Increased CD16a (FcγRIIIA) Expression in The Tumor Microenvironment of Atypical Neurofibromatous Neoplasms of Uncertain Biologic Potential May Be Associated with Progression from Neurofibromas to Atypical Neurofibromas.

Neurofibroma (NF) is a benign tumor in the peripheral nervous system, but it can infiltrate around structures and cause functional impairment and disfigurement. We incidentally found that the expression of CD16a (Fc gamma receptor IIIA) was increased in NFs compared to in non-neoplastic nerves and hypothesized that CD16 could be relevant to NF progression. We evaluated the expressions of CD16a, CD16b, CD68, TREM2, Galectin-3, S-100, and SOX10 in 38 cases of neurogenic tumors (NF, n = 18; atypical neurofibromatous neoplasm of uncertain biologic potential (ANNUBP), n = 14; and malignant peripheral nerve sheath tumor (MPNST), n = 6) by immunohistochemical staining. In the tumor microenvironment (TME) of the ANNUBPs, CD16a and CD16b expression levels had increased more than in the NFs or MPNSTs. CD68 and Galectin-3 expression levels in the ANNUBPs were higher than in the MPNSTs. Dual immunohistochemical staining showed an overlapping pattern for CD16a and CD68 in TME immune cells. Increased CD16a expression was detected in the ANNUBPs compared to the NFs but decreased with malignant progression. The CD16a overexpression with CD68 positivity in the ANNUBPs potentially reflects that the TME immune modulation could be associated with NF progression to an ANNUBP. Further studies should explore the role of CD16a in immunomodulation for accelerating NF growth.

deepGBLUP: joint deep learning networks and GBLUP framework for accurate genomic prediction of complex traits in Korean native cattle.

BACKGROUND: Genomic prediction has become widespread as a valuable tool to estimate genetic merit in animal and plant breeding. Here we develop a novel genomic prediction algorithm, called deepGBLUP, which integrates deep learning networks and a genomic best linear unbiased prediction (GBLUP) framework. The deep learning networks assign marker effects using locally-connected layers and subsequently use them to estimate an initial genomic value through fully-connected layers. The GBLUP framework estimates three genomic values (additive, dominance, and epistasis) by leveraging respective genetic relationship matrices. Finally, deepGBLUP predicts a final genomic value by summing all the estimated genomic values. RESULTS: We compared the proposed deepGBLUP with the conventional GBLUP and Bayesian methods. Extensive experiments demonstrate that the proposed deepGBLUP yields state-of-the-art performance on Korean native cattle data across diverse traits, marker densities, and training sizes. In addition, they show that the proposed deepGBLUP can outperform the previous methods on simulated data across various heritabilities and quantitative trait loci (QTL) effects. CONCLUSIONS: We introduced a novel genomic prediction algorithm, deepGBLUP, which successfully integrates deep learning networks and GBLUP framework. Through comprehensive evaluations on the Korean native cattle data and simulated data, deepGBLUP consistently achieved superior performance across various traits, marker densities, training sizes, heritabilities, and QTL effects. Therefore, deepGBLUP is an efficient method to estimate an accurate genomic value. The source code and manual for deepGBLUP are available at https://github.com/gywns6287/deepGBLUP .

A genome-wide association study for eumelanin pigmentation in chicken plumage using a computer vision approach.

Chicken plumage colouration is an important trait related to productivity in poultry industry. Therefore, the genetic basis for pigmentation in chicken plumage is an area of great interest. However, the colour trait is generally regarded as a qualitative trait and representing colour variations is difficult. In this study, we developed a method to quantify and classify colour using an F2 population crossed from two pure lines: White Leghorn and the Korean indigenous breed Yeonsan Ogye. Using red, green, and blue values in the cropped body region, we identified significant genomic regions on chromosomes 33:3 160 480-7 447 197 and Z:78 748 287-79 173 793. Furthermore, we identified two potential candidate genes (PMEL and MTAP) that might have significant effects on melanin-based plumage pigmentation. Our study presents a new phenotyping method using a computer vision approach and provides new insights into the genetic basis of melanin-based feather colouration in chickens.

