GATR: A Road Network Traffic Violation Prediction Method Based on Graph Attention Network.

Prediction of traffic violations plays a key role in transportation safety. Combining with deep learning to predict traffic violations has become a new development trend. However, existing methods are based on regular spatial grids which leads to a fuzzy spatial expression and ignores the strong correlation between traffic violations and road network. A spatial topological graph can express the spatiotemporal correlation more accurately and then improve the accuracy of traffic violation prediction. Therefore, we propose a GATR (graph attention network based on road network) model to predict the spatiotemporal distribution of traffic violations, which adopts a graph attention network model combined with historical traffic violation features, external environmental features, and urban functional features. Experiments show that the GATR model can express the spatiotemporal distribution pattern of traffic violations more clearly and has higher prediction accuracy (RMSE = 1.7078) than Conv-LSTM (RMSE = 1.9180). The verification of the GATR model based on GNN Explainer shows the subgraph of the road network and the influence degree of features, which proves GATR is reasonable. GATR can provide an important reference for prevention and control of traffic violations and improve traffic safety.

A theory-guided graph networks based PM2.5 forecasting method.

The theory-guided air quality model solves the mathematical equations of chemical and physical processes in pollution transportation numerically. While the data-driven model, as another scientific research paradigm with powerful extraction of complex high-level abstractions, has shown unique advantages in the PM2.5 prediction applications. In this paper, to combine the two advantages of strong interpretability and feature extraction capability, we integrated the partial differential equation of PM2.5 dispersion with deep learning methods based on the newly proposed DPGN model. We extended its ability to perform long-term multi-step prediction and used advection and diffusion effects as additional constraints for graph neural network training. We used hourly PM2.5 monitoring data to verify the validity of the proposed model, and the experimental results showed that our model achieved higher prediction accuracy than the baseline models. Besides, our model significantly improved the correct prediction rate of pollution exceedance days. Finally, we used the GNNExplainer model to explore the subgraph structure that is most relevant to the prediction to interpret the results. We found that the hybrid model is more biased in selecting stations with Granger causality when predicting.

Aegilops tauschii genome assembly Aet v5.0 features greater sequence contiguity and improved annotation.

Aegilops tauschii is the donor of the D subgenome of hexaploid wheat and an important genetic resource. The reference-quality genome sequence Aet v4.0 for Ae. tauschii acc. AL8/78 was therefore an important milestone for wheat biology and breeding. Further advances in sequencing acc. AL8/78 and release of the Aet v5.0 sequence assembly are reported here. Two new optical maps were constructed and used in the revision of pseudomolecules. Gaps were closed with Pacific Biosciences long-read contigs, decreasing the gap number by 38,899. Transposable elements and protein-coding genes were reannotated. The number of annotated high-confidence genes was reduced from 39,635 in Aet v4.0 to 32,885 in Aet v5.0. A total of 2245 biologically important genes, including those affecting plant phenology, grain quality, and tolerance of abiotic stresses in wheat, was manually annotated and disease-resistance genes were annotated by a dedicated pipeline. Disease-resistance genes encoding nucleotide-binding site domains, receptor-like protein kinases, and receptor-like proteins were preferentially located in distal chromosome regions, whereas those encoding transmembrane coiled-coil proteins were dispersed more evenly along the chromosomes. Discovery, annotation, and expression analyses of microRNA (miRNA) precursors, mature miRNAs, and phasiRNAs are reported, including miRNA target genes. Other small RNAs, such as hc-siRNAs and tRFs, were characterized. These advances enhance the utility of the Ae. tauschii genome sequence for wheat genetics, biotechnology, and breeding.

Forecasting PM2.5 using hybrid graph convolution-based model considering dynamic wind-field to offer the benefit of spatial interpretability.

Air pollution is a complex process and is affected by meteorological conditions and other chemical components. Numerous studies have demonstrated that data-driven spatio-temporal prediction models of PM2.5 concentration are comparable with the model-driven model. However, data-driven models are usually depending on the statistical correlation between PM2.5 and other factors and have challenges in dealing with causality in complex systems. In this paper, we argue that domain knowledge should be incorporated into data-driven models to enhance prediction accuracy and make the model more physically realistic. We focus on the influence of dynamic wind-field on PM2.5 concentration distribution and fuse the pollution diffusion distance with the deep learning model based on a wind-field surface. In order to model spatial dependence between monitoring stations, which is dynamic and anisotropic because of the wind-field, we proposed a hybrid deep learning framework, dynamic directed spatio-temporal graph convolution networks (DD-STGCN). It expanded the ability to deal with space-time prediction in the continuous and dynamic wind-field. We used a directed graph time-series to describe the vertex state and topological relationship between vertices and replaced traditional Euclidean distance with wind-field diffusion distance to describe the proximity relationship between vertices. Our experiment results demonstrated that the DD-STGCN model achieved a better prediction ability than LSTM, GC-LSTM, and STGCN models. Compared to the best comparison model, MAPE, MAE, and RMSE were improved by 10.2%, 9.7%, and 9.6% in 12 h on an average, respectively. The performance of our model was further tested during a haze period. In the case that two models both considered the effect of wind, compared with the pure data-driven model, our model performed better in prediction distribution and showed the benefit of spatial interpretability provided by domain knowledge.

