Search

We propose a counterfactual approach to train "causality-aware" predictive models that are able to leverage causal information in static anticausal machine learning tasks (i.e., prediction tasks where the outcome influences the inputs). In applications plagued by confounding, the approach can be used to generate predictions that are free from the influence of observed confounders. In applications involving observed mediators, the approach can be used to generate predictions that only capture the direct or the indirect causal influences. Mechanistically, we train supervised learners on (counterfactually) simulated inputs that retain only the associations generated by the causal relations of interest. We focus on linear models, where analytical results connecting covariances, causal effects, and prediction mean square errors are readily available. Quite importantly, we show that our approach does not require knowledge of the full causal graph. It suffices to know which variables represent potential confounders and/or mediators. We investigate the stability of the method with respect to dataset shifts generated by selection biases and also relax the linearity assumption by extending the approach to additive models better able to account for nonlinearities in the data. We validate our approach in a series of synthetic data experiments and illustrate its application to a real dataset.

BackgroundPsoriasis and psoriatic arthritis are common immune-mediated inflammatory conditions that primarily affect the skin, joints and entheses and can lead to significant disability and worsening quality of life. Although early recognition and treatment can prevent the development of permanent damage, psoriatic disease remains underdiagnosed and undertreated due in part to the disparity between disease prevalence and relative lack of access to clinical specialists in dermatology and rheumatology. Remote patient self-assessment aided by smartphone sensor technology may be able to address these gaps in care, however, these innovative disease measurements require robust clinical validation.MethodsWe developed smartphone-based assessments, collectively named the Psorcast suite, that can be self-administered to measure cutaneous and musculoskeletal signs and symptoms of psoriatic disease. The image and motion sensor data collected by these assessments was processed to generate digital biomarkers or machine learning models to detect psoriatic disease phenotypes. To evaluate these digital endpoints, a cross-sectional, in-clinic validation study was performed with 92 participants across two specialized academic sites consisting of healthy controls and participants diagnosed with psoriasis and/or psoriatic arthritis.FindingsIn the domain of skin disease, digital patient assessment of percent body surface area (BSA) affected with psoriasis demonstrated very strong concordance (CCC = 0·94, [95%CI = 0·91–0·96]) with physician-assessed BSA. Patient-captured psoriatic plaque photos were remotely assessed by physicians and compared to in-clinic Physician Global Assessment parameters for the same plaque with fair to moderate concordance (CCCerythema=0·72 [0·59–0·85]; CCCinduration=0·72 [0·62–0·82]; CCCscaling=0·60 [0·48–0·72]). Arm range of motion was measured by the Digital Jar Open assessment to classify physician-assessed upper extremity involvement with joint tenderness or enthesitis, demonstrating an AUROC = 0·68 (0·47–0·85). Patient-captured hand photos were processed with object detection and deep learning models to classify clinically-diagnosed nail psoriasis with an accuracy of 0·76, which is on par with remote physician rating of nail images (avg. accuracy = 0·63) with model performance maintaining accuracy when raters were too unsure or image quality was too poor for a remote assessment.InterpretationThe Psorcast digital assessments, performed by patient self-measurement, achieve significant clinical validity when compared to in-person physical exams. These assessments should be considered appropriately validated for self-monitoring and exploratory research applications, particularly those that require frequent, remote disease measurements. However, further validation in larger cohorts will be necessary to demonstrate robustness and generalizability across populations for use in evidence-based medicine or clinical trial settings. The smartphone software and analysis pipelines from the Psorcast suite are open source and available to the scientific community.FundingThis work is funded by the Psorcast Digital Biomarker Consortium consisting of Sage Bionetworks, Psoriasis and Psoriatic Arthritis Centers for Multicenter Advancement Network (PPACMAN), Novartis, UCB, Pfizer, and Janssen Pharmaceuticals. J.U.S work was supported by the Snyder Family Foundation and the Riley Family Foundation.Research in contextEvidence before this studyNo systematic literature review was performed. Patient self-measurement with smartphone sensors has been shown to be clinically valid for assessing signs and symptoms such as tremor, gait, physical activity, or range of motion across multiple disease indications. While smartphone-based applications have been developed for digitally tracking psoriatic disease, they have largely focused on questionnaire-based patient reported outcomes.Added value of this studyTo our knowledge, Psorcast is the first application using ubiquitous smartphone sensor technology for patients to remotely measure their psoriatic disease phenotypes, including detection of nail psoriasis and a continuous variable outcome measure of joint tenderness and enthesitis based on range of motion. This study not only developed a suite of novel, smartphone sensor-based assessment that can be self-administered to measure cutaneous and musculoskeletal signs and symptoms, but provides clinical validation of these measures.Implications of all the available evidenceThe developed Psorcast suite of measurements can serve as groundwork for patient-driven, remote measurement of psoriatic disease. The use and continued development of this technology opens up new possibilities for both clinical care and research endeavors on a large scale. Psorcast measurements are currently being validated for their ability to assess disease changes longitudinally, allowing for more frequent symptom monitoring in clinical trials, more granular insight into the time course of medication action, and possible identification of responders from non-responders to specific therapies.

