Patterns of mosaicism for sequence and copy-number variants discovered through clinical deep sequencing of disease-related genes in one million individuals.

DNA variants that arise after conception can show mosaicism, varying in presence and extent among tissues. Mosaic variants have been reported in Mendelian diseases, but further investigation is necessary to broadly understand their incidence, transmission, and clinical impact. A mosaic pathogenic variant in a disease-related gene may cause an atypical phenotype in terms of severity, clinical features, or timing of disease onset. Using high-depth sequencing, we studied results from one million unrelated individuals referred for genetic testing for almost 1,900 disease-related genes. We observed 5,939 mosaic sequence or intragenic copy number variants distributed across 509 genes in nearly 5,700 individuals, constituting approximately 2% of molecular diagnoses in the cohort. Cancer-related genes had the most mosaic variants and showed age-specific enrichment, in part reflecting clonal hematopoiesis in older individuals. We also observed many mosaic variants in genes related to early-onset conditions. Additional mosaic variants were observed in genes analyzed for reproductive carrier screening or associated with dominant disorders with low penetrance, posing challenges for interpreting their clinical significance. When we controlled for the potential involvement of clonal hematopoiesis, most mosaic variants were enriched in younger individuals and were present at higher levels than in older individuals. Furthermore, individuals with mosaicism showed later disease onset or milder phenotypes than individuals with non-mosaic variants in the same genes. Collectively, the large compendium of variants, disease correlations, and age-specific results identified in this study expand our understanding of the implications of mosaic DNA variation for diagnosis and genetic counseling.

A comparison of RNA-Seq data preprocessing pipelines for transcriptomic predictions across independent studies.

BACKGROUND: RNA sequencing combined with machine learning techniques has provided a modern approach to the molecular classification of cancer. Class predictors, reflecting the disease class, can be constructed for known tissue types using the gene expression measurements extracted from cancer patients. One challenge of current cancer predictors is that they often have suboptimal performance estimates when integrating molecular datasets generated from different labs. Often, the quality of the data is variable, procured differently, and contains unwanted noise hampering the ability of a predictive model to extract useful information. Data preprocessing methods can be applied in attempts to reduce these systematic variations and harmonize the datasets before they are used to build a machine learning model for resolving tissue of origins. RESULTS: We aimed to investigate the impact of data preprocessing steps-focusing on normalization, batch effect correction, and data scaling-through trial and comparison. Our goal was to improve the cross-study predictions of tissue of origin for common cancers on large-scale RNA-Seq datasets derived from thousands of patients and over a dozen tumor types. The results showed that the choice of data preprocessing operations affected the performance of the associated classifier models constructed for tissue of origin predictions in cancer. CONCLUSION: By using TCGA as a training set and applying data preprocessing methods, we demonstrated that batch effect correction improved performance measured by weighted F1-score in resolving tissue of origin against an independent GTEx test dataset. On the other hand, the use of data preprocessing operations worsened classification performance when the independent test dataset was aggregated from separate studies in ICGC and GEO. Therefore, based on our findings with these publicly available large-scale RNA-Seq datasets, the application of data preprocessing techniques to a machine learning pipeline is not always appropriate.

Calcium signaling in endothelial and vascular smooth muscle cells: sex differences and the influence of estrogens and androgens.

Calcium signaling in vascular endothelial cells (ECs) and smooth muscle cells (VSMCs) is essential for the regulation of vascular tone. However, the changes to intracellular Ca2+ concentrations are often influenced by sex differences. Furthermore, a large body of evidence shows that sex hormone imbalance leads to dysregulation of Ca2+ signaling and this is a key factor in the pathogenesis of cardiovascular diseases. In this review, the effects of estrogens and androgens on vascular calcium-handling proteins are discussed, with emphasis on the associated genomic or nongenomic molecular mechanisms. The experimental models from which data were collected were also considered. The review highlights 1) in female ECs, transient receptor potential vanilloid 4 (TRPV4) and mitochondrial Ca2+ uniporter (MCU) enhance Ca2+-dependent nitric oxide (NO) generation. In males, only transient receptor potential canonical 3 (TRPC3) plays a fundamental role in this effect. 2) Female VSMCs have lower cytosolic Ca2+ levels than males due to differences in the activity and expression of stromal interaction molecule 1 (STIM1), calcium release-activated calcium modulator 1 (Orai1), calcium voltage-gated channel subunit-α1C (CaV1.2), Na+-K+-2Cl- symporter (NKCC1), and the Na+/K+-ATPase. 3) When compared with androgens, the influence of estrogens on Ca2+ homeostasis, vascular tone, and incidence of vascular disease is better documented. 4) Many studies use supraphysiological concentrations of sex hormones, which may limit the physiological relevance of outcomes. 5) Sex-dependent differences in Ca2+ signaling mean both sexes ought to be included in experimental design.

