Biology subjects

Cheng, T.

Publications and source records attributed to Cheng, T..

At least 55 records · Page 3Linked to original sources

bioRxiv2021

A live attenuated influenza virus-vectored intranasal COVID-19 vaccine provides rapid, prolonged, and broad protection against SARS-CoV-2 infection

Remarkable progress has been made in developing intramuscular vaccines against severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); however, they are limited with respect to eliciting local immunity in the respiratory tract, which is the primary infection site for SARS-CoV-2. To overcome the limitations of intramuscular vaccines, we constructed a nasal vaccine candidate based on an influenza vector by inserting a gene encoding the receptor-binding domain (RBD) of the spike protein of SARS-CoV-2, named CA4-dNS1-nCoV-RBD (dNS1-RBD). A preclinical study showed that in hamsters challenged 1 day and 7 days after single-dose vaccination or 6 months after booster vaccination, dNS1-RBD largely mitigated lung pathology, with no loss of body weight, caused by either the prototype-like strain or beta variant of SARS-CoV-2. Lasted data showed that the animals could be well protected against beta variant challenge 9 months after vaccination. Notably, the weight loss and lung pathological changes of hamsters could still be significantly reduced when the hamster was vaccinated 24 h after challenge. Moreover, such cellular immunity is relatively unimpaired for the most concerning SARS-CoV-2 variants. The protective immune mechanism of dNS1-RBD could be attributed to the innate immune response in the nasal epithelium, local RBD-specific T cell response in the lung, and RBD-specific IgA and IgG response. Thus, this study demonstrates that the intranasally delivered dNS1-RBD vaccine candidate may offer an important addition to fight against the ongoing COVID-19 pandemic, compensating limitations of current intramuscular vaccines, particularly at the start of an outbreak.

pathology↗

bioRxiv2021

iCn3D: from Web-based 3D Viewer to Structure Analysis Tool in Batch Mode

iCn3D was initially developed as a web-based 3D molecular viewer. It then evolved from visualization into a full-featured interactive structural analysis software. It became a collaborative research instrument through the sharing of permanent, shortened URLs that encapsulate not only annotated visual molecular scenes, but also all underlying data and analysis scripts in a FAIR manner. More recently, with the growth of structural databases, the need to analyze large structural datasets systematically led us to use Python scripts and convert the code to be used in Node.js scripts. We showed a few examples of Python scripts at https://github.com/ncbi/icn3d/tree/master/icn3dpython to export secondary structures or PNG images from iCn3D. Users just need to replace the URL in the Python scripts to export other annotations from iCn3D. Furthermore, any interactive iCn3D feature can be converted into a Node.js script to be run in batch mode, enabling an interactive analysis performed on one or a handful of protein complexes to be scaled up to analysis features of large ensembles of structures. Currently available Node.js analysis scripts examples are available at https://github.com/ncbi/icn3d/tree/master/icn3dnode. This development will enable ensemble analyses on growing structural databases such as AlphaFold or RoseTTAFold on one hand and Electron Microscopy on the other. In this paper, we also review new features such as DelPhi electrostatic potential, 3D view of mutations, alignment of multiple chains, assembly of multiple structures by realignment, dynamic symmetry calculation, 2D cartoons at different levels, interactive contact maps, and use of iCn3D in Jupyter Notebook as described at https://pypi.org/project/icn3dpy.

bioinformatics↗

bioRxiv2021

WDR82-binding long non-coding RNA lncEry controls mouse erythroid differentiation and maturation

Hematopoietic differentiation is controlled by both genetic and epigenetic regulators. Long non-coding RNAs (lncRNAs) have been demonstrated to be important for normal hematopoiesis, but their function in erythropoiesis needs to be further explored. We profiled the transcriptomes of 16 murine hematopoietic cell populations by deep RNA-sequencing and identified a novel lncRNA, Gm15915, that was highly expressed in erythroid-related progenitors and erythrocytes. For this reason, we named it lncEry. We also identified a novel lncEry isoform, which was also the principal transcript that has not been reported before. LncEry depletion impaired erythropoiesis, indicating the important role of the lncRNA in regulating erythroid differentiation and maturation. Mechanistically, we found that lncEry interacted with WD repeat-containing protein 82 (WDR82) to promote the transcription of Klf1 and globin genes and thus control the early and late stages of erythropoiesis, respectively. These findings identified lncEry as an important player in the transcriptional regulation of erythropoiesis.

cell biology↗

bioRxiv2021

Enhancing the interoperability of glycan data flow between ChEBI, PubChem, and GlyGen.

