Search

Many studies have examined how the 2019 Coronavirus Disease (COVID-19) has impacted sleep health. Early evidence suggests that lockdown policies worldwide have led to changes in sleep timing, duration, and quality; however, few studies have attempted to look at the longer-term effects across multiple countries in a large data set. This study uses self-reported data from 64,858 users of the Sleep As Android smartphone application from around the world over a 24-month period in 2019 to 2020. We found a significant but modest increase in time in bed (TIB), as well as a significant delay in sleep timing that was especially prominent on weekdays. While this effect persisted throughout the year, differences in sleep timing were more widespread and pronounced in the earlier months of the pandemic. We observed a small overall increase in TIB when comparing 2020 to 2019, but these changes depended on location and time of year, suggesting that sleep duration may have more closely tracked the progression of the pandemic in each country. Our findings suggest that pandemic-induced changes in lifestyle, such as remote work and lockdown policies, may have facilitated later sleep timing but that these changes may diminish as restrictions are lifted., (© 2022. The Author(s).)

In this paper, we propose a new approach for variable selection using a collection of Bayesian neural networks with a focus on quantifying uncertainty over which variables are selected. Motivated by fine-mapping applications in statistical genetics, we refer to our framework as an "ensemble of single-effect neural networks" (ESNN) which generalizes the "sum of single effects" regression framework by both accounting for nonlinear structure in genotypic data (e.g., dominance effects) and having the capability to model discrete phenotypes (e.g., case-control studies). Through extensive simulations, we demonstrate our method's ability to produce calibrated posterior summaries such as credible sets and posterior inclusion probabilities, particularly for traits with genetic architectures that have significant proportions of non-additive variation driven by correlated variants. Lastly, we use real data to demonstrate that the ESNN framework improves upon the state of the art for identifying true effect variables underlying various complex traits., Competing Interests: The authors declare no competing interests., (© 2022 The Author(s).)

One of the most striking features of human cognition is the ability to plan. Two aspects of human planning stand out-its efficiency and flexibility. Efficiency is especially impressive because plans must often be made in complex environments, and yet people successfully plan solutions to many everyday problems despite having limited cognitive resources 1-3 . Standard accounts in psychology, economics and artificial intelligence have suggested that human planning succeeds because people have a complete representation of a task and then use heuristics to plan future actions in that representation 4-11 . However, this approach generally assumes that task representations are fixed. Here we propose that task representations can be controlled and that such control provides opportunities to quickly simplify problems and more easily reason about them. We propose a computational account of this simplification process and, in a series of preregistered behavioural experiments, show that it is subject to online cognitive control 12-14 and that people optimally balance the complexity of a task representation and its utility for planning and acting. These results demonstrate how strategically perceiving and conceiving problems facilitates the effective use of limited cognitive resources., (© 2022. The Author(s), under exclusive licence to Springer Nature Limited.)

Long-range regulatory interactions among genomic regions are critical for controlling gene expression, and their disruption has been associated with a host of diseases. However, when modeling the effects of regulatory factors, most deep learning models either neglect long-range interactions or fail to capture the inherent 3D structure of the underlying genomic organization. To address these limitations, we present a Graph Convolutional Model for Epigenetic Regulation of Gene Expression (GC-MERGE). Using a graph-based framework, the model incorporates important information about long-range interactions via a natural encoding of genomic spatial interactions into the graph representation. It integrates measurements of both the global genomic organization and the local regulatory factors, specifically histone modifications, to not only predict the expression of a given gene of interest but also quantify the importance of its regulatory factors. We apply GC-MERGE to data sets for three cell lines-GM12878 (lymphoblastoid), K562 (myelogenous leukemia), and HUVEC (human umbilical vein endothelial)-and demonstrate its state-of-the-art predictive performance. Crucially, we show that our model is interpretable in terms of the observed biological regulatory factors, highlighting both the histone modifications and the interacting genomic regions contributing to a gene's predicted expression. We provide model explanations for multiple exemplar genes and validate them with evidence from the literature. Our model presents a novel setup for predicting gene expression by integrating multimodal data sets in a graph convolutional framework. More importantly, it enables interpretation of the biological mechanisms driving the model's predictions .

A large percentage of the world's population is affected by gastric diseases ranging from erosion and ulcer to serious ailments such as gastric cancer, which is mainly caused by Helicobacter pylori(H.pylori) infection. While most erosions and ulcers are benign, severe cases of gastric diseases can still develop into cancer. Thus, early screening and treatment of all gastric diseases are of great importance. Upper gastroscopy is one such common screening procedure that visualizes the patient's upper digestive system by inserting a camera attached to a rubber tube down the patient's digestive tracts, but since the procedure requires manual inspection of the video feed, it is prone to human errors. To improve the sensitivity and specificity of gastroscopies, we applied deep learning methods to develop an automated gastric disease detection system that detects frames of the video feed showing signs of gastric diseases. To this end, we collected data from images in anonymous patient case reports and gastroscopy videos to train and evaluate a convolutional neural network (CNN), and we used sliding window to improve the stability of our model's video performance. Our CNN model achieved 84.92% sensitivity, 88.26% specificity, and 85.2% F1-score on the test set, as well as 97% true positive rate and 16.2% false positive rate on a separate video test set., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2022 Zhang, Xiong, Chen, Ding, Cao, Liu and Liu.)

While COVID-19 diagnosis and prognosis artificial intelligence models exist, very few can be implemented for practical use given their high risk of bias. We aimed to develop a diagnosis model that addresses notable shortcomings of prior studies, integrating it into a fully automated triage pipeline that examines chest radiographs for the presence, severity, and progression of COVID-19 pneumonia. Scans were collected using the DICOM Image Analysis and Archive, a system that communicates with a hospital's image repository. The authors collected over 6,500 non-public chest X-rays comprising diverse COVID-19 severities, along with radiology reports and RT-PCR data. The authors provisioned one internally held-out and two external test sets to assess model generalizability and compare performance to traditional radiologist interpretation. The pipeline was evaluated on a prospective cohort of 80 radiographs, reporting a 95% diagnostic accuracy. The study mitigates bias in AI model development and demonstrates the value of an end-to-end COVID-19 triage platform., (© 2022. The Author(s).)

Recent advances in sequencing technologies have allowed us to capture various aspects of the genome at single-cell resolution. However, with the exception of a few of co-assaying technologies, it is not possible to simultaneously apply different sequencing assays on the same single cell. In this scenario, computational integration of multi-omic measurements is crucial to enable joint analyses. This integration task is particularly challenging due to the lack of sample-wise or feature-wise correspondences. We present single-cell alignment with optimal transport (SCOT), an unsupervised algorithm that uses the Gromov-Wasserstein optimal transport to align single-cell multi-omics data sets. SCOT performs on par with the current state-of-the-art unsupervised alignment methods, is faster, and requires tuning of fewer hyperparameters. More importantly, SCOT uses a self-tuning heuristic to guide hyperparameter selection based on the Gromov-Wasserstein distance. Thus, in the fully unsupervised setting, SCOT aligns single-cell data sets better than the existing methods without requiring any orthogonal correspondence information.