Universal Germline-Genetic Testing for Breast Cancer: Implementation in a Rural Practice and Impact on Shared Decision-Making.

BACKGROUND: Whereas the National Comprehensive Cancer Network (NCCN) criteria restrict germline-genetic testing (GGT) to a subset of breast cancer (BC) patients, the American Society of Breast Surgeons recommends universal GGT. Although the yield of pathogenic germline variants (PGV) in unselected BC patients has been studied, the practicality and utility of incorporating universal GGT into routine cancer care in community and rural settings is understudied. This study reports real-world implementation of universal GGT for patients with breast cancer and genetics-informed, treatment decision-making in a rural, community practice with limited resources. METHODS: From 2019 to 2022, all patients with breast cancer at a small, rural hospital were offered GGT, using a genetics-extender model. Statistical analyses included Fisher's exact test, t-tests, and calculation of odds ratios. Significance was set at p < 0.05. RESULTS: Of 210 patients with breast cancer who were offered GGT, 192 (91.4%) underwent testing with 104 (54.2%) in-criteria (IC) and 88 (45.8%) out-of-criteria (OOC) with NCCN guidelines. Pathogenic germline variants were identified in 25 patients (13.0%), with PGV frequencies of 15 of 104 (14.4%) in IC and ten of 88 (11.4%) in OOC patients (p = 0.495). GGT informed treatment for 129 of 185 (69.7%) patients. CONCLUSIONS: Universal GGT was successfully implemented in a rural, community practice with > 90% uptake. Treatment was enhanced or de-escalated in those with and without clinically actionable PGVs, respectively. Universal GGT for patients with breast cancer is feasible within rural populations, enabling optimization of clinical care to patients' genetic profile, and may reduce unnecessary healthcare, resource utilization.

EEG Dataset Collection for Mental Workload Predictions in Flight-Deck Environment.

High mental workload reduces human performance and the ability to correctly carry out complex tasks. In particular, aircraft pilots enduring high mental workloads are at high risk of failure, even with catastrophic outcomes. Despite progress, there is still a lack of knowledge about the interrelationship between mental workload and brain functionality, and there is still limited data on flight-deck scenarios. Although recent emerging deep-learning (DL) methods using physiological data have presented new ways to find new physiological markers to detect and assess cognitive states, they demand large amounts of properly annotated datasets to achieve good performance. We present a new dataset of electroencephalogram (EEG) recordings specifically collected for the recognition of different levels of mental workload. The data were recorded from three experiments, where participants were induced to different levels of workload through tasks of increasing cognition demand. The first involved playing the N-back test, which combines memory recall with arithmetical skills. The second was playing Heat-the-Chair, a serious game specifically designed to emphasize and monitor subjects under controlled concurrent tasks. The third was flying in an Airbus320 simulator and solving several critical situations. The design of the dataset has been validated on three different levels: (1) correlation of the theoretical difficulty of each scenario to the self-perceived difficulty and performance of subjects; (2) significant difference in EEG temporal patterns across the theoretical difficulties and (3) usefulness for the training and evaluation of AI models.

Chemical Characterization of Phoenix dactylifera L. Seeds and their Beneficial Effects on the Vascular Response in Hypertensive Rats.

