Advancing data science in drug development through an innovative computational framework for data sharing and statistical analysis.

BACKGROUND: Novartis and the University of Oxford's Big Data Institute (BDI) have established a research alliance with the aim to improve health care and drug development by making it more efficient and targeted. Using a combination of the latest statistical machine learning technology with an innovative IT platform developed to manage large volumes of anonymised data from numerous data sources and types we plan to identify novel patterns with clinical relevance which cannot be detected by humans alone to identify phenotypes and early predictors of patient disease activity and progression. METHOD: The collaboration focuses on highly complex autoimmune diseases and develops a computational framework to assemble a research-ready dataset across numerous modalities. For the Multiple Sclerosis (MS) project, the collaboration has anonymised and integrated phase II to phase IV clinical and imaging trial data from ≈35,000 patients across all clinical phenotypes and collected in more than 2200 centres worldwide. For the "IL-17" project, the collaboration has anonymised and integrated clinical and imaging data from over 30 phase II and III Cosentyx clinical trials including more than 15,000 patients, suffering from four autoimmune disorders (Psoriasis, Axial Spondyloarthritis, Psoriatic arthritis (PsA) and Rheumatoid arthritis (RA)). RESULTS: A fundamental component of successful data analysis and the collaborative development of novel machine learning methods on these rich data sets has been the construction of a research informatics framework that can capture the data at regular intervals where images could be anonymised and integrated with the de-identified clinical data, quality controlled and compiled into a research-ready relational database which would then be available to multi-disciplinary analysts. The collaborative development from a group of software developers, data wranglers, statisticians, clinicians, and domain scientists across both organisations has been key. This framework is innovative, as it facilitates collaborative data management and makes a complicated clinical trial data set from a pharmaceutical company available to academic researchers who become associated with the project. CONCLUSIONS: An informatics framework has been developed to capture clinical trial data into a pipeline of anonymisation, quality control, data exploration, and subsequent integration into a database. Establishing this framework has been integral to the development of analytical tools.

Application of a convolutional neural network to the quality control of MRI defacing.

Large-scale neuroimaging datasets present unique challenges for automated processing pipelines. Motivated by a large clinical trials dataset with over 235,000 MRI scans, we consider the challenge of defacing - anonymisation to remove identifying facial features. The defacing process must undergo quality control (QC) checks to ensure that the facial features have been removed and that the brain tissue is left intact. Visual QC checks are time-consuming and can cause delays in preparing data. We have developed a convolutional neural network (CNN) that can assist with the QC of the application of MRI defacing; our CNN is able to distinguish between scans that are correctly defaced and can classify defacing failures into three sub-types to facilitate parameter tuning during remedial re-defacing. Since integrating the CNN into our anonymisation pipeline, over 75,000 scans have been processed. Strict thresholds have been applied so that ambiguous classifications are referred for visual QC checks, however all scans still undergo an efficient verification check before being marked as passed. After applying the thresholds, our network is 92% accurate and can classify nearly half of the scans without the need for protracted manual checks. Our model can generalise across MRI modalities and has comparable performance when tested on an independent dataset. Even with the introduction of the verification checks, incorporation of the CNN has reduced the time spent undertaking QC checks by 42% during initial defacing, and by 35% overall. With the help of the CNN, we have been able to successfully deface 96% of the scans in the project whilst maintaining high QC standards. In a similarly sized new project, we would expect the model to reduce the time spent on manual QC checks by 125 h. Our approach is applicable to other projects with the potential to greatly improve the efficiency of imaging anonymisation pipelines.

Identifying genetic determinants of inflammatory pain in mice using a large-scale gene-targeted screen.

ABSTRACT: Identifying the genetic determinants of pain is a scientific imperative given the magnitude of the global health burden that pain causes. Here, we report a genetic screen for nociception, performed under the auspices of the International Mouse Phenotyping Consortium. A biased set of 110 single-gene knockout mouse strains was screened for 1 or more nociception and hypersensitivity assays, including chemical nociception (formalin) and mechanical and thermal nociception (von Frey filaments and Hargreaves tests, respectively), with or without an inflammatory agent (complete Freund's adjuvant). We identified 13 single-gene knockout strains with altered nocifensive behavior in 1 or more assays. All these novel mouse models are openly available to the scientific community to study gene function. Two of the 13 genes (Gria1 and Htr3a) have been previously reported with nociception-related phenotypes in genetically engineered mouse strains and represent useful benchmarking standards. One of the 13 genes (Cnrip1) is known from human studies to play a role in pain modulation and the knockout mouse reported herein can be used to explore this function further. The remaining 10 genes (Abhd13, Alg6, BC048562, Cgnl1, Cp, Mmp16, Oxa1l, Tecpr2, Trim14, and Trim2) reveal novel pathways involved in nociception and may provide new knowledge to better understand genetic mechanisms of inflammatory pain and to serve as models for therapeutic target validation and drug development.

An ancient Turing-like patterning mechanism regulates skin denticle development in sharks.

Vertebrates have a vast array of epithelial appendages, including scales, feathers, and hair. The developmental patterning of these diverse structures can be theoretically explained by Alan Turing's reaction-diffusion system. However, the role of this system in epithelial appendage patterning of early diverging lineages (compared to tetrapods), such as the cartilaginous fishes, is poorly understood. We investigate patterning of the unique tooth-like skin denticles of sharks, which closely relates to their hydrodynamic and protective functions. We demonstrate through simulation models that a Turing-like mechanism can explain shark denticle patterning and verify this system using gene expression analysis and gene pathway inhibition experiments. This mechanism bears remarkable similarity to avian feather patterning, suggesting deep homology of the system. We propose that a diverse range of vertebrate appendages, from shark denticles to avian feathers and mammalian hair, use this ancient and conserved system, with slight genetic modulation accounting for broad variations in patterning.

The Rise of Jaw Protrusion in Spiny-Rayed Fishes Closes the Gap on Elusive Prey.

Jaw protrusion is one of the most important innovations in vertebrate feeding over the last 400 million years [1, 2]. Protrusion enables a fish to rapidly decrease the distance between itself and its prey [2, 3]. We assessed the evolution and functional implications of jaw protrusion in teleost fish assemblages from shallow coastal seas since the Cretaceous. By examining extant teleost fishes, we identified a robust morphological predictor of jaw protrusion that enabled us to predict the extent of jaw protrusion in fossil fishes. Our analyses revealed increases in both average and maximum jaw protrusion over the last 100 million years, with a progressive increase in the potential impact of fish predation on elusive prey. Over this period, the increase in jaw protrusion was initially driven by a taxonomic restructuring of fish assemblages, with an increase in the proportion of spiny-rayed fishes (Acanthomorpha), followed by an increase in the extent of protrusion within this clade. By increasing the ability of fishes to catch elusive prey [2, 4], jaw protrusion is likely to have fundamentally changed the nature of predator-prey interactions and may have contributed to the success of the spiny-rayed fishes, the dominant fish clade in modern oceans [5].