We often specify tasks for a robot using temporal language that can include different levels of abstraction. For example, the command "go to the kitchen before going to the second floor" contains spatial abstraction, given that "floor" consists of individual rooms that can also be referred to in isolation ("kitchen", for example). There is also a temporal ordering of events, defined by the word "before". Previous works have used syntactically co-safe Linear Temporal Logic (sc-LTL) to interpret temporal language (such as "before"), and Abstract Markov Decision Processes (AMDPs) to interpret hierarchical abstractions (such as "kitchen" and "second floor"), separately. To handle both types of commands at once, we introduce the Abstract Product Markov Decision Process (AP-MDP), a novel approach capable of representing non-Markovian reward functions at different levels of abstractions. The AP-MDP framework translates LTL into its corresponding automata, creates a product Markov Decision Process (MDP) of the LTL specification and the environment MDP, and decomposes the problem into subproblems to enable efficient planning with abstractions. AP-MDP performs faster than a non-hierarchical method of solving LTL problems in over 95 % of path planning tasks, and this number only increases as the size of the environment domain increases. In a cleanup world domain, AP-MDP performs faster in over 98 % of tasks. We also present a neural sequence-to-sequence model trained to translate language commands into LTL expression, and a new corpus of non-Markovian language commands spanning different levels of abstraction. We test our framework with the collected language commands on two drones, demonstrating that our approach enables robots to efficiently solve temporal commands at different levels of abstraction in both indoor and outdoor environments., (© The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2022.)

Although the availability of various sequencing technologies allows us to capture different genome properties at single-cell resolution, with the exception of a few co-assaying technologies, applying different sequencing assays on the same single cell is impossible. Single-cell alignment using optimal transport (SCOT) is an unsupervised algorithm that addresses this limitation by using optimal transport to align single-cell multiomics data. First, it preserves the local geometry by constructing a k -nearest neighbor ( k -NN) graph for each data set (or domain) to capture the intra-domain distances. SCOT then finds a probabilistic coupling matrix that minimizes the discrepancy between the intra-domain distance matrices. Finally, it uses the coupling matrix to project one single-cell data set onto another through barycentric projection, thus aligning them. SCOT requires tuning only two hyperparameters and is robust to the choice of one. Furthermore, the Gromov-Wasserstein distance in the algorithm can guide SCOT's hyperparameter tuning in a fully unsupervised setting when no orthogonal alignment information is available. Thus, SCOT is a fast and accurate alignment method that provides a heuristic for hyperparameter selection in a real-world unsupervised single-cell data alignment scenario. We provide a tutorial for SCOT and make its source code publicly available on GitHub.

Virtual and augmented reality (VR/AR) are new technologies with the power to revolutionize the study of morphology. Modern imaging approaches such as computed tomography, laser scanning, and photogrammetry have opened up a new digital world, enabling researchers to share and analyze morphological data electronically and in great detail. Because this digital data exists on a computer screen, however, it can remain difficult to understand and unintuitive to interact with. VR/AR technologies bridge the analog-to-digital divide by presenting 3D data to users in a very similar way to how they would interact with actual anatomy, while also providing a more immersive experience and greater possibilities for exploration. This manuscript describes VR/AR hardware, software, and techniques, and is designed to give practicing morphologists and educators a primer on using these technologies in their research, pedagogy, and communication to a wide variety of audiences. We also include a series of case studies from the presentations and workshop given at the 2019 International Congress of Vertebrate Morphology, and suggest best practices for the use of VR/AR in comparative morphology., (© 2021 Wiley Periodicals LLC.)

Population and public health are in the midst of an artificial intelligence revolution capable of radically altering existing models of care delivery and practice. Just as AI seeks to mirror human cognition through its data-driven analytics, it can also reflect the biases present in our collective conscience. In this Viewpoint, we use past and counterfactual examples to illustrate the sequelae of unmitigated bias in healthcare artificial intelligence. Past examples indicate that if the benefits of emerging AI technologies are to be realized, consensus around the regulation of algorithmic bias at the policy level is needed to ensure their ethical integration into the health system. This paper puts forth regulatory strategies for uprooting bias in healthcare AI that can inform ongoing efforts to establish a framework for federal oversight. We highlight three overarching oversight principles in bias mitigation that maps to each phase of the algorithm life cycle., (© 2021. The Author(s), under exclusive licence to Springer Nature Limited.)

Purpose: The purpose of this paper is to describe the course, "Designing Education for Better Prisoner and Community Health," which provided students with the knowledge, skills and resources needed to build real-world health education materials for persons who are criminal justice involved., Design/methodology/approach: A multiphase engaged scholarship course was designed and implemented through the Brown University School of Public Health in Rhode Island, USA., Findings: Students collaborated closely with instructors, subject matter experts and affected community members to develop highly tailored health education projects across six topic areas. The structure and outcomes of the paper are described with the hope that other instructors and institutions might replicate components of the model., Originality/value: Engaged scholarship in public health can provide students with rich, collaborative learning experiences, and when executed effectively, these endeavors can provide underserved communities with robust and informed health education interventions and programs., (© Emerald Publishing Limited.)

Motivation: Hi-C is the most widely used assay for investigating genome-wide 3D organization of chromatin. When working with Hi-C data, it is often useful to calculate the similarity between contact matrices in order to assess experimental reproducibility or to quantify relationships among Hi-C data from related samples. The HiCRep algorithm has been widely adopted for this task, but the existing R implementation suffers from run time limitations on high-resolution Hi-C data or on large single-cell Hi-C datasets., Results: We introduce a Python implementation of HiCRep and demonstrate that it is much faster and consumes much less memory than the existing R implementation. Furthermore, we give examples of HiCRep's ability to accurately distinguish replicates from non-replicates and to reveal cell type structure among collections of Hi-C data., Availability and Implementation: HiCRep.py and its documentation are available with a GPL license at https://github.com/Noble-Lab/hicrep. The software may be installed automatically using the pip package installer., Supplementary Information: Supplementary data are available at Bioinformatics online., (© The Author(s) 2021. Published by Oxford University Press.)

Background: Mammalian development is associated with extensive changes in gene expression, chromatin accessibility, and nuclear structure. Here, we follow such changes associated with mouse embryonic stem cell differentiation and X inactivation by integrating, for the first time, allele-specific data from these three modalities obtained by high-throughput single-cell RNA-seq, ATAC-seq, and Hi-C., Results: Allele-specific contact decay profiles obtained by single-cell Hi-C clearly show that the inactive X chromosome has a unique profile in differentiated cells that have undergone X inactivation. Loss of this inactive X-specific structure at mitosis is followed by its reappearance during the cell cycle, suggesting a "bookmark" mechanism. Differentiation of embryonic stem cells to follow the onset of X inactivation is associated with changes in contact decay profiles that occur in parallel on both the X chromosomes and autosomes. Single-cell RNA-seq and ATAC-seq show evidence of a delay in female versus male cells, due to the presence of two active X chromosomes at early stages of differentiation. The onset of the inactive X-specific structure in single cells occurs later than gene silencing, consistent with the idea that chromatin compaction is a late event of X inactivation. Single-cell Hi-C highlights evidence of discrete changes in nuclear structure characterized by the acquisition of very long-range contacts throughout the nucleus. Novel computational approaches allow for the effective alignment of single-cell gene expression, chromatin accessibility, and 3D chromosome structure., Conclusions: Based on trajectory analyses, three distinct nuclear structure states are detected reflecting discrete and profound simultaneous changes not only to the structure of the X chromosomes, but also to that of autosomes during differentiation. Our study reveals that long-range structural changes to chromosomes appear as discrete events, unlike progressive changes in gene expression and chromatin accessibility., (© 2021. The Author(s).)