Although Phoenix dactylifera dates are traditionally consumed for their health benefits, no research has been done on the vascular response in hypertensive animals. This study evaluated the vascular relaxation of hydroalcoholic extracts from seeds of three varieties of P. dactylifera; Sukkari seed (SS), Ajwa seed (AS), and Mabroom seed (MS) on L-NAME-induced hypertension and spontaneously hypertensive rats (SHR). Results showed that all extracts (10 µg/mL) caused relaxations higher than 60% in the aortic rings precontracted with 10- 6 M phenylephrine in normotensive rats, the SS extract was the most potent. Endothelial nitric oxide (NO) pathway is involved as significantly reduced vascular relaxation in denuded-endothelium rat aorta and with an inhibitor (10- 4 M L-Nω-Nitro arginine methyl ester; L-NAME) of endothelial nitric oxide synthase (eNOS). Confocal microscopy confirmed that 10 µg/mL SS extract increases NO generation as detected by DAF-FM fluorescence in intact aortic rings. Consistent with these findings, vascular relaxation in intact aortic rings at 10 µg/mL SS extract was significantly decreased in L-NAME-induced hypertensive rats (endothelial dysfunction model), but not in SHR. In both hypertensive models, the denuded endothelium blunted the vascular relaxation. In conclusion, the hydroalcoholic extract of the seed of P. dactylifera (Sukkari, Ajwa and Mabroom varieties) presents a potent endothelium-dependent vascular relaxation, via NO, in normotensive rats as well as in two different models of hypertension. This effect could be mediated by the presence of phenolic compounds identified by UHPLC-ESI-MS/MS, such as protocatechuic acid, and caftaric acid.

Mycobacterium leprae in Armadillo Tissues from Museum Collections, United States.

We examined armadillos from museum collections in the United States using molecular assays to detect leprosy-causing bacilli. We found Mycobacterium leprae bacilli in samples from the United States, Bolivia, and Paraguay; prevalence was 14.8% in nine-banded armadillos. US isolates belonged to subtype 3I-2, suggesting long-term circulation of this genotype.

Baseline Severity and Inflammation Would Influence the Effect of Simvastatin on Clinical Outcomes in Cirrhosis Patients.

BACKGROUND: Simvastatin administration to decompensated cirrhosis patients improved Child-Pugh (CP) at the end of a safety trial (EST). AIM: To evaluate whether simvastatin reduces cirrhosis severity through a secondary analysis of the safety trial. METHODS: Thirty patients CP class (CPc) CPc A (n = 6), CPc B (n = 22), and CPc C (n = 2) received simvastatin for one year. PRIMARY ENDPOINT: cirrhosis severity. Secondary endpoints: health-related quality of life (HRQoL) and hospitalizations for cirrhosis complications. RESULTS: Cirrhosis severity decreased baseline versus EST only across CP score (7.3 ± 1.3 versus 6.7 ± 1.7, P = 0.041), and CPc: 12 patients lessened from CPc B to CPc A, and three patients increased from CPc A to CPc B (P = 0.029). Due to cirrhosis severity changes and differences in clinical outcomes, 15 patients completed the trial as CPc AEST and another 15 as CPc B/C. At baseline, CPc AEST showed greater albumin and high-density lipoprotein cholesterol concentrations than CPc B/C (P = 0.036 and P = 0.028, respectively). Comparing EST versus baseline, only in CPc AEST, there was a reduction in white-cell blood (P = 0.012), neutrophils (P = 0.029), monocytes (P = 0.035), and C-reactive protein (P = 0.046); an increase in albumin (P = 0.011); and a recovery in HRQoL (P < 0.030). Finally, admissions for cirrhosis complications decreased in CPc AEST versus CPc B/C (P = 0.017). CONCLUSIONS: Simvastatin would reduce cirrhosis severity only in CPc B at baseline in a suitable protein and lipid milieu, possibly due to its anti-inflammatory effects. Furthermore, only in CPc AEST would improve HRQoL and reduce admissions by cirrhosis complications. However, as these outcomes were not primary endpoints, they require validation.

The effect of tyrosine supplementation on whole-body endurance performance in physically active population: A systematic review and meta-analysis including GRADE qualification.

