Summary The pollen wall exine provides a protective layer for the male gametophyte and is largely composed of sporopollenin, which comprises fatty acid derivatives and phenolics. However, the biochemical nature of the external exine is poorly understood. Here, we show that the male sterile line 1355A of cotton mutated in NO SPINE POLLEN (GhNSP) leads to defective exine formation. The GhNSP locus was identified through map‐based cloning and confirmed by genetic analysis (co‐segregation test and allele prediction using the CRISPR/Cas9 system). In situ hybridization showed that GhNSP is highly expressed in tapetum. GhNSP encodes a polygalacturonase protein homologous to AtQRT3, which suggests a function for polygalacturonase in pollen exine formation. These results indicate that GhNSP is functionally different from AtQRT3, the latter has the function of microspore separation. Biochemical analysis showed that the percentage of de‐esterified pectin was significantly increased in the 1355A anthers at developmental stage 8. Furthermore, immunofluorescence studies using antibodies to the de‐esterified and esterified homogalacturonan (JIM5 and JIM7) showed that the Ghnsp mutant exhibits abundant of de‐esterified homogalacturonan in the tapetum and exine, coupled with defective exine formation. The characterization of GhNSP provides new understanding of the role of polygalacturonase and de‐esterified homogalacturonan in pollen exine formation.

Anther indehiscence and pollen sterility caused by high temperature (HT) stress have become a major problem that decreases the yield of cotton. Pollen- and anther-specific genes play a critical role in the process of male reproduction and the response to HT stress. In order to identify pollen-specific genes that respond to HT stress, a comparative transcriptome profiling analysis was performed in the pollen and anthers of Gossypium hirsutum HT-sensitive Line H05 against other tissue types under normal temperature (NT) conditions, and the analysis of a differentially expressed gene was conducted in the pollen of H05 under NT and HT conditions. In total, we identified 1111 pollen-specific genes (PSGs), 1066 anther-specific genes (ASGs), and 833 pollen differentially expressed genes (DEGs). Moreover, we found that the late stage of anther included more anther- and pollen-specific genes (APSGs). Stress-related cis-regulatory elements (CREs) and hormone-responsive CREs are enriched in the promoters of APSGs, suggesting that APSGs may respond to HT stress. However, 833 pollen DEGs had only 10 common genes with 1111 PSGs, indicating that PSGs are mainly involved in the processes of pollen development and do not respond to HT stress. Promoters of these 10 common genes are enriched for stress-related CREs and MeJA-responsive CREs, suggesting that these 10 common genes are involved in the process of pollen development while responding to HT stress. This study provides a pathway for rapidly identifying cotton pollen-specific genes that respond to HT stress.

Background From an economic perspective, cotton is one of the most important crops in the world. The fertility of male reproductive organs is a key determinant of cotton yield. Anther dehiscence or indehiscence directly determines the probability of fertilization in cotton. Thus, rapid and accurate identification of cotton anther dehiscence status is important for judging anther growth status and promoting genetic breeding research. The development of computer vision technology and the advent of big data have prompted the application of deep learning techniques to agricultural phenotype research. Therefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers. Result The single-stage model based on YOLOv5 has higher recognition speed and the ability to deploy to the mobile end. Breeding researchers can apply this model to terminals to achieve a more intuitive understanding of cotton anther dehiscence status. Moreover, three improvement strategies are proposed for the Faster R-CNN model, where the improved model has higher detection accuracy than the YOLOv5 model. We have made three improvements to the Faster R-CNN model and after the ensemble of the three models and original Faster R-CNN model, R2 of “open” reaches to 0.8765, R2 of “close” reaches to 0.8539, R2 of “all” reaches to 0.8481, higher than the prediction results of either model alone, which are completely able to replace the manual counting results. We can use this model to quickly extract the dehiscence rate of cotton anthers under high temperature (HT) conditions. In addition, the percentage of dehiscent anthers of 30 randomly selected cotton varieties were observed from the cotton population under normal conditions and HT conditions through the ensemble of the Faster R-CNN model and manual counting. The results show that HT decreased the percentage of dehiscent anthers in different cotton lines, consistent with the manual method. Conclusions Deep learning technology have been applied to cotton anther dehiscence status recognition instead of manual methods for the first time to quickly screen HT–tolerant cotton varieties. Deep learning can help to explore the key genetic improvement genes in the future, promoting cotton breeding and improvement.

BackgroundCotton is one of the most economically important crops in the world. The fertility of male reproductive organs is a key determinant of cotton yield. The anther dehiscence or indehiscence directly determine the probability of fertilization in cotton. Thus, the rapid and accurate identification of cotton anther dehiscence status is important for judging anther growth status and promoting genetic breeding research. The development of computer vision technology and the advent of big data have prompted the application of deep learning techniques to agricultural phenotype research. Therefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers. ResultThe single-stage model based on YOLOv5 has higher recognition efficiency and the ability to deploy to the mobile end. Breeding researchers can apply this model to terminals to achieve a more intuitive understanding of cotton anther dehiscence status. Moreover, three improvement strategies of Faster R-CNN model were proposed, the improved model has higher detection accuracy than YOLOv5 model. We have made four improvements to the Faster R-CNN model and after the ensemble of the four models, R2 of “open” reaches 0.8765, R2 of “close” reaches 0.8539, R2 of “all” reaches 0.8481, higher than the prediction result of either model alone, and can completely replace the manual counting method. We can use this model to quickly extract the dehiscence rate of cotton anther under high temperature (HT) condition. In addition, the percentage of dehiscent anther of randomly selected 30 cotton varieties were observed from cotton population under normal conditions and HT conditions through the ensemble of Faster R-CNN model and manual observation. The result showed HT varying decreased the percentage of dehiscent anther in different cotton lines, consistent with the manual method. ConclusionsThe deep learning technology first time been applied to cotton anther dehiscence status recognition instead of manual method to quickly screen the HT tolerant cotton varieties and can help to explore the key genetic improvement genes in the future, promote cotton breeding and improvement.

Cotton is one of the most economically important crops in the world. The fertility of male reproductive organs is a key determinant of cotton yield. The anther dehiscence or indehiscence directly determine the probability of fertilization in cotton. Thus, the rapid and accurate identification of cotton anther dehiscence status is important for judging anther growth status and promoting genetic breeding research. The development of computer vision technology and the advent of big data have prompted the application of deep learning techniques to agricultural phenotype research. Therefore, two deep learning models (Faster R-CNN and YOLOv5) were proposed to detect the number and dehiscence status of anthers. The single-stage model based on YOLOv5 has higher recognition efficiency and the ability to deploy to the mobile end. Breeding researchers can apply this model to terminals to achieve a more intuitive understanding of cotton anther dehiscence status. Moreover, three improvement strategies of Faster R-CNN model were proposed, the improved model has higher detection accuracy than YOLOv5 model. In addition, the percentage of dehiscent anther of randomly selected 30 cotton varieties were observed from cotton population under normal temperature and high temperature (HT) conditions through the integrated Faster R-CNN model and manual observation. The result showed HT varying decreased the percentage of dehiscent anther in different cotton lines, consistent with the manual method. Thus, this system can help us to rapid and accurate identification of HT-tolerant cotton.One sentence summaryThe deep learning technique was applied to identify the anther dehiscence state for the first time to quickly screen heat tolerant cotton varieties and help to explore key genetic improvement genes.