While the past decade has seen meaningful improvements in clinical outcomes for multiple myeloma patients, a subset of patients do not benefit from current therapeutics for unclear reasons. Many gene expression-based models of risk have been developed, but each model uses a different combination of genes and often involve assaying many genes making them difficult to implement. We organized the Multiple Myeloma DREAM Challenge, a crowdsourced effort to develop models of rapid progression in newly diagnosed myeloma patients and to benchmark these against previously published models. This effort lead to more robust predictors and found that incorporating specific demographic and clinical features improved gene expression-based models of high risk. Furthermore, post challenge analysis identified a novel expression-based risk marker and histone modifier,PHF19, which featured prominently in several independent models. Lastly, we show that a simple four feature predictor composed of age, International Staging System stage (ISS), and expression ofPHF19andMMSETperforms similarly to more complex models with many more gene expression features included.Key pointsMost comprehensive and unbiased assessment of prognostic biomarkers in MM resulting in a robust and parsimonious model.Identification ofPHF19as the expression based biomarker most strongly associated with rapid progression in MM patients.

Contains fulltext : 252104.pdf (Publisher’s version ) (Open Access) Remote health assessments that gather real-world data (RWD) outside clinic settings require a clear understanding of appropriate methods for data collection, quality assessment, analysis and interpretation. Here we examine the performance and limitations of smartphones in collecting RWD in the remote mPower observational study of Parkinson's disease (PD). Within the first 6 months of study commencement, 960 participants had enrolled and performed at least five self-administered active PD symptom assessments (speeded tapping, gait/balance, phonation or memory). Task performance, especially speeded tapping, was predictive of self-reported PD status (area under the receiver operating characteristic curve (AUC) = 0.8) and correlated with in-clinic evaluation of disease severity (r = 0.71; P

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 interestnamely, 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 trialENTHUSE M1in 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 2·394·62, p, European Union within the ERC grant LatentCauses supported the work of C.F and I.K. German Research Foundation (DFG) within the Collaborative Research Centre 1243, subproject A17 awarded to C.F. German Federal Ministry of Education and Research (BMBF) through the Research Consortium e:AtheroMED (Systems medicine of myocardial infarction and stroke) under the auspices of the e:Med Programme (grant # 01ZX1313C) supported the work of D.P.A., P.D., C.F., C.K., I.K., N.K., M.L., H.S. and J.F.S. at the Institute of Computational Biology. NIH Grants RR025747-01, MH086633 and 1UL1TR001111, and NSF Grants SES-1357666, DMS-14-07655 and BCS0826844 supported the work of C.H., J.I., E.L., Y.W., H.Y., H.Z. and J.Z. NSFC Grant Nos. 61332013, 61572139 supported the work of X.L, Y.L, Y.Z., and S.Z. National Natural Science Foundation of China grants [Nos. 61422309, 61379092] was awarded to S.Z. The Patrick C. Walsh Prostate Research Fund and the Johns Hopkins Individualized Health Initiative supported the work of R.Y.C., D.D., Y.D., Z.J., K.R., Z.W. and Y.Z. FCT Ph.D. Grant SFRH/BD/80925/2011 was awarded to S.C. Clinical Persona Inc., East Palo Alto, CA supported the work of L.B. and D.K. The Finnish Cultural Foundation and the Drug Research Doctoral Programme (DRDP) at the University of Turku supported T.D.L. The National Research Foundation Singapore and the Singapore Ministry of Education, under its Research Centres of Excellence initiative, supported the work of J.G. and K.T. A grant from the Russian Science Foundation 14-24-00155 was awarded to M.D.K. A*MIDEX grant (no. ANR-11-IDEX-0001-02) was awarded to P.J.B. NSERC supported the work of R.G. The Israeli Centers of Research Excellence (I-CORE) program (Center No. 4/11) supported the work of E.G. Academy of Finland (grants 292611, 269862, 272437, 279163, 295504), National Cancer Institute (16X064), and Cancer Society of Finland supported the work of T.A. Academy of Finland (grant 268531) supported the work of T.M

