Robust, scalable, and informative clustering for diverse biological networks.

Clustering molecular data into informative groups is a primary step in extracting robust conclusions from big data. However, due to foundational issues in how they are defined and detected, such clusters are not always reliable, leading to unstable conclusions. We compare popular clustering algorithms across thousands of synthetic and real biological datasets, including a new consensus clustering algorithm-SpeakEasy2: Champagne. These tests identify trends in performance, show no single method is universally optimal, and allow us to examine factors behind variation in performance. Multiple metrics indicate SpeakEasy2 generally provides robust, scalable, and informative clusters for a range of applications.

Explainable deep learning approach for extracting cognitive features from hand-drawn images of intersecting pentagons.

Hand drawing, which requires multiple neural systems for planning and controlling sequential movements, is a useful cognitive test for older adults. However, the conventional visual assessment of these drawings only captures limited attributes and overlooks subtle details that could help track cognitive states. Here, we utilized a deep-learning model, PentaMind, to examine cognition-related features from hand-drawn images of intersecting pentagons. PentaMind, trained on 13,777 images from 3111 participants in three aging cohorts, explained 23.3% of the variance in the global cognitive scores, 1.92 times more than the conventional rating. This accuracy improvement was due to capturing additional drawing features associated with motor impairments and cerebrovascular pathologies. By systematically modifying the input images, we discovered several important drawing attributes for cognition, including line waviness. Our results demonstrate that deep learning models can extract novel drawing metrics to improve the assessment and monitoring of cognitive decline and dementia in older adults.

A Molecular Basis of Human Brain Connectivity.

Neuroimaging is commonly used to infer human brain connectivity, but those measurements are far-removed from the molecular underpinnings at synapses. To uncover the molecular basis of human brain connectivity, we analyzed a unique cohort of 98 individuals who provided neuroimaging and genetic data contemporaneous with dendritic spine morphometric, proteomic, and gene expression data from the superior frontal and inferior temporal gyri. Through cellular contextualization of the molecular data with dendritic spine morphology, we identified hundreds of proteins related to synapses, energy metabolism, and RNA processing that explain between-individual differences in functional connectivity and structural covariation. By integrating data at the genetic, molecular, subcellular, and tissue levels, we bridged the divergent fields of molecular biology and neuroimaging to identify a molecular basis of brain connectivity. One-Sentence Summary: Dendritic spine morphometry and synaptic proteins unite the divergent fields of molecular biology and neuroimaging.

Interpretable deep learning approach for extracting cognitive features from hand-drawn images of intersecting pentagons in older adults.

Hand drawing involves multiple neural systems for planning and precise control of sequential movements, making it a valuable cognitive test for older adults. However, conventional visual assessment of drawings may not capture intricate nuances that could help track cognitive states. To address this issue, we utilized a deep-learning model, PentaMind, to examine cognition-related features from hand-drawn images of intersecting pentagons. PentaMind, trained on 13,777 images from 3,111 participants in three aging cohorts, explained 23.3% of the variance in global cognitive scores, a comprehensive hour-long cognitive battery. The model’s performance, which was 1.92 times more accurate than conventional visual assessment, significantly improved the detection of cognitive decline. The improvement in accuracy was due to capturing additional drawing features that we found to be associated with motor impairments and cerebrovascular pathologies. By systematically modifying the input images, we discovered several important drawing attributes for cognition, including line waviness. Our results demonstrate that hand-drawn images can provide rich cognitive information, enabling rapid assessment of cognitive decline and suggesting potential clinical implications in dementia.

Development and validation of the CHIME simulation model to assess lifetime health outcomes of prediabetes and type 2 diabetes in Chinese populations: A modeling study.

