Unsupervised learning to characterize patients with known coronary artery disease undergoing myocardial perfusion imaging.

PURPOSE: Patients with known coronary artery disease (CAD) comprise a heterogenous population with varied clinical and imaging characteristics. Unsupervised machine learning can identify new risk phenotypes in an unbiased fashion. We use cluster analysis to risk-stratify patients with known CAD undergoing single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI). METHODS: From 37,298 patients in the REFINE SPECT registry, we identified 9221 patients with known coronary artery disease. Unsupervised machine learning was performed using clinical (23), acquisition (17), and image analysis (24) parameters from 4774 patients (internal cohort) and validated with 4447 patients (external cohort). Risk stratification for all-cause mortality was compared to stress total perfusion deficit (< 5%, 5-10%, ≥10%). RESULTS: Three clusters were identified, with patients in Cluster 3 having a higher body mass index, more diabetes mellitus and hypertension, and less likely to be male, have dyslipidemia, or undergo exercise stress imaging (p < 0.001 for all). In the external cohort, during median follow-up of 2.6 [0.14, 3.3] years, all-cause mortality occurred in 312 patients (7%). Cluster analysis provided better risk stratification for all-cause mortality (Cluster 3: hazard ratio (HR) 5.9, 95% confidence interval (CI) 4.0, 8.6, p < 0.001; Cluster 2: HR 3.3, 95% CI 2.5, 4.5, p < 0.001; Cluster 1, reference) compared to stress total perfusion deficit (≥10%: HR 1.9, 95% CI 1.5, 2.5 p < 0.001; < 5%: reference). CONCLUSIONS: Our unsupervised cluster analysis in patients with known CAD undergoing SPECT MPI identified three distinct phenotypic clusters and predicted all-cause mortality better than ischemia alone.

Machine learning to predict abnormal myocardial perfusion from pre-test features.

BACKGROUND: Accurately predicting which patients will have abnormal perfusion on MPI based on pre-test clinical information may help physicians make test selection decisions. We developed and validated a machine learning (ML) model for predicting abnormal perfusion using pre-test features. METHODS: We included consecutive patients who underwent SPECT MPI, with 20,418 patients from a multi-center (5 sites) international registry in the training population and 9019 patients (from 2 separate sites) in the external testing population. The ML (extreme gradient boosting) model utilized 30 pre-test features to predict the presence of abnormal myocardial perfusion by expert visual interpretation. RESULTS: In external testing, the ML model had higher prediction performance for abnormal perfusion (area under receiver-operating characteristic curve [AUC] 0.762, 95% CI 0.750-0.774) compared to the clinical CAD consortium (AUC 0.689) basic CAD consortium (AUC 0.657), and updated Diamond-Forrester models (AUC 0.658, p < 0.001 for all). Calibration (validation of the continuous risk prediction) was superior for the ML model (Brier score 0.149) compared to the other models (Brier score 0.165 to 0.198, all p < 0.001). CONCLUSION: ML can predict abnormal myocardial perfusion using readily available pre-test information. This model could be used to help guide physician decisions regarding non-invasive test selection.

Showcasing MESMER-X: Spatially Resolved Emulation of Annual Maximum Temperatures of Earth System Models.

Emulators of Earth System Models (ESMs) are complementary to ESMs by providing climate information at lower computational costs. Thus far, the emulation of spatially resolved climate extremes has only received limited attention, even though extreme events are one of the most impactful aspects of climate change. Here, we propose a method for the emulation of local annual maximum temperatures, with a focus on reproducing essential statistical properties such as correlations in space and time. We test different emulator configurations and find that driving the emulations with global mean surface temperature offers an optimal compromise between model complexity and performance. We show that the emulations can mimic the temporal evolution and spatial patterns of the underlying climate model simulations and are able to reproduce their natural variability. The general design and the good performance for annual maximum temperatures suggest that the proposed methodology can be applied to other climate extremes.

