The haplotype-resolved T2T reference genome highlights structural variation underlying agronomic traits of melon

Melon(Cucumis melo L.)is an important vegetable crop that has an extensive history of cultivation.However,the genome of wild and semi-wild melon types that can be used for the analysis of agronomic traits is not yet available.Here we report a chromosome-level T2T genome assembly for 821(C.melo ssp.agrestis var.acidulus),a semi-wild melon with two haplotypes of∼373 Mb and∼364 Mb,respectively.Comparative genome analysis discovered a significant number of structural variants(SVs)between melo(C.melo ssp.melo)and agrestis(C.melo ssp.agrestis)genomes,including a copy number variation located in the ToLCNDV resistance locus on chromosome 11.Genome-wide association studies detected a significant signal associated with climacteric ripening and identified one candidate gene CM_ac12g14720.1(CmABA2),encoding a cytoplasmic short chain dehydrogenase/reductase,which controls the biosynthesis of abscisic acid.This study provides valuable genetic resources for future research on melon breeding.

Correg-Yolov3:a Method for Dense Buildings Detection in High-resolution Remote Sensing Images

The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.

Genetic dissection of climacteric fruit ripening in a melon population segregating for ripening behavior

Melon is as an alternative model to understand fruit ripening due to the coexistence of climacteric and non-climacteric varieties within the same species,allowing the study of the processes that regulate this complex trait with genetic approaches.We phenotyped a population of recombinant inbred lines(RILs),obtained by crossing a climacteric(Védrantais,cantalupensis type)and a non-climcteric variety(Piel de Sapo T111,inodorus type),for traits related to climacteric maturation and ethylene production.Individuals in the RIL population exhibited various combinations of phenotypes that differed in the amount of ethylene produced,the early onset of ethylene production,and other phenotypes associated with ripening.We characterized a major QTL on chromosome 8,ETHQV8.1,which is sufficient to activate climacteric ripening,and other minor QTLs that may modulate the climacteric response.The ETHQV8.1 allele was validated by using two reciprocal introgression line populations generated by crossing Védrantais and Piel de Sapo and analyzing the ETHQV8.1 region in each of the genetic backgrounds.A Genome-wide association study(GWAS)using 211 accessions of the ssp.melo further identified two regions on chromosome 8 associated with the production of aromas,one of these regions overlapping with the 154.1 kb interval containing ETHQV8.1.The ETHQV8.1 region contains several candidate genes that may be related to fruit ripening.This work sheds light into the regulation mechanisms of a complex trait such as fruit ripening.

MDC-Net:a multi-directional constrained and prior assisted neural network for wood and leaf separation from terrestrial laser scanning

Wood-leaf separation from terrestrial laser scanning(TLS)is a crucial prerequisite for quantifying many biophysical properties and understanding ecological functions.In this study,we propose a novel multi-directional collaborative convolutional neural network(MDC-Net)that takes the original 3D coordinates and useful features from prior knowledge(prior features)as input,and outputs the semantic labels of TLS point clouds.The MDC-Net contains two key units:(1)a multi-directional neighborhood construction(MDNC)unit to obtain more representative neighbors and enable directionally aware feature encoding in the subsequent local feature extraction,to mitigate occlusion effects;(2)a collaborative feature encoding(CFE)unit is introduced to incorporate useful features from prior knowledge into the network through a collaborative cross coding to enhance the discrimination for thin structures(e.g.small branches and leaf).The MDC-Net is evaluated onfive plots from forests in Guangxi,China,with different branch architectures and leaf distributions.Experimental results showed that the MDC-Net achieved an OA of 0.973 and a mIoU of 0.821 and outperformed other related methods.We believe the MDC-Net would facilitate the usage of TLS in ecology studies for quantifying tree size and morphology and thus promote the development of relevant ecological applications.