Collection of high-dimensional, longitudinal digital health data has the potential to support a wide-variety of research and clinical applications including diagnostics and longitudinal health tracking. Algorithms that process these data and inform digital diagnostics are typically developed using training and test sets generated from multiple repeated measures collected across a set of individuals. However, the inclusion of repeated measurements is not always appropriately taken into account in the analytical evaluations of predictive performance. The assignment of repeated measurements from each individual to both the training and the test sets (“record-wise” data split) is a common practice and can lead to massive underestimation of the prediction error due to the presence of “identity confounding.” In essence, these models learn to identify subjects, in addition to diagnostic signal. Here, we present a method that can be used to effectively calculate the amount of identity confounding learned by classifiers developed using a record-wise data split. By applying this method to several real datasets, we demonstrate that identity confounding is a serious issue in digital health studies and that record-wise data splits for machine learning- based applications need to be avoided.

Digital technologies such as smartphones are transforming the way scientists conduct biomedical research. Several remotely conducted studies have recruited thousands of participants over a span of a few months allowing researchers to collect real-world data at scale and at a fraction of the cost of traditional research. Unfortunately, remote studies have been hampered by substantial participant attrition, calling into question the representativeness of the collected data including generalizability of outcomes. We report the findings regarding recruitment and retention from eight remote digital health studies conducted between 2014–2019 that provided individual-level study-app usage data from more than 100,000 participants completing nearly 3.5 million remote health evaluations over cumulative participation of 850,000 days. Median participant retention across eight studies varied widely from 2–26 days (median across all studies = 5.5 days). Survival analysis revealed several factors significantly associated with increase in participant retention time, including (i) referral by a clinician to the study (increase of 40 days in median retention time); (ii) compensation for participation (increase of 22 days, 1 study); (iii) having the clinical condition of interest in the study (increase of 7 days compared with controls); and (iv) older age (increase of 4 days). Additionally, four distinct patterns of daily app usage behavior were identified by unsupervised clustering, which were also associated with participant demographics. Most studies were not able to recruit a sample that was representative of the race/ethnicity or geographical diversity of the US. Together these findings can help inform recruitment and retention strategies to enable equitable participation of populations in future digital health research.

Importance: Mammography screening currently relies on subjective human interpretation. Artificial intelligence (AI) advances could be used to increase mammography screening accuracy by reducing missed cancers and false positives. Objective: To evaluate whether AI can overcome human mammography interpretation limitations with a rigorous, unbiased evaluation of machine learning algorithms. Design, Setting, and Participants: In this diagnostic accuracy study conducted between September 2016 and November 2017, an international, crowdsourced challenge was hosted to foster AI algorithm development focused on interpreting screening mammography. More than 1100 participants comprising 126 teams from 44 countries participated. Analysis began November 18, 2016. Main Outcomes and Measurements: Algorithms used images alone (challenge 1) or combined images, previous examinations (if available), and clinical and demographic risk factor data (challenge 2) and output a score that translated to cancer yes/no within 12 months. Algorithm accuracy for breast cancer detection was evaluated using area under the curve and algorithm specificity compared with radiologists' specificity with radiologists' sensitivity set at 85.9% (United States) and 83.9% (Sweden). An ensemble method aggregating top-performing AI algorithms and radiologists' recall assessment was developed and evaluated. Results: Overall, 144 231 screening mammograms from 85 580 US women (952 cancer positive ≤12 months from screening) were used for algorithm training and validation. A second independent validation cohort included 166 578 examinations from 68 008 Swedish women (780 cancer positive). The top-performing algorithm achieved an area under the curve of 0.858 (United States) and 0.903 (Sweden) and 66.2% (United States) and 81.2% (Sweden) specificity at the radiologists' sensitivity, lower than community-practice radiologists' specificity of 90.5% (United States) and 98.5% (Sweden). Combining top-performing algorithms and US radiologist assessments resulted in a higher area under the curve of 0.942 and achieved a significantly improved specificity (92.0%) at the same sensitivity. Conclusions and Relevance: While no single AI algorithm outperformed radiologists, an ensemble of AI algorithms combined with radiologist assessment in a single-reader screening environment improved overall accuracy. This study underscores the potential of using machine learning methods for enhancing mammography screening interpretation. CA extern