Largest GWAS of PTSD (N=20 070) yields genetic overlap with schizophrenia and sex differences in heritability.

The Psychiatric Genomics Consortium-Posttraumatic Stress Disorder group (PGC-PTSD) combined genome-wide case-control molecular genetic data across 11 multiethnic studies to quantify PTSD heritability, to examine potential shared genetic risk with schizophrenia, bipolar disorder, and major depressive disorder and to identify risk loci for PTSD. Examining 20 730 individuals, we report a molecular genetics-based heritability estimate (h2SNP) for European-American females of 29% that is similar to h2SNP for schizophrenia and is substantially higher than h2SNP in European-American males (estimate not distinguishable from zero). We found strong evidence of overlapping genetic risk between PTSD and schizophrenia along with more modest evidence of overlap with bipolar and major depressive disorder. No single-nucleotide polymorphisms (SNPs) exceeded genome-wide significance in the transethnic (overall) meta-analysis and we do not replicate previously reported associations. Still, SNP-level summary statistics made available here afford the best-available molecular genetic index of PTSD-for both European- and African-American individuals-and can be used in polygenic risk prediction and genetic correlation studies of diverse phenotypes. Publication of summary statistics for ∼10 000 African Americans contributes to the broader goal of increased ancestral diversity in genomic data resources. In sum, the results demonstrate genetic influences on the development of PTSD, identify shared genetic risk between PTSD and other psychiatric disorders and highlight the importance of multiethnic/racial samples. As has been the case with schizophrenia and other complex genetic disorders, larger sample sizes are needed to identify specific risk loci.

Interaction of Pure Marangoni Convection with a Propagating Reactive Interface under Microgravity.

A reactive interface in the form of an autocatalytic reaction front propagating in a bulk phase can generate a dynamic contact line upon reaching the free surface when a surface tension gradient builds up due to the change in chemical composition. Experiments in microgravity evidence the existence of a self-organized autonomous and localized coupling of a pure Marangoni flow along the surface with the reaction in the bulk. This dynamics results from the advancement of the contact line at the surface that acts as a moving source of the reaction, leading to the reorientation of the front propagation. Microgravity conditions allow one to isolate the transition regime during which the surface propagation is enhanced, whereas diffusion remains the main mode of transport in the bulk with negligible convective mixing, a regime typically concealed on Earth because of buoyancy-driven convection.

Amb a 1 isoforms: Unequal siblings with distinct immunological features.

BACKGROUND: Ragweed pollen represents a major allergy risk factor. Ragweed extracts contain five different isoforms of the major allergen Amb a 1. However, the immunological characteristics of Amb a 1 isoforms are not fully investigated. Here, we compared the physicochemical and immunological properties of three most important Amb a 1 isoforms. METHODS: After purification, the isoforms were physicochemically characterized, tested for antibody binding and induction of human T-cell proliferative responses. Their immunological properties were further evaluated in vitro and in vivo in a mouse model. RESULTS: Amb a 1 isoforms exhibited distinct patterns of IgE binding and immunogenicity. Compared to Amb a 1.02 or 03 isoforms, Amb a 1.01 showed higher IgE-binding activity. Isoforms 01 and 03 were the most potent stimulators of patients' T cells. In a mouse model of immunization, Amb a 1.01 induced higher levels of IgG and IgE antibodies when compared to isoforms 02 and 03. Interestingly, ragweed-sensitized patients also displayed an IgG response to Amb a 1 isoforms. However, unlike therapy-induced antibodies, sensitization-induced IgG did not show IgE-blocking activity. CONCLUSION: The present study showed that naturally occurring isoforms of Amb a 1 possess different immunogenic and sensitizing properties. These findings should be considered when selecting sequences for molecule-based diagnosis and therapy for ragweed allergy. Due to its high IgE-binding activity, isoform Amb a 1.01 should be included in diagnostic tests. In contrast, due to their limited B- and T-cell cross-reactivity patterns, a combination of different isoforms might be a more attractive strategy for ragweed immunotherapy.

