Impacts of meteorological variables and machine learning algorithms on rice yield prediction in Korea.

As crop productivity is greatly influenced by weather conditions, many attempts have been made to estimate crop yields using meteorological data and have achieved great progress with the development of machine learning. However, most yield prediction models are developed based on observational data, and the utilization of climate model output in yield prediction has been addressed in very few studies. In this study, we estimate rice yields in South Korea using the meteorological variables provided by ERA5 reanalysis data (ERA-O) and its dynamically downscaled data (ERA-DS). After ERA-O and ERA-DS are validated against observations (OBS), two different machine learning models, Support Vector Machine (SVM) and Long Short-Term Memory (LSTM), are trained with different combinations of eight meteorological variables (mean temperature, maximum temperature, minimum temperature, precipitation, diurnal temperature range, solar irradiance, mean wind speed, and relative humidity) obtained from OBS, ERA-O, and ERA-DS at weekly and monthly timescales from May to September. Regardless of the model type and the source of the input data, training a model with weekly datasets leads to better yield estimates compared to monthly datasets. LSTM generally outperforms SVM, especially when the model is trained with ERA-DS data at a weekly timescale. The best yield estimates are produced by the LSTM model trained with all eight variables at a weekly timescale. Altogether this study shows the significance of high spatial and temporal resolution of input meteorological data in yield prediction, which can also serve to substantiate the added value of dynamical downscaling.

A deep learning analysis of Drosophila body kinematics during magnetically tethered flight.

Flying Drosophila rely on their vision to detect visual objects and adjust their flight course. Despite their robust fixation on a dark, vertical bar, our understanding of the underlying visuomotor neural circuits remains limited, in part due to difficulties in analyzing detailed body kinematics in a sensitive behavioral assay. In this study, we observed the body kinematics of flying Drosophila using a magnetically tethered flight assay, in which flies are free to rotate around their yaw axis, enabling naturalistic visual and proprioceptive feedback. Additionally, we used deep learning-based video analyses to characterize the kinematics of multiple body parts in flying animals. By applying this pipeline of behavioral experiments and analyses, we characterized the detailed body kinematics during rapid flight turns (or saccades) in two different visual conditions: spontaneous flight saccades under static screen and bar-fixating saccades while tracking a rotating bar. We found that both types of saccades involved movements of multiple body parts and that the overall dynamics were comparable. Our study highlights the importance of sensitive behavioral assays and analysis tools for characterizing complex visual behaviors.

Structural mechanism of ergosterol regulation by fungal sterol transcription factor Upc2.

Transcriptional regulation of ergosterol biosynthesis in fungi is crucial for sterol homeostasis and for resistance to azole drugs. In Saccharomyces cerevisiae, the Upc2 transcription factor activates the expression of related genes in response to sterol depletion by poorly understood mechanisms. We have determined the structure of the C-terminal domain (CTD) of Upc2, which displays a novel α-helical fold with a deep hydrophobic pocket. We discovered that the conserved CTD is a ligand-binding domain and senses the ergosterol level in the cell. Ergosterol binding represses its transcription activity, while dissociation of the ligand leads to relocalization of Upc2 from cytosol to nucleus for transcriptional activation. The C-terminal activation loop is essential for ligand binding and for transcriptional regulation. Our findings highlight that Upc2 represents a novel class of fungal zinc cluster transcription factors, which can serve as a target for the developments of antifungal therapeutics.

Crystallization and preliminary X-ray crystallographic analysis of sterol transcription factor Upc2 from Saccharomyces cerevisiae.

Upc2, a zinc-cluster transcription factor, is a regulator of ergosterol biosynthesis in yeast. In response to sterol levels, the transcriptional activity of Upc2 is controlled by the C-terminal domain. In this study, the C-terminal regulatory domain of Upc2 from Saccharomyces cerevisiae was purified and crystallized by the vapour-diffusion method. To improve the diffraction quality of Upc2 crystals, a Upc2 fusion protein in which 11 residues of the variable loop (residues 715-725) were replaced by T4 lysozymes in Upc2 (Upc2-T4L) was engineered. The Upc2-T4L crystals diffracted to 2.9 Å resolution using synchrotron radiation. The crystal was trigonal, belonging to space group P3(2) with unit-cell parameters a = 67.2, b = 67.2, c = 257.5 Å. The Matthews coefficient was determined to be 3.41 Å(3) Da(-1) with two molecules in the asymmetric unit. Initial attempts to solve the structure by the single-anomalous dispersion technique using selenomethionine were successful.

Crystallization and preliminary X-ray crystallographic analysis of the oxysterol-binding protein Osh3 from Saccharomyces cerevisiae.

Oxysterol-binding protein (OSBP) related proteins (ORPs) are conserved from yeast to humans and are implicated in regulation of sterol homeostasis and in signal transduction pathways. Osh3 of Saccharomyces cerevisiae is a pleckstrin-homology (PH) domain-containing ORP member that regulates phosphoinositide metabolism at endoplasmic reticulum-plasma membrane contact sites. The N-terminal PH domain of Osh3 was purified and crystallized as a lysozyme fusion and the resulting crystal diffracted to 2.3 Šresolution. The crystal belonged to the monoclinic space group C2, with unit-cell parameters a=98.03, b=91.31, c=84.13 Å, ß=81.41°. With two molecules in the asymmetric unit, the Matthews coefficient was 3.13 Å3 Da(-1). Initial attempts to solve the structure by molecular-replacement techniques using T4 lysozyme as a search model were successful. The C-terminal OSBP-related domain (OBD) of Osh3 was crystallized by the vapour-diffusion method and the resulting crystal diffracted to 1.5 Šresolution. The crystal was orthorhombic, belonging to space group P2(1)2(1)2(1), with unit-cell parameters a=41.57, b=87.52, c=100.58 Å. With one molecule in the asymmetric unit, the Matthews coefficient was 2.01 Å3 Da(-1). Initial attempts to solve the structure by the single-wavelength anomalous dispersion technique using bromine were successful.