once, and the ability to execute it on a variety of hardware products from many vendors, especially including accelerators. We think without these solutions, the scientific success of our experiments and endeavors is in danger, as software development could be expert driven and costly to be able to run on available hardware infrastructure. We think the best solution for the community would be an extension to the C++ standard with a very low entry bar for users, supporting all hardware forms and vendors. We are very far from that ideal though. We argue that in the future, as a community, we need to request and work on portability solutions and strive to reach this ideal.

Computing plays an essential role in all aspects of high energy physics. As computational technology evolves rapidly in new directions, and data throughput and volume continue to follow a steep trend-line, it is important for the HEP community to develop an effective response to a series of expected challenges. In order to help shape the desired response, the HEP Forum for Computational Excellence (HEP-FCE) initiated a roadmap planning activity with two key overlapping drivers -- 1) software effectiveness, and 2) infrastructure and expertise advancement. The HEP-FCE formed three working groups, 1) Applications Software, 2) Software Libraries and Tools, and 3) Systems (including systems software), to provide an overview of the current status of HEP computing and to present findings and opportunities for the desired HEP computational roadmap. The final versions of the reports are combined in this document, and are presented along with introductory material.

Particle physics has an ambitious and broad experimental programme for the coming decades. This programme requires large investments in detector hardware, either to build new facilities and experiments, or to upgrade existing ones. Similarly, it requires commensurate investment in the R&D of software to acquire, manage, process, and analyse the shear amounts of data to be recorded. In planning for the HL-LHC in particular, it is critical that all of the collaborating stakeholders agree on the software goals and priorities, and that the efforts complement each other. In this spirit, this white paper describes the R&D activities required to prepare for this software upgrade.