Pub Date : 2024-09-01DOI: 10.1016/j.inpa.2023.03.002
Detection and counting of abalones is one of key technologies of abalones breeding density estimation. The abalones in the breeding stage are small in size, densely distributed, and occluded between individuals, so the existing object detection algorithms have low precision for detecting the abalones in the breeding stage. To solve this problem, a detection and counting method of juvenile abalones based on improved SSD network is proposed in this research. The innovation points of this method are: Firstly, the multi-layer feature dynamic fusion method is proposed to obtain more color and texture information and improve detection precision of juvenile abalones with small size; secondly, the multi-scale attention feature extraction method is proposed to highlight shape and edge feature information of juvenile abalones and increase detection precision of juvenile abalones with dense distribution and individual coverage; finally, the loss feedback training method is used to increase the diversity of data and the pixels of juvenile abalones in the images to get the even higher detection precision of juvenile abalones with small size. The experimental results show that the [email protected] value, [email protected] value and [email protected] value of the detection results of the proposed method are 91.14%, 89.90% and 80.14%, respectively. The precision and recall rates of the counting results are 99.59% and 97.74%, respectively, which are superior to the counting results of SSD, FSSD, MutualGuide, EfficientDet and VarifocalNet models. The proposed method can provide support for real-time monitoring of aquaculture density for juvenile abalones.
{"title":"Detection and counting method of juvenile abalones based on improved SSD network","authors":"","doi":"10.1016/j.inpa.2023.03.002","DOIUrl":"10.1016/j.inpa.2023.03.002","url":null,"abstract":"<div><p>Detection and counting of abalones is one of key technologies of abalones breeding density estimation. The abalones in the breeding stage are small in size, densely distributed, and occluded between individuals, so the existing object detection algorithms have low precision for detecting the abalones in the breeding stage. To solve this problem, a detection and counting method of juvenile abalones based on improved SSD network is proposed in this research. The innovation points of this method are: Firstly, the multi-layer feature dynamic fusion method is proposed to obtain more color and texture information and improve detection precision of juvenile abalones with small size; secondly, the multi-scale attention feature extraction method is proposed to highlight shape and edge feature information of juvenile abalones and increase detection precision of juvenile abalones with dense distribution and individual coverage; finally, the loss feedback training method is used to increase the diversity of data and the pixels of juvenile abalones in the images to get the even higher detection precision of juvenile abalones with small size. The experimental results show that the [email protected] value, [email protected] value and [email protected] value of the detection results of the proposed method are 91.14%, 89.90% and 80.14%, respectively. The precision and recall rates of the counting results are 99.59% and 97.74%, respectively, which are superior to the counting results of SSD, FSSD, MutualGuide, EfficientDet and VarifocalNet models. The proposed method can provide support for real-time monitoring of aquaculture density for juvenile abalones.</p></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"11 3","pages":"Pages 325-336"},"PeriodicalIF":7.7,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S221431732300046X/pdfft?md5=0e659a821a078f0956cfc5f7356a7af0&pid=1-s2.0-S221431732300046X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43549565","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sen Yang, Bao-Xia Ma, Hong-Run Qian, Jie-Yu Cui, Xiao-Jun Zhang, Li-da Li, Ze-Hui Wei, Zhi-Ying Zhang, Jian-Gang Wang, Kun Xu
