Computer vision-based phenotyping for improvement of plant productivity: a machine learning perspective.

Employing computer vision to extract useful information from images and videos is becoming a key technique for identifying phenotypic changes in plants. Here, we review the emerging aspects of computer vision for automated plant phenotyping. Recent advances in image analysis empowered by machine learning-based techniques, including convolutional neural network-based modeling, have expanded their application to assist high-throughput plant phenotyping. Combinatorial use of multiple sensors to acquire various spectra has allowed us to noninvasively obtain a series of datasets, including those related to the development and physiological responses of plants throughout their life. Automated phenotyping platforms accelerate the elucidation of gene functions associated with traits in model plants under controlled conditions. Remote sensing techniques with image collection platforms, such as unmanned vehicles and tractors, are also emerging for large-scale field phenotyping for crop breeding and precision agriculture. Computer vision-based phenotyping will play significant roles in both the nowcasting and forecasting of plant traits through modeling of genotype/phenotype relationships.

A constant-time algorithm for finding neighbors in quadtrees.

Quadtrees and linear quadtrees are well-known hierarchical data structures to represent square images of size 2(r) x 2(r). Finding the neighbors of a specific leaf node is a fundamental operation for many algorithms that manipulate quadtree data structures. In quadtrees, finding neighbors takes O(r) computational time for the worst case, where r is the resolution (or height) of a given quadtree. Schrack [1] proposed a constant-time algorithm for finding equal-sized neighbors in linear quadtrees. His algorithm calculates the location codes of equal-sized neighbors; it says nothing, however, about their existence. To ensure their existence, additional checking of the location codes is needed, which usually takes O(r) computational time. In this paper, a new algorithm to find the neighbors of a given leaf node in a quadtree is proposed which requires just O(1) (i.e., constant) computational time for the worst case. Moreover, the algorithm takes no notice of the existence or nonexistence of neighbors. Thus, no additional checking is needed. The new algorithm will greatly reduce the computational complexities of almost all algorithms based on quadtrees.

Colorimetric multiplexed immunoassay using specific aggregation of antigenic peptide-modified luminous nanoparticles.

A rapid immunoassay capable of detecting specific antibodies in one-step procedure is described. Antigenic peptides with cationic (KKKKC) or anionic (DDDDC) pentamer tail were immobilized on luminous nanospheres of 40 nm diameter (Ø) through cystamine and bifunctional linker molecules under various conditions. The numbers of each peptide anchored to a sphere were 5.0 x 10(2) and 0.8-3.8 x 10(3), respectively. A mixture of the antigenic peptides of FAK and c-Myc was immobilized to the spheres with red emission, while that of c-Myc and alpha-catenin was likewise to green spheres. Multiplexed immunoassay was easily achieved by adding the antibodies to a mixed dispersed solution of these spheres under appropriate conditions. Anti-FAK and anti-alpha-catenin antibodies formed aggregates with red and green emissions, respectively. On the other hand, the anti-c-Myc antibody formed aggregates emitting a yellow light. This system enabled us to differentiate three antibodies in one vessel from the definite differences in aggregate color.

Preparation of DNA-modified nanoparticles and preliminary study for colorimetric SNP analysis using their selective aggregations.

DNA-modified nanospheres were prepared by anchoring amino-terminated oligodeoxynucleotides (ODNs) with carboxylates onto a colored polystyrene sphere surface through amido bonds. About 220 ODN molecules were immobilized onto a nanosphere 40 nm in diameter. Preliminary studies using the microspheres with 1 microm diameter reveal that the specificity of hybridization was retained after modification. Three kinds of differently colored (RGB, red/green/blue) nanospheres bearing unique ODNs on their surface were prepared for detecting the p53 gene. Each ODN is complementary to a different part in the 45mer sample that is a part of a conservative region of the p53 gene containing one of the hot spots. In a binary system using spheres R and G, the wild-type 45mer made the aggregates with yellow emission as the result of mixing both colors. The mutant 45mer containing one nucleotide displacement did not give such aggregates with distinct colors. The study of fluorescence resonance energy transfer (FRET) showed that spheres R and G directly contact each other in the aggregates with the wild type. The RGB ternary system gave aggregates with specific colors corresponding to the added ODN samples, wild type or mutant. In addition, in the presence of both samples, all of the spheres formed aggregates with white emission as a consequence of mixing three primary colors of light. This means that the present technique should allow us to conduct an allele analysis.

Colorimetric SNP analysis using oligonucleotide-modified nanoparticles.

A point mutation in the p53 gene has been detected by means of fluorescence microscopy and fluorescent resonance energy transfer (FRET) through sequence selective aggregation of DNA-modified nanoparticles, in which fluorescent dyes were impregnated.