In this article, we present Biologically Annotated Neural Networks (BANNs), a nonlinear probabilistic framework for association mapping in genome-wide association (GWA) studies. BANNs are feedforward models with partially connected architectures that are based on biological annotations. This setup yields a fully interpretable neural network where the input layer encodes SNP-level effects, and the hidden layer models the aggregated effects among SNP-sets. We treat the weights and connections of the network as random variables with prior distributions that reflect how genetic effects manifest at different genomic scales. The BANNs software uses variational inference to provide posterior summaries which allow researchers to simultaneously perform (i) mapping with SNPs and (ii) enrichment analyses with SNP-sets on complex traits. Through simulations, we show that our method improves upon state-of-the-art association mapping and enrichment approaches across a wide range of genetic architectures. We then further illustrate the benefits of BANNs by analyzing real GWA data assayed in approximately 2,000 heterogenous stock of mice from the Wellcome Trust Centre for Human Genetics and approximately 7,000 individuals from the Framingham Heart Study. Lastly, using a random subset of individuals of European ancestry from the UK Biobank, we show that BANNs is able to replicate known associations in high and low-density lipoprotein cholesterol content., Competing Interests: The authors have declared that no competing interests exist.

The demand for the sensor-based detection of camouflage objects widely exists in biological research, remote sensing, and military applications. However, the performance of traditional object detection algorithms is limited, as they are incapable of extracting informative parts from low signal-to-noise ratio features. To address this problem, we propose Camouflaged Object Detection with Cascade and Feedback Fusion (CODCEF), a deep learning framework based on an RGB optical sensor that leverages a cascaded structure with Feedback Partial Decoders (FPD) instead of a traditional encoder-decoder structure. Through a selective fusion strategy and feedback loop, FPD reduces the loss of information and the interference of noises in the process of feature interweaving. Furthermore, we introduce Pixel Perception Fusion (PPF) loss, which aims to pay more attention to local pixels that might become the edges of an object. Experimental results on an edge device show that CODCEF achieved competitive results compared with 10 state-of-the-art methods.

Traditional techniqueset identification, we developed GraphDTI, a robust machine learning framework integrating the molecular-level information on drugs, proteins, and binding sites with the system-level information on gene expression and protein-protein interactions. In order to properly evaluate the performance of GraphDTI, we compiled a high-quality benchmarking dataset and devised a new cluster-based cross-validation p to identify macromolecular targets for drugs utilize solely the information on a query drug and a putative target. Nonetheless, the mechanisms of action of many drugs depend not only on their binding affinity toward a single protein, but also on the signal transduction through cascades of molecular interactions leading to certain phenotypes. Although using protein-protein interaction networks and drug-perturbed gene expression profiles can facilitate system-level investigations of drug-target interactions, utilizing such large and heterogeneous data poses notable challenges. To improve the state-of-the-art in drug targrotocol. Encouragingly, GraphDTI not only yields an AUC of 0.996 against the validation dataset, but it also generalizes well to unseen data with an AUC of 0.939, significantly outperforming other predictors. Finally, selected examples of identified drug-target interactions are validated against the biomedical literature. Numerous applications of GraphDTI include the investigation of drug polypharmacological effects, side effects through off-target binding, and repositioning opportunities., (© 2021. The Author(s).)

Interacting, self-propelled particles such as epithelial cells can dynamically self-organize into complex multicellular patterns, which are challenging to classify without a priori information. Classically, different phases and phase transitions have been described based on local ordering, which may not capture structural features at larger length scales. Instead, topological data analysis (TDA) determines the stability of spatial connectivity at varying length scales (i.e. persistent homology), and can compare different particle configurations based on the "cost" of reorganizing one configuration into another. Here, we demonstrate a topology-based machine learning approach for unsupervised profiling of individual and collective phases based on large-scale loops. We show that these topological loops (i.e. dimension 1 homology) are robust to variations in particle number and density, particularly in comparison to connected components (i.e. dimension 0 homology). We use TDA to map out phase diagrams for simulated particles with varying adhesion and propulsion, at constant population size as well as when proliferation is permitted. Next, we use this approach to profile our recent experiments on the clustering of epithelial cells in varying growth factor conditions, which are compared to our simulations. Finally, we characterize the robustness of this approach at varying length scales, with sparse sampling, and over time. Overall, we envision TDA will be broadly applicable as a model-agnostic approach to analyze active systems with varying population size, from cytoskeletal motors to motile cells to flocking or swarming animals.

Background: Chest x-ray is a relatively accessible, inexpensive, fast imaging modality that might be valuable in the prognostication of patients with COVID-19. We aimed to develop and evaluate an artificial intelligence system using chest x-rays and clinical data to predict disease severity and progression in patients with COVID-19., Methods: We did a retrospective study in multiple hospitals in the University of Pennsylvania Health System in Philadelphia, PA, USA, and Brown University affiliated hospitals in Providence, RI, USA. Patients who presented to a hospital in the University of Pennsylvania Health System via the emergency department, with a diagnosis of COVID-19 confirmed by RT-PCR and with an available chest x-ray from their initial presentation or admission, were retrospectively identified and randomly divided into training, validation, and test sets (7:1:2). Using the chest x-rays as input to an EfficientNet deep neural network and clinical data, models were trained to predict the binary outcome of disease severity (ie, critical or non-critical). The deep-learning features extracted from the model and clinical data were used to build time-to-event models to predict the risk of disease progression. The models were externally tested on patients who presented to an independent multicentre institution, Brown University affiliated hospitals, and compared with severity scores provided by radiologists., Findings: 1834 patients who presented via the University of Pennsylvania Health System between March 9 and July 20, 2020, were identified and assigned to the model training (n=1285), validation (n=183), or testing (n=366) sets. 475 patients who presented via the Brown University affiliated hospitals between March 1 and July 18, 2020, were identified for external testing of the models. When chest x-rays were added to clinical data for severity prediction, area under the receiver operating characteristic curve (ROC-AUC) increased from 0·821 (95% CI 0·796-0·828) to 0·846 (0·815-0·852; p<0·0001) on internal testing and 0·731 (0·712-0·738) to 0·792 (0·780-0 ·803; p<0·0001) on external testing. When deep-learning features were added to clinical data for progression prediction, the concordance index (C-index) increased from 0·769 (0·755-0·786) to 0·805 (0·800-0·820; p<0·0001) on internal testing and 0·707 (0·695-0·729) to 0·752 (0·739-0·764; p<0·0001) on external testing. The image and clinical data combined model had significantly better prognostic performance than combined severity scores and clinical data on internal testing (C-index 0·805 vs 0·781; p=0·0002) and external testing (C-index 0·752 vs 0·715; p<0·0001)., Interpretation: In patients with COVID-19, artificial intelligence based on chest x-rays had better prognostic performance than clinical data or radiologist-derived severity scores. Using artificial intelligence, chest x-rays can augment clinical data in predicting the risk of progression to critical illness in patients with COVID-19., Funding: Brown University, Amazon Web Services Diagnostic Development Initiative, Radiological Society of North America, National Cancer Institute and National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health., Competing Interests: Declaration of interests HXB reports grants from Brown University, Amazon Web Service, Radiological Society of North America, and National Cancer Institute of the National Institute of Health, during the conduct of the study. XF currently works in Carina Medical, a for-profit organisation that develops clinical products, outside of the submitted work. KC reports grants from National Institute of Biomedical Imaging and Bioengineering and National Cancer Institute of the National Institute of Health, during the conduct of the study. YF reports grants from National Institute of Health, during the conduct of the study. All other authors declare no competing interests., (Copyright © 2021 The Author(s). Published by Elsevier Ltd. This is an Open Access article under the CC BY-NC-ND 4.0 license. Published by Elsevier Ltd.. All rights reserved.)