Targeted precise point editing and knock-in can be achieved by homology-directed repair(HDR) based gene editing strategies in mammalian cells. However, the inefficiency of HDR strategies seriously restricts their application in precision medicine and molecular design breeding. In view of the problem that exogenous donor DNA cannot be efficiently recruited autonomously at double-stranded breaks(DSBs) when using HDR strategies for gene editing, the concept of donor adapting system(DAS) was proposed and the CRISPR/Cas9-Gal4BD DAS was developed previously. Due to the large size of SpCas9 protein, its fusion with the Gal4BD adaptor is inconvenient for protein expression, virus vector packaging and in vivo delivery. In this study, two novel CRISPR/Gal4BD-SlugCas9 and CRISPR/Gal4BD-AsCas12a DASs were further developed, using two miniaturized Cas proteins, namely SlugCas9-HF derived from Staphylococcus lugdunensis and AsCas12a derived from Acidaminococcus sp. Firstly, the SSA reporter assay was used to assess the targeting activity of different Cas-Gal4BD fusions, and the results showed that the fusion of Gal4BD with SlugCas9 and AsCas12a N-terminals had minimal distraction on their activities. Secondly, the HDR efficiency reporter assay was conducted for the functional verification of the two DASs and the corresponding donor patterns were optimized simultaneously. The results demonstrated that the fusion of the Gal4BD adaptor binding sequence at the 5'-end of intent dsDNA template (BS-dsDNA) was better for the CRISPR/Gal4BD-AsCas12a DAS, while for the CRISPR/Gal4BD-SlugCas9 DAS, the dsDNA-BS donor pattern was recommended. Finally, CRISPR/Gal4BD-SlugCas9 DAS was used to achieve gene editing efficiency of 24%, 37% and 31% respectively for EMX1, NUDT5 and AAVS1 gene loci in HEK293T cells, which was significantly increased compared with the controls. In conclusion, this study provides a reference for the subsequent optimization of the donor adapting systems, and expands the gene editing technical toolbox for the researches on animal molecular design breeding.
基于同源定向修复(HDR)的基因编辑策略可以在哺乳动物细胞中实现靶向精确点编辑和基因敲入。然而,HDR 策略的低效率严重制约了其在精准医学和分子设计育种中的应用。鉴于在使用 HDR 策略进行基因编辑时,外源供体 DNA 无法在双链断裂(DSB)处有效地自主招募,人们提出了供体适配系统(DAS)的概念,并开发了 CRISPR/Cas9-Gal4BD DAS。由于SpCas9蛋白体积较大,其与Gal4BD适配体融合后不便于蛋白表达、病毒载体包装和体内递送。本研究利用两种小型化的Cas蛋白,即来源于卢格杜氏葡萄球菌的SlugCas9-HF和来源于酸性球菌的AsCas12a,进一步开发了两种新型的CRISPR/Gal4BD-SlugCas9和CRISPR/Gal4BD-AsCas12a DAS。结果表明,Gal4BD 与 SlugCas9 和 AsCas12a N 端融合对其活性的影响极小。其次,为验证两种DAS的功能,进行了HDR效率报告实验,并同时优化了相应的供体模式。结果表明,在CRISPR/Gal4BD-AsCas12a DAS中,意向dsDNA模板5'端融合Gal4BD适配体结合序列(BS-dsDNA)的效果更好;而在CRISPR/Gal4BD-SlugCas9 DAS中,推荐使用dsDNA-BS供体模式。最后,利用CRISPR/Gal4BD-SlugCas9 DAS在HEK293T细胞中对EMX1、NUDT5和AAVS1基因位点的基因编辑效率分别达到24%、37%和31%,与对照组相比显著提高。总之,本研究为后续供体适配系统的优化提供了参考,为动物分子设计育种研究拓展了基因编辑技术工具箱。
{"title":"CRISPR/Gal4BD-Cas donor adapting systems based on miniaturized Cas proteins for improved gene editing.","authors":"Sen Yang, Bao-Xia Ma, Hong-Run Qian, Jie-Yu Cui, Xiao-Jun Zhang, Li-da Li, Ze-Hui Wei, Zhi-Ying Zhang, Jian-Gang Wang, Kun Xu","doi":"10.16288/j.yczz.24-124","DOIUrl":"https://doi.org/10.16288/j.yczz.24-124","url":null,"abstract":"<p><p>Targeted precise point editing and knock-in can be achieved by homology-directed repair(HDR) based gene editing strategies in mammalian cells. However, the inefficiency of HDR strategies seriously restricts their application in precision medicine and molecular design breeding. In