The relation between child feeding problems as measured by parental report and mealtime behavior observation: A pilot study.

Because feeding problems have clear negative consequences for both child and caretakers, early diagnosis and intervention are important. Parent-report questionnaires can contribute to early identification, because they are efficient and typically offer a 'holistic' perspective of the child's eating in different contexts. In this pilot study, we aim to explore the concurrent validity of a short screening instrument (the SEP, which is the Dutch MCH-FS) in one of its target populations (a group of premature children) by comparing the total score with the observed behavior of the child and caretaker during a regular home meal. 28 toddlers (aged 9-18 months) and their caretakers participated in the study. Video-observations of the meals were coded for categories of eating behavior and parent-child interaction. The results show that the total SEP-score correlates with food refusal, feeding efficiency, and self-feeding, but not with negative affect and parental instructions. This confirms that the SEP has a certain degree of concurrent validity in the sense that its total score is associated with specific 'benchmark' feeding behaviors: food refusal, feeding efficiency and autonomy. Future studies with larger samples are needed to generalize the findings from this pilot to a broader context.

Novel methods to study the effect of protein content and dissolution temperature on the solubility of milk protein concentrate: Focused beam reflectance and ultrasonic flaw detector-based methods.

Processing, storage, dissolution conditions, and the composition of milk protein concentrates (MPC) affect the solubility of high-protein dairy powders. Increasing the storage temperature and time decrease the solubility of MPC and milk protein isolates (MPI). The MPC and MPI are popular ingredients in high-protein food products and have a variety of protein contents. In addition, the dissolution temperature has been shown to affect the solubility of the powders. This study focused on determining how protein content and dissolution temperature affect the solubility of MPC and MPI. For this study, 11 powders were obtained from a commercial manufacturer. The powders were classified as A, B, C, and D, and they had a mean protein content of 85, 87, 88, and 90%, respectively. A 5% (wt/wt) concentration of powder was dissolved in water at 40 and 48°C. The solubility of the MPC and MPI samples were characterized using an ultrasonic flaw detector (UFD) and focused beam reflectance measurement (FBRM). The UFD and FBRM data were collected every 15 and 10 s, respectively, for 1,800 s. At both dissolution temperatures, the UFD and FBRM data showed that the solubility decreased as the protein content increased. Powders A and B were found to be more soluble because they had a lower relative velocity standard deviation, high area under the attenuation curve, high peak height, and low peak time. With the FBRM, the fine and medium particle count decreased and large particle count increased as the protein content increased. Powders dissolved at 48°C typically had a lower relative velocity standard deviation, higher area under the attenuation curve, higher peak height, and lower peak time than the powders dissolved at 40°C. The FBRM showed that powders dissolved at 48°C reached a stable counts before the powders dissolved at 40°C. Overall, the study showed that increasing the protein content led to a reduction in solubility and increasing the dissolution temperature improved the solubility of the powders.

Development of a method to characterize high-protein dairy powders using an ultrasonic flaw detector.

Dissolution behavior of high-protein dairy powders plays a critical role for achieving functional and nutritional characteristics of a finished food product. Current methods for evaluating powder dissolution properties are time consuming, difficult to reproduce, and subjective. Ultrasound spectroscopy is a rapid and precise method, but requires expensive equipment and skilled technicians to carry out the tests. In the present study, an ultrasonic flaw detector (UFD) was used as an economical alternative to characterize the powder dissolution properties. The objective of study was to develop a method to characterize the dissolution behavior of milk protein concentrate (MPC) using a UFD. The experimental setup included a UFD connected to a 1-MHz immersion transducer that was kept a constant distance from a reflector plate. To validate the method, 2 batches of MPC80 from a commercial manufacturer were procured and stored at 25 and 40°C for 4 wk. Focus beam reflectance measurement and solubility index were used as reference methods. Relative ultrasound velocity and ultrasound attenuation were acquired during the dissolution of MPC samples. To characterize the MPC dissolution, 4 parameters including standard deviation of relative velocity, area under the attenuation curve, and peak attenuation were extracted from ultrasound data. As the storage temperature and time increased, the area under the attenuation curve and peak height decreased, indicating a loss of solubility. The proposed UFD-based method was able to capture the changes in dissolution of MPC during storage at 25 and 40°C. It was observed that a high-quality MPC had a low standard deviation and a larger area under the attenuation curve. As the MPC aged at 40°C, the particle dispersion rate decreased and, consequently, an increase in standard deviation and reduction in area were observed. Overall, the UFD can be a low-cost method to characterize the dissolution behavior of high-protein dairy powders.

