Temporospatial hierarchy and allele-specific expression of zygotic genome activation revealed by distant interspecific urochordate hybrids.

Zygotic genome activation (ZGA) is a universal process in early embryogenesis of metazoan, when the quiescent zygotic nucleus initiates global transcription. However, the mechanisms related to massive genome activation and allele-specific expression (ASE) remain not well understood. Here, we develop hybrids from two deeply diverged (120 Mya) ascidian species to symmetrically document the dynamics of ZGA. We identify two coordinated ZGA waves represent early developmental and housekeeping gene reactivation, respectively. Single-cell RNA sequencing reveals that the major expression wave exhibits spatial heterogeneity and significantly correlates with cell fate. Moreover, allele-specific expression occurs in a species- rather than parent-related manner, demonstrating the divergence of cis-regulatory elements between the two species. These findings provide insights into ZGA in chordates.

Young LINE-1 transposon 5' UTRs marked by elongation factor ELL3 function as enhancers to regulate naïve pluripotency in embryonic stem cells.

LINE-1s are the major clade of retrotransposons with autonomous retrotransposition activity. Despite the potential genotoxicity, LINE-1s are highly activated in early embryos. Here we show that a subset of young LINE-1s, L1Md_Ts, are marked by the RNA polymerase II elongation factor ELL3, and function as enhancers in mouse embryonic stem cells. ELL3 depletion dislodges the DNA hydroxymethylase TET1 and the co-repressor SIN3A from L1Md_Ts, but increases the enrichment of the Bromodomain protein BRD4, leading to loss of 5hmC, gain of H3K27ac, and upregulation of the L1Md_T nearby genes. Specifically, ELL3 occupies and represses the L1Md_T-based enhancer located within Akt3, which encodes a key regulator of AKT pathway. ELL3 is required for proper ERK activation and efficient shutdown of naïve pluripotency through inhibiting Akt3 during naïve-primed transition. Our study reveals that the enhancer function of a subset of young LINE-1s controlled by ELL3 in transcription regulation and mouse early embryo development.

A Novel Defect Inspection System Using Convolutional Neural Network for MEMS Pressure Sensors.

Defect inspection using imaging-processing techniques, which detects and classifies manufacturing defects, plays a significant role in the quality control of microelectromechanical systems (MEMS) sensors in the semiconductor industry. However, high-precision classification and location are still challenging because the defect images that can be obtained are small and the scale of the different defects on the picture of the defect is different. Therefore, a simple, flexible, and efficient convolutional neural network (CNN) called accurate-detection CNN (ADCNN) to inspect MEMS pressure-sensor-chip packaging is proposed in this paper. The ADCNN is based on the faster region-based CNN, which improved the performance of the network by adding random-data augmentation and defect classifiers. Specifically, the ADCNN achieved a mean average precision of 92.39% and the defect classifier achieved a mean accuracy of 97.2%.

Design of Plant Protection UAV Variable Spray System Based on Neural Networks.

Recently, unmanned aerial vehicles (UAVs) have rapidly emerged as a new technology in the fields of plant protection and pest control in China. Based on existing variable spray research, a plant protection UAV variable spray system integrating neural network based decision making is designed. Using the existing data on plant protection UAV operations, combined with artificial neural network (ANN) technology, an error back propagation (BP) neural network model between the factors affecting droplet deposition is trained. The factors affecting droplet deposition include ambient temperature, ambient humidity, wind speed, flight speed, flight altitude, propeller pitch, nozzles pitch and prescription value. Subsequently, the BP neural network model is combined with variable rate spray control for plant protection UAVs, and real-time information is collected by multi-sensor. The deposition rate is determined by the neural network model, and the flow rate of the spray system is regulated according to the predicted deposition amount. The amount of droplet deposition can meet the prescription requirement. The results show that the training variance of the ANN is 0.003, and thus, the model is stable and reliable. The outdoor tests show that the error between the predicted droplet deposition and actual droplet deposition is less than 20%. The ratio of droplet deposition to prescription value in each unit is approximately equal, and a variable spray operation under different conditions is realized.