Although tyrosine supplementation is well recognized to improve cognitive function, its impact on endurance performance is debatable and needs to be clarified further. The purpose of this systematic review and meta-analysis was to evaluate the effects of tyrosine supplementation on whole-body endurance performance in physically active population. The search strategy follow the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), using four databases (Cochrane Library, Web of Science, Scopus, PsycINFO, and PubMed) until 3 August 2023. The effect of tyrosine (experimental condition) was compared against placebo (control condition). The methodological quality of the included studies was evaluated using the Physiotherapy Evidence Database (PEDro) scale. The Grading of Recommendations Assessment, Development, and Evaluation (GRADE Pro software) System was also used to assess the quality of evidence. A total of 10 interventions from 8 studies were included. The sub-group analysis revealed no significant differences between tyrosine and placebo conditions for time to exhaustion (SMD = 0.02; p = 0.94) and time trial performance (SMD = -0.04; p = 0.85). The level of evidence as qualified with GRADE was moderate. In conclusion, moderate-quality evidence suggests that tyrosine supplementation is ineffective on endurance performance in the physically active population, independently of the endurance task (TTE or ETT).

Carrier screening in the Mexican Jewish community using a pan-ethnic expanded carrier screening NGS panel.

PURPOSE: The Mexican Jewish community (MJC) is a previously uncharacterized, genetically isolated group composed of Ashkenazi and Sephardi-Mizrahi Jews who migrated in the early 1900s. We aimed to determine the heterozygote frequency of disease-causing variants in 302 genes in this population. METHODS: We conducted a cross-sectional study of the MJC involving individuals representing Ashkenazi Jews, Sephardi-Mizrahi Jews, or mixed-ancestry Jews. We offered saliva-based preconception pan-ethnic expanded carrier screening, which examined 302 genes. We analyzed heterozygote frequencies of pathogenic/likely pathogenic variants and compared them with those in the Genome Aggregation Database (gnomAD). RESULTS: We recruited 208 participants. The carrier screening results showed that 72.1% were heterozygous for at least 1 severe disease-causing variant in 1 of the genes analyzed. The most common genes with severe disease-causing variants were CFTR (16.8% of participants), MEFV (11.5%), WNT10A (6.7%), and GBA (6.7%). The allele frequencies were compared with those in the gnomAD; 85% of variant frequencies were statistically different from those found in gnomAD (P <.05). Finally, 6% of couples were at risk of having a child with a severe disorder. CONCLUSION: The heterozygote frequency of at least 1 severe disease-causing variant in the MJC was 72.1%. The use of carrier screening in the MJC and other understudied populations could help parents make more informed decisions.

Extracellular vesicles released upon stimulation with antiphospholipid antibodies: An actual direct procoagulant mechanism or a new factor in the lupus anticoagulant paradox?

Antiphospholipid antibodies (aPL) lead to a hypercoagulable state in vivo. Paradoxically, some of these autoantibodies perform as inhibitors of the coagulation cascade in vitro (a phenomenon referred to as "lupus anticoagulant"). The presence of lupus anticoagulant has been related to an increased quantity of plasma extracellular vesicles, which may constitute a direct procoagulant mechanism in antiphospholipid syndrome. This study investigates whether or not endothelial cell-derived extracellular vesicles released upon stimulation with aPL (aPL-EDEVs) are related to a higher direct coagulation activity. Using an in vitro model of endothelium, flow cytometry and a recalcified plasma-based assay, we found that the coagulation activity of aPL-EDEVs is mainly conditioned by the lupus anticoagulant-like activity of autoantibodies. Nevertheless, in the presence of ß2 glycoprotein I, a cofactor of aPL during the stimulation of endothelial cells, the coagulation activity of EDEVs is restored in a mitogen-activated protein kinase kinases 1 and 2 (MEK1/2)-dependent manner. This phenomenon was especially evident when using immunoglobulins G from patients with vascular and obstetric primary antiphospholipid syndrome who manifest refractoriness to treatment. Our findings suggest that the role of aPL-EDEVs in the antiphospholipid syndrome-related hypercoagulable state may not rely on their capacity to enhance clotting directly. While ß2 glycoprotein I performs as a procoagulant cofactor and restores the coagulation activity of extracellular vesicles via MEK1/2 pathway, proportionally, autoantibodies interact with aPL-EDEVs and exhaust their coagulation properties. Further analysis is required to establish whether lupus anticoagulant-like autoantibodies opsonise extracellular vesicles and whether opsonised vesicles may lead to thrombosis by indirect means.