Electron spin polarization by isospin ordering in correlated two-layer quantum Hall systems.

Enhancement of the electron spin polarization in a correlated two-layer, two-dimensional electron system at a total Landau level filling factor of 1 is reported. Using resistively detected nuclear magnetic resonance, we demonstrate that the electron spin polarization of two closely spaced two-dimensional electron systems becomes maximized when interlayer Coulomb correlations establish spontaneous isospin ferromagnetic order. This correlation-driven polarization dominates over the spin polarizations of competing single-layer fractional quantum Hall states under electron density imbalances.

Pollen-derived nonallergenic substances enhance Th2-induced IgE production in B cells.

BACKGROUND: B cells play a central role in IgE-mediated allergies. In damaged airway epithelium, they are exposed directly to aeroallergens. We aimed to assess whether direct exposure of B cells to pollen constituents affects allergic sensitization. METHODS: B cells from murine splenocytes and from blood samples of healthy donors were incubated for 8 days under Th2-like conditions with aqueous ragweed pollen extracts (Amb-APE) or its constituents. Secreted total IgM, IgG, and IgE was quantified by ELISA. Additionally, birch, grass, or pine-pollen extracts were tested. The number of viable cells was evaluated by ATP measurements. B-cell proliferation was measured by CFSE staining. IgE class switch was analyzed by quantitation of class switch transcripts. In an OVA/Alum i.p.-sensitization mouse model, Amb-APE was intranasally instilled for 11 consecutive days. RESULTS: Upon Th2 priming of murine B cells, ragweed pollen extract caused a dose-dependent increase in IgE production, while IgG and IgM were not affected. The low-molecular-weight fraction and phytoprostane E1 (PPE1) increased IgE production, while Amb a 1 did not. PPE1 enhanced IgE also in human memory B cells. Under Th1 conditions, Amb-APE did not influence immunoglobulin secretion. The IgE elevation was not ragweed specific. It correlated with proliferation of viable B cells, but not with IgE class switch. In vivo, Amb-APE increased total IgE and showed adjuvant activity in allergic airway inflammation. CONCLUSIONS: Aqueous pollen extracts, the protein-free fraction of Amb-APE, and the pollen-contained substance PPE1 specifically enhance IgE production in Th2-primed B cells. Thus, pollen-derived nonallergenic substances might be responsible for B-cell-dependent aggravation of IgE-mediated allergies.

Pollen-derived adenosine is a necessary cofactor for ragweed allergy.

BACKGROUND: Ragweed (Ambrosia artemisiifolia) is a strong elicitor of allergic airway inflammation with worldwide increasing prevalence. Various components of ragweed pollen are thought to play a role in the development of allergic responses. The aim of this study was to identify critical factors for allergenicity of ragweed pollen in a physiological model of allergic airway inflammation. METHODS: Aqueous ragweed pollen extract, the low molecular weight fraction or the major allergen Amb a 1 was instilled intranasally on 1-11 consecutive days, and allergic airway inflammation was evaluated by bronchoalveolar lavage, lung histology, serology, gene expression in lung tissue, and measurement of lung function. Pollen-derived adenosine was removed from the extract enzymatically to analyze its role in ragweed-induced allergy. Migration of human neutrophils and eosinophils toward supernatants of ragweed-stimulated bronchial epithelial cells was analyzed. RESULTS: Instillation of ragweed pollen extract, but not of the major allergen or the low molecular weight fraction, induced specific IgG1 , pulmonary infiltration with inflammatory cells, a Th2-associated cytokine signature in pulmonary tissue, and impaired lung function. Adenosine aggravated ragweed-induced allergic lung inflammation. In vitro, human neutrophils and eosinophils migrated toward supernatants of bronchial epithelial cells stimulated with ragweed extract only if adenosine was present. CONCLUSIONS: Pollen-derived adenosine is a critical factor in ragweed-pollen-induced allergic airway inflammation. Future studies aim at therapeutic strategies to control these allergen-independent pathways.