A classic problem in computational biology is the identification of altered subnetworks : subnetworks of an interaction network that contain genes/proteins that are differentially expressed, highly mutated, or otherwise aberrant compared with other genes/proteins. Numerous methods have been developed to solve this problem under various assumptions, but the statistical properties of these methods are often unknown. For example, some widely used methods are reported to output very large subnetworks that are difficult to interpret biologically. In this work, we formulate the identification of altered subnetworks as the problem of estimating the parameters of a class of probability distributions that we call the Altered Subset Distribution (ASD). We derive a connection between a popular method, jActiveModules, and the maximum likelihood estimator (MLE) of the ASD. We show that the MLE is statistically biased , explaining the large subnetworks output by jActiveModules. Based on these insights, we introduce NetMix, an algorithm that uses Gaussian mixture models to obtain less biased estimates of the parameters of the ASD. We demonstrate that NetMix outperforms existing methods in identifying altered subnetworks on both simulated and real data, including the identification of differentially expressed genes from both microarray and RNA-seq experiments and the identification of cancer driver genes in somatic mutation data.

We propose a novel approach for processing diffusion MRI tractography datasets using the sparse closest point transform (SCPT). Tractography enables the 3D geometry of white matter pathways to be reconstructed; however, algorithms for processing them are often highly customized, and thus, do not leverage the existing wealth of machine learning (ML) algorithms. We investigated a vector-space tractography representation that aims to bridge this gap by using the SCPT, which consists of two steps: first, extracting sparse and representative landmarks from a tractography dataset, and second transforming curves relative to these landmarks with a closest point transform. We explore its use in three typical tasks: fiber bundle clustering, simplification, and selection across a population. The clustering algorithm groups fibers from single whole-brain datasets using a non-parametric k-means clustering algorithm, with performance compared with three alternative methods and across four datasets. The simplification algorithm removes redundant curves to improve interactive visualization, with performance gauged relative to random subsampling. The selection algorithm extracts bundles across a population using a one-class Gaussian classifier derived from an atlas prototype, with performance gauged by scan-rescan reliability and sensitivity to normal aging, as compared to manual mask-based selection. Our results demonstrate how the SCPT enables the novel application of existing vector-space ML algorithms to create effective and efficient tools for tractography processing. Our experimental data is available online, and our software implementation is available in the Quantitative Imaging Toolkit.

Anginal symptoms can connote increased cardiac risk and a need for change in cardiovascular management. In this study, a pre-trained transformer architecture was used to automatically detect and characterize anginal symptoms from within the history of present illness sections of 459 primary care physician notes. Consecutive patients referred for cardiac testing were included. Notes were annotated for positive and negative mentions of chest pain and shortness of breath characterization. The results demonstrate high sensitivity and specificity for the detection of chest pain or discomfort, substernal chest pain, shortness of breath, and dyspnea on exertion. Model performance extracting factors related to provocation and palliation of chest pain were limited by small sample size. Overall, this study shows that pre-trained transformer architectures have promise in automating the extraction of anginal symptoms from clinical texts., (©2020 AMIA - All rights reserved.)

Background: The Los Angeles Motor Scale (LAMS) is a 3-item, 0-to-5-point motor stroke-deficit scale derived from the Los Angeles Prehospital Stroke Screen. We assessed the predictive validity (for interventions performed and discharge disposition) of the LAMS performed in the field by paramedics in a geographic region of over 5,200 km2, covering both rural and urban areas., Methods: We analyzed data gathered from Phase I of the LIT-PASS study (Large Vessel Occlusion Identification Through Prehospital Administration of Stroke Scales) which included all patients with suspected acute cerebrovascular disease, as assessed by the Balance, Eyes, Face, Arm, Speech, Terrible Headache/Time to Call 911 (BE-FAST) test., Results: Among 1,906 patients with median age 72 years (interquartile range [IQR] 60-81), 53% were female with a median on-scene time of 15 min (IQR 12-19). C statistics for the interventions of mechanical thrombectomy, alteplase administration, computed tomography angiography, and perfusion imaging were 0.681, 0.643, and 0.680, respectively. The cut point for predicting these 3 interventions was confirmed to be LAMS ≥ 4. LAMS ≥ 4 had sensitivity 0.730 (0.661-0.790) and specificity 0.570 (0.539-0.601) for mechanical intervention (endovascular thrombectomy, coiling, or clipping) and relative risk of 2.98 (2.19-4.07) for in-hospital death., Conclusions: This real-world field study validates the LAMS as an effective tool for prehospital assessment of suspected strokes in determining transport decisions, with predictive validity for interventions performed., (© 2021 The Author(s). Published by S. Karger AG, Basel.)

Background: Behavioral lifestyle intervention (BLI) is recommended as a first-line treatment for obesity. While BLI has been adapted for online delivery to improve potential for dissemination while reducing costs and barriers to access, weight losses are typically inferior to gold standard treatment delivered in-person. It is therefore important to refine and optimize online BLI in order to improve the proportion of individuals who achieve a minimum clinically significant weight loss and mean weight loss., Study Design: Five experimental intervention components will be tested as adjuncts to an established 12-month online BLI: virtual reality for BLI skills training, interactive video feedback, tailored intervention to promote physical activity, skills for dysregulated eating, and social support combined with friendly competition. Following the Multiphase Optimization Strategy (MOST) framework, the components will first be refined and finalized during Preparation Phase pilot testing and then evaluated in a factorial experiment with 384 adults with overweight or obesity. A priori optimization criteria that balance efficacy and efficiency will be used to create a finalized treatment package that produces the best weight loss outcomes with the fewest intervention components. Mediation analysis will be conducted to test hypothesized mechanisms of action and a moderator analysis will be conducted to understand for whom and under what circumstances the interventions are effective., Conclusion: This study will provide important information about intervention strategies that are useful for improving outcomes of online BLI. The finalized treatment package will be suitable for testing in a future randomized trial in the MOST Evaluation Phase., (Copyright © 2020 Elsevier Inc. All rights reserved.)