Plant apocarotenoid metabolism utilizes defense mechanisms against reactive carbonyl species and xenobiotics.

Carotenoid levels in plant tissues depend on the relative rates of synthesis and degradation of the molecules in the pathway. While plant carotenoid biosynthesis has been extensively characterized, research on carotenoid degradation and catabolism into apocarotenoids is a relatively novel field. To identify apocarotenoid metabolic processes, we characterized the transcriptome of transgenic Arabidopsis (Arabidopsis thaliana) roots accumulating high levels of ß-carotene and, consequently, ß-apocarotenoids. Transcriptome analysis revealed feedback regulation on carotenogenic gene transcripts suitable for reducing ß-carotene levels, suggesting involvement of specific apocarotenoid signaling molecules originating directly from ß-carotene degradation or after secondary enzymatic derivatizations. Enzymes implicated in apocarotenoid modification reactions overlapped with detoxification enzymes of xenobiotics and reactive carbonyl species (RCS), while metabolite analysis excluded lipid stress response, a potential secondary effect of carotenoid accumulation. In agreement with structural similarities between RCS and ß-apocarotenoids, RCS detoxification enzymes also converted apocarotenoids derived from ß-carotene and from xanthophylls into apocarotenols and apocarotenoic acids in vitro. Moreover, glycosylation and glutathionylation-related processes and translocators were induced. In view of similarities to mechanisms found in crocin biosynthesis and cellular deposition in saffron (Crocus sativus), our data suggest apocarotenoid metabolization, derivatization and compartmentalization as key processes in (apo)carotenoid metabolism in plants.

Computational Design of Rhenium(I) Carbonyl Complexes for Anticancer Photodynamic Therapy.

New Re(I) carbonyl complexes are proposed as candidates for photodynamic therapy after investigating the effects of the pyridocarbazole-type ligand conjugation, addition of substituents to this ligand, and replacement of one CO by phosphines in [Re(pyridocarbazole)(CO)3(pyridine)] complexes by means of the density functional theory (DFT) and time-dependent DFT. We have found, first, that increasing the conjugation in the bidentate ligand reduces the highest occupied molecular orbital (HOMO)-lowest unoccupied molecular orbital (LUMO) energy gap of the complex, so its absorption wavelength red-shifts. When the enlargement of this ligand is carried out by merging the electron-withdrawing 1H-pyrrole-2,5-dione heterocycle, it enhances even more the stabilization of the LUMO due to its electron-acceptor character. Second, the analysis of the shape and composition of the orbitals involved in the band of interest indicates which substituents of the bidentate ligand and which positions are optimal for reducing the HOMO-LUMO energy gap. The introduction of electron-withdrawing substituents into the pyridine ring of the pyridocarbazole ligand mainly stabilizes the LUMO, whereas the HOMO energy increases primarily when electron-donating substituents are introduced into its indole moiety. Each type of substituents results in a bathochromic shift of the lowest-lying absorption band, which is even larger if they are combined in the same complex. Finally, the removal of the π-backbonding interaction between Re and the CO trans to the monodentate pyridine when it is replaced by phosphines PMe3, 1,4-diacetyl-1,3,7-triaza-5-phosphabicyclo[3.3.1]nonane (DAPTA), and 1,4,7-triaza-9-phosphatricyclo[5.3.2.1]tridecane (CAP) causes another extra bathochromic shift due to the destabilization of the HOMO, which is low with DAPTA, moderate with PMe3, but especially large with CAP. Through the combination of the PMe3 or CAP ligands with adequate electron-withdrawing and/or electron-donating substituents at the pyridocarbazole ligand, we have found several complexes with significant absorption at the therapeutic window. In addition, according to our results on the singlet-triplet energy gap, all of them should be able to produce cytotoxic singlet oxygen.

To isolate or not to isolate: the impact of changing behavior on COVID-19 transmission.