view of the problem that exogenous donor DNA cannot be efficiently recruited autonomously at double-stranded breaks(DSBs) when using HDR strategies for gene editing, the concept of donor adapting system(DAS) was proposed and the CRISPR/Cas9-Gal4BD DAS was developed previously. Due to the large size of SpCas9 protein, its fusion with the Gal4BD adaptor is inconvenient for protein expression, virus vector packaging and <i>in vivo</i> delivery. In this study, two novel CRISPR/Gal4BD-SlugCas9 and CRISPR/Gal4BD-AsCas12a DASs were further developed, using two miniaturized Cas proteins, namely SlugCas9-HF derived from <i>Staphylococcus lugdunensis</i> and AsCas12a derived from <i>Acidaminococcus</i> sp<i>.</i> Firstly, the SSA reporter assay was used to assess the targeting activity of different Cas-Gal4BD fusions, and the results showed that the fusion of Gal4BD with SlugCas9 and AsCas12a N-terminals had minimal distraction on their activities. Secondly, the HDR efficiency reporter assay was conducted for the functional verification of the two DASs and the corresponding donor patterns were optimized simultaneously. The results demonstrated that the fusion of the Gal4BD adaptor binding sequence at the 5'-end of intent dsDNA template (BS-dsDNA) was better for the CRISPR/Gal4BD-AsCas12a DAS, while for the CRISPR/Gal4BD-SlugCas9 DAS, the dsDNA-BS donor pattern was recommended. Finally, CRISPR/Gal4BD-SlugCas9 DAS was used to achieve gene editing efficiency of 24%, 37% and 31% respectively for <i>EMX1, NUDT5</i> and <i>AAVS1</i> gene loci in HEK293T cells, which was significantly increased compared with the controls. In conclusion, this study provides a reference for the subsequent optimization of the donor adapting systems, and expands the gene editing technical toolbox for the researches on animal molecular design breeding.</p>","PeriodicalId":35536,"journal":{"name":"Yi chuan = Hereditas / Zhongguo yi chuan xue hui bian ji","volume":"46 9","pages":"716-726"},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142297199","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Qian-Qian Ao, Fang-Xiao Lu, Liu-Qing Yang, Chun Li, Zeng-Kang Zhai, Dong-Ye Jia, Yuan-Qing Jiang, Bo Yang
Rapeseed is one important oil crop in China. However, its planting benefit is frequently affected by environmental stresses such as drought in the northwest region of China. The abscisic acid(ABA) signaling pathway plays an important role in plant abiotic stress response and tolerance, and ABFs/AREBs(ABA-responsive element binding factors/ABA-responsive element binding proteins) are the core transcription factors that regulate the expression of ABA-responsive genes. To dissect the key transcription factors mediated abiotic stress, we mainly characterized abscisic acid insensitive 5(BnaABI5) in rapeseed, including its subcellular localization, expression pattern in response to various stress and tissue-specific expression analysis, transcriptional activity analysis as well as interaction screening with BnaMPKs(mitogen-activated protein kinases). Our results showed that the BnaABI5-GFP fusion protein was localized in the nucleus, and its transcript level is induced by drought stress and was mainly expressed in the roots of rapeseed. Furthermore, BnaABI5 showed transcriptional activation activity through a yeast transactivation assay and it also activated the promoter activity of EM6 target gene in the transient expression system in tobacco leaves. Moreover, BnaABI5 interacted with BnaMPK6 and BnaMPK13 through BiFC and Y2H analysis. This study preliminarily explored the expression characteristics of transcription factor BnaABI5 and its interaction with BnaMPKs, which might help us for further understanding the function of BnaABI5.