Background Large vessel occlusion (LVO) stroke is one of the most time-sensitive diagnoses in medicine and requires emergent endovascular therapy to reduce morbidity and mortality. Leveraging recent advances in deep learning may facilitate rapid detection and reduce time to treatment. Purpose To develop a convolutional neural network to detect LVOs at multiphase CT angiography. Materials and Methods This multicenter retrospective study evaluated 540 adults with CT angiography examinations for suspected acute ischemic stroke from February 2017 to June 2018. Examinations positive for LVO ( n = 270) were confirmed by catheter angiography and LVO-negative examinations ( n = 270) were confirmed through review of clinical and radiology reports. Preprocessing of the CT angiography examinations included vasculature segmentation and the creation of maximum intensity projection images to emphasize the contrast agent-enhanced vasculature. Seven experiments were performed by using combinations of the three phases (arterial, phase 1; peak venous, phase 2; and late venous, phase 3) of the CT angiography. Model performance was evaluated on the held-out test set. Metrics included area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. Results The test set included 62 patients (mean age, 69.5 years; 48% women). Single-phase CT angiography achieved an AUC of 0.74 (95% confidence interval [CI]: 0.63, 0.85) with sensitivity of 77% (24 of 31; 95% CI: 59%, 89%) and specificity of 71% (22 of 31; 95% CI: 53%, 84%). Phases 1, 2, and 3 together achieved an AUC of 0.89 (95% CI: 0.81, 0.96), sensitivity of 100% (31 of 31; 95% CI: 99%, 100%), and specificity of 77% (24 of 31; 95% CI: 59%, 89%), a statistically significant improvement relative to single-phase CT angiography ( P = .01). Likewise, phases 1 and 3 and phases 2 and 3 also demonstrated improved fit relative to single phase ( P = .03). Conclusion This deep learning model was able to detect the presence of large vessel occlusion and its diagnostic performance was enhanced by using delayed phases at multiphase CT angiography examinations. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Ospel and Goyal in this issue.

We posit the likely architecture of complex diseases is that subgroups of patients share variants in genes in specific networks which are sufficient to give rise to a shared phenotype. We developed Proteinarium, a multi-sample protein-protein interaction (PPI) tool, to identify clusters of patients with shared gene networks. Proteinarium converts user defined seed genes to protein symbols and maps them onto the STRING interactome. A PPI network is built for each sample using Dijkstra's algorithm. Pairwise similarity scores are calculated to compare the networks and cluster the samples. A layered graph of PPI networks for the samples in any cluster can be visualized. To test this newly developed analysis pipeline, we reanalyzed publicly available data sets, from which modest outcomes had previously been achieved. We found significant clusters of patients with unique genes which enhanced the findings in the original study., (Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.)

Interest is growing rapidly in using deep learning to classify biomedical images, and interpreting these deep-learned models is necessary for life-critical decisions and scientific discovery. Effective interpretation techniques accelerate biomarker discovery and provide new insights into the etiology, diagnosis, and treatment of disease. Most interpretation techniques aim to discover spatially-salient regions within images, but few techniques consider imagery with multiple channels of information. For instance, highly multiplexed tumor and tissue images have 30-100 channels and require interpretation methods that work across many channels to provide deep molecular insights. We propose a novel channel embedding method that extracts features from each channel. We then use these features to train a classifier for prediction. Using this channel embedding, we apply an interpretation method to rank the most discriminative channels. To validate our approach, we conduct an ablation study on a synthetic dataset. Moreover, we demonstrate that our method aligns with biological findings on highly multiplexed images of breast cancer cells while outperforming baseline pipelines. Code is available at https://sabdelmagid.github.io/miccai2020-project/.

Holographic microscopy has emerged as a tool for in situ imaging of microscopic organisms and other particles in the marine environment: appealing because of the relatively larger sampling volume and simpler optical configuration compared to other imaging systems. However, its quantitative capabilities have so far remained uncertain, in part because hologram reconstruction and image recognition have required manual operation. Here, we assess the quantitative skill of our automated hologram processing pipeline (CCV Pipeline), to evaluate the size and concentration measurements of environmental and cultured assemblages of marine plankton particles, and microspheres. Over 1 million particles, ranging from 10 to 200  μ m in equivalent spherical diameter, imaged by the 4-Deep HoloSea digital inline holographic microscope (DIHM) are analyzed. These measurements were collected in parallel with a FlowCam (FC), Imaging FlowCytobot (IFCB), and manual microscope identification. Once corrections for particle location and nonuniform illumination were developed and applied, the DIHM showed an underestimate in ESD of about 3% to 10%, but successfully reproduced the size spectral slope from environmental samples, and the size distribution of cultures ( Dunaliella tertiolecta , Heterosigma akashiwo , and Prorocentrum micans ) and microspheres. DIHM concentrations (order 1 to 1000 particles ml -1 ) showed a linear agreement ( r 2 = 0.73) with the other instruments, but individual comparisons at times had large uncertainty. Overall, we found the DIHM and the CCV Pipeline required extensive manual correction, but once corrected, provided concentration and size estimates comparable to the other imaging systems assessed in this study. Holographic cameras are mechanically simple, autonomous, can operate at very high pressures, and provide a larger sampling volume than comparable lens-based tools. Thus, we anticipate that these characterization efforts will be rewarded with novel discovery in new oceanic environments., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (© 2020 The Authors. Limnology and Oceanography: Methods published by Wiley Periodicals LLC. on behalf of Association for the Sciences of Limnology and Oceanography.)

Ophthalmic microsurgery is technically difficult because the scale of required surgical tool manipulations challenge the limits of the surgeon's visual acuity, sensory perception, and physical dexterity. Intraoperative optical coherence tomography (OCT) imaging with micrometer-scale resolution is increasingly being used to monitor and provide enhanced real-time visualization of ophthalmic surgical maneuvers, but surgeons still face physical limitations when manipulating instruments inside the eye. Autonomously controlled robots are one avenue for overcoming these physical limitations. We demonstrate the feasibility of using learning from demonstration and reinforcement learning with an industrial robot to perform OCT-guided corneal needle insertions in an ex vivo model of deep anterior lamellar keratoplasty (DALK) surgery. Our reinforcement learning agent trained on ex vivo human corneas, then outperformed surgical fellows in reaching a target needle insertion depth in mock corneal surgery trials. This work shows the combination of learning from demonstration and reinforcement learning is a viable option for performing OCT guided robotic ophthalmic surgery.