BACKGROUND: Existing predictive outcomes models for type 2 diabetes developed and validated in historical European populations may not be applicable for East Asian populations due to differences in the epidemiology and complications. Despite the continuum of risk across the spectrum of risk factor values, existing models are typically limited to diabetes alone and ignore the progression from prediabetes to diabetes. The objective of this study is to develop and externally validate a patient-level simulation model for prediabetes and type 2 diabetes in the East Asian population for predicting lifetime health outcomes. METHODS AND FINDINGS: We developed a health outcomes model from a population-based cohort of individuals with prediabetes or type 2 diabetes: Hong Kong Clinical Management System (CMS, 97,628 participants) from 2006 to 2017. The Chinese Hong Kong Integrated Modeling and Evaluation (CHIME) simulation model comprises of 13 risk equations to predict mortality, micro- and macrovascular complications, and development of diabetes. Risk equations were derived using parametric proportional hazard models. External validation of the CHIME model was assessed in the China Health and Retirement Longitudinal Study (CHARLS, 4,567 participants) from 2011 to 2018 for mortality, ischemic heart disease, cerebrovascular disease, renal failure, cataract, and development of diabetes; and against 80 observed endpoints from 9 published trials using 100,000 simulated individuals per trial. The CHIME model was compared to United Kingdom Prospective Diabetes Study Outcomes Model 2 (UKPDS-OM2) and Risk Equations for Complications Of type 2 Diabetes (RECODe) by assessing model discrimination (C-statistics), calibration slope/intercept, root mean square percentage error (RMSPE), and R2. CHIME risk equations had C-statistics for discrimination from 0.636 to 0.813 internally and 0.702 to 0.770 externally for diabetes participants. Calibration slopes between deciles of expected and observed risk in CMS ranged from 0.680 to 1.333 for mortality, myocardial infarction, ischemic heart disease, retinopathy, neuropathy, ulcer of the skin, cataract, renal failure, and heart failure; 0.591 for peripheral vascular disease; 1.599 for cerebrovascular disease; and 2.247 for amputation; and in CHARLS outcomes from 0.709 to 1.035. CHIME had better discrimination and calibration than UKPDS-OM2 in CMS (C-statistics 0.548 to 0.772, slopes 0.130 to 3.846) and CHARLS (C-statistics 0.514 to 0.750, slopes -0.589 to 11.411); and small improvements in discrimination and better calibration than RECODe in CMS (C-statistics 0.615 to 0.793, slopes 0.138 to 1.514). Predictive error was smaller for CHIME in CMS (RSMPE 3.53% versus 10.82% for UKPDS-OM2 and 11.16% for RECODe) and CHARLS (RSMPE 4.49% versus 14.80% for UKPDS-OM2). Calibration performance of CHIME was generally better for trials with Asian participants (RMSPE 0.48% to 3.66%) than for non-Asian trials (RMPSE 0.81% to 8.50%). Main limitations include the limited number of outcomes recorded in the CHARLS cohort, and the generalizability of simulated cohorts derived from trial participants. CONCLUSIONS: Our study shows that the CHIME model is a new validated tool for predicting progression of diabetes and its outcomes, particularly among Chinese and East Asian populations that has been lacking thus far. The CHIME model can be used by health service planners and policy makers to develop population-level strategies, for example, setting HbA1c and lipid targets, to optimize health outcomes.

Impact of sleep duration, physical activity, and screen time on health-related quality of life in children and adolescents.

BACKGROUND: Existing studies on health-related quality of life (HRQoL) mainly covered single growth stages of childhood or adolescence and did not report on the trends in the relationships of HRQoL with sleep duration, physical activity, and screen time. This study aimed to establish the population norm of HRQoL in children and adolescents aged 6-17 years and examine the associations of screen time, sleep duration, and physical activity with HRQoL in this population. METHODS: We conducted a large-scale cross-sectional population-based survey study of Hong Kong children and adolescents aged 6 to 17 years. A representative sample of students were interviewed to assess their HRQoL using PedsQL and EQ-5D-Y-5L. Multivariable homoscedastic Tobit regression with linear form or restricted cubic spline of predictors was used to analyze the associations between screen time, sleep duration, and HRQoL. Multiple imputation by chained equations was performed to deal with missing data. RESULTS: A total of 7555 respondents (mean age 11.5, SD 3.2; 55.1% female) were sampled. Their EQ VAS scores, PedsQL physical summary scores, and psychosocial summary scores were positively correlated with sleep duration and moderate/vigorous activity but was negatively correlated with screen time. CONCLUSIONS: Children and adolescents who had longer exposure to screen, shorter sleep duration, and lower physical activity levels appeared to have poorer HRQoL as assessed by PedsQL and EQ-5D-Y-5L. Advice and guidance on screen time allocation for children and adolescents should be provided at the levels of school, community, and family.