Glycans play a vital role in health, disease, bioenergy, biomaterials, and biotherapeutics. As a result, there is keen interest to identify and increase glycan data in bioinformatics databases like ChEBI and PubChem, and connecting them to resources at the EMBL-EBI and NCBI to facilitate access to important annotations at a global level. GlyTouCan is a comprehensive archival database that contains glycans obtained primarily through batch upload from glycan repositories, glycoprotein databases, and individual laboratories. In many instances, the glycan structures deposited in GlyTouCan may not be fully defined or have supporting experimental evidence and citations. Databases like ChEBI and PubChem were designed to accommodate complete atomistic structures with well-defined chemical linkages. As a result, they cannot easily accommodate the structural ambiguity inherent in glycan databases. Consequently, there is a need to improve the organization of glycan data coherently to enhance connectivity across the major NCBI, EMBL-EBI, and glycoscience databases. This paper outlines a workflow developed in collaboration between GlyGen, ChEBI, and PubChem to improve the visibility and connectivity of glycan data across these resources. GlyGen hosts a subset of glycans (~29,000) from the GlyTouCan database and has submitted valuable glycan annotations to the PubChem database and integrated over 10,500 (including ambiguously defined) glycans into the ChEBI database. The integrated glycans were prioritized based on links to PubChem and connectivity to glycoprotein data. The pipeline provides a blueprint for how glycan data can be harmonized between different resources. The current PubChem, ChEBI, and GlyTouCan mappings can be downloaded from GlyGen (https://data.glygen.org).

bioinformatics↗

bioRxiv2021

Single cell response landscape of graded Nodal signaling in zebrafish explants

Nodal, as a morphogen, plays important roles in cell fate decision, pattern formation and organizer function. But because of the complex context in vivo and technology limitations, systematic studying of genes, cell types and patterns induced by Nodal alone is still missing. Here, by using a relatively simplified model, the zebrafish blastula animal pole explant avoiding additional instructive signals and prepatterns, we constructed a single cell response landscape of graded Nodal signaling, identified 105 Nodal immediate targets and depicted their expression patterns. Our results show that Nodal signaling is sufficient to induce anterior-posterior patterned axial mesoderm and head structure. Surprisingly, the endoderm induced by Nodal alone is mainly the anterior endoderm which gives rise to the pharyngeal pouch only, but not internal organs. Among the 105 Nodal targets, we identified 14 genes carrying varying levels of axis induction capability. Overall, our work provides new insights for understanding of the Nodal function and a valuable resource for future studies of patterning and morphogenesis induced by it.

developmental biology↗

bioRxiv2021

SNHG16 promotes cell proliferation and inhibits cell apoptosis via regulation of the miR-1303p/STARD9 axis in renal cell carcinoma

BackgroundRenal cell carcinoma (RCC) is a fatal malignant tumor with high morbidity. Numerous medical studies have suggested that long noncoding RNAs (lncRNAs) exert their biological function on various cancerous progresses. Herein, functions of lncRNA SNHG16 in RCC cells and the mechanism medicated by SNHG16 were investigated. MethodsThe expression levels of SNHG16 and its downstream genes in RCC cells and tissues were examined utilizing reverse transcription quantitative polymerase chain reaction analyses. Cell counting kit-8 and 5-Ethynyl-2-deoxyuridine assays were carried out to evaluate the proliferation of RCC cells, and flow cytometry analyses were employed to determine the apoptosis of RCC cells. Western blot analysis was applied to examine protein levels associated with cell proliferation and apoptosis. The combination between SNHG16 and miRNA as well as miRNA and its target gene were explored by luciferase reporter, RNA pull down, and RNA immunoprecipitation assays. ResultsThe significant upregulation of SNHG16 was observed in RCC tissues and cells. SNHG16 downregulation inhibited the proliferation and promoted the apoptosis of RCC cells. In addition, SNHG16 served as a competing endogenous RNA for miR-1301-3p, and STARD9 was a target gene of miR-1301-3p in RCC cells. SNHG16 upregulated STARD9 expression by binding with miR-1301-3p in RCC cells. Rescue assays validated that SNHG16 promoted RCC cell promotion and induced RCC cell apoptosis by upregulating STARD9 expression. ConclusionsSNHG16 promotes RCC cell proliferation and suppresses RCC cell apoptosis via interaction with miR-1301-3p to upregulate STARD9 expression in RCC cells.