BACKGROUND: The COVID-19 pandemic has caused more than 25 million cases and 800 thousand deaths worldwide to date. In early days of the pandemic, neither vaccines nor therapeutic drugs were available for this novel coronavirus. All measures to prevent the spread of COVID-19 are thus based on reducing contact between infected and susceptible individuals. Most of these measures such as quarantine and self-isolation require voluntary compliance by the population. However, humans may act in their (perceived) self-interest only. METHODS: We construct a mathematical model of COVID-19 transmission with quarantine and hospitalization coupled with a dynamic game model of adaptive human behavior. Susceptible and infected individuals adopt various behavioral strategies based on perceived prevalence and burden of the disease and sensitivity to isolation measures, and they evolve their strategies using a social learning algorithm (imitation dynamics). RESULTS: This results in complex interplay between the epidemiological model, which affects success of different strategies, and the game-theoretic behavioral model, which in turn affects the spread of the disease. We found that the second wave of the pandemic, which has been observed in the US, can be attributed to rational behavior of susceptible individuals, and that multiple waves of the pandemic are possible if the rate of social learning of infected individuals is sufficiently high. CONCLUSIONS: To reduce the burden of the disease on the society, it is necessary to incentivize such altruistic behavior by infected individuals as voluntary self-isolation.

Diagnosis of Obstructive Sleep Apnea in Patients with Associated Comorbidity.

Obstructive sleep apnea (OSA) is a heterogeneous disease with many physiological implications. OSA is associated with a great diversity of diseases, with which it shares common and very often bidirectional pathophysiological mechanisms, leading to significantly negative implications on morbidity and mortality. In these patients, underdiagnosis of OSA is high. Concerning cardiorespiratory comorbidities, several studies have assessed the usefulness of simplified screening tests for OSA in patients with hypertension, COPD, heart failure, atrial fibrillation, stroke, morbid obesity, and in hospitalized elders.The key question is whether there is any benefit in the screening for the existence of OSA in patients with comorbidities. In this regard, there are few studies evaluating the performance of the various diagnostic procedures in patients at high risk for OSA. The purpose of this chapter is to review the existing literature about diagnosis in those diseases with a high risk for OSA, with special reference to artificial intelligence-related methods.

Oximetry Indices in the Management of Sleep Apnea: From Overnight Minimum Saturation to the Novel Hypoxemia Measures.

Obstructive sleep apnea (OSA) is a multidimensional disease often underdiagnosed due to the complexity and unavailability of its standard diagnostic method: the polysomnography. Among the alternative abbreviated tests searching for a compromise between simplicity and accurateness, oximetry is probably the most popular. The blood oxygen saturation (SpO2) signal is characterized by a near-constant profile in healthy subjects breathing normally, while marked drops (desaturations) are linked to respiratory events. Parameterization of the desaturations has led to a great number of indices of severity assessment commonly used to assist in OSA diagnosis. In this chapter, the main methodologies used to characterize the overnight oximetry profile are reviewed, from visual inspection and simple statistics to complex measures involving signal processing and pattern recognition techniques. We focus on the individual performance of each approach, but also on the complementarity among the great amount of indices existing in the state of the art, looking for the most relevant oximetric feature subset. Finally, a quick overview of SpO2-based deep learning applications for OSA management is carried out, where the raw oximetry signal is analyzed without previous parameterization. Our research allows us to conclude that all the methodologies (conventional, time, frequency, nonlinear, and hypoxemia-based) demonstrate high ability to provide relevant oximetric indices, but only a reduced set provide non-redundant complementary information leading to a significant performance increase. Finally, although oximetry is a robust tool, greater standardization and prospective validation of the measures derived from complex signal processing techniques are still needed to homogenize interpretation and increase generalizability.

Conventional Machine Learning Methods Applied to the Automatic Diagnosis of Sleep Apnea.

The overnight polysomnography shows a range of drawbacks to diagnose obstructive sleep apnea (OSA) that have led to the search for artificial intelligence-based alternatives. Many classic machine learning methods have been already evaluated for this purpose. In this chapter, we show the main approaches found in the scientific literature along with the most used data to develop the models, useful and large easily available databases, and suitable methods to assess performances. In addition, a range of results from selected studies are presented as examples of these methods. Very high diagnostic performances are reported in these results regardless of the approaches taken. This leads us to conclude that conventional machine learning methods are useful techniques to develop new OSA diagnosis simplification proposals and to act as benchmark for other more recent methods such as deep learning.