Vedolizumab: Potential Mechanisms of Action for Reducing Pathological Inflammation in Inflammatory Bowel Diseases.

Inflammatory bowel diseases (IBD), encompassing ulcerative colitis (UC), and Crohn's disease (CD), are a group of disorders characterized by chronic, relapsing, and remitting, or progressive inflammation along the gastrointestinal tract. IBD is accompanied by massive infiltration of circulating leukocytes into the intestinal mucosa. Leukocytes such as neutrophils, monocytes, and T-cells are recruited to the affected site, exacerbating inflammation and causing tissue damage. Current treatments used to block inflammation in IBD include aminosalicylates, corticosteroids, immunosuppressants, and biologics. The first successful biologic, which revolutionized IBD treatment, targeted the pro-inflammatory cytokine, tumor necrosis factor alpha (TNFα). Infliximab, adalimumab, and other anti-TNF antibodies neutralize TNFα, preventing interactions with its receptors and reducing the inflammatory response. However, up to 40% of people with IBD become unresponsive to anti-TNFα therapy. Thus, more recent biologics have been designed to block leukocyte trafficking to the inflamed intestine by targeting integrins and adhesins. For example, natalizumab targets the α4 chain of integrin heterodimers, α4ß1 and α4ß7, on leukocytes. However, binding of α4ß1 is associated with increased risk for developing progressive multifocal leukoencephalopathy, an often-fatal disease, and thus, it is not used to treat IBD. To target leukocyte infiltration without this life-threatening complication, vedolizumab was developed. Vedolizumab specifically targets the α4ß7 integrin and was approved to treat IBD based on the presumption that it would block T-cell recruitment to the intestine. Though vedolizumab is an effective treatment for IBD, some studies suggest that it may not block T-cell recruitment to the intestine and its mechanism(s) of action remain unclear. Vedolizumab may reduce inflammation by blocking recruitment of T-cells, or pro-inflammatory monocytes and dendritic cells to the intestine, and/or vedolizumab may lead to changes in the programming of innate and acquired immune cells dampening down inflammation.

Comparing laboratory and in-the-wild data for continuous Parkinson's Disease tremor detection.

Passive, continuous monitoring of Parkinson's Disease (PD) symptoms in the wild (i.e., in home environments) could improve disease management, thereby improving a patient's quality of life. We envision a system that uses machine learning to automatically detect PD symptoms from accelerometer data collected in the wild. Building such systems, however, is challenging because it is difficult to obtain labels of symptom occurrences in the wild. Many researchers therefore train machine learning algorithms on laboratory data with the assumption that findings will translate to the wild. This paper assesses how well laboratory data represents wild data by comparing PD symptom (tremor) detection performance of three models on both lab and wild data. Findings indicate that, for this application, laboratory data is not a good representation of wild data. Results also show that training on wild data, even though labels are less precise, leads to better performance on wild data than training on accurate labels from laboratory data.

Parkinson's Disease Tremor Detection in the Wild Using Wearable Accelerometers.