cell biology↗

bioRxiv2020

Sterilizing immunity against SARS-CoV-2 in hamsters conferred by a novel recombinant subunit vaccine

A safe and effective SARS-CoV-2 vaccine is essential to avert the on-going COVID-19 pandemic. Here, we developed a subunit vaccine, which is comprised of CHO-expressed spike ectodomain protein (StriFK) and nitrogen bisphosphonates-modified zinc-aluminum hybrid adjuvant (FH002C). This vaccine candidate rapidly elicited the robust humoral response, Th1/Th2 balanced helper CD4 T cell and CD8 T cell immune response in animal models. In mice, hamsters, and non-human primates, 2-shot and 3-shot immunization of StriFK-FH002C generated 28- to 38-fold and 47- to 269-fold higher neutralizing antibody titers than the human COVID-19 convalescent plasmas, respectively. More importantly, the StriFK-FH002C immunization conferred sterilizing immunity to prevent SARS-CoV-2 infection and transmission, which also protected animals from virus-induced weight loss, COVID-19-like symptoms, and pneumonia in hamsters. Vaccine-induced neutralizing and cell-based receptor-blocking antibody titers correlated well with protective efficacy in hamsters, suggesting vaccine-elicited protection is immune-associated. The StriFK-FH002C provided a promising SARS-CoV-2 vaccine candidate for further clinical evaluation.

microbiology↗

bioRxiv2020

Co-editing PINK1 and DJ-1 genes via AAV-delivered CRISPR/Cas9 system in adult monkey brains elicits classic Parkinsonian phenotypes

Whether direct manipulation of Parkinsons disease (PD) risk genes in monkey brain can elicit Parkinsonian phenotypes remains an unsolved issue. Here, we employed an adeno-associated virus (AAV)-delivered CRISPR/Cas9 system to directly co-edit PINK1 and DJ-1 genes in the substantia nigra (SN) region of four adult monkey brains. After the operation, two of the monkeys exhibited all classic PD symptoms, including bradykinesia, tremor, and postural instability, accompanied by severe nigral dopaminergic neuron loss (over 60%) and -synuclein pathology. The aged monkeys were more vulnerable to gene editing by showing faster PD progression, higher final total PD scores, and severer pathologic changes compared with their younger counterparts, suggesting both the genetic and aging factors played important roles in PD development. This gene editing system can be used to develop a large quantity of genetically edited PD monkeys over a short period, thus providing a practical transgenic monkey model for future PD studies.

neuroscience↗

bioRxiv2020

Distribution of Epsilon-Polylysine Synthetases in Coryneform Bacteria Isolated from Cheese and Human Skin

Epsilon-polylysine ({varepsilon}-PL) is an antimicrobial commercially produced by Streptomyces fermentation and widely used in Asian countries for food preservation. Here we discovered a gene from cheese bacterium Corynebacterium variabile that showed high similarity to the {varepsilon}-PL synthetase from Streptomyces in terms of enzymatic domain architecture and gene context. By cloning it into Streptomyces coelicolor with a Streptomyces albulus {varepsilon}-PL synthetase promoter, we confirmed that its product is indeed {varepsilon}-PL. A comprehensive sequence analysis suggests that {varepsilon}-PL synthetases are widely spread among coryneform bacteria isolated from cheese and human skin; 14 out of 15 Brevibacterium isolates and 10 out of 12 Corynebacterium isolates contain Pls gene. This discovery raises the possibility that {varepsilon}-PL as a bioactive secondary metabolite might be produced and play a role in the cheese and skin ecosystems. IMPORTANCEEvery year, microbial contamination causes billions of tons of food wasted and millions of cases of foodborne illness. {varepsilon}-PL is an excellent food preservative as it is potent, wide spectrum and is heat stable and biodegradable. It has not been accepted by all countries (e.g those in the EU) partially because it was not a natural composition of food but rather originated from the soil bacteria Streptomyces, a famous producer of various antibiotic drugs and toxins. The unexpected finding of {varepsilon}-PL synthetases in cheese and skin bacteria suggests that {varepsilon}-PL may naturally exist in cheese and on our skin.