Deep-Learning Model Based on Convolutional Neural Networks to Classify Apnea-Hypopnea Events from the Oximetry Signal.

Automated analysis of the blood oxygen saturation (SpO2) signal from nocturnal oximetry has shown usefulness to simplify the diagnosis of obstructive sleep apnea (OSA), including the detection of respiratory events. However, the few preceding studies using SpO2 recordings have focused on the automated detection of respiratory events versus normal respiration, without making any distinction between apneas and hypopneas. In this sense, the characteristics of oxygen desaturations differ between obstructive apnea and hypopnea episodes. In this chapter, we use the SpO2 signal along with a convolutional neural network (CNN)-based deep-learning architecture for the automatic identification of apnea and hypopnea events. A total of 398 SpO2 signals from adult OSA patients were used for this purpose. A CNN architecture was trained using 30-s epochs from the SpO2 signal for the automatic classification of three classes: normal respiration, apnea, and hypopnea. Then, the apnea index (AI), the hypopnea index (HI), and the apnea-hypopnea index (AHI) were obtained by aggregating the outputs of the CNN for each subject (AICNN, HICNN, and AHICNN). This model showed a promising diagnostic performance in an independent test set, with 80.3% 3-class accuracy and 0.539 3-class Cohen's kappa for the classification of respiratory events. Furthermore, AICNN, HICNN, and AHICNN showed a high agreement with the values obtained from the standard PSG: 0.8023, 0.6774, and 0.8466 intra-class correlation coefficients (ICCs), respectively. This suggests that CNN can be used to analyze SpO2 recordings for the automated diagnosis of OSA in at-home oximetry tests.

Proof of concept for identifying cystic fibrosis from perspiration samples.

The gold standard for cystic fibrosis (CF) diagnosis is the determination of chloride concentration in sweat. Current testing methodology takes up to 3 h to complete and has recognized shortcomings on its diagnostic accuracy. We present an alternative method for the identification of CF by combining desorption electrospray ionization mass spectrometry and a machine-learning algorithm based on gradient boosted decision trees to analyze perspiration samples. This process takes as little as 2 min, and we determined its accuracy to be 98 ± 2% by cross-validation on analyzing 277 perspiration samples. With the introduction of statistical bootstrap, our method can provide a confidence estimate of our prediction, which helps diagnosis decision-making. We also identified important peaks by the feature selection algorithm and assigned the chemical structure of the metabolites by high-resolution and/or tandem mass spectrometry. We inspected the correlation between mild and severe CFTR gene mutation types and lipid profiles, suggesting a possible way to realize personalized medicine with this noninvasive, fast, and accurate method.

A protocol for adding knowledge to Wikidata: aligning resources on human coronaviruses.

BACKGROUND: Pandemics, even more than other medical problems, require swift integration of knowledge. When caused by a new virus, understanding the underlying biology may help finding solutions. In a setting where there are a large number of loosely related projects and initiatives, we need common ground, also known as a "commons." Wikidata, a public knowledge graph aligned with Wikipedia, is such a commons and uses unique identifiers to link knowledge in other knowledge bases. However, Wikidata may not always have the right schema for the urgent questions. In this paper, we address this problem by showing how a data schema required for the integration can be modeled with entity schemas represented by Shape Expressions. RESULTS: As a telling example, we describe the process of aligning resources on the genomes and proteomes of the SARS-CoV-2 virus and related viruses as well as how Shape Expressions can be defined for Wikidata to model the knowledge, helping others studying the SARS-CoV-2 pandemic. How this model can be used to make data between various resources interoperable is demonstrated by integrating data from NCBI (National Center for Biotechnology Information) Taxonomy, NCBI Genes, UniProt, and WikiPathways. Based on that model, a set of automated applications or bots were written for regular updates of these sources in Wikidata and added to a platform for automatically running these updates. CONCLUSIONS: Although this workflow is developed and applied in the context of the COVID-19 pandemic, to demonstrate its broader applicability it was also applied to other human coronaviruses (MERS, SARS, human coronavirus NL63, human coronavirus 229E, human coronavirus HKU1, human coronavirus OC4).