Context-specific stress causes compartmentalized SARM1 activation and local degeneration in cortical neurons.

SARM1 is an inducible NADase that localizes to mitochondria throughout neurons and senses metabolic changes that occur after injury. Minimal proteomic changes are observed upon either SARM1 depletion or activation, suggesting that SARM1 does not exert broad effects on neuronal protein homeostasis. However, whether SARM1 activation occurs throughout the neuron in response to injury and cell stress remains largely unknown. Using a semi-automated imaging pipeline and a custom-built deep learning scoring algorithm, we studied degeneration in both mixed sex mouse primary cortical neurons and male human iPSC derived cortical neurons in response to a number of different stressors. We show that SARM1 activation is differentially restricted to specific neuronal compartments depending on the stressor. Cortical neurons undergo SARM1-dependent axon degeneration after mechanical transection and SARM1 activation is limited to the axonal compartment distal of the injury site. However, global SARM1 activation following vacor treatment causes both cell body and axon degeneration. Context-specific stressors, such as microtubule dysfunction and mitochondrial stress, induce axonal SARM1 activation leading to SARM1-dependent axon degeneration and SARM1-independent cell body death. Our data reveal that compartment-specific SARM1-mediated death signaling is dependent on the type of injury and cellular stressor.Significance Statement SARM1 is an important regulator of active axon degeneration after injury in the peripheral nervous system. Here we show that SARM1 can also be activated by a number of different cellular stressors in cortical neurons of the central nervous system. Loss or activation of SARM1 does not cause large scale changes in global protein homeostasis. However, context-dependent SARM1 activation is localized to specific neuronal compartments and results in localized degeneration of axons. Understanding which cell stress pathways are responsible for driving degeneration of distinct neuronal compartments under what cellular stress conditions and in which neuronal subtypes, will inform development of neurodegenerative disease therapeutics.

Deep Learning Approaches for Detecting of Nascent Geographic Atrophy in Age-Related Macular Degeneration.

Purpose: Nascent geographic atrophy (nGA) refers to specific features seen on OCT B-scans, which are strongly associated with the future development of geographic atrophy (GA). This study sought to develop a deep learning model to screen OCT B-scans for nGA that warrant further manual review (an artificial intelligence [AI]-assisted approach), and to determine the extent of reduction in OCT B-scan load requiring manual review while maintaining near-perfect nGA detection performance. Design: Development and evaluation of a deep learning model. Participants: One thousand eight hundred and eighty four OCT volume scans (49 B-scans per volume) without neovascular age-related macular degeneration from 280 eyes of 140 participants with bilateral large drusen at baseline, seen at 6-monthly intervals up to a 36-month period (from which 40 eyes developed nGA). Methods: OCT volume and B-scans were labeled for the presence of nGA. Their presence at the volume scan level provided the ground truth for training a deep learning model to identify OCT B-scans that potentially showed nGA requiring manual review. Using a threshold that provided a sensitivity of 0.99, the B-scans identified were assigned the ground truth label with the AI-assisted approach. The performance of this approach for detecting nGA across all visits, or at the visit of nGA onset, was evaluated using fivefold cross-validation. Main Outcome Measures: Sensitivity for detecting nGA, and proportion of OCT B-scans requiring manual review. Results: The AI-assisted approach (utilizing outputs from the deep learning model to guide manual review) had a sensitivity of 0.97 (95% confidence interval [CI] = 0.93-1.00) and 0.95 (95% CI = 0.87-1.00) for detecting nGA across all visits and at the visit of nGA onset, respectively, when requiring manual review of only 2.7% and 1.9% of selected OCT B-scans, respectively. Conclusions: A deep learning model could be used to enable near-perfect detection of nGA onset while reducing the number of OCT B-scans requiring manual review by over 50-fold. This AI-assisted approach shows promise for substantially reducing the current burden of manual review of OCT B-scans to detect this crucial feature that portends future development of GA. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

A Novel Tropical Geometry-Based Interpretable Machine Learning Method: Pilot Application to Delivery of Advanced Heart Failure Therapies.