microbiology↗

bioRxiv2020

Virus-free and live-cell visualizing SARS-CoV-2 cell entry for studies of neutralizing antibodies and compound inhibitors

The ongoing COVID-19 pandemic, caused by SARS-CoV-2 infection, has resulted in hundreds of thousands of deaths. Cellular entry of SARS-CoV-2, which is mediated by the viral spike protein and host ACE2 receptor, is an essential target for the development of vaccines, therapeutic antibodies, and drugs. Using a mammalian cell expression system, we generated a recombinant fluorescent protein (Gamillus)-fused SARS-CoV-2 spike trimer (STG) to probe the viral entry process. In ACE2-expressing cells, we found that the STG probe has excellent performance in the live-cell visualization of receptor binding, cellular uptake, and intracellular trafficking of SARS-CoV-2 under virus-free conditions. The new system allows quantitative analyses of the inhibition potentials and detailed influence of COVID-19-convalescent human plasmas, neutralizing antibodies and compounds, providing a versatile tool for high-throughput screening and phenotypic characterization of SARS-CoV-2 entry inhibitors. This approach may also be adapted to develop a viral entry visualization system for other viruses.

microbiology↗

bioRxiv2020

Loss of Nupr1 promotes engraftment by tuning the dormancy threshold of hematopoietic stem cell repository via regulating p53-checkpoint pathway

Hematopoietic stem cells (HSCs) are dominantly quiescent under homeostasis, which is a key mechanism of maintaining the HSC pool for life-long hematopoiesis. Dormant HSCs poise to be immediately activated on urgent conditions and can return to quiescence after regaining homeostasis. To date, the molecular networks of regulating the threshold of HSC dormancy, if exist, remain largely unknown. Here, we unveiled that deletion of Nupr1, a gene preferentially expressed in HSCs, activated the quiescence HSCs under homeostatic status, which conferred engraftment competitive advantage on HSCs without compromising their stemness and multi-lineage differentiation abilities in serial transplantation settings. Following an expansion protocol, the Nupr1-/- HSCs proliferate more robustly than their wild type counterparts in vitro. Nupr1 inhibits the expression of p53 and the rescue of which offsets the engraftment advantage. Our data unveil the de novo role of Nupr1 as an HSC quiescence-regulator, which provides insights into accelerating the engraftment efficacy of HSC transplantation by targeting the HSC quiescence-controlling network.

cell biology↗

bioRxiv2020

SARS-CoV-2 envelope protein causes acute respiratory distress syndrome (ARDS)-like pathological damage and constitutes an antiviral target

Cytokine storm and multi-organ failure are the main causes of SARS-CoV-2-related death. However, the origin of the virus excessively damaging abilities remains unknown. Here we show that the SARS-CoV-2 envelope (2-E) protein alone is sufficient to cause acute respiratory distress syndrome (ARDS)-like damage in vitro and in vivo. Overexpression of 2-E protein induced rapid pyroptosis-like cell death in various susceptible cells and robust secretion of cytokines and chemokines in macrophages. Intravenous administration of purified 2-E protein into mice caused ARDS-like pathological damage in lung and spleen. Overexpressed 2-E protein formed cation channels in host cell membranes, eventually leading to membrane rupture. Newly identified channel inhibitors exhibited potent anti-SARS-CoV-2 activity and excellent protective effects against the 2-E-induced damage both in vitro and in vivo. Importantly, their channel inhibition, cell protection and antiviral activities were positively correlated with each other, supporting 2-E is a promising drug target against SARS-CoV-2.

microbiology↗

bioRxiv2020

Integrated decoding hematopoiesis and leukemogenesis at single-cell resolution and its clinical implication

Integrated analyses of hematopoiesis and leukemogenesis could provide new biological and clinical insights1,2. Here we constructed a comprehensive cell atlas using [~]100,000 single cell transcriptomes of bone marrow mononuclear cells and its subsets from 5 healthy samples and 13 leukemia samples. Trajectory analysis showed hematopoietic stem cells continuously differentiated through tree-like structure into 7 lineages. Although our single cell analyses showed the major cellular heterogeneity were inter-patients, there were distinct leukemia cell subpopulations within patient. We developed counterpart composite index (CCI) for projecting leukemia cell subpopulation into reference hematopoietic cells, to identify their healthy counterparts that could predict leukemia subtype and clinical outcome. Interestingly, we found the trajectories of leukemogenesis were similar to that of their healthy counterparts, indicating lineage relationship of leukemia cell subpopulations. Single cell analyses of leukemia patient at diagnosis, refractory, remission and relapse vividly presented dynamics of cell population and the underlying genes. Single cell transcriptomic variants analyses showed the relapsed leukemia cells, whose healthy counterparts were closer to the root of hematopoietic tree, were derived from an early minor leukemia cell population. This study not only increased our understanding of hematopoiesis and leukemogenesis, but also provided an approach for leukemia classification and clinical outcome prediction.