{"title":"Analysis of expression characteristics and identification of interaction proteins of transcription factor BnaABI5 in <i>Brassica napus</i>.","authors":"Qian-Qian Ao, Fang-Xiao Lu, Liu-Qing Yang, Chun Li, Zeng-Kang Zhai, Dong-Ye Jia, Yuan-Qing Jiang, Bo Yang","doi":"10.16288/j.yczz.24-064","DOIUrl":"10.16288/j.yczz.24-064","url":null,"abstract":"<p><p>Rapeseed is one important oil crop in China. However, its planting benefit is frequently affected by environmental stresses such as drought in the northwest region of China. The abscisic acid(ABA) signaling pathway plays an important role in plant abiotic stress response and tolerance, and ABFs/AREBs(ABA-responsive element binding factors/ABA-responsive element binding proteins) are the core transcription factors that regulate the expression of ABA-responsive genes. To dissect the key transcription factors mediated abiotic stress, we mainly characterized abscisic acid insensitive 5(BnaABI5) in rapeseed, including its subcellular localization, expression pattern in response to various stress and tissue-specific expression analysis, transcriptional activity analysis as well as interaction screening with BnaMPKs(mitogen-activated protein kinases). Our results showed that the BnaABI5-GFP fusion protein was localized in the nucleus, and its transcript level is induced by drought stress and was mainly expressed in the roots of rapeseed. Furthermore, BnaABI5 showed transcriptional activation activity through a yeast transactivation assay and it also activated the promoter activity of <i>EM6</i> target gene in the transient expression system in tobacco leaves. Moreover, BnaABI5 interacted with BnaMPK6 and BnaMPK13 through BiFC and Y2H analysis. This study preliminarily explored the expression characteristics of transcription factor BnaABI5 and its interaction with BnaMPKs, which might help us for further understanding the function of BnaABI5.</p>","PeriodicalId":35536,"journal":{"name":"遗传","volume":"46 9","pages":"737-749"},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142297198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-01DOI: 10.1016/j.inpa.2023.03.003
Collections of biological specimens are essential in entomology laboratories for scientific knowledge and the characterization of natural varieties. It is vital to liberate useful information from physical collections by digitizing specimens, allowing them to be shared, examined, annotated, and compared more readily. As a result, current research has concentrated on developing 3D modeling machine systems to digitize insect specimens. Despite many great outcomes, these systems have certain drawbacks. In this research, a new scanning machine is proposed for creating 3D virtual models of insects. Our method has overcome certain previous constraints by aiding in the automation of the entire imaging process at a low cost, lowering shooting time, and generating 3D models with accurate color, high resolution, and high accuracy of insect samples with small sizes and complicated structures. Because of its ease of installation and modification, our system may be expanded and utilized in a variety of settings and areas.
{"title":"A low-cost digital 3D insect scanner","authors":"","doi":"10.1016/j.inpa.2023.03.003","DOIUrl":"10.1016/j.inpa.2023.03.003","url":null,"abstract":"<div><p>Collections of biological specimens are essential in entomology laboratories for scientific knowledge and the characterization of natural varieties. It is vital to liberate useful information from physical collections by digitizing specimens, allowing them to be shared, examined, annotated, and compared more readily. As a result, current research has concentrated on developing 3D modeling machine systems to digitize insect specimens. Despite many great outcomes, these systems have certain drawbacks. In this research, a new scanning machine is proposed for creating 3D virtual models of insects. Our method has overcome certain previous constraints by aiding in the automation of the entire imaging process at a low cost, lowering shooting time, and generating 3D models with accurate color, high resolution, and high accuracy of insect samples with small sizes and complicated structures. Because of its ease of installation and modification, our system may be expanded and utilized in a variety of settings and areas.</p></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"11 3","pages":"Pages 337-355"},"PeriodicalIF":7.7,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2214317323000471/pdfft?md5=db78072a9c6e7a9eeba9abb938606551&pid=1-s2.0-S2214317323000471-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45333040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gene editing is a kind of genetic engineering technology that can modify the genome. In recent years, with the rapid development of molecular biotechnology, the clustered regularly interspaced short palindromic repeats associated protein system has been widely used as a powerful gene editing tool due to its high efficiency, accuracy and flexibility. The CRISPR-Cas system makes a significant contribution to different aspects of livestock production by introducing site-specific modifications such as insertions, deletions or single base replacements at specific genomic sites. In terms of sheep production applications, by establishing animal models that improve production economic traits and disease resistance, the function of key genes can be studied to accelerate the improvement of traits, thereby accelerating the improvement of traits. In this review, we summarize the mechanism and function of CRISPR-Cas system and its application in the production of reproductive traits, meat use traits, wool production traits, lactation traits and disease resistance traits of sheep and the establishment of sheep animal models.