A model's interpretability is essential to many practical applications such as clinical decision support systems. In this article, a novel interpretable machine learning method is presented, which can model the relationship between input variables and responses in humanly understandable rules. The method is built by applying tropical geometry to fuzzy inference systems, wherein variable encoding functions and salient rules can be discovered by supervised learning. Experiments using synthetic datasets were conducted to demonstrate the performance and capacity of the proposed algorithm in classification and rule discovery. Furthermore, we present a pilot application in identifying heart failure patients that are eligible for advanced therapies as proof of principle. From our results on this particular application, the proposed network achieves the highest F1 score. The network is capable of learning rules that can be interpreted and used by clinical providers. In addition, existing fuzzy domain knowledge can be easily transferred into the network and facilitate model training. In our application, with the existing knowledge, the F1 score was improved by over 5%. The characteristics of the proposed network make it promising in applications requiring model reliability and justification.

Identifying potential candidates for advanced heart failure therapies using an interpretable machine learning algorithm.

BACKGROUND: Systems level barriers to heart failure (HF) care limit access to HF advanced therapies (heart transplantation, left ventricular assist devices). There is a need for automated systems that can help clinicians ensure patients with HF are evaluated for HF advanced therapies at the appropriate time to optimize outcomes. METHODS: We performed a retrospective study using the REVIVAL (Registry Evaluation of Vital Information for VADs in Ambulatory Life) and INTERMACS (Interagency Registry for Mechanically Assisted Circulatory Support) registries. We developed a novel machine learning model based on principles of tropical geometry and fuzzy logic that can accommodate clinician knowledge and provide recommendations regarding need for advanced therapies evaluations that are accessible to end-users. RESULTS: The model was trained and validated using data from 4,694 HF patients. When initiated with clinical knowledge from HF and transplant cardiologists, the model achieved an F1 score of 43.8%, recall of 51.1%, and precision of 46.9%. The model achieved comparable performance compared with other commonly used machine learning models. Importantly, our model was 1 of only 3 models providing transparent and parsimonious clinical rules, significantly outperforming the other 2 models. Eleven clinical rules were extracted from the model which can be leveraged in clinical practice. CONCLUSIONS: A machine learning model capable of accepting clinical knowledge and making accessible recommendations was trained to identify patients with advanced HF. While this model was developed for HF care, the methodology has multiple potential uses in other important clinical applications.

Snow Parameters Inversion from Passive Microwave Remote Sensing Measurements by Deep Convolutional Neural Networks.

This paper proposes a novel inverse method based on the deep convolutional neural network (ConvNet) to extract snow's layer thickness and temperature via passive microwave remote sensing (PMRS). The proposed ConvNet is trained using simulated data obtained through conventional computational electromagnetic methods. Compared with the traditional inverse method, the trained ConvNet can predict the result with higher accuracy. Besides, the proposed method has a strong tolerance for noise. The proposed ConvNet composes three pairs of convolutional and activation layers with one additional fully connected layer to realize regression, i.e., the inversion of snow parameters. The feasibility of the proposed method in learning the inversion of snow parameters is validated by numerical examples. The inversion results indicate that the correlation coefficient (R2) ratio between the proposed ConvNet and conventional methods reaches 4.8, while the ratio for the root mean square error (RMSE) is only 0.18. Hence, the proposed method experiments with a novel path to improve the inversion of passive microwave remote sensing through deep learning approaches.

Comprehensive enhancer-target gene assignments improve gene set level interpretation of genome-wide regulatory data.

BACKGROUND: Revealing the gene targets of distal regulatory elements is challenging yet critical for interpreting regulome data. Experiment-derived enhancer-gene links are restricted to a small set of enhancers and/or cell types, while the accuracy of genome-wide approaches remains elusive due to the lack of a systematic evaluation. We combined multiple spatial and in silico approaches for defining enhancer locations and linking them to their target genes aggregated across >500 cell types, generating 1860 human genome-wide distal enhancer-to-target gene definitions (EnTDefs). To evaluate performance, we used gene set enrichment (GSE) testing on 87 independent ENCODE ChIP-seq datasets of 34 transcription factors (TFs) and assessed concordance of results with known TF Gene Ontology annotations, and other benchmarks. RESULTS: The top ranked 741 (40%) EnTDefs significantly outperform the common, naïve approach of linking distal regions to the nearest genes, and the top 10 EnTDefs perform well when applied to ChIP-seq data of other cell types. The GSE-based ranking of EnTDefs is highly concordant with ranking based on overlap with curated benchmarks of enhancer-gene interactions. Both our top general EnTDef and cell-type-specific EnTDefs significantly outperform seven independent computational and experiment-based enhancer-gene pair datasets. We show that using our top EnTDefs for GSE with either genome-wide DNA methylation or ATAC-seq data is able to better recapitulate the biological processes changed in gene expression data performed in parallel for the same experiment than our lower-ranked EnTDefs. CONCLUSIONS: Our findings illustrate the power of our approach to provide genome-wide interpretation regardless of cell type.