Continuous in-home monitoring of Parkinson's Disease (PD) symptoms might allow improvements in assessment of disease progression and treatment effects. As a first step towards this goal, we evaluate the feasibility of a wrist-worn wearable accelerometer system to detect PD tremor in the wild (uncontrolled scenarios). We evaluate the performance of several feature sets and classification algorithms for robust PD tremor detection in laboratory and wild settings. We report results for both laboratory data with accurate labels and wild data with weak labels. The best performance was obtained using a combination of a pre-processing module to extract information from the tremor spectrum (based on non-negative factorization) and a deep neural network for learning relevant features and detecting tremor segments. We show how the proposed method is able to predict patient self-report measures, and we propose a new metric for monitoring PD tremor (i.e., percentage of tremor over long periods of time), which may be easier to estimate the start and end time points of each tremor event while still providing clinically useful information.

Weakly-supervised learning for Parkinson's Disease tremor detection.

Continuous, automated monitoring of Parkinsons Disease (PD) symptoms would provide clinicians with more information to understand their patients' disease progression and adjust treatment protocols, thereby improving PD care. Collecting precisely labeled data for Parkinson's symptoms, such as tremor, is difficult. Therefore, algorithms for monitoring should only require weakly-labeled training data. In this paper, we evaluate five standard weakly-supervised algorithms and propose a "stratified" version of three of the algorithms, which take advantage of knowing the approximate amount of tremor within each segment. In particular, we analyze PD tremor detection performance as training segments increase in length from 30 seconds to 10 minutes, and labels thereby become less precise. As segment length increases to 10 minutes, standard algorithms are not able to discriminate tremor from non-tremor. However, our stratified algorithms, which can make use of more nuanced labels, show little decrease in performance as segment length increases.

Wherever I may roam: social viscosity and kin affiliation in a wild population despite natal dispersal.

Dispersal affects the social contexts individuals experience by redistributing individuals in space, and the nature of social interactions can have important fitness consequences. During the vagrancy stage of natal dispersal, after an individual has left its natal site and before it has settled to breed, social affiliations might be predicted by opportunities to associate (e.g., distance in space and time between natal points of origin) or kin preferences. We investigated the social structure of a population of juvenile great tits (Parus major) and asked whether social affiliations during vagrancy were predicted by 1) the distance between natal nest-boxes, 2) synchrony in fledge dates, and 3) accounting for spatial and temporal predictors, whether siblings tended to stay together. We show that association strength was affected predominantly by spatial proximity at fledging and, to a lesser extent, temporal proximity in birth dates. Independently of spatial and temporal effects, sibling pairs associated more often than expected by chance. Our results suggest that the structure of the winter population is shaped primarily by limits to dispersal through incomplete population mixing. In addition, our results reveal kin structure, and hence the scope for fitness-related interactions between particular classes of kin. Both spatial-mediated and socially mediated population structuring can have implications for our understanding of the evolution of sociality.

Purification of monoclonal antibodies from clarified cell culture fluid using Protein A capture continuous countercurrent tangential chromatography.

Recent studies using simple model systems have demonstrated that continuous countercurrent tangential chromatography (CCTC) has the potential to overcome many of the limitations of conventional Protein A chromatography using packed columns. The objective of this work was to optimize and implement a CCTC system for monoclonal antibody purification from clarified Chinese Hamster Ovary (CHO) cell culture fluid using a commercial Protein A resin. Several improvements were introduced to the previous CCTC system including the use of retentate pumps to maintain stable resin concentrations in the flowing slurry, the elimination of a slurry holding tank to improve productivity, and the introduction of an "after binder" to the binding step to increase antibody recovery. A kinetic binding model was developed to estimate the required residence times in the multi-stage binding step to optimize yield and productivity. Data were obtained by purifying two commercial antibodies from two different manufactures, one with low titer (∼ 0.67 g/L) and one with high titer (∼ 6.9 g/L), demonstrating the versatility of the CCTC system. Host cell protein removal, antibody yields and purities were similar to those obtained with conventional column chromatography; however, the CCTC system showed much higher productivity. These results clearly demonstrate the capabilities of continuous countercurrent tangential chromatography for the commercial purification of monoclonal antibody products.