Introduction: The Framingham risk score (FRS) is widely used to predict cardiovascular disease (CVD), but it neglects to account for social risk factors. Our study examined whether use of a cumulative social risk score in addition to the FRS improves prediction of CVD among South Korean adults., Methods: We used nationally representative data on 19,147 adults aged 19 or older from the Korea National Health and Nutrition Examination Survey 2013-2016. We computed a cumulative social risk score (range, 0-3) based on 3 social risk factors: low household income, low level of education, and single-living status. CVD outcomes were stroke, myocardial infarction, and angina. Weighted logistic regression examined the associations between cumulative social risk, FRS, and CVD. McFadden pseudo-R 2 and area under receiver operating characteristic curve (AUC) assessed model performance. We conducted mediation analyses to quantify the association between cumulative social risk score and CVD outcomes that is not mediated by the FRS., Results: A unit increase in social risk was associated with 89.4% higher risk of stroke diagnosis, controlling for the FRS (P < .001). The FRS explained 8.0% of stroke diagnosis (R 2 ) with fair discrimination (AUC = 0.728), and adding the cumulative social risk score enhanced R 2 and AUC by 2.4% and 0.039. In the association between cumulative social risk and stroke, the proportion not mediated by the FRS was 65% (P < .001). We observed similar trends in myocardial infarction and angina, such that an increase in social risk was associated with increased relative risk of disease and improved disease diagnosis, and a large proportion of the association was not mediated by the FRS., Conclusion: Controlling for the FRS, cumulative social risks predicted stroke, myocardial infarction, and angina among adults in South Korea. Future research is needed to examine non-FRS mediators between cumulative social risk and CVD.

A small number of somatic mutations drive the development of cancer, but all somatic mutations are markers of the evolutionary history of a tumor. Prominent methods to construct phylogenies from single-cell sequencing data use single-nucleotide variants (SNVs) as markers but fail to adequately account for copy-number aberrations (CNAs), which can overlap SNVs and result in SNV losses. Here, we introduce SCARLET, an algorithm that infers tumor phylogenies from single-cell DNA sequencing data while accounting for both CNA-driven loss of SNVs and sequencing errors. SCARLET outperforms existing methods on simulated data, with more accurate inference of the order in which mutations were acquired and the mutations present in individual cells. Using a single-cell dataset from a patient with colorectal cancer, SCARLET constructs a tumor phylogeny that is consistent with the observed CNAs and suggests an alternate origin for the patient's metastases. SCARLET is available at: github.com/raphael-group/scarlet., Competing Interests: Declaration of Interests BJR is a founder of Medley Genomics and a member of its board of directors.

The Supplemental Nutrition Assistance Program (SNAP) is the second-largest and most contentious public assistance program administered by the United States government. The media forums where SNAP discourse occurs have changed with the advent of social and web-based media. We used machine learning techniques to characterize media coverage of SNAP over time (1990-2017), between outlets with national readership and those with narrower scopes, and, for a subset of web-based media, by the outlet's political leaning. We applied structural topic models, a machine learning methodology that categorizes and summarizes large bodies of text that have document-level covariates or metadata, to a corpus of print media retrieved via LexisNexis (n = 76,634). For comparison, we complied a separate corpus via web-scrape algorithm of the Google News API (2012-2017), and assigned political alignment metadata to a subset documents according to a recent study of partisanship on social media. A similar procedure was used on a subset of the print media documents that could be matched to the same alignment index. Using linear regression models, we found some, but not all, topics to vary significantly with time, between large and small media outlets, and by political leaning. Our findings offer insights into the polarized and partisan nature of a major social welfare program in the United States, and the possible effects of new media environments on the state of this discourse., Competing Interests: The authors have declared that no competing interests exist.

Little is known about the contribution of white matter integrity to inhibitory cognitive control, particularly in healthy aging. The present study examines the correspondence between white matter fiber bundle length and behavioral inhibition in 37 community-dwelling older adults (aged 51-78 years). Participants underwent neuroimaging with 3 Tesla MRI, and completed a behavioral test of inhibition (i.e., Go/NoGo task). Quantitative tractography derived from diffusion tensor imaging (qtDTI) was used to measure white matter fiber bundle lengths (FBLs) in tracts known to innervate frontal brain regions, including the anterior corpus callosum (AntCC), the cingulate gyrus segment of the cingulum bundle (CING), uncinate fasciculus (UNC), and the superior longitudinal fasciculus (SLF). Performance on the Go/NoGo task was measured by the number of commission errors standardized to reaction time. Hierarchical regression models revealed that shorter FBLs in the CING (p < 0.05) and the bilateral UNC (p < 0.01) were associated with lower inhibitory performance after adjusting for multiple comparisons, supporting a disconnection model of response inhibition in older adults. Prospective longitudinal studies are needed to examine the evolution of inhibitory errors in older adult populations and potential for therapeutic intervention.

The wrist can be considered a 2 degrees-of-freedom joint with all movements reflecting the combination of flexion-extension and radial-ulnar deviation. Wrist motions are accomplished by the kinematic reduction of the 42 degrees-of-freedom of the individual carpal bones. While previous studies have demonstrated the minimal motion of the scaphoid and lunate as the wrist moves along the dart-thrower's path or small relative motion between hamate-capitate-trapezoid, an understanding of the kinematics of the complete carpus across all wrist motions remains lacking. To address this, we assembled an open-source database of in vivo carpal motions and developed mathematical models of the carpal kinematics as a function of wrist motion. Quadratic surfaces were trained for each of the 42-carpal bone degrees-of-freedom and the goodness of fits were evaluated. Using the models, paths of wrist motion that generated minimal carpal rotations or translations were determined. Model predictions were best for flexion-extension, radial-ulnar deviation, and volar-dorsal translations for all carpal bones with R 2  > 0.8, while the estimates were least effective for supination-pronation with R 2  < 0.6. The wrist path of motion's analysis indicated that the distal row of carpal bones moves rigidly together (<3° motion), along the anatomical axis of wrist motion, while the bones in the proximal row undergo minimal motion when the wrist moves in a path oblique to the main axes. The open-source dataset along with its graphical user interface and mathematical models should facilitate clinical visualization and enable new studies of carpal kinematics and function. © 2019 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 37:2661-2670, 2019., (© 2019 Orthopaedic Research Society. Published by Wiley Periodicals, Inc.)

The regulatory genome controls genome activity throughout the life of an organism. This requires that complex information processing functions are encoded in, and operated by, the regulatory genome. Although much remains to be learned about how the regulatory genome works, we here discuss two cases where regulatory functions have been experimentally dissected in great detail and at the systems level, and formalized by computational logic models. Both examples derive from the sea urchin embryo, but assess two distinct organizational levels of genomic information processing. The first example shows how the regulatory system of a single gene, endo16 , executes logic operations through individual transcription factor binding sites and cis -regulatory modules that control the expression of this gene. The second example shows information processing at the gene regulatory network (GRN) level. The GRN controlling development of the sea urchin endomesoderm has been experimentally explored at an almost complete level. A Boolean logic model of this GRN suggests that the modular logic functions encoded at the single-gene level show compositionality and suffice to account for integrated function at the network level. We discuss these examples both from a biological-experimental point of view and from a computer science-informational point of view, as both illuminate principles of how the regulatory genome works.

Longitudinal DNA sequencing of cancer patients yields insight into how tumors evolve over time or in response to treatment. However, sequencing data from bulk tumor samples often have considerable ambiguity in clonal composition, complicating the inference of ancestral relationships between clones. We introduce Cancer Analysis of Longitudinal Data through Evolutionary Reconstruction (CALDER), an algorithm to infer phylogenetic trees from longitudinal bulk DNA sequencing data. CALDER explicitly models a longitudinally observed phylogeny incorporating constraints that longitudinal sampling imposes on phylogeny reconstruction. We show on simulated bulk tumor data that longitudinal constraints substantially reduce ambiguity in phylogeny reconstruction and that CALDER outperforms existing methods that do not leverage this longitudinal information. On real data from two chronic lymphocytic leukemia patients, we find that CALDER reconstructs more plausible and parsimonious phylogenies than existing methods, with CALDER phylogenies containing fewer tumor clones per sample. CALDER's use of longitudinal information will be advantageous in further studies of tumor heterogeneity and evolution., (Copyright © 2019 Elsevier Inc. All rights reserved.)