genomics↗

bioRxiv2019

Single-cell transcriptome profiling reveals neutrophil heterogeneity and orchestrated maturation during homeostasis and bacterial infection

The full neutrophil heterogeneity and differentiation landscape remains incompletely characterized. Here we profiled >25,000 differentiating and mature mouse neutrophils using single-cell RNA sequencing to provide a comprehensive transcriptional landscape of neutrophil maturation, function, and fate decision in their steady state and during bacterial infection. Eight neutrophil populations were defined by distinct molecular signatures. The three mature peripheral blood neutrophil subsets arise from distinct maturing bone marrow neutrophil subsets. Driven by both known and uncharacterized transcription factors, neutrophils gradually acquire microbicidal capability as they traverse the transcriptional landscape, representing an evolved mechanism for fine-tuned regulation of an effective but balanced neutrophil response. Bacterial infection reprograms the genetic architecture of neutrophil populations, alters dynamic transition between each subpopulation, and primes neutrophils for augmented functionality without affecting overall heterogeneity. In summary, these data establish a reference model and general framework for studying neutrophil-related disease mechanisms, biomarkers, and therapeutic targets at single-cell resolution.\n\nGraphical Abstract\n\nO_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=119 SRC=\"FIGDIR/small/792200v1_ufig1.gif\" ALT=\"Figure 1\">\nView larger version (28K):\norg.highwire.dtl.DTLVardef@18fed35org.highwire.dtl.DTLVardef@1e68b7org.highwire.dtl.DTLVardef@6cfbc8org.highwire.dtl.DTLVardef@1061a26_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LIA comprehensive single-cell resolution transcriptional landscape of mouse neutrophil maturation and fate decision under steady-state and bacterial infection conditions.\nC_LIO_LIThe pathogen clearance machinery in neutrophils is continuously and gradually built during neutrophil differentiation, maturation, and aging, driven by both known and uncharacterized transcription factors.\nC_LIO_LIThe three mature neutrophil subsets in peripheral blood, including a novel ISG-expressing subset, are derived from distinct bone marrow neutrophil precursors.\nC_LIO_LIBacterial infection reprograms the genetic architecture of neutrophil populations, alters dynamic transition between each subpopulation, and primes neutrophils for augmented functionality without affecting overall neutrophil heterogeneity.\nC_LIO_LIBacterial infection-induced emergency granulopoiesis is mediated by augmented proliferation of early stage neutrophil progenitors and accelerated post-mitotic maturation.\nC_LI

immunology↗

bioRxiv2019

High content analysis of granuloma histology and neutrophilic inflammation in adult zebrafish infected with Mycobacterium marinum

Infection of zebrafish with natural pathogen Mycobacterium marinum is a useful surrogate for studying the human granulomatous inflammatory response to infection by Mycobacterium tuberculosis. The adaptive immune system of the adult stage zebrafish offers an advance on the commonly used embryo infection model as adult zebrafish form granulomas with striking similarities to human-M. tuberculosis granulomas. Here, we present workflows to perform high content analyses of granulomas in adult zebrafish infected with M. marinum by cryosectioning to take advantage of strong endogenous transgenic fluorescence adapted from common zebrafish embryo infection tools. Specific guides to classifying granuloma necrosis and organisation, quantifying bacterial burden and leukocyte infiltration of granulomas, and visualizing extracellular matrix remodelling and foam cell formation are also provided. We use these methods to characterize neutrophil recruitment to M. marinum granulomas across time and find an inverse relation to granuloma necrosis suggesting granuloma necrosis is not a marker of immunopathology in the natural infection system of the adult zebrafish-M. marinum pairing. The methods can be easily translated to studying the zebrafish adaptive immune response to other chronic and granuloma-forming pathogens.