[Dog and fox faecal contamination of farmland]. / Kontamination landwirtschaftlicher Nutzflächen durch Hunde- und Fuchskot.

The contamination with faeces from dogs and foxes was documented on 14 different grassland areas in the canton of Zurich, Switzerland, over one year. A total of 402 dog and 58 fox faecal samples were collected from the grasslands, further 236 faecal samples were retrieved from Robidog® units (disposal units for dog waste bags) in the immediate vicinity. The degree of fecal contamination per 100 m2 and year was 0.07-0.75 for dog samples and 0-0.06 for fox samples. Dog faeces from Robidog® units and grasslands contained stages of the following parasites, respectively (sedimentation/flotation method): Toxocara sp. (2.5%; 1.2%), Taenia crassiceps (with molecular confirmation; 0.8%; 0.2%), Capillaria sp. (0.4%; 0.7%), Trichuris sp. (0.8%; 1%), Isospora sp. (2.1%; 2%) and Angiostrongylus vasorum (0.4%; 0.5%). In fox faeces parasite stages were more frequently detected: 19% Toxocara sp., 8.6% Taenia crassiceps, 6.9% Echinococcus multilocularis, 60.3% Capillaria sp., 29.3% Trichuris sp. In two fecal samples from foxes, Taenia saginata eggs or Toxoplasmagondii oocysts were confirmed by molecular analyses, these findings may be explained as an intestinal passage after coprophagy of human or cat feces, respectively. Therefore, foxes can also indirectly play a role in parasite transmission to livestock.

Allergen hybrids - next generation vaccines for Fagales pollen immunotherapy.

BACKGROUND: Trees belonging to the order of Fagales show a distinct geographical distribution. While alder and birch are endemic in the temperate zones of the Northern Hemisphere, hazel, hornbeam and oak prefer a warmer climate. However, specific immunotherapy of Fagales pollen-allergic patients is mainly performed using birch pollen extracts, thus limiting the success of this intervention in birch-free areas. OBJECTIVES: T cells are considered key players in the modification of an allergic immune response during specific immunotherapy (SIT), therefore we thought to combine linear T cell epitope-containing stretches of the five most important Fagales allergens from birch, hazel, alder, oak and hornbeam resulting in a Fagales pollen hybrid (FPH) molecule applicable for SIT. METHODS: A Fagales pollen hybrid was generated by PCR-based recombination of low IgE-binding allergen epitopes. Moreover, a structural-variant FPH4 was calculated by in silico mutagenesis, rendering the protein unable to adopt the Bet v 1-like fold. Both molecules were produced in Escherichia coli, characterized physico-chemically as well as immunologically, and tested in mouse models of allergic sensitization as well as allergy prophylaxis. RESULTS: Using spectroscopic analyses, both proteins were monomeric, and the secondary structure elements of FPH resemble the ones typical for Bet v 1-like proteins, whereas FPH4 showed increased amounts of unordered structure. Both molecules displayed reduced binding capacities of Bet v 1-specific IgE antibodies. However, in a mouse model, the proteins were able to induce high IgG titres cross-reactive with all parental allergens. Moreover, prophylactic treatment with the hybrid proteins prevented pollen extract-induced allergic lung inflammation in vivo. CONCLUSION: The hybrid molecules showed a more efficient uptake and processing by dendritic cells resulting in a modified T cell response. The proteins had a lower IgE-binding capacity compared with the parental allergens, thus the high safety profile and increased efficacy emphasize clinical application for the treatment of Fagales multi-sensitization.

