A multi-layer perceptron-based approach for early detection of BSR disease in oil palm trees using hyperspectral images.

Basal Stem Rot (BSR) disease caused by Ganoderma boninense is identified as the biggest threat in oil palm industry in Malaysia, resulting in significant yield losses. Effective BSR disease detection is important for plantation management to ensure stable palm oil production. Existing method is done by experience personnel, via visual inspection it is very time consuming. Rapid development of unmanned aerial vehicle (UAV) and machine learning has the potential to address this issue with higher efficiency. This paper proposed a new framework to automate BSR disease detection with UAV images to improve time efficiency and automate detection process. The proposed method has two steps, first hyperspectral image (HSI) pre-processing, followed by artificial neural network disease detection. Multilayer-Perceptron model is introduced to learn spectral features from different infection stages. The model is trained with ground truth collected by trained surveyors. The HSI sample size consists of 2 healthy trees, 5 Stage A (mild infection), 5 Stage B (moderate infection), and 3 Stage C (severe infection). Performance is examined with support vector machine (SVM), 1 dimensional convolutional network (1D CNN), and several vegetation indices, namely Normalized Difference Vegetation Index (NDVI), Normalized Difference Red Edge (NDRE), Optimised Soil-Adjusted Vegetation Index (OSAVI), and Merris Terrestrial Chlorophyll Index (MTCI). All machine learning algorithms can segregate infection stages, MLP modal had a highest overall accuracy 86.67%, compared to SVM and 1D CNN at 66.67% and 73.33%. Whereas for vegetation index, it can only detect Stage C tree, and not able to differentiate between Healthy, Stage A and Stage B tree. In term of computational cost, MLP modal had balance performance with moderate training time, but faster inference time. It demonstrates effectiveness on BSR disease detection, even at early infection stage.

Draft genome assembly dataset of the Basidiomycete pathogenic fungus, Ganoderma boninense.

Ganoderma boninense is a soil-borne Basidiomycete pathogenic fungus that eminent as the key causal of devastating disease in oil palm, named basal stem rot. Being a threat to sustainable palm oil production, it is essential to comprehend the fundamental view of this fungus. However, there is gap of information due to its limited number of genome sequence that is available for this pathogenic fungus. This implies the hitches in performing biological research to unravel the mechanism underlying the pathogen attack in oil palm. Therefore, here we report a dataset of draft genome of G. boninense that was sequenced using Illumina Hiseq 2000. The raw reads were deposited into NCBI database (SRX7136614 and SRX7136615) and can be accessed via Bioproject accession number PRJNA503786.

Transcriptomic data of mature oil palm basal trunk tissue infected with Ganoderma boninense.

To date, Ganoderma boninense is known to be the causal agent of basal stem rot (BSR) disease in oil palm (Elaeis guineensis). This disease causes rotting in the roots, basal and upper stem of oil palm. Infection causes progressive destruction of the basal tissues at the oil palm trunk and internal dry rotting, particularly at the intersection between the bole and trunk. Molecular responses of oil palm during infection are not well study although this information is crucial to strategize effective measures to control or eliminate BSR. Here we report three sets of transcriptome data from samples of near-rot section of basal stem tissue of oil palm tree infected with G. boninense (IPIT), healthy section of basal stem tissue of the same G. boninense infected palm (IPHT) and the healthy section of basal stem tissue of the healthy palm (HPHT). The raw reads were deposited into NCBI database and can be accessed via BioProject accession number PRJNA530030.

Natural Variation in Freezing Tolerance and Cold Acclimation Response in Arabidopsis thaliana and Related Species.

During low-temperature exposure, temperate plant species increase their freezing tolerance in a process termed cold acclimation. The molecular mechanisms involved in cold acclimation have been mostly investigated in Arabidopsis thaliana. In addition, other Brassicaceae species related to A. thaliana have been employed in recent years to study plant stress responses on a phylogenetically broader basis and in some cases with extremophile species with a much higher stress tolerance. In this paper, we briefly summarize cold acclimation responses in A. thaliana and current knowledge about cold acclimation in A. thaliana relatives with special emphasis on Eutrema salsugineum and two closely related Thellungiella species. We then present a transcriptomic and metabolomic analysis of cold acclimation in five A. thaliana and two E. salsugineum accessions that differ widely in their freezing tolerance. Differences in the cold responses of the two species are discussed.

About Ganoderma boninense in oil palm plantations of Sumatra and peninsular Malaysia: Ancient population expansion, extensive gene flow and large scale dispersion ability.