{"title":"Progress on CRISPR-Cas gene editing technology in sheep production.","authors":"Dong-Xia Pan, Hui Wang, Ben-Hai Xiong, Xiang-Fang Tang","doi":"10.16288/j.yczz.24-155","DOIUrl":"https://doi.org/10.16288/j.yczz.24-155","url":null,"abstract":"<p><p>Gene editing is a kind of genetic engineering technology that can modify the genome. In recent years, with the rapid development of molecular biotechnology, the clustered regularly interspaced short palindromic repeats associated protein system has been widely used as a powerful gene editing tool due to its high efficiency, accuracy and flexibility. The CRISPR-Cas system makes a significant contribution to different aspects of livestock production by introducing site-specific modifications such as insertions, deletions or single base replacements at specific genomic sites. In terms of sheep production applications, by establishing animal models that improve production economic traits and disease resistance, the function of key genes can be studied to accelerate the improvement of traits, thereby accelerating the improvement of traits. In this review, we summarize the mechanism and function of CRISPR-Cas system and its application in the production of reproductive traits, meat use traits, wool production traits, lactation traits and disease resistance traits of sheep and the establishment of sheep animal models.</p>","PeriodicalId":35536,"journal":{"name":"Yi chuan = Hereditas / Zhongguo yi chuan xue hui bian ji","volume":"46 9","pages":"690-700"},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142297204","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-01DOI: 10.1016/j.inpa.2022.03.001
Rural energy plays an important role in realizing the goals of “carbon peak” and “carbon neutrality” in China. In this paper, the countryside was regarded as the research object, and the rural energy internet was constructed to study the impact of rural energy development on rural carbon emissions. The most advanced energy and informative technologies in the development of rural energy were introduced from three perspectives, including rural living, rural planting and rural breeding. The benefits of rural energy internet in practical application, including energy and carbon benefits, were presented through three application cases. In general, a low-carbon, digital and intelligent rural energy will be developed, and the goals of “carbon peak” and “carbon neutrality” will be achieved by constructing and applying of rural energy internet in China.
{"title":"Key technologies and applications of rural energy internet in China","authors":"","doi":"10.1016/j.inpa.2022.03.001","DOIUrl":"10.1016/j.inpa.2022.03.001","url":null,"abstract":"<div><p>Rural energy plays an important role in realizing the goals of “carbon peak” and “carbon neutrality” in China. In this paper, the countryside was regarded as the research object, and the rural energy internet was constructed to study the impact of rural energy development on rural carbon emissions. The most advanced energy and informative technologies in the development of rural energy were introduced from three perspectives, including rural living, rural planting and rural breeding. The benefits of rural energy internet in practical application, including energy and carbon benefits, were presented through three application cases. In general, a low-carbon, digital and intelligent rural energy will be developed, and the goals of “carbon peak” and “carbon neutrality” will be achieved by constructing and applying of rural energy internet in China.</p></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"11 3","pages":"Pages 277-298"},"PeriodicalIF":7.7,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2214317322000282/pdfft?md5=64eda4c88ae8eb55c157e27b6bc98064&pid=1-s2.0-S2214317322000282-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46987028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-09-01DOI: 10.1016/j.inpa.2023.03.004
With the vigorous development of intelligence agriculture, the progress of automated large-scale and intensive pig farming has accelerated significantly. As a biological feature, the pig face has important research significance for precise breeding of pigs and traceability of health. In the management of live pigs, many managers adopt traditional methods, including color marking and RFID identification, but there will be problems such as off-label, mixed-label and waste of manpower. This work proposes a non-invasive way to study the identification of multiple individuals in pigs. The model was to first replace the original backbone network of YOLOv4 with MobileNet-v3, a popular lightweight network. Then depth-wise separable convolution was adopted in YOLOv4′s feature extraction network SPP and PANet to further reduce network parameters. Moreover, CBAM attention mechanism formed by the concatenation of CAM and SAM was added to PANet to ensure the network accuracy while reducing the model weight. The introduction of multi-attention mechanism selectively strengthened key areas of pig face and filtered out weak correlation features, so as to improve the overall model effect. Finally, an improved MobileNetv3-YOLOv4-PACNet (M-YOLOv4-C) network model was proposed to identify individual sows. The mAP were 98.15 %, the detection speed FPS were 106.3frames/s, and the model parameter size was only 44.74 MB, which can be well implanted into the small-volume pig house management sensors and applied to the pig management system in a lightweight, fast and accurate manner. This model will provide model support for subsequent pig behavior recognition and posture analysis.