Current clinimetrics assessment of Parkinson's disease (PD) is insensitive, episodic, subjective, and provider-centered. Ubiquitous technologies such as smartphones promise to fundamentally change PD assessments. To enable frequent remote assessment of PD tremor severity, here we present a 39-month smartphone research study in a real-world setting without supervision. More than 15,000 consented participants used the smartphone application, mPower, to perform self-administered active tasks. In the scope of this abstract, we developed an objective smartphone measure of PD tremor severity called mPower Tremor Scores (mPTS) using machine learning. Efficacy, and reliability of mPTS was further tested and validated in a separate cohort in the real world and in-clinic setting. This study demonstrates the utility of using structured activities with built-in smartphone sensors to measure PD tremor severity remotely and objectively in a real-world setting using more than 1100 participants.

Reconstructing biological networks using high-throughput technologies has the potential to produce condition-specific interactomes. But are these reconstructed networks a reliable source of biological interactions? Do some network inference methods offer dramatically improved performance on certain types of networks? To facilitate the use of network inference methods in systems biology, we report a large-scale simulation study comparing the ability of Markov chain Monte Carlo (MCMC) samplers to reverse engineer Bayesian networks. The MCMC samplers we investigated included foundational and state-of-the-art Metropolis–Hastings and Gibbs sampling approaches, as well as novel samplers we have designed. To enable a comprehensive comparison, we simulated gene expression and genetics data from known network structures under a range of biologically plausible scenarios. We examine the overall quality of network inference via different methods, as well as how their performance is affected by network characteristics. Our simulations reveal that network size, edge density, and strength of gene-to-gene signaling are major parameters that differentiate the performance of various samplers. Specifically, more recent samplers including our novel methods outperform traditional samplers for highly interconnected large networks with strong gene-to-gene signaling. Our newly developed samplers show comparable or superior performance to the top existing methods. Moreover, this performance gain is strongest in networks with biologically oriented topology, which indicates that our novel samplers are suitable for inferring biological networks. The performance of MCMC samplers in this simulation framework can guide the choice of methods for network reconstruction using systems genetics data.

Mental Health conditions are now amongst the top five burdensome diseases in the US. Disparities in access to services and health outcomes vary due to several factors including socioeconomic status, shortage of mental health professionals, stigma and the linguistic gap between providers and non-English speaking minority population. This study explores the utility of providing Spanish (mono and bilingual) speaking Latino/Hispanics an option to access low-cost yet modern depression assessment and interventions available through smartphones. This is a fully remotely run study in order to investigate access, engagement, costs, and impact in an ecologically valid manner in a "real life" setting. The main purpose is to directly address issues of culture and language often overlooked in the digital health space, beginning with a thorough characterization of how these modern tools are perceived, utilized, and digested in the largest minority population in the US.

Mindboggle (http://mindboggle.info) is an open source brain morphometry platform that takes in preprocessed T1-weighted MRI data and outputs volume, surface, and tabular data containing label, feature, and shape information for further analysis. In this article, we document the software and demonstrate its use in studies of shape variation in healthy and diseased humans. The number of different shape measures and the size of the populations make this the largest and most detailed shape analysis of human brains ever conducted. Brain image morphometry shows great potential for providing much-needed biological markers for diagnosing, tracking, and predicting progression of mental health disorders. Very few software algorithms provide more than measures of volume and cortical thickness, while more subtle shape measures may provide more sensitive and specific biomarkers. Mindboggle computes a variety of (primarily surface-based) shapes: area, volume, thickness, curvature, depth, Laplace-Beltrami spectra, Zernike moments, etc. We evaluate Mindboggle’s algorithms using the largest set of manually labeled, publicly available brain images in the world and compare them against state-of-the-art algorithms where they exist. All data, code, and results of these evaluations are publicly available., National Institute of Mental Health (U.S.) (R01 MH084029), National Institute of Mental Health (U.S.) (U01 MH074813), National Institute of Mental Health (U.S.) (3U01MH092250-03S1), United States. National Institutes of Health (1R01EB020740)