Motion-based camera localization system in colonoscopy videos.

Optical colonoscopy is an essential diagnostic and prognostic tool for many gastrointestinal diseases, including cancer screening and staging, intestinal bleeding, diarrhea, abdominal symptom evaluation, and inflammatory bowel disease assessment. However, the evaluation, classification, and quantification of findings from colonoscopy are subject to inter-observer variation. Automated assessment of colonoscopy is of interest considering the subjectivity present in qualitative human interpretations of colonoscopy findings. Localization of the camera is essential to interpreting the meaning and context of findings for diseases evaluated by colonoscopy. In this study, we propose a camera localization system to estimate the relative location of the camera and classify the colon into anatomical segments. The camera localization system begins with non-informative frame detection and removal. Then a self-training end-to-end convolutional neural network is built to estimate the camera motion, where several strategies are proposed to improve its robustness and generalization on endoscopic videos. Using the estimated camera motion a camera trajectory can be derived and a relative location index calculated. Based on the estimated location index, anatomical colon segment classification is performed by constructing a colon template. The proposed motion estimation algorithm was evaluated on an external dataset containing the ground truth for camera pose. The experimental results show that the performance of the proposed method is superior to other published methods. The relative location index estimation and anatomical region classification were further validated using colonoscopy videos collected from routine clinical practice. This validation yielded an average accuracy in classification of 0.754, which is substantially higher than the performances obtained using location indices built from other methods.

Fully automated endoscopic disease activity assessment in ulcerative colitis.

BACKGROUND AND AIMS: Endoscopy is essential for disease assessment in ulcerative colitis (UC), but subjectivity threatens accuracy and precision. We aimed to pilot a fully automated video analysis system for grading endoscopic disease in UC. METHODS: A developmental set of high-resolution UC endoscopic videos were assigned Mayo endoscopic scores (MESs) provided by 2 experienced reviewers. Video still-image stacks were annotated for image quality (informativeness) and MES. Models to predict still-image informativeness and disease severity were trained using convolutional neural networks. A template-matching grid search was used to estimate whole-video MESs provided by human reviewers using predicted still-image MES proportions. The automated whole-video MES workflow was tested using unaltered endoscopic videos from a multicenter UC clinical trial. RESULTS: The developmental high-resolution and testing multicenter clinical trial sets contained 51 and 264 videos, respectively. The still-image informative classifier had excellent performance with a sensitivity of 0.902 and specificity of 0.870. In high-resolution videos, fully automated methods correctly predicted MESs in 78% (41 of 50, κ = 0.84) of videos. In external clinical trial videos, reviewers agreed on MESs in 82.8% (140 of 169) of videos (κ = 0.78). Automated and central reviewer scoring agreement occurred in 57.1% of videos (κ = 0.59), but improved to 69.5% (107 of 169) when accounting for reviewer disagreement. Automated MES grading of clinical trial videos (often low resolution) correctly distinguished remission (MES 0,1) versus active disease (MES 2,3) in 83.7% (221 of 264) of videos. CONCLUSIONS: These early results support the potential for artificial intelligence to provide endoscopic disease grading in UC that approximates the scoring of experienced reviewers.

Automated hematoma segmentation and outcome prediction for patients with traumatic brain injury.

Traumatic brain injury (TBI) is a major cause of death and disability worldwide. Automated brain hematoma segmentation and outcome prediction for patients with TBI can effectively facilitate patient management. In this study, we propose a novel Multi-view convolutional neural network with a mixed loss to segment total acute hematoma on head CT scans collected within 24 h after the injury. Based on the automated segmentation, the volumetric distribution and shape characteristics of the hematoma were extracted and combined with other clinical observations to predict 6-month mortality. The proposed hematoma segmentation network achieved an average Dice coefficient of 0.697 and an intraclass correlation coefficient of 0.966 between the volumes estimated from the predicted hematoma segmentation and volumes of the annotated hematoma segmentation on the test set. Compared with other published methods, the proposed method has the most accurate segmentation performance and volume estimation. For 6-month mortality prediction, the model achieved an average area under the precision-recall curve (AUCPR) of 0.559 and area under the receiver operating characteristic curve (AUC) of 0.853 using 10-fold cross-validation on a dataset consisting of 828 patients. The average AUCPR and AUC of the proposed model are respectively more than 10% and 5% higher than those of the widely used IMPACT model.

