labeling method
Recently Published Documents


TOTAL DOCUMENTS

587
(FIVE YEARS 109)

H-INDEX

42
(FIVE YEARS 5)

2022 ◽  
Vol 14 (2) ◽  
pp. 861
Author(s):  
Han-Cheng Dan ◽  
Hao-Fan Zeng ◽  
Zhi-Heng Zhu ◽  
Ge-Wen Bai ◽  
Wei Cao

Image recognition based on deep learning generally demands a huge sample size for training, for which the image labeling becomes inevitably laborious and time-consuming. In the case of evaluating the pavement quality condition, many pavement distress patching images would need manual screening and labeling, meanwhile the subjectivity of the labeling personnel would greatly affect the accuracy of image labeling. In this study, in order for an accurate and efficient recognition of the pavement patching images, an interactive labeling method is proposed based on the U-Net convolutional neural network, using active learning combined with reverse and correction labeling. According to the calculation results in this paper, the sample size required by the interactive labeling is about half of the traditional labeling method for the same recognition precision. Meanwhile, the accuracy of interactive labeling method based on the mean intersection over union (mean_IOU) index is 6% higher than that of the traditional method using the same sample size and training epochs. In addition, the accuracy analysis of the noise and boundary of the prediction results shows that this method eliminates 92% of the noise in the predictions (the proportion of noise is reduced from 13.85% to 1.06%), and the image definition is improved by 14.1% in terms of the boundary gray area ratio. The interactive labeling is considered as a significantly valuable approach, as it reduces the sample size in each epoch of active learning, greatly alleviates the demand for manpower, and improves learning efficiency and accuracy.


Molecules ◽  
2022 ◽  
Vol 27 (1) ◽  
pp. 267
Author(s):  
Jiejie Feng ◽  
Changshun Chu ◽  
Zhanfang Ma

Appropriate labeling method of signal substance is necessary for the construction of multiplexed electrochemical immunosensing interface to enhance the specificity for the diagnosis of cancer. So far, various electrochemical substances, including organic molecules, metal ions, metal nanoparticles, Prussian blue, and other methods for an electrochemical signal generation have been successfully applied in multiplexed biosensor designing. However, few works have been reported on the summary of electrochemical signal substance applied in constructing multiplexed immunosensing interface. Herein, according to the classification of labeled electrochemical signal substance, this review has summarized the recent state-of-art development for the designing of electrochemical immunosensing interface for simultaneous detection of multiple tumor markers. After that, the conclusion and prospects for future applications of electrochemical signal substances in multiplexed immunosensors are also discussed. The current review can provide a comprehensive summary of signal substance selection for workers researched in electrochemical sensors, and further, make contributions for the designing of multiplexed electrochemical immunosensing interface with well signal.


2022 ◽  
Vol 12 (1) ◽  
pp. 25
Author(s):  
Varvara Koshman ◽  
Anastasia Funkner ◽  
Sergey Kovalchuk

Electronic medical records (EMRs) include many valuable data about patients, which is, however, unstructured. Therefore, there is a lack of both labeled medical text data in Russian and tools for automatic annotation. As a result, today, it is hardly feasible for researchers to utilize text data of EMRs in training machine learning models in the biomedical domain. We present an unsupervised approach to medical data annotation. Syntactic trees are produced from initial sentences using morphological and syntactical analyses. In retrieved trees, similar subtrees are grouped using Node2Vec and Word2Vec and labeled using domain vocabularies and Wikidata categories. The usage of Wikidata categories increased the fraction of labeled sentences 5.5 times compared to labeling with domain vocabularies only. We show on a validation dataset that the proposed labeling method generates meaningful labels correctly for 92.7% of groups. Annotation with domain vocabularies and Wikidata categories covered more than 82% of sentences of the corpus, extended with timestamp and event labels 97% of sentences got covered. The obtained method can be used to label EMRs in Russian automatically. Additionally, the proposed methodology can be applied to other languages, which lack resources for automatic labeling and domain vocabulary.


2021 ◽  
Author(s):  
Elisabeth Holzer ◽  
Cornelia Rumpf-Kienzl ◽  
Sebastian Falk ◽  
Alexander Dammermann

Proximity-dependent labeling approaches such as BioID have been a great boon to studies of protein-protein interactions in the context of cytoskeletal structures such as centrosomes which are poorly amenable to traditional biochemical approaches like immunoprecipitation and tandem affinity purification. Yet, these methods have so far not been applied extensively to invertebrate experimental models such as C. elegans given the long labeling times required for the original promiscuous biotin ligase variant BirA*. Here, we show that the recently developed variant TurboID successfully probes the interactomes of both stably associated (SPD-5) and dynamically localized (PLK-1) centrosomal components. We further develop an indirect proximity labeling method employing a GFP nanobody- TurboID fusion, which allows the identification of protein interactors in a tissue-specific manner in the context of the whole animal. Critically, this approach utilizes available endogenous GFP fusions, avoiding the need to generate multiple additional strains for each target protein and the potential complications associated with overexpressing the protein from transgenes. Using this method, we identify homologs of two highly conserved centriolar components, Cep97 and Bld10/Cep135, which are present in various somatic tissues of the worm. Surprisingly, neither protein is expressed in early embryos, likely explaining why these proteins have escaped attention until now. Our work expands the experimental repertoire for C. elegans and opens the door for further studies of tissue-specific variation in centrosome architecture.