Topographic factor models separate overlapping signals into latent spatial functions to identify correlation structure across observations. These methods require the underlying structure to be held fixed and are not robust to deviations commonly found across images. We present autoencoding topographic factors, a novel variational inference scheme, to decompose irregular observations on a lattice into a superposition of low-rank sources. By exploiting recent developments in variational autoencoders, we replace fixed sources with a nonlinear mapping that parameterizes an unnormalized distribution on the lattice. In doing so, we permit sources to drift dynamically, filtering residual differences in location across comparable areas of interest. This gives an implicit mapping to a unique latent representation while simultaneously forcing the posterior to model group variability in spatial structure. Simulation results and applications to functional imaging demonstrate the effectiveness of our method and its ability to outperform existing spatial factor models.

Recent large cancer studies have measured somatic alterations in an unprecedented number of tumours. These large datasets allow the identification of cancer-related sets of genetic alterations by identifying relevant combinatorial patterns. Among such patterns, mutual exclusivity has been employed by several recent methods that have shown its effectiveness in characterizing gene sets associated to cancer. Mutual exclusivity arises because of the complementarity, at the functional level, of alterations in genes which are part of a group (e.g., a pathway) performing a given function. The availability of quantitative target profiles, from genetic perturbations or from clinical phenotypes, provides additional information that can be leveraged to improve the identification of cancer related gene sets by discovering groups with complementary functional associations with such targets. In this work we study the problem of finding groups of mutually exclusive alterations associated with a quantitative (functional) target. We propose a combinatorial formulation for the problem, and prove that the associated computational problem is computationally hard. We design two algorithms to solve the problem and implement them in our tool UNCOVER. We provide analytic evidence of the effectiveness of UNCOVER in finding high-quality solutions and show experimentally that UNCOVER finds sets of alterations significantly associated with functional targets in a variety of scenarios. In particular, we show that our algorithms find sets which are better than the ones obtained by the state-of-the-art method, even when sets are evaluated using the statistical score employed by the latter. In addition, our algorithms are much faster than the state-of-the-art, allowing the analysis of large datasets of thousands of target profiles from cancer cell lines. We show that on two such datasets, one from project Achilles and one from the Genomics of Drug Sensitivity in Cancer project, UNCOVER identifies several significant gene sets with complementary functional associations with targets. Software available at: https://github.com/VandinLab/UNCOVER., Competing Interests: The authors have declared that no competing interests exist.

Carrots and sticks motivate behavior, and people can teach new behaviors to other organisms, such as children or nonhuman animals, by tapping into their reward learning mechanisms. But how people teach with reward and punishment depends on their expectations about the learner. We examine how people teach using reward and punishment by contrasting two hypotheses. The first is evaluative feedback as reinforcement, where rewards and punishments are used to shape learner behavior through reinforcement learning mechanisms. The second is evaluative feedback as communication, where rewards and punishments are used to signal target behavior to a learning agent reasoning about a teacher's pedagogical goals. We present formalizations of learning from these 2 teaching strategies based on computational frameworks for reinforcement learning. Our analysis based on these models motivates a simple interactive teaching paradigm that distinguishes between the two teaching hypotheses. Across 3 sets of experiments, we find that people are strongly biased to use evaluative feedback communicatively rather than as reinforcement. (PsycINFO Database Record (c) 2019 APA, all rights reserved).

Decentralized partially observable Markov decision processes (Dec-POMDPs) are general models for decentralized multi-agent decision making under uncertainty. However, they typically model a problem at a low level of granularity, where each agent's actions are primitive operations lasting exactly one time step. We address the case where each agent has macro-actions: temporally extended actions that may require different amounts of time to execute. We model macro-actions as options in a Dec-POMDP, focusing on actions that depend only on information directly available to the agent during execution. Therefore, we model systems where coordination decisions only occur at the level of deciding which macro-actions to execute. The core technical difficulty in this setting is that the options chosen by each agent no longer terminate at the same time. We extend three leading Dec-POMDP algorithms for policy generation to the macro-action case, and demonstrate their effectiveness in both standard benchmarks and a multi-robot coordination problem. The results show that our new algorithms retain agent coordination while allowing high-quality solutions to be generated for significantly longer horizons and larger state-spaces than previous Dec-POMDP methods. Furthermore, in the multi-robot domain, we show that, in contrast to most existing methods that are specialized to a particular problem class, our approach can synthesize control policies that exploit opportunities for coordination while balancing uncertainty, sensor information, and information about other agents.

This study examines white matter microstructure using quantitative tractography diffusion magnetic resonance imaging (qtdMRI) in HIV+ individuals from South Africa who were naïve or early in the initiation of antiretroviral therapy. Fiber bundle length (FBL) metrics, generated from qtdMRI, for whole brain and six white matter tracts of interest (TOI) were assessed for 135 HIV+ and 21 HIV- individuals. The association between FBL metrics, measures of disease burden, and neuropsychological performance were also investigated. Results indicate significantly reduced sum of whole brain fiber bundle lengths (FBL, p < 0.001), but not average whole brain FBL in the HIV+ group compared to the HIV- controls. The HIV+ group exhibited significantly shorter sum of FBL in all six TOIs examined: the anterior thalamic radiation, cingulum bundle, inferior and superior longitudinal fasciculi, inferior frontal occipital fasciculus, and the uncinate fasciculus. Additionally, average FBLs were significantly shorter select TOIs including the inferior longitudinal fasciculus, cingulum bundle, and the anterior thalamic radiation. Shorter whole brain FBL sum metrics were associated with poorer neuropsychological performance, but were not associated with markers of disease burden. Taken together these findings suggest HIV affects white matter architecture primarily through reductions in white matter fiber numbers and, to a lesser degree, the shortening of fibers along a bundle path.

The primary goal of this study was to examine the relations between limb control and handedness in adults. Participants were categorized as left or right handed for analyses using the Edinburgh Handedness Inventory. Three-dimensional recordings were made of each arm on two reach-to-place tasks: adults reached to a ball and placed it into the opening of a toy (fitting task), or reached to a Cheerio inside a cup, which they placed on a designated mark after each trial (cup task). We hypothesized that limb control and handedness were related, and we predicted that we would observe side differences favoring the dominant limb based on the dynamic dominance hypothesis of motor lateralization. Specifically, we predicted that the dominant limb would be straighter and smoother on both tasks compared with the nondominant limb (i.e., right arm in right-handers and left arm in left-handers). Our results only partially supported these predictions for right-handers, but not for left-handers. When differences between hands were observed, the right hand was favored regardless of handedness group. Our findings suggest that left-handers are not reversed right-handers when compared on interlimb kinematics for reach-to-place tasks, and reaffirm that task selection is critical when evaluating manual asymmetries.