Current efforts in systems genetics have focused on the development of statistical approaches that aim to disentangle causal relationships among molecular phenotypes in segregating populations. Reverse engineering of transcriptional networks plays a key role in the understanding of gene regulation. However, transcriptional regulation is only one possible mechanism, as methylation, phosphorylation, direct protein–protein interaction, transcription factor binding, etc., can also contribute to gene regulation. These additional modes of regulation can be interpreted as unobserved variables in the transcriptional gene network and can potentially affect its reconstruction accuracy. We develop tests of causal direction for a pair of phenotypes that may be embedded in a more complicated but unobserved network by extending Vuong’s selection tests for misspecified models. Our tests provide a significance level, which is unavailable for the widely used AIC and BIC criteria. We evaluate the performance of our tests against the AIC, BIC, and a recently published causality inference test in simulation studies. We compare the precision of causal calls using biologically validated causal relationships extracted from a database of 247 knockout experiments in yeast. Our model selection tests are more precise, showing greatly reduced false-positive rates compared to the alternative approaches. In practice, this is a useful feature since follow-up studies tend to be time consuming and expensive and, hence, it is important for the experimentalist to have causal predictions with low false-positive rates.

Clinical trials traditionally employ blinding as a design mechanism to reduce the influence of placebo effects. In practice, however, it can be difficult or impossible to blind study participants and unblinded trials are common in medical research. Here we show how instrumental variables can be used to quantify and disentangle treatment and placebo effects in randomized clinical trials comparing control and active treatments in the presence of confounders. The key idea is to use randomization to separately manipulate treatment assignment and psychological encouragement messages that increase the participants' desire for improved symptoms. The proposed approach is able to improve the estimation of treatment effects in blinded studies and, most importantly, opens the doors to account for placebo effects in unblinded trials., 29 pages, 13 figures. Version 2 includes randomization confidence intervals and more references

BackgroundDocetaxel has a demonstrated survival benefit for metastatic castration-resistant prostate cancer (mCRPC). However, 10-20% of patients discontinue docetaxel prematurely because of toxicity-induced adverse events, and managing risk factors for toxicity remains an ongoing challenge for health care providers and patients. Prospective identification of high-risk patients for early discontinuation has the potential to assist clinical decision-making and can improve the design of more efficient clinical trials. In partnership with Project Data Sphere (PDS), a non-profit initiative facilitating clinical trial data-sharing, we designed an open-data, crowdsourced DREAM (Dialogue for Reverse Engineering Assessments and Methods) Challenge for developing models to predict early discontinuation of docetaxelMethodsData from the comparator arms of four phase III clinical trials in first-line mCRPC were obtained from PDS, including 476 patients treated with docetaxel and prednisone from the ASCENT2 trial, 598 patients treated with docetaxel, prednisone/prednisolone, and placebo in the VENICE trial, 526 patients treated with docetaxel, prednisone, and placebo in the MAINSAIL trial, and 528 patients treated with docetaxel and placebo in the ENTHUSE 33 trial. Early discontinuation was defined as treatment stoppage within three months due to adverse treatment effects. Over 150 clinical features including laboratory values, medical history, lesion measures, prior treatment, and demographic variables were curated and made freely available for model building for all four trials. The ASCENT2, VENICE, and MAINSAIL trial data sets formed the training set that also included patient discontinuation status. The ENTHUSE 33 trial, with patient discontinuation status hidden, was used as an independent validation set to evaluate model performance. Prediction performance was assessed using area under the precision-recall curve (AUPRC) and the Bayes factor was used to compare the performance between prediction models.ResultsThe frequency of early discontinuation was similar between training (ASCENT2, VENICE, and MAINSAIL) and validation (ENTHUSE 33) sets, 12.3% versus 10.4% of docetaxel-treated patients, respectively. In total, 34 independent teams submitted predictions from 61 different models. AUPRC ranged from 0.088 to 0.178 across submissions with a random model performance of 0.104. Seven models with comparable AUPRC scores (Bayes factor ≤; 3) were observed to outperform all other models. A post-challenge analysis of risk predictions generated by these seven models revealed three distinct patient subgroups: patients consistently predicted to be at high-risk or low-risk for early discontinuation and those with discordant risk predictions. Early discontinuation events were two-times higher in the high-versus low-risk subgroup and baseline clinical features such as presence/absence of metastatic liver lesions, and prior treatment with analgesics and ACE inhibitors exhibited statistically significant differences between the high- and low-risk subgroups (adjustedP< 0.05). An ensemble-based model constructed from a post-Challenge community collaboration resulted in the best overall prediction performance (AUPRC = 0.230) and represented a marked improvement over any individual Challenge submission. AFindingsOur results demonstrate that routinely collected clinical features can be used to prospectively inform clinicians of mCRPC patients’ risk to discontinue docetaxel treatment early due to adverse events and to the best of our knowledge is the first to establish performance benchmarks in this area. This work also underscores the “wisdom of crowds” approach by demonstrating that improved prediction of patient outcomes is obtainable by combining methods across an extended community. These findings were made possible because data from separate trials were made publicly available and centrally compiled through PDS.