2021 ◽  
Vol 7 (4) ◽  
pp. 235-239
Author(s):  
Surbhi Sharma ◽  
Reeta Jain ◽  
Shanta Chopra ◽  
Shaveta Kaushal

Forensic odontology is the branch that comes under forensic science which deals with proper handling, examination and evaluation of dental evidences. This manuscript describes various techniques that can be adopted for denture identification. The labeling method followed here is inclusion method where photographic sheet was used to mark dentures as this sheet is solvent resistant. The area selected for denture marking is palatal area on maxillary denture and distolingual flange of mandibular area as these areas have sufficient space for inclusion of details and there are not esthetically compromising areas. By this method denture labeling could be done in existing prosthetic devices or could be incorporated in newly constructed prosthesis. The American Board of Forensic Odontology guidelines indicate that most dental identifications are based on restorations, caries, missing teeth and/or prosthetic devices.


Author(s):  
Liwei Che ◽  
Zewei Long ◽  
Jiaqi Wang ◽  
Yaqing Wang ◽  
Houping Xiao ◽  
...  

2021 ◽  
Author(s):  
Chen Zhu ◽  
Yi Wang ◽  
Zhen Lin ◽  
Rongxia Li ◽  
Bei Jia ◽  
...  

Abstract Clade A PP2C phosphatases are central components of the ABA-receptor coupled core signaling pathway, and are involved in multiple stress responses and developmental processes. However, the direct targets or partner proteins of A clade PP2Cs that participate in these biological processes are largely unknown. Here, we used a TurboID-based proximity labeling method to identify putative associated proteins of one A clade PP2C phosphatase, ABI1. By combining the results from affinity purification or proximity labeling of biotinylated proteins, we identified more than four hundred putative ABI1-associated proteins, including dozens of known ABI1-intreacting proteins, as well as proteins involved in TOR signaling, phospho-regulation, and other biological processes. We found that RAFs, a group of protein kinases that phosphorylate and activate SnRK2s in ABA and osmotic stress signaling, are direct substrates of ABI1. A conserved serine residue located in the P-loop of the kinase domain, corresponding to Ser619 in RAF3, is a major functional ABI1 target site. ABI1-mediated dephosphorylation on this site strongly promotes the kinase activity of most B2 and B3 RAFs. Thus, ABI1 has dual functions in ABA signaling by dephosphorylating and inhibiting SnRK2 to prevent SnRK2 activation in unstressed conditions, while dephosphorylating B2 and B3 subgroup RAFs to maintain their basal kinase activity. PP2C-mediated dephosphorylation at the conserved serine residue may be a mechanism for RAF activation in both plants and animals, with potential implications for tumorigenesis in humans.


2021 ◽  
Author(s):  
Dimitra Sakoula ◽  
Garrett J. Smith ◽  
Jeroen Frank ◽  
Rob J. Mesman ◽  
Linnea F. M. Kop ◽  
...  

AbstractThe advance of metagenomics in combination with intricate cultivation approaches has facilitated the discovery of novel ammonia-, methane-, and other short-chain alkane-oxidizing microorganisms, indicating that our understanding of the microbial biodiversity within the biogeochemical nitrogen and carbon cycles still is incomplete. The in situ detection and phylogenetic identification of novel ammonia- and alkane-oxidizing bacteria remain challenging due to their naturally low abundances and difficulties in obtaining new isolates from complex samples. Here, we describe an activity-based protein profiling protocol allowing cultivation-independent unveiling of ammonia- and alkane-oxidizing bacteria. In this protocol, 1,7-octadiyne is used as a bifunctional enzyme probe that, in combination with a highly specific alkyne-azide cycloaddition reaction, enables the fluorescent or biotin labeling of cells harboring active ammonia and alkane monooxygenases. Biotinylation of these enzymes in combination with immunogold labeling revealed the subcellular localization of the tagged proteins, which corroborated expected enzyme targets in model strains. In addition, fluorescent labeling of cells harboring active ammonia or alkane monooxygenases provided a direct link of these functional lifestyles to phylogenetic identification when combined with fluorescence in situ hybridization. Furthermore, we show that this activity-based labeling protocol can be successfully coupled with fluorescence-activated cell sorting for the enrichment of nitrifiers and alkane-oxidizing bacteria from complex environmental samples, enabling the recovery of high-quality metagenome-assembled genomes. In conclusion, this study demonstrates a novel, functional tagging technique for the reliable detection, identification, and enrichment of ammonia- and alkane-oxidizing bacteria present in complex microbial communities.


eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Ian F Price ◽  
Hannah L Hertz ◽  
Benjamin Pastore ◽  
Jillian Wagner ◽  
Wen Tang

The germ line produces gametes that transmit genetic and epigenetic information to the next generation. Maintenance of germ cells and development of gametes require germ granules-well-conserved membraneless and RNA-rich organelles. The composition of germ granules is elusive owing to their dynamic nature and their exclusive expression in the germ line. Using C. elegans germ granule, called P granule, as a model system, we employed a proximity-based labeling method in combination with mass spectrometry to comprehensively define its protein components. This set of experiments identified over 200 proteins, many of which contain intrinsically disordered regions. An RNAi-based screen identified factors that are essential for P granule assembly, notably EGGD-1 and EGGD-2, two putative LOTUS-domain proteins. Loss of eggd-1 and eggd-2 results in separation of P granules from the nuclear envelope, germline atrophy and reduced fertility. We show that intrinsically disordered regions of EGGD-1 are required to anchor EGGD-1 to the nuclear periphery while its LOTUS domains are required to promote perinuclear localization of P granules. Together, our work expands the repertoire of P granule constituents and provides new insights into the role of LOTUS-domain proteins in germ granule organization.


Sign in / Sign up

Export Citation Format

Share Document