Wood rot fungi form one of the main classes of phytopathogenic fungus. The group includes many species, but has remained poorly studied. Many species belonging to the Ganoderma genus are well known for causing decay in a wide range of tree species around the world. Ganoderma boninense, causal agent of oil palm basal stem rot, is responsible for considerable yield losses in Southeast Asian oil palm plantations. In a large-scale sampling operation, 357 sporophores were collected from oil palm plantations spread over peninsular Malaysia and Sumatra and genotyped using 11 SSR markers. The genotyping of these samples made it possible to investigate the population structure and demographic history of G. boninense across the oldest known area of interaction between oil palm and G. boninense. Results show that G. boninense possesses a high degree of genetic diversity and no detectable genetic structure at the scale of Sumatra and peninsular Malaysia. The fact that few duplicate genotypes were found in several studies including this one supports the hypothesis of spore dispersal in the spread of G. boninense. Meanwhile, spatial autocorrelation analysis shows that G. boninense is able to disperse across both short and long distances. These results bring new insight into mechanisms by which G. boninense spreads in oil palm plantations. Finally, the use of approximate Bayesian computation (ABC) modelling indicates that G. boninense has undergone a demographic expansion in the past, probably before the oil palm was introduced into Southeast Asia.

Salt stress responses in a geographically diverse collection of Eutrema/Thellungiella spp. accessions.

Salinity strongly impairs plant growth and development. Natural genetic variation can be used to dissect complex traits such as plant salt tolerance. We used 16 accessions of the halophytic species Eutrema salsugineum (previously called Thellungiella salsuginea (Pallas) O.E.Schulz, Thellungiella halophila (C.A.Meyer) O.E. Schulz and Thellungiella botschantzevii D.A.German to investigate their natural variation in salinity tolerance. Although all accessions showed survival and growth up to 700mM NaCl in hydroponic culture, their relative salt tolerance varied considerably. All accessions accumulated the compatible solutes proline, sucrose, glucose and fructose and the polyamines putrescine and spermine. Relative salt tolerance was not correlated with the content of any of the investigated solutes. We compared the metabolomes and transcriptomes of Arabidopsis thaliana (L. Heynh.) Col-0 and E. salsugineum Yukon under control and salt stress conditions. Higher content of several metabolites in Yukon compared with Col-0 under control conditions indicated metabolic pre-adaptation to salinity in the halophyte. Most metabolic salt responses in Yukon took place at 200mM NaCl, whereas few additional changes were observed between 200 and 500mM. The opposite trend was observed for the transcriptome, with only little overlap between salt-regulated genes in the two species. In addition, only about half of the salt-regulated Yukon unigenes had orthologues in Col-0.

Time-dependent deacclimation after cold acclimation in Arabidopsis thaliana accessions.

During low temperature exposure, Arabidopsis thaliana and many other plants from temperate climates increase in freezing tolerance in a process termed cold acclimation. However, the correct timing and rate of deacclimation, resulting in loss of freezing tolerance and initiation of growth is equally important for plant fitness and survival. While the molecular basis of cold acclimation has been investigated in detail, much less information is available about deacclimation. We have characterized the responses of 10 natural accessions of Arabidopsis thaliana that vary widely in their freezing tolerance, to deacclimation conditions. Sugar, proline and transcript levels declined sharply over three days in all accessions after transfer of cold acclimated plants to ambient temperatures, while freezing tolerance only declined in tolerant accessions. Correlations between freezing tolerance and the expression levels of COR genes and the content of glucose, fructose and sucrose, as well as many correlations among transcript and solute levels, that were highly significant in cold acclimated plants, were lost during deacclimation. Other correlations persisted, indicating that after three days of deacclimation, plant metabolism had not completely reverted back to the non-acclimated state. These data provide the basis for further molecular and genetic studies to unravel the regulation of deacclimation.

Transcriptome sequencing and microarray design for functional genomics in the extremophile Arabidopsis relative Thellungiella salsuginea (Eutrema salsugineum).