{"title":"Pig face recognition based on improved YOLOv4 lightweight neural network","authors":"","doi":"10.1016/j.inpa.2023.03.004","DOIUrl":"10.1016/j.inpa.2023.03.004","url":null,"abstract":"<div><p>With the vigorous development of intelligence agriculture, the progress of automated large-scale and intensive pig farming has accelerated significantly. As a biological feature, the pig face has important research significance for precise breeding of pigs and traceability of health. In the management of live pigs, many managers adopt traditional methods, including color marking and RFID identification, but there will be problems such as off-label, mixed-label and waste of manpower. This work proposes a non-invasive way to study the identification of multiple individuals in pigs. The model was to first replace the original backbone network of YOLOv4 with MobileNet-v3, a popular lightweight network. Then depth-wise separable convolution was adopted in YOLOv4′s feature extraction network SPP and PANet to further reduce network parameters. Moreover, CBAM attention mechanism formed by the concatenation of CAM and SAM was added to PANet to ensure the network accuracy while reducing the model weight. The introduction of multi-attention mechanism selectively strengthened key areas of pig face and filtered out weak correlation features, so as to improve the overall model effect. Finally, an improved MobileNetv3-YOLOv4-PACNet (M-YOLOv4-C) network model was proposed to identify individual sows. The mAP were 98.15 %, the detection speed FPS were 106.3frames/s, and the model parameter size was only 44.74 MB, which can be well implanted into the small-volume pig house management sensors and applied to the pig management system in a lightweight, fast and accurate manner. This model will provide model support for subsequent pig behavior recognition and posture analysis.</p></div>","PeriodicalId":53443,"journal":{"name":"Information Processing in Agriculture","volume":"11 3","pages":"Pages 356-371"},"PeriodicalIF":7.7,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2214317323000483/pdfft?md5=15cedd90f8b826def2e4ca0a3a7b3834&pid=1-s2.0-S2214317323000483-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46956825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Li-Bin Mei, Yi-Yuan Zhang, Xian-Jing Huang, Hong Ji, Ping-Ping Qiu, Lu Ding, Xuemei He, Ping Li
Split-hand/foot malformation is a serious congenital limb malformation characterized by syndactyly and underdevelopment of the phalanges and metatarsals. In this study, we reported a case of a fetus with hand-foot cleft deformity. Whole exome and Sanger sequencing were used to filter out candidate gene mutation sites and provide pre-implantation genetic testing(PGT) for family members. Genetic testing results showed that there was a homozygous mutation c.786G>A (p.Trp262*) in the fetal WNT10B, and both parents were carriers of heterozygous mutations. PGT results showed that out of the two blastocysts, one was a heterozygous mutant and the other was a homozygous mutant. All the embryos had diploid chromosomes. The heterozygous embryo was transferred, and a singleton pregnancy was successfully achieved. This study suggests that homozygous mutations in WNT10B are the likely cause of hand-foot clefts in this family. For families with monogenic diseases, preimplantation genetic testing can effectively prevent the birth of an affected child only after identifying the pathogenic mutation.