Modelling electrical conduction in nanostructure assemblies through complex networks.

Carrier transport processes in assemblies of nanostructures rely on morphology-dependent and hierarchical conduction mechanisms, whose complexity cannot be captured by current modelling approaches. Here we apply the concept of complex networks to modelling carrier conduction in such systems. The approach permits assignment of arbitrary connectivity and connection strength between assembly constituents and is thus ideal for nanostructured films, composites and other geometries. Modelling of simplified rod-like nanostructures is consistent with analytical solutions, whereas results for more realistic nanostructure assemblies agree with experimental data and reveal conduction behaviour not captured by previous models. Fitting of ensemble measurements also allows the conduction properties of individual constituents to be extracted, which are subsequently used to guide the realization of transparent electrodes with improved performance. A global optimization process was employed to identify geometries and properties with high potential for transparent conductors. Our intuitive discretization approach, combined with a simple solver tool, allows researchers with little computational experience to carry out realistic simulations.

Lateral Two-Dimensional Material Heterojunction Photodetectors with Ultrahigh Speed and Detectivity.

Lateral heterojunctions in two-dimensional (2D) materials have demonstrated potential for high-performance sensors because of the unique electrostatic conditions at the interface. The increased complexity of producing such structures, however, has prevented their widespread use. We here demonstrate the simple and scalable fabrication of heterojunctions by a one-step synthesis process that yields photodetectors with superior device performance. Catalytic conversion of a solid precursor at optimized conditions was found to produce lateral nanostructured junctions between graphene domains and 3 nm thin amorphous carbon films. Carrier transport in these heterojunctions was found to proceed by minimizing the path through the amorphous carbon barriers, which results in a self-selective Schottky emission process with high uniformity and low emission barriers. We demonstrate the potential of thus produced heterojunctions by realizing a photodetector that combines an ultrahigh detectivity of 1013 Jones with microsecond response time, which represents the highest performance of 2D material heterojunction devices. These attractive features are retained even for millimeter-scale devices, and the demonstrated ability to produce transparent, patterned, and flexible sensors extends lateral heterojunction sensors toward wearable and large-scale electronics.

Characterizing percolative materials by straining.

Carrier transport in a wide range of nanomaterial assemblies proceeds by percolation through discontinuous networks of constituents. Improving percolative nanomaterials could enhance transparent conductors, sensors, and electronic devices. A significant obstacle in optimizing percolative materials is the challenge in their characterization. The critical connection pathways which determine a percolative material's conductivity are not easily accessible with existing metrology tools and traditional investigation approaches rely on indirect methods based on many samples and on simplifying assumptions. We here demonstrate the direct extraction of characteristic parameters from a single sample by analyzing the strain-dependent resistance of percolative materials. An analytical model is derived that can explain experimental data for various percolative materials, morphologies, and straining conditions. The relationship of the extracted parameters with previously introduced figures of merit allows us to compare nanostructures of diverse dimensionalities and compositions for applications such as strain gauges and transparent conductors.

Automated Detection of Non-Informative Frames for Colonoscopy Through a Combination of Deep Learning and Feature Extraction.

Colonoscopy is a standard medical examination used to inspect the mucosal surface and detect abnormalities of the colon. Objective assessment and scoring of disease features in the colon are important in conditions such as colorectal cancer and inflammatory bowel disease. However, subjectivity in human disease assessment and measurement is hampered by interobserver variation and several biases. A computer-aided system for colonoscopy video analysis could facilitate diagnosis and disease severity measurement, which would aid in treatment selection and clinical outcome prediction. However, a large number of images captured during colonoscopy are non-informative, making detecting and removing those frames an important first step in performing automated analysis. In this paper, we present a combination of deep learning and conventional feature extraction to distinguish non-informative from informative images in patients with ulcerative colitis. Our result shows that the combination of bottleneck features in the RGB color space and hand-crafted features in the HSV color space can boost the classification performance. Our proposed method was validated using 5-fold cross-validation and achieved an average AUC of 0.939 and an average F1 score of 0.775.

Filter-Pruned 3D Convolutional Neural Network for Drowsiness Detection.