Current measures of health and disease are often insensitive, episodic, and subjective. Further, these measures generally are not designed to provide meaningful feedback to individuals. The impact of high-resolution activity data collected from mobile phones is only beginning to be explored. Here we present data from mPower, a clinical observational study about Parkinson disease conducted purely through an iPhone app interface. The study interrogated aspects of this movement disorder through surveys and frequent sensor-based recordings from participants with and without Parkinson disease. Benefitting from large enrollment and repeated measurements on many individuals, these data may help establish baseline variability of real-world activity measurement collected via mobile phones, and ultimately may lead to quantification of the ebbs-and-flows of Parkinson symptoms. App source code for these data collection modules are available through an open source license for use in studies of other conditions. We hope that releasing data contributed by engaged research participants will seed a new community of analysts working collaboratively on understanding mobile health data to advance human health.

Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimer's disease. The Alzheimer's disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state-of-the-art in predicting cognitive outcomes in Alzheimer's disease based on high dimensional, publicly available genetic and structural imaging data. This meta-analysis failed to identify a meaningful predictor developed from either data modality, suggesting that alternate approaches should be considered for prediction of cognitive performance.

A major challenge in biomedical research is to identify causal relationships among genotypes, phenotypes, and clinical outcomes from high-dimensional measurements. Causal networks have been widely used in systems genetics for modeling gene regulatory systems and for identifying causes and risk factors of diseases. In this chapter, we describe fundamental concepts and algorithms for constructing causal networks from observational data. In biological context, causal inferences can be drawn from the natural experimental setting provided by Mendelian randomization, a term that refers to the random assignment of genotypes at meiosis. We show that genetic variants may serve as instrumental variables, improving estimation accuracy of the causal effects. In addition, identifiability issues that commonly arise when learning network structures may be overcome by using prior information on genotype–phenotype relations. We discuss four recent algorithms for genotype–phenotype network structure learning, namely (1) QTL-directed dependency graph, (2) QTL+Phenotype supervised orientation, (3) QTL-driven phenotype network, and (4) sparsity-aware maximum likelihood (SML).

Type 2 diabetes results from severe insulin resistance coupled with a failure of b cells to compensate by secreting sufficient insulin. Multiple genetic loci are involved in the development of diabetes, although the effect of each gene on diabetes susceptibility is thought to be small. MicroRNAs (miRNAs) are noncoding 19-22-nucleotide RNA molecules that potentially regulate the expression of thousands of genes. To understand the relationship between miRNA regulation and obesity-induced diabetes, we quantitatively profiled approximately 220 miRNAs in pancreatic islets, adipose tissue, and liver from diabetes-resistant (B6) and diabetes-susceptible (BTBR) mice. More than half of the miRNAs profiled were expressed in all three tissues, with many miRNAs in each tissue showing significant changes in response to genetic obesity. Furthermore, several miRNAs in each tissue were differentially responsive to obesity in B6 versus BTBR mice, suggesting that they may be involved in the pathogenesis of diabetes. In liver there were approximately 40 miRNAs that were downregulated in response to obesity in B6 but not BTBR mice, indicating that genetic differences between the mouse strains play a critical role in miRNA regulation. In order to elucidate the genetic architecture of hepatic miRNA expression, we measured the expression of miRNAs in genetically obese F2 mice. Approximately 10% of the miRNAs measured showed significant linkage (miR-eQTLs), identifying loci that control miRNA abundance. Understanding the influence that obesity and genetics exert on the regulation of miRNA expression will reveal the role miRNAs play in the context of obesity-induced type 2 diabetes.