{"title":"Identification of a pathogenic variant and pre-implantation genetic testing for a Chinese family affected with split-hand/foot malformation.","authors":"Li-Bin Mei, Yi-Yuan Zhang, Xian-Jing Huang, Hong Ji, Ping-Ping Qiu, Lu Ding, Xuemei He, Ping Li","doi":"10.16288/j.yczz.24-141","DOIUrl":"https://doi.org/10.16288/j.yczz.24-141","url":null,"abstract":"<p><p>Split-hand/foot malformation is a serious congenital limb malformation characterized by syndactyly and underdevelopment of the phalanges and metatarsals. In this study, we reported a case of a fetus with hand-foot cleft deformity. Whole exome and Sanger sequencing were used to filter out candidate gene mutation sites and provide pre-implantation genetic testing(PGT) for family members. Genetic testing results showed that there was a homozygous mutation c.786G>A (p.Trp262*) in the fetal <i>WNT10B</i>, and both parents were carriers of heterozygous mutations. PGT results showed that out of the two blastocysts, one was a heterozygous mutant and the other was a homozygous mutant. All the embryos had diploid chromosomes. The heterozygous embryo was transferred, and a singleton pregnancy was successfully achieved. This study suggests that homozygous mutations in <i>WNT10B</i> are the likely cause of hand-foot clefts in this family. For families with monogenic diseases, preimplantation genetic testing can effectively prevent the birth of an affected child only after identifying the pathogenic mutation.</p>","PeriodicalId":35536,"journal":{"name":"Yi chuan = Hereditas / Zhongguo yi chuan xue hui bian ji","volume":"46 9","pages":"750-756"},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142297202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yan-Chun Bao, Cai-Xia Shi, Chuan-Qiang Zhang, Ming-Juan Gu, Lin Zhu, Zai-Xia Liu, Le Zhou, Feng-Ying Ma, Ri-Su Na, Wen-Guang Zhang
With the rapid growth of data driven by high-throughput sequencing technologies, genomics has entered an era characterized by big data, which presents significant challenges for traditional bioinformatics methods in handling complex data patterns. At this critical juncture of technological progress, deep learning-an advanced artificial intelligence technology-offers powerful capabilities for data analysis and pattern recognition, revitalizing genomic research. In this review, we focus on four major deep learning models: Convolutional Neural Network(CNN), Recurrent Neural Network(RNN), Long Short-Term Memory(LSTM), and Generative Adversarial Network(GAN). We outline their core principles and provide a comprehensive review of their applications in DNA, RNA, and protein research over the past five years. Additionally, we also explore the use of deep learning in livestock genomics, highlighting its potential benefits and challenges in genetic trait analysis, disease prevention, and genetic enhancement. By delivering a thorough analysis, we aim to enhance precision and efficiency in genomic research through deep learning and offer a framework for developing and applying livestock genomic strategies, thereby advancing precision livestock farming and genetic breeding technologies.