Human drowsiness while operating motor vehicles or heavy machinery can have potentially lethal consequences for the operator and others in their immediate vicinity. In this study, we developed a visual-based drowsiness detection system that can analyze videos and make predictions on attention status. A 3D convolutional neural network (CNN) was built for spatio-temporal feature extraction in consecutive frames, and temporal smoothing was used to remove noisy predictions. As a part of an assistance system, a real-time, lightweight and computationally-efficient system is preferable. Thus, we proposed a Scale Module that can be easily integrated into the convolutional layer and estimate the importance of filters. Our results show that scale values calculated from the Scale Module are good indicators for filter pruning, and that filters with small scale values can be removed with negligible loss in the model's performance.

Hematoma Segmentation Using Dilated Convolutional Neural Network.

Traumatic brain injury (TBI) is a global health challenge. Accurate and fast automatic detection of hematoma in the brain is essential for TBI diagnosis and treatment. In this study, we developed a fully automated system to detect and segment hematoma regions in head Computed Tomography (CT) images of patients with acute TBI. We adapted the structure of a fully convolutional network by introducing dilated convolution and removing down-sampling and up-sampling layers. Skip layers are also used to combine low-level features and high-level features. By integrating the information from different scales without losing spatial resolution, the network can perform more accurate segmentation. Our final hematoma segmentations achieved the Dice, sensitivity, and specificity of 0.62, 0.81, and 0.96, respectively, which outperformed the results from previous methods.

New shape-selectivity discovered on graphene-based materials in catching tobacco specific nitrosamines.

New shape-selectivity of graphene-based materials was discovered on this article. To explore the new selectivity, the structure and surface state of graphene and carbon nanotube were examined firstly, and their specific selectivity was verified and was compared with that of ZSM-5 zeolite in aqueous solutions of tobacco specific nitrosamines (TSNA) along with dyes. These two adsorbents trapped about 55% and 70% of 4-methylnitrosamino-1-3-pyridyl-1-butanone (NNK) but only 3% of N'-nitrosonornicotine (NNN) in solution, having an obvious selectivity for the former, due to its stronger interaction with graphene. NNK on graphene sheet obtained more electrons (0.015 e) and owned larger adsorption energy (15.63 kcal mol-1) than that of NNN (0.003 e, 9.19 kcal mol-1), according to theoretical calculation and FTIR results. More 95 or 136 mg g -1 acid red 88 than methyl orange was captured by graphene or carbon nanotube, demonstrating this special and abnormal selectivity again. With new selectivity, graphene showed a higher capacity (6.9%) and shorter adorption equilibrium time (5 min) for TSNA than the typical selecive sorbent ZSM-5 zeolite (1.7% and 20 min) in tobacco solution but kept the similar selctivity to NNK, paving a new way to control the carcinogens like TSNA in environment.

Analyzing multiple pesticides in tobacco leaf using gas chromatography with quadrupole time-of-flight mass spectrometry.

A method combining gas chromatography with quadrupole time-of-flight mass spectrometry has been developed for the simultaneous analysis of multiple pesticide residues in tobacco leaf. The retention index and high accurate masses of ions from the first-stage and the second-stage mass spectra of each pesticide were collected for qualitation and quantification. A total of 115 pesticides were evaluated. The extract from organic tobacco leaf was used as a model matrix. The limit of detection was <10 ng/mL, and the limit of quantification was in the range of 1-20 ng/mL for 95% of the tested pesticides. The correlation coefficients were >0.9900 for all tested pesticides. At three concentrations (10, 50, and 100 ng/mL), most compounds presented satisfactory recoveries ranging from 70 to 120% and good precision <20%. Finally, three tobacco leaf samples collected from a local market were analyzed. A total of three pesticides were found, including dimethachlon, triadimenol, and flumetralin. Each pesticide was confirmed by the presence of three ions at the expected retention index and mass. In conclusion, gas chromatography with quadrupole time-of-flight mass spectrometry appears to be one of the most efficient tools for the analysis of pesticide residues in tobacco leaf.

Development of Multiple Heart-Cutting Two-Dimensional Liquid Chromatography Coupled to Quadrupole-Orbitrap High Resolution Mass Spectrometry for Simultaneous Determination of Aflatoxin B1, B2, G1, G2, and Ochratoxin A in Snus, a Smokeless Tobacco Product.