Exome sequencing detection of two untranslated GFPT1 mutations in a family with limb-girdle myasthenia.

The term 'limb-girdle myasthenia' (LGM) was first used to describe three siblings with proximal limb weakness without oculobulbar involvement, but with EMG decrement and responsiveness to anticholinesterase medication. We report here that exome sequencing in the proband of this family revealed several sequence variations in genes linked to proximal limb weakness. However, the only mutations that cosegregated with disease were an intronic IVS7-8A>G mutation and the previously reported 3'-UTR c.*22C>A mutation in GFPT1, a gene linked to LGM. A minigene assay showed that IVS7-8A>G activates an alternative splice acceptor that results in retention of the last seven nucleotides of intron 7 and a frameshift leading to a termination codon 13 nucleotides downstream from the new splice site. An anconeus muscle biopsy revealed mild reduction of the axon terminal size and postsynaptic fold simplification. The amplitudes of miniature endplate potentials and quantal release were also diminished. The DNA of the mildly affected father of the proband showed only the intronic mutation along with sequence variations in other genes potentially relevant to LGM. Thus, this study performed in the family originally described with LGM showed two GFPT1 untranslated mutations, which may cause disease by reducing GFPT1 expression and ultimately impairing protein glycosylation.

Differences in the intrinsic immunogenicity and allergenicity of Bet v 1 and related food allergens revealed by site-directed mutagenesis.

BACKGROUND: Birch pollen allergies are frequently associated with adverse reactions to various fruits, nuts, or vegetables, described as pollen-food syndrome (PFS) and caused by cross-reactive IgE antibodies primarily directed against Bet v 1. Specific immunotherapy (SIT) represents an effective treatment for inhalant allergies; however, successful birch pollen SIT does not correlate well with the amelioration of concomitant food allergies. METHODS: As vaccine candidates, apple Mal d 1 as well as hazelnut Cor a 1 derivatives were designed by in silico backbone analyses of the respective allergens. The proteins were produced by site-directed mutagenesis as fold variants of their parental allergens. Because Mal d 1 and Cor a 1 form cysteine-mediated aggregates, nonaggregative cysteine to serine mutants were also generated. The proteins were characterized physicochemically, immunologically, and in in vivo models with or without adjuvant. RESULTS: The structurally modified proteins showed significantly decreased IgE binding capacity. Notably, both in vivo models revealed reduced immunogenicity of the hypoallergenic fold variants. When formulated with alum, the monomeric cysteine mutants induced a similar immune response as the aggregated parental allergens, which is in contrast with data published on Bet v 1. CONCLUSION: These findings lead to the suggestion that the Bet v 1 structure has unique intrinsic properties, which could account for its high allergenicity. Obviously, these characteristics are not entirely shared with its food homologues from apple and hazelnut. Thus, it is important to tackle pollen-related food allergies from different angles for the generation of effective vaccine candidates to treat birch PFS.

Clinical phenotypes among patients with normal cardiac perfusion using unsupervised learning: a retrospective observational study.