{"title":"Progress on deep learning in genomics.","authors":"Yan-Chun Bao, Cai-Xia Shi, Chuan-Qiang Zhang, Ming-Juan Gu, Lin Zhu, Zai-Xia Liu, Le Zhou, Feng-Ying Ma, Ri-Su Na, Wen-Guang Zhang","doi":"10.16288/j.yczz.24-151","DOIUrl":"https://doi.org/10.16288/j.yczz.24-151","url":null,"abstract":"<p><p>With the rapid growth of data driven by high-throughput sequencing technologies, genomics has entered an era characterized by big data, which presents significant challenges for traditional bioinformatics methods in handling complex data patterns. At this critical juncture of technological progress, deep learning-an advanced artificial intelligence technology-offers powerful capabilities for data analysis and pattern recognition, revitalizing genomic research. In this review, we focus on four major deep learning models: Convolutional Neural Network(CNN), Recurrent Neural Network(RNN), Long Short-Term Memory(LSTM), and Generative Adversarial Network(GAN). We outline their core principles and provide a comprehensive review of their applications in DNA, RNA, and protein research over the past five years. Additionally, we also explore the use of deep learning in livestock genomics, highlighting its potential benefits and challenges in genetic trait analysis, disease prevention, and genetic enhancement. By delivering a thorough analysis, we aim to enhance precision and efficiency in genomic research through deep learning and offer a framework for developing and applying livestock genomic strategies, thereby advancing precision livestock farming and genetic breeding technologies.</p>","PeriodicalId":35536,"journal":{"name":"Yi chuan = Hereditas / Zhongguo yi chuan xue hui bian ji","volume":"46 9","pages":"701-715"},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142297205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Asteraceae is a large class of eudicots with complex capitulum, and little is known regarding the molecular regulation mechanism of flower development. APETALA1(AP1) belongs to the MADS-box gene family and plays a key role in plant floral induction and floral organ development. In this study, the bioinformatics and tissue-specific expression of AP1 homologous gene SvAP1-5 in Senecio vulgaris were analyzed. Based on VIGS technology, SvAP1-5 gene silencing plants were created, and SvAP1-5 was overexpressed in Solanum nigrum. The results of bioinformatics analysis showed that SvAP1-5 gene had typical MADS-box and K-box structure, and contains FUL motif and paleoAP1 motif at the C-terminal. SvAP1-5 belongs to the euFUL branch of AP1 gene. qRT-PCR results showed that SvAP1-5 was expressed in bracts, petals and carpels, and was highly expressed in carpels. Compared with the control group, SvAP1-5 gene silencing resulted in irregular petal dehiscence, increased stigma division, and carpel dysplasia. The fruit development of SvAP1-5 overexpressing S.nigrum plants was abnormal, and the hyperplastic tissue similar to fruit appeared. In summary, SvAP1-5 gene may be involved in the development of petals and carpels and plays an important role during the development of S.vulgaris.
{"title":"Effects of <i>SvAPETALA1-5</i> gene on floral organ development in <i>Senecio vulgaris</i>.","authors":"Yu-Na Zhang, Yan-Min Hao, Min-Long Cui, Chun-Lan Piao","doi":"10.16288/j.yczz.24-147","DOIUrl":"10.16288/j.yczz.24-147","url":null,"abstract":"<p><p>Asteraceae is a large class of eudicots with complex capitulum, and little is known regarding the molecular regulation mechanism of flower development. <i>APETALA1</i>(<i>AP1</i>) belongs to the MADS-box gene family and plays a key role in plant floral induction and floral organ development. In this study, the bioinformatics and tissue-specific expression of <i>AP1</i> homologous gene <i>SvAP1-5</i> in <i>Senecio vulgaris</i> were analyzed. Based on VIGS technology, <i>SvAP1-5</i> gene silencing plants were created, and <i>SvAP1-5</i> was overexpressed in <i>Solanum nigrum</i>. The results of bioinformatics analysis showed that <i>SvAP1-5</i> gene had typical MADS-box and K-box structure, and contains FUL motif and paleoAP1 motif at the C-terminal. <i>SvAP1-5</i> belongs to the euFUL branch of <i>AP1</i> gene. qRT-PCR results showed that <i>SvAP1-5</i> was expressed in bracts, petals and carpels, and was highly expressed in carpels. Compared with the control group, <i>SvAP1-5</i> gene silencing resulted in irregular petal dehiscence, increased stigma division, and carpel dysplasia. The fruit development of <i>SvAP1-5</i> overexpressing <i>S.nigrum</i> plants was abnormal, and the hyperplastic tissue similar to fruit appeared. In summary, <i>SvAP1-5</i> gene may be involved in the development of petals and carpels and plays an important role during the development of <i>S.vulgaris</i>.</p>","PeriodicalId":35536,"journal":{"name":"遗传","volume":"46 9","pages":"727-736"},"PeriodicalIF":0.0,"publicationDate":"2024-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142297200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}