The combination of multiple heart-cutting two-dimensional liquid chromatography (MHC-LC/LC) and quadrupole-orbitrap high-resolution mass spectrometry (HRMS) for simultaneous determination of the aflatoxins and ochratoxin A in snus is presented in this work. A C18 capillary column was used as the first dimension (1D) to isolate the aflatoxins and ochratoxin A from the complex matrices; then, a 2-position/10-port high-pressure valve equipped with two 60 µL loops was employed to transfer the heart-cuts of 1D-LC into a pentafluorophenyl (PFP) column for the second dimension (2D) separation. With the better separation of the MHC-LC/LC system, the sensitivity of the method was improved, which is essential for the trace mycotoxins analysis. Furthermore, HRMS performed in parallel reaction monitoring mode was employed to eliminate the interferences, and the sample pretreatment procedure was simplified. A new approach utilizing ethyl acetate with 1% formic acid/water solution was adopted to extract aflatoxins and ochratoxin A in snus, which provided parallel recoveries for aflatoxins and ochratoxin A with higher responses in comparison with the QuEChERS method. A dynamic range between 0.2 and 20 µg/kg was achieved with LOQs of 0.05 µg/kg for aflatoxin B1, 0.1 µg/kg for aflatoxin B2, G1, G2, and 1.0 µg/kg for ochratoxin A in dry mass of product. The results revealed that the established method exhibited good repeatability and recovery and could be used as a rapid and reliable approach for routine analysis of aflatoxins and ochratoxin A in snus.

Creating an Optimal Microenvironment within Mesoporous Silica MCM-41 for Capture of Tobacco-Specific Nitrosamines in Solution.

To meet the requirement of capturing tobacco-specific nitrosamines (TSNA) for environment protection, a unique microenvironment was carefully created inside the channels of mesoporous silica MCM-41. In situ carbonization of template micelles at 923 K, combined with the excess aluminum used in one-pot synthesis of MCM-41, is adopted to tailor the tortuosity of mecsoporous channels, while loaded metal oxides (5 wt %) and the Al component in the framework are employed to exert the necessary electrostatic interaction toward the target carcinogens TSNA in solution. The elaborated microenvironment created in mesoporous sorbents was characterized with XRD, N2 adsorption-desorption, TEM, XPS, and TG-DSC methods. Various solutions of Burley- and Virginia-type tobaccos were used to assess the adsorption performance of new mesoporous sorbents, and the influence of the solid-to-liquid ratio, adsorption time, and loading amount of CuO on the adsorption was carefully examined. The representative sample 5%Cu/AM-10c could capture 27.2% of TSNA in Burley tobacco solution, and its capacity reached 0.3 mg g-1 in Snus tobacco extract solution, offering a promising candidate for the protection of the environment and public health.

SMART precision cancer medicine: a FHIR-based app to provide genomic information at the point of care.

BACKGROUND: Precision cancer medicine (PCM) will require ready access to genomic data within the clinical workflow and tools to assist clinical interpretation and enable decisions. Since most electronic health record (EHR) systems do not yet provide such functionality, we developed an EHR-agnostic, clinico-genomic mobile app to demonstrate several features that will be needed for point-of-care conversations. METHODS: Our prototype, called Substitutable Medical Applications and Reusable Technology (SMART)® PCM, visualizes genomic information in real time, comparing a patient's diagnosis-specific somatic gene mutations detected by PCR-based hotspot testing to a population-level set of comparable data. The initial prototype works for patient specimens with 0 or 1 detected mutation. Genomics extensions were created for the Health Level Seven® Fast Healthcare Interoperability Resources (FHIR)® standard; otherwise, the prototype is a normal SMART on FHIR app. RESULTS: The PCM prototype can rapidly present a visualization that compares a patient's somatic genomic alterations against a distribution built from more than 3000 patients, along with context-specific links to external knowledge bases. Initial evaluation by oncologists provided important feedback about the prototype's strengths and weaknesses. We added several requested enhancements and successfully demonstrated the app at the inaugural American Society of Clinical Oncology Interoperability Demonstration; we have also begun to expand visualization capabilities to include cancer specimens with multiple mutations. DISCUSSION: PCM is open-source software for clinicians to present the individual patient within the population-level spectrum of cancer somatic mutations. The app can be implemented on any SMART on FHIR-enabled EHRs, and future versions of PCM should be able to evolve in parallel with external knowledge bases.