immunology↗

bioRxiv2019

An integrated Asian human SNV and indel benchmark combining multiple sequencing methods

Precision medicine of human requires an accurate and complete reference variant benchmark for different populations. A human standard cell line of NA12878 provides a good reference for part of the human populations, but it is still lack of a fine reference standard sample and variant benchmark for the Asians. Here, we constructed a stabilized cell line of a Chinese Han volunteer. We received about 4.16T clean data of the sample using eight sequencing strategies in different laboratories, including two BGI regular NGS platforms, three Illumina regular NGS platforms, two linked-read libraries, and PacBio CCS model. The sequencing depth and reference coverage of eight sequencing strategies have reached the saturation. We detected small variants of SNPs and Indels using the eight data sets and obtained eight variant sets by performing a series of strictly quality control. Finally, we got 3.35M SNPs and 349K indels supported by all of sequencing data, which could be considered as a high confidence standard small variant sets for the studies. Besides, we also detected 5,913 high quality SNPs located in the high homologous regions supported by both linked-reads and CCS data benefited by their long-range information, while these regions are recalcitrant to regular NGS data due to the limited mappability and read length. We compared the later SNPs against the public databases and 969 sites of them were novel SNPs, indicating these SNPs provide a vital complement for the variant database. Moreover, we also phased more than 99% heterozygous SNPs also supported by linked-reads and CCS data. This work provided an integrated Asians SNV and indel benchmark for the further basic studies and precision medicine.

genomics↗

bioRxiv2019

Mesenchymal stem cells restore local microenvironment and systemically suppress leukemia via reprogramming macrophages

Bone marrow (BM) mesenchymal stem cells (MSCs) are critical components of the BM microenvironment and play an essential role in supporting hematopoiesis. Dysfunction of MSCs is associated with the impaired BM microenvironment that promotes leukemia development. However, whether and how restoration of the impaired BM microenvironment can inhibit leukemia development remain unknown. Using an established leukemia model and the RNA-seq analysis, we discovered functional degeneration of MSCs during leukemia progression. Importantly, intra-BM instead of systemic transfusion of donor healthy MSCs restored the BM microenvironment, thus systemically altering cytokine expression patterns, improving normal hematopoiesis, reducing tumor burden, and ultimately prolonging survival of the leukemia-bearing mice. Donor MSC treatment restored the function of host MSCs and reprogrammed host macrophages to fulfill tissue-repair function. Transfusion of MSC-reprogrammed macrophages largely recapitulated the therapeutic effects of MSCs. Further, we found that donor MSCs reprogrammed macrophages to reduce leukemia burden through autocrine of IL-6. Taken together, our study reveals that donor MSCs reprogram host macrophages to restore the BM microenvironment and inhibit leukemia development, thus offering rationales for local MSC administration as a potentially effective therapy for leukemia.\n\nKey PointsKey Point 1: Intra-BM transfusion of MSCs restores the BM microenvironment, improves thrombopoiesis, and suppresses MDS/MPN initiated by Nras mutation.\n\nKey Point 2: Donor MSCs reprogram macrophages to restore the BM microenvironment, improve thrombopoiesis, and suppress leukemia.

cancer biology↗

bioRxiv2019

AirSurf-Lettuce: an aerial image analysis platform for ultra-scale field phenotyping and precision agriculture using computer vision and deep learning

Aerial imagery is regularly used by farmers and growers to monitor crops during the growing season. To extract meaningful phenotypic information from large-scale aerial images collected regularly from the field, high-throughput analytic solutions are required, which not only produce high-quality measures of key crop traits, but also support agricultural practitioners to make reliable management decisions of their crops. Here, we report AirSurf-Lettuce, an automated and open-source aerial image analysis platform that combines modern computer vision, up-to-date machine learning, and modular software engineering to measure yield-related phenotypes of millions of lettuces across the field. Utilising ultra-large normalized difference vegetation index (NDVI) images acquired by fixed-wing light aircrafts together with a deep-learning classifier trained with over 100,000 labelled lettuce signals, the platform is capable of scoring and categorising iceberg lettuces with high accuracy (>98%). Furthermore, novel analysis functions have been developed to map lettuce size distribution in the field, based on which global positioning system (GPS) tagged harvest regions can be derived to enable growers and farmers precise harvest strategies and marketability estimates before the harvest.

bioinformatics↗