Residential water and energy consumption prediction at hourly resolution based on a hybrid machine learning approach.

Predicting water and energy consumption at high resolution over a short-term horizon is critical for water and energy resource management. Water and energy are shown to be closely interlinked in household consumption. However, hourly predictions are often based only on historical consumption data for the resource being predicted, with activity or appliance information and household attribution as additional information. Few studies have used aggregated water and energy consumption for predictions. Within this context, the current study proposed a novel hybrid machine learning model based on the Prophet time-series model, Gated Recurrent Unit network, and self-adaptive weights, called the Prophet-GRU model, which could jointly include historical water and electricity consumption as inputs for hourly water or electricity prediction. Data on hourly water and electricity consumption in six households in Beijing during January-March 2020 were used to train and validate the Prophet-GRU model. The goodness of fit indicator (R2) and prediction accuracy (mean squared error and mean absolute error) for the water and electricity predictions were evaluated. Compared with the single input of water or electricity, with the combined input of data of these two resources, the proposed Prophet-GRU model achieved improvements of 29.2 % and 48.5 % in R2, for water and electricity consumption prediction, respectively. Our results could help better understand water-energy linkages and promote collaborative water and energy management practices.

A presumed missense variant in the U2AF2 gene causes exon skipping in neurodevelopmental diseases.

U2 small nuclear RNA auxiliary factor 2 (U2AF2) is an indispensable pre-mRNA splicing factor in the early process of splicing. Recently, U2AF2 was reported as a novel candidate gene associated with neurodevelopmental disorders. Herein, we report a patient with a novel presumed heterozygous missense variant in the U2AF2 gene (c.603G>T), who has a similar clinical phenotype as the patient reported before, including epilepsy, intellectual disability, language delay, microcephaly, and hypoplastic corpus callosum. We reviewed the phenotypic and genetic spectrum of patients with U2AF2-related neurological diseases, both newly diagnosed and previously reported. To investigate the possible pathogenesis, EBV-immortalized lymphoblastoid cells were derived from the peripheral blood obtained from the patient and control groups. Furthermore, according to the results of WB, RT-PCR, Q-PCR, and cDNA sequencing of RT-PCR products, the presumed missense variant c.603G>T caused exon 6 skipping in the U2AF2 mRNA transcript and led to a truncated protein (p.E163_E201del). Cell Counting Kit-8 (CCK-8) and cell cycle detection demonstrated that the variant c.603G>T inhibited the proliferation of patient lymphocyte cells compared with the control group. This study is aimed at expanding the phenotypic and genetic spectrum of U2AF2-related neurodevelopmental diseases and investigating the potential effects. This is the first report of the possible pathogenesis of a U2AF2 gene pathogenic variant in a patient with neurodevelopmental diseases and shows that a novel presumed missense variant in the U2AF2 gene causes exon skipping.

Probabilistic Prediction of Laboratory Test Information Yield.

Low-yield repetitive laboratory diagnostics burden patients and inflate cost of care. In this study, we assess whether stability in repeated laboratory diagnostic measurements is predictable with uncertainty estimates using electronic health record data available before the diagnostic is ordered. We use probabilistic regression to predict a distribution of plausible values, allowing use-time customization for various definitions of "stability" given dynamic ranges and clinical scenarios. After converting distributions into "stability" scores, the models achieve a sensitivity of 29% for white blood cells, 60% for hemoglobin, 100% for platelets, 54% for potassium, 99% for albumin and 35% for creatinine for predicting stability at 90% precision, suggesting those fractions of repetitive tests could be reduced with low risk of missing important changes. The findings demonstrate the feasibility of using electronic health record data to identify low-yield repetitive tests and offer personalized guidance for better usage of testing while ensuring high quality care.

Functional Investigation of TUBB4A Variants Associated with Different Clinical Phenotypes.

Dominant TUBB4A variants result in different phenotypes, including hypomyelination with atrophy of the basal ganglia and cerebellum (H-ABC), dystonia type 4 (DYT4), and isolated hypomyelination. Here, we report four new patients with a novel TUBB4A variant (p.K324T) and three new patients with previously reported variants (p.Q292K, p.V255I, p.E410K). The individual carrying the novel p.K324T variant exhibits epilepsy of infancy with migrating focal seizures (EIMFS), while the other three have isolated hypomyelination phenotype. We also present a study of the cellular effects of TUBB4A variants responsible for H-ABC (p.D249N), DYT4 (p.R2G), a severe combined phenotype with combination of hypomyelination and EIMFS (p.K324T), and isolated hypomyelination (p.Q292K and p.E410K) on microtubule stability and dynamics, neurite outgrowth, dendritic spine development, and kinesin binding. Cellular-based assays reveal that all variants except p.R2G increase microtubule stability, decrease microtubule polymerization rates, reduce axonal outgrowth, and alter the density and shape of dendritic spines. We also find that the p.K324T and p.E410K variants perturb the binding of TUBB4A to KIF1A, a neuron-specific kinesin required for transport of synaptic vesicle precursors. Taken together, our data suggest that impaired microtubule stability and dynamics, defected axonal growth, and dendritic spine development form the common molecular basis of TUBB4A-related leukodystrophy. Impairment of TUBB4A binding to KIF1A is more likely to be involved in the isolated hypomyelination phenotype, which suggests that alterations in kinesin binding may cause different phenotypes. In conclusion, our study extends the spectrum of TUBB4A mutations and related phenotypes and provides insight into why different TUBB4A variants cause distinct clinical phenotypes.

NUP210 and MicroRNA-22 Modulate Fas to Elicit HeLa Cell Cycle Arrest.

PURPOSE: Cervical cancer is one of the most fatal diseases among women in under-developed countries. To improve cervical cancer treatment, discovery of new targets is needed. In this study, we investigated the expression of NUP210, miR-22, and Fas in cervical cancer tissues and their functions in cell cycle regulation. MATERIALS AND METHODS: We detected and compared the expression levels of NUP210, miR-22, and Fas in cervical cancer tissues with paired normal tissues using immunohistochemistry, Western blot, and real-time quantitative polymerase chain reaction. NUP210 was knocked down in HeLa cells via lentivirus, followed by cell cycle and proliferation analysis. Using a luciferase reporter assay, we explored the link between miR-22 and NUP210. We overexpressed miR-22 in HeLa cells and analyzed cell cycle and proliferation function. We then overexpressed miR-22 in NUP210 knockdown cells to explore the connection between Fas and miR-22-NUP210 signaling. RESULTS: We found that NUP210 was overexpressed in cervical cancer patients. Knocking down NUP210 restored cell apoptosis and proliferation. We confirmed miR-22 as a regulator of NUP210 and verified that miR-22 was inhibited in cervical cancer development. We also found that restoring miR-22 expression could induce cell apoptosis. Finally, we found that miR-22-regulated expression of NUP210 could alter Fas expression and, in turn, elicit cell cycle arrest and proliferation. CONCLUSION: miR-22 in cervical cancer is downregulated, resulting in NUP210 overexpression and inhibition of Fas-induced cell apoptosis.