BACKGROUND: Myocardial perfusion imaging (MPI) is one of the most common cardiac scans and is used for diagnosis of coronary artery disease and assessment of cardiovascular risk. However, the large majority of MPI patients have normal results. We evaluated whether unsupervised machine learning could identify unique phenotypes among patients with normal scans and whether those phenotypes were associated with risk of death or myocardial infarction. METHODS: Patients from a large international multicenter MPI registry (10 sites) with normal perfusion by expert visual interpretation were included in this cohort analysis. The training population included 9849 patients, and external testing population 12,528 patients. Unsupervised cluster analysis was performed, with separate training and external testing cohorts, to identify clusters, with four distinct phenotypes. We evaluated the clinical and imaging features of clusters and their associations with death or myocardial infarction. FINDINGS: Patients in Clusters 1 and 2 almost exclusively underwent exercise stress, while patients in Clusters 3 and 4 mostly required pharmacologic stress. In external testing, the risk for Cluster 4 patients (20.2% of population, unadjusted hazard ratio [HR] 6.17, 95% confidence interval [CI] 4.64-8.20) was higher than the risk associated with pharmacologic stress (HR 3.03, 95% CI 2.53-3.63), or previous myocardial infarction (HR 1.82, 95% CI 1.40-2.36). INTERPRETATION: Unsupervised learning identified four distinct phenotypes of patients with normal perfusion scans, with a significant proportion of patients at very high risk of myocardial infarction or death. Our results suggest a potential role for patient phenotyping to improve risk stratification of patients with normal imaging results. FUNDING: This work was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R35HL161195 to PS]. The REFINE SPECT database was supported by the National Heart, Lung, and Blood Institute at the National Institutes of Health [R01HL089765 to PS]. MCW was supported by the British Heart Foundation [FS/ICRF/20/26002].

A web-based tool for personalized prediction of long-term disease course in patients with multiple sclerosis.

BACKGROUND AND PURPOSE: The Evidence-Based Decision Support Tool in Multiple Sclerosis (EBDiMS) is the first web-based prognostic calculator in multiple sclerosis (MS) capable of delivering individualized estimates of disease progression. It has recently been extended to provide long-term predictions based on the data from a large natural history cohort. METHODS: We compared the predictive accuracy and consistency of EBDiMS with that of 17 neurologists highly specialized in MS. RESULTS: We show that whilst the predictive accuracy was similar, neurologists showed a significant intra-rater and inter-rater variability. CONCLUSIONS: Because EBDiMS was consistent, it is of superior utility in a specialist setting. Further field testing of EBDiMS in non-specialist settings, and investigation of its usefulness for counselling patients in treatment decisions, is warranted.

A recombination-based assay demonstrates that the fragile X sequence is transcribed widely during development.

To identify transcribed sequences rapidly and efficiently, we have developed a recombination-based assay to screen bacteriophage lambda libraries for sequences that share homology with a given probe. This strategy determines analytically whether a given probe is transcribed in a given tissue at a given time of development, and may also be used to isolate preparatively the transcribed sequence free of the screening probe. We illustrate this technology for the fragile X sequence, demonstrating that it is transcribed ubiquitously in an 11 week fetus, in a variety of 20 week human fetal tissues, including brain, spinal cord, eye, liver, kidney and skeletal muscle, and in adult jejunum.

Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging.

Standard clinical interpretation of myocardial perfusion imaging (MPI) has proven prognostic value for predicting major adverse cardiovascular events (MACE). However, personalizing predictions to a specific event type and time interval is more challenging. We demonstrate an explainable deep learning model that predicts the time-specific risk separately for all-cause death, acute coronary syndrome (ACS), and revascularization directly from MPI and 15 clinical features. We train and test the model internally using 10-fold hold-out cross-validation (n = 20,418) and externally validate it in three separate sites (n = 13,988) with MACE follow-ups for a median of 3.1 years (interquartile range [IQR]: 1.6, 3.6). We evaluate the model using the cumulative dynamic area under receiver operating curve (cAUC). The best model performance in the external cohort is observed for short-term prediction - in the first six months after the scan, mean cAUC for ACS and all-cause death reaches 0.76 (95% confidence interval [CI]: 0.75, 0.77) and 0.78 (95% CI: 0.78, 0.79), respectively. The model outperforms conventional perfusion abnormality measures at all time points for the prediction of death in both internal and external validations, with improvement increasing gradually over time. Individualized patient explanations are visualized using waterfall plots, which highlight the contribution degree and direction for each feature. This approach allows the derivation of individual event probability as a function of time as well as patient- and event-specific risk explanations that may help draw attention to modifiable risk factors. Such a method could help present post-scan risk assessments to the patient and foster shared decision-making.