The bracteatus pineapple genome and domestication of clonally propagated crops.

Domestication of clonally propagated crops such as pineapple from South America was hypothesized to be a 'one-step operation'. We sequenced the genome of Ananas comosus var. bracteatus CB5 and assembled 513 Mb into 25 chromosomes with 29,412 genes. Comparison of the genomes of CB5, F153 and MD2 elucidated the genomic basis of fiber production, color formation, sugar accumulation and fruit maturation. We also resequenced 89 Ananas genomes. Cultivars 'Smooth Cayenne' and 'Queen' exhibited ancient and recent admixture, while 'Singapore Spanish' supported a one-step operation of domestication. We identified 25 selective sweeps, including a strong sweep containing a pair of tandemly duplicated bromelain inhibitors. Four candidate genes for self-incompatibility were linked in F153, but were not functional in self-compatible CB5. Our findings support the coexistence of sexual recombination and a one-step operation in the domestication of clonally propagated crops. This work guides the exploration of sexual and asexual domestication trajectories in other clonally propagated crops.

Structural Characterization of ABCB1, the Gene Underlying the d2 Dwarf Phenotype in Pearl Millet, Cenchrus Americanus (L.) Morrone.

Pearl millet is an important food crop in arid and semi-arid regions of South Asia and sub-Saharan Africa and is grown in Australia and the United States as a summer fodder crop. The d2 dwarf germplasm has been widely used in the last half-century to develop high-performing pearl millet hybrids. We previously mapped the d2 phenotype to a 1.6 cM region in linkage group (LG) 4 and identified the ABCB1 gene as a candidate underlying the trait. Here, we report the sequence, structure and expression of ABCB1 in tall (D2D2) and d2 dwarf (d2d2) germplasm. The ABCB1 allele in d2 dwarfs differs from that in tall inbreds by the presence of two different high copy transposable elements, one in the coding region and the second located 664 bp upstream of the ATG start codon. These transposons were present in all d2 dwarfs tested that were reported to be of independent origin and absent in the analyzed wild-type tall germplasm. We also compared the expression profile of this gene in different organs of multiple tall and d2 dwarf inbreds, including the near-isogenic inbreds at the d2 locus, Tift 23B (D2D2) and Tift 23DB (d2d2). Heterologous transformation of the tall (Ca_ABCB1) and the d2 dwarf (Ca_abcb1) pearl millet alleles in the Arabidopsis double mutant abcb1abcb19 showed that the pearl millet D2 but not the d2 allele complements the Arabidopsis abcb1 mutation. Our studies also show the importance of the COOH-terminal 22 amino acids of the ABCB1 protein in either protein function or stability.

Birth and Death of LTR-Retrotransposons in Aegilops tauschii.

Long terminal repeat-retrotransposons (LTR-RTs) are a major component of all flowering plant genomes. To analyze the time dynamics of LTR-RTs, we modeled the insertion rates of the 35 most abundant LTR-RT families in the genome of Aegilops tauschii, one of the progenitors of wheat. Our model of insertion rate (birth) takes into account random variation in LTR divergence and the deletion rate (death) of LTR-RTs. Modeling the death rate is crucial because ignoring it would underestimate insertion rates in the distant past. We rejected the hypothesis of constancy of insertion rates for all 35 families and showed by simulations that our hypothesis test controlled the false-positive rate. LTR-RT insertions peaked from 0.064 to 2.39 MYA across the 35 families. Among other effects, the average age of elements within a family was negatively associated with recombination rate along a chromosome, with proximity to the closest gene, and weakly associated with the proximity to its 5' end. Elements within a family that were near genes colinear with genes in the genome of tetraploid emmer wheat tended to be younger than those near noncolinear genes. We discuss these associations in the context of genome evolution and stability of genome sizes in the tribe Triticeae. We demonstrate the general utility of our models by analyzing the two most abundant LTR-RT families in Arabidopsis lyrata, and show that these families differed in their insertion dynamics. Our estimation methods are available in the R package TE on CRAN.

The pineapple genome and the evolution of CAM photosynthesis.

Pineapple (Ananas comosus (L.) Merr.) is the most economically valuable crop possessing crassulacean acid metabolism (CAM), a photosynthetic carbon assimilation pathway with high water-use efficiency, and the second most important tropical fruit. We sequenced the genomes of pineapple varieties F153 and MD2 and a wild pineapple relative, Ananas bracteatus accession CB5. The pineapple genome has one fewer ancient whole-genome duplication event than sequenced grass genomes and a conserved karyotype with seven chromosomes from before the ρ duplication event. The pineapple lineage has transitioned from C3 photosynthesis to CAM, with CAM-related genes exhibiting a diel expression pattern in photosynthetic tissues. CAM pathway genes were enriched with cis-regulatory elements associated with the regulation of circadian clock genes, providing the first cis-regulatory link between CAM and circadian clock regulation. Pineapple CAM photosynthesis evolved by the reconfiguration of pathways in C3 plants, through the regulatory neofunctionalization of preexisting genes and not through the acquisition of neofunctionalized genes via whole-genome or tandem gene duplication.