Motivation: Current technologies for single-cell DNA sequencing require whole-genome amplification (WGA), as a single cell contains too little DNA for direct sequencing. Unfortunately, WGA introduces biases in the resulting sequencing data, including non-uniformity in genome coverage and high rates of allele dropout. These biases complicate many downstream analyses, including the detection of genomic variants., Results: We show that amplification biases have a potential upside: long-range correlations in rates of allele dropout provide a signal for phasing haplotypes at the lengths of amplicons from WGA, lengths which are generally longer than than individual sequence reads. We describe a statistical test to measure concurrent allele dropout between single-nucleotide polymorphisms (SNPs) across multiple sequenced single cells. We use results of this test to perform haplotype assembly across a collection of single cells. We demonstrate that the algorithm predicts phasing between pairs of SNPs with higher accuracy than phasing from reads alone. Using whole-genome sequencing data from only seven neural cells, we obtain haplotype blocks that are orders of magnitude longer than with sequence reads alone (median length 10.2 kb versus 312 bp), with error rates <2%. We demonstrate similar advantages on whole-exome data from 16 cells, where we obtain haplotype blocks with median length 9.2 kb-comparable to typical gene lengths-compared with median lengths of 41 bp with sequence reads alone, with error rates <4%. Our algorithm will be useful for haplotyping of rare alleles and studies of allele-specific somatic aberrations., Availability and Implementation: Source code is available at https://www.github.com/raphael-group., Supplementary Information: Supplementary data are available at Bioinformatics online.

Metastasis is the migration of cancerous cells from a primary tumor to other anatomical sites. Although metastasis was long thought to result from monoclonal seeding, or single cellular migrations, recent phylogenetic analyses of metastatic cancers have reported complex patterns of cellular migrations between sites, including polyclonal migrations and reseeding. However, accurate determination of migration patterns from somatic mutation data is complicated by intratumor heterogeneity and discordance between clonal lineage and cellular migration. We introduce MACHINA, a multi-objective optimization algorithm that jointly infers clonal lineages and parsimonious migration histories of metastatic cancers from DNA sequencing data. MACHINA analysis of data from multiple cancers shows that migration patterns are often not uniquely determined from sequencing data alone and that complicated migration patterns among primary tumors and metastases may be less prevalent than previously reported. MACHINA's rigorous analysis of migration histories will aid in studies of the drivers of metastasis.

This study investigates multimodal structural MR imaging biomarkers of development trajectories in pediatric bipolar disorder. T1-weighted and diffusion-weighted MR imaging was conducted to investigate cross-sectional group differences with age between typically developing controls (N = 26) and youths diagnosed with bipolar disorder (N = 26). Region-based analysis was used to examine cortical thickness of gray matter and diffusion tensor parameters in superficial white matter, and tractography-based analysis was used to examine deep white matter fiber bundles. Patients and controls showed significantly different maturation trajectories across brain areas; however, the magnitude of differences varied by region. The rate of cortical thinning with age was greater in patients than controls in the left frontal pole. While controls showed increasing fractional anisotropy (FA) and axial diffusivity (AD) with age, patients showed an opposite trend of decreasing FA and AD with age in fronto-temporal-striatal regions located in both superficial and deep white matter. The findings support fronto-temporal-striatal alterations in the developmental trajectories of youths diagnosed with bipolar disorder, and further, show the value of multimodal computational techniques in the assessment of neuropsychiatric disorders. These preliminary results warrant further investigation into longitudinal changes and the effects of treatment in the brain areas identified in this study., (Copyright © 2018 Elsevier B.V. All rights reserved.)

We introduce an online active exploration algorithm for data-efficiently learning an abstract symbolic model of an environment. Our algorithm is divided into two parts: the first part quickly generates an intermediate Bayesian symbolic model from the data that the agent has collected so far, which the agent can then use along with the second part to guide its future exploration towards regions of the state space that the model is uncertain about. We show that our algorithm outperforms random and greedy exploration policies on two different computer game domains. The first domain is an Asteroids-inspired game with complex dynamics but basic logical structure. The second is the Treasure Game, with simpler dynamics but more complex logical structure.

Humans often attempt to influence one another's behavior using rewards and punishments. How does this work? Psychologists have often assumed that "evaluative feedback" influences behavior via standard learning mechanisms that learn from environmental contingencies. On this view, teaching with evaluative feedback involves leveraging learning systems designed to maximize an organism's positive outcomes. Yet, despite its parsimony, programs of research predicated on this assumption, such as ones in developmental psychology, animal behavior, and human-robot interaction, have had limited success. We offer an explanation by analyzing the logic of evaluative feedback and show that specialized learning mechanisms are uniquely favored in the case of evaluative feedback from a social partner. Specifically, evaluative feedback works best when it is treated as communicating information about the value of an action rather than as a form of reward to be maximized. This account suggests that human learning from evaluative feedback depends on inferences about communicative intent, goals and other mental states-much like learning from other sources, such as demonstration, observation and instruction. Because these abilities are especially developed in humans, the present account also explains why evaluative feedback is far more widespread in humans than non-human animals., (Copyright © 2017 Elsevier B.V. All rights reserved.)

Natural selection designs some social behaviors to depend on flexible learning processes, whereas others are relatively rigid or reflexive. What determines the balance between these two approaches? We offer a detailed case study in the context of a two-player game with antisocial behavior and retaliatory punishment. We show that each player in this game-a "thief" and a "victim"-must balance two competing strategic interests. Flexibility is valuable because it allows adaptive differentiation in the face of diverse opponents. However, it is also risky because, in competitive games, it can produce systematically suboptimal behaviors. Using a combination of evolutionary analysis, reinforcement learning simulations, and behavioral experimentation, we show that the resolution to this tension-and the adaptation of social behavior in this game-hinges on the game's learning dynamics. Our findings clarify punishment's adaptive basis, offer a case study of the evolution of social preferences, and highlight an important connection between natural selection and learning in the resolution of social conflicts., Competing Interests: The authors declare no conflict of interest.

Background: Although communication is a key component of US strategies to prevent suicide and there are a number of marketing campaigns promoting messages that suicide is a preventable public health problem, there has been little evaluation of these campaigns., Aims: The study describes the development of a checklist of best practices for suicide prevention communication campaigns and the use of the checklist to evaluate California's investment in "Know the Signs" (KTS-M), a suicide prevention mass media campaign., Method: We conducted a literature review and solicited expert feedback to identify best practices and then used the RAND/UCLA appropriateness method to assess whether KTS-M was consistent with the identified best practices., Results: Overall, experts agreed that KTS-M adhered to most of the 46 checklist items and suggested that the campaign was among the best suicide prevention media campaigns they had observed., Limitations: The checklist was developed through expert input and literature review and focuses only on media campaigns., Conclusion: Given the nascent state of the evidence about what makes an effective suicide prevention message and the growing number of campaigns, the checklist of best practices reflects one way of promoting quality in this evolving field. The consistency between the experts' comments and their ratings of KTS-M suggests that the checklist may provide important guidance to inform the development of future campaigns and the evaluation of ongoing campaigns.