Suppose that X is a random vector with probability distribution P and suppose that P denotes a proposed model that involves interesting parameters and relationship between variables. We consider statistical inference procedures for the case where PeP constructed as follows: let hðPÞ denote the parameter of the distribution Q 2 P that minimizes a Kullback–Leibler (K–L)-type discrepancy KðQ; PÞ between Q and P. We take hðPÞ to be the parameter of interest. The estimate of hðPÞ, when it exists, is defined by ^ h ¼ hð ^

We propose hypothesis tests for detecting dopaminergic medication response in Parkinson disease patients, using longitudinal sensor data collected by smartphones. The processed data is composed of multiple features extracted from active tapping tasks performed by the participant on a daily basis, before and after medication, over several months. Each extracted feature corresponds to a time series of measurements annotated according to whether the measurement was taken before or after the patient has taken his/her medication. Even though the data is longitudinal in nature, we show that simple hypothesis tests for detecting medication response, which ignore the serial correlation structure of the data, are still statistically valid, showing type I error rates at the nominal level. We propose two distinct personalized testing approaches. In the first, we combine multiple feature-specific tests into a single union-intersection test. In the second, we construct personalized classifiers of the before/after medication labels using all the extracted features of a given participant, and test the null hypothesis that the area under the receiver operating characteristic curve of the classifier is equal to 1/2. We compare the statistical power of the personalized classifier tests and personalized union-intersection tests in a simulation study, and illustrate the performance of the proposed tests using data from mPower Parkinsons disease study, recently launched as part of Apples ResearchKit mobile platform. Our results suggest that the personalized tests, which ignore the longitudinal aspect of the data, can perform well in real data analyses, suggesting they might be used as a sound baseline approach, to which more sophisticated methods can be compared to.

DREAM challenges are community competitions designed to advance computational methods and address fundamental questions in system biology and translational medicine. Each challenge asks participants to develop and apply computational methods to either predict unobserved outcomes or to identify unknown model parameters given a set of training data. Computational methods are evaluated using an automated scoring metric, scores are posted to a public leaderboard, and methods are published to facilitate community discussions on how to build improved methods. By engaging participants from a wide range of science and engineering backgrounds, DREAM challenges can comparatively evaluate a wide range of statistical, machine learning, and biophysical methods. Here, we describe DREAMTools, a Python package for evaluating DREAM challenge scoring metrics. DREAMTools provides a command line interface that enables researchers to test new methods on past challenges, as well as a framework for scoring new challenges. As of March 2016, DREAMTools includes more than 80% of completed DREAM challenges. DREAMTools complements the data, metadata, and software tools available at the DREAM website http://dreamchallenges.org and on the Synapse platform at https://www.synapse.org.Availability: DREAMTools is a Python package. Releases and documentation are available at http://pypi.python.org/pypi/dreamtools. The source code is available at http://github.com/dreamtools/dreamtools.

Biological functions are carried out by groups of interacting molecules, cells or tissues, known as communities. Membership in these communities may overlap when biological components are involved in multiple functions. However, traditional clustering methods detect non-overlapping communities. These detected communities may also be unstable and difficult to replicate, because traditional methods are sensitive to noise and parameter settings. These aspects of traditional clustering methods limit our ability to detect biological communities and therefore our ability to understand biological functions. To address these limitations and detect robust overlapping biological communities, we propose an unorthodox clustering method called SpeakEasy which identifies communities using top-down and bottom-up approaches simultaneously. Specifically, nodes join communities based on their local connections, as well as global information about the network structure. This method can quantify the stability of each community, automatically identify the number of communities and quickly cluster networks with hundreds of thousands of nodes. SpeakEasy shows top performance on synthetic clustering benchmarks and accurately identifies meaningful biological communities in a range of datasets, including: gene microarrays, protein interactions, sorted cell populations, electrophysiology and fMRI brain imaging.