BACKGROUND: Most molecular studies of plant stress tolerance have been performed with Arabidopsis thaliana, although it is not particularly stress tolerant and may lack protective mechanisms required to survive extreme environmental conditions. Thellungiella salsuginea has attracted interest as an alternative plant model species with high tolerance of various abiotic stresses. While the T. salsuginea genome has recently been sequenced, its annotation is still incomplete and transcriptomic information is scarce. In addition, functional genomics investigations in this species are severely hampered by a lack of affordable tools for genome-wide gene expression studies. RESULTS: Here, we report the results of Thellungiella de novo transcriptome assembly and annotation based on 454 pyrosequencing and development and validation of a T. salsuginea microarray. ESTs were generated from a non-normalized and a normalized library synthesized from RNA pooled from samples covering different tissues and abiotic stress conditions. Both libraries yielded partially unique sequences, indicating their necessity to obtain comprehensive transcriptome coverage. More than 1 million sequence reads were assembled into 42,810 unigenes, approximately 50% of which could be functionally annotated. These unigenes were compared to all available Thellungiella genome sequence information. In addition, the groups of Late Embryogenesis Abundant (LEA) proteins, Mitogen Activated Protein (MAP) kinases and protein phosphatases were annotated in detail. We also predicted the target genes for 384 putative miRNAs. From the sequence information, we constructed a 44 k Agilent oligonucleotide microarray. Comparison of same-species and cross-species hybridization results showed superior performance of the newly designed array for T. salsuginea samples. The developed microarrays were used to investigate transcriptional responses of T. salsuginea and Arabidopsis during cold acclimation using the MapMan software. CONCLUSIONS: This study provides the first comprehensive transcriptome information for the extremophile Arabidopsis relative T. salsuginea. The data constitute a more than three-fold increase in the number of publicly available unigene sequences and will greatly facilitate genome annotation. In addition, we have designed and validated the first genome-wide microarray for T. salsuginea, which will be commercially available. Together with the publicly available MapMan software this will become an important tool for functional genomics of plant stress tolerance.

Comparison of freezing tolerance, compatible solutes and polyamines in geographically diverse collections of Thellungiella sp. and Arabidopsis thaliana accessions.

BACKGROUND: Thellungiella has been proposed as an extremophile alternative to Arabidopsis to investigate environmental stress tolerance. However, Arabidopsis accessions show large natural variation in their freezing tolerance and here the tolerance ranges of collections of accessions in the two species were compared. RESULTS: Leaf freezing tolerance of 16 Thellungiella accessions was assessed with an electrolyte leakage assay before and after 14 days of cold acclimation at 4°C. Soluble sugars (glucose, fructose, sucrose, raffinose) and free polyamines (putrescine, spermidine, spermine) were quantified by HPLC, proline photometrically. The ranges in nonacclimated freezing tolerance completely overlapped between Arabidopsis and Thellungiella. After cold acclimation, some Thellungiella accessions were more freezing tolerant than any Arabidopsis accessions. Acclimated freezing tolerance was correlated with sucrose levels in both species, but raffinose accumulation was lower in Thellungiella and only correlated with freezing tolerance in Arabidopsis. The reverse was true for leaf proline contents. Polyamine levels were generally similar between the species. Only spermine content was higher in nonacclimated Thellungiella plants, but decreased during acclimation and was negatively correlated with freezing tolerance. CONCLUSION: Thellungiella is not an extremophile with regard to freezing tolerance, but some accessions significantly expand the range present in Arabidopsis. The metabolite data indicate different metabolic adaptation strategies between the species.

Analysis and functional annotation of expressed sequence tags (ESTs) from multiple tissues of oil palm (Elaeis guineensis Jacq.).

BACKGROUND: Oil palm is the second largest source of edible oil which contributes to approximately 20% of the world's production of oils and fats. In order to understand the molecular biology involved in in vitro propagation, flowering, efficient utilization of nitrogen sources and root diseases, we have initiated an expressed sequence tag (EST) analysis on oil palm. RESULTS: In this study, six cDNA libraries from oil palm zygotic embryos, suspension cells, shoot apical meristems, young flowers, mature flowers and roots, were constructed. We have generated a total of 14537 expressed sequence tags (ESTs) from these libraries, from which 6464 tentative unique contigs (TUCs) and 2129 singletons were obtained. Approximately 6008 of these tentative unique genes (TUGs) have significant matches to the non-redundant protein database, from which 2361 were assigned to one or more Gene Ontology categories. Predominant transcripts and differentially expressed genes were identified in multiple oil palm tissues. Homologues of genes involved in many aspects of flower development were also identified among the EST collection, such as CONSTANS-like, AGAMOUS-like (AGL)2, AGL20, LFY-like, SQUAMOSA, SQUAMOSA binding protein (SBP) etc. Majority of them are the first representatives in oil palm, providing opportunities to explore the cause of epigenetic homeotic flowering abnormality in oil palm, given the importance of flowering in fruit production. The transcript levels of two flowering-related genes, EgSBP and EgSEP were analysed in the flower tissues of various developmental stages. Gene homologues for enzymes involved in oil biosynthesis, utilization of nitrogen sources, and scavenging of oxygen radicals, were also uncovered among the oil palm ESTs. CONCLUSION: The EST sequences generated will allow comparative genomic studies between oil palm and other monocotyledonous and dicotyledonous plants, development of gene-targeted markers for the reference genetic map, design and fabrication of DNA array for future studies of oil palm. The outcomes of such studies will contribute to oil palm improvements through the establishment of breeding program using marker-assisted selection, development of diagnostic assays using gene targeted markers, and discovery of candidate genes related to important agronomic traits of oil palm.