Use of a graph neural network to the weighted gene co-expression network analysis of Korean native cattle.

In the general framework of the weighted gene co-expression network analysis (WGCNA), a hierarchical clustering algorithm is commonly used to module definition. However, hierarchical clustering depends strongly on the topological overlap measure. In other words, this algorithm may assign two genes with low topological overlap to different modules even though their expression patterns are similar. Here, a novel gene module clustering algorithm for WGCNA is proposed. We develop a gene module clustering network (gmcNet), which simultaneously addresses single-level expression and topological overlap measure. The proposed gmcNet includes a "co-expression pattern recognizer" (CEPR) and "module classifier". The CEPR incorporates expression features of single genes into the topological features of co-expressed ones. Given this CEPR-embedded feature, the module classifier computes module assignment probabilities. We validated gmcNet performance using 4,976 genes from 20 native Korean cattle. We observed that the CEPR generates more robust features than single-level expression or topological overlap measure. Given the CEPR-embedded feature, gmcNet achieved the best performance in terms of modularity (0.261) and the differentially expressed signal (27.739) compared with other clustering methods tested. Furthermore, gmcNet detected some interesting biological functionalities for carcass weight, backfat thickness, intramuscular fat, and beef tenderness of Korean native cattle. Therefore, gmcNet is a useful framework for WGCNA module clustering.

MSENet: Marbling score estimation network for automated assessment of Korean beef.

A novel beef marbling score estimation algorithm is proposed in this work. We develop a marbling score estimation network (MSENet), which simultaneously performs marbling score estimation and eye muscle area segmentation. The proposed MSENet includes a segmentation module, a bridge block, and a marbling scoring module. The segmentation module segments out eye muscle area from input images and the scoring module estimates marbling scores of input beef images. The proposed bridge block conveys the segmentation information for eye muscle area from the segmentation module to the scoring module. MSENet is trained on a new large-scale beef image dataset (more than 10,000), called the Hanwoo dataset. Experimental results demonstrate that the proposed MSENet achieves the reliable score estimation performance on the Hanwoo Dataset and the proposed bridge block effectively improves the estimation accuracy (Pearson's correlation coefficient: 0.952, Mean absolute error: 0.543).

Blind and Compact Denoising Network Based on Noise Order Learning.

A lightweight blind image denoiser, called blind compact denoising network (BCDNet), is proposed in this paper to achieve excellent trade-offs between performance and network complexity. With only 330K parameters, the proposed BCDNet is composed of the compact denoising network (CDNet) and the guidance network (GNet). From a noisy image, GNet extracts a guidance feature, which encodes the severity of the noise. Then, using the guidance feature, CDNet filters the image adaptively according to the severity to remove the noise effectively. Moreover, by reducing the number of parameters without compromising the performance, CDNet achieves denoising not only effectively but also efficiently. Experimental results show that the proposed BCDNet yields state-of-the-art or competitive denoising performances on various datasets while requiring significantly fewer parameters.

Light Field Super-Resolution via Adaptive Feature Remixing.

A novel light field super-resolution algorithm to improve the spatial and angular resolutions of light field images is proposed in this work. We develop spatial and angular super-resolution (SR) networks, which can faithfully interpolate images in the spatial and angular domains regardless of the angular coordinates. For each input image, we feed adjacent images into the SR networks to extract multi-view features using a trainable disparity estimator. We concatenate the multi-view features and remix them through the proposed adaptive feature remixing (AFR) module, which performs channel-wise pooling. Finally, the remixed feature is used to augment the spatial or angular resolution. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art algorithms on various light field datasets. The source codes and pre-trained models are available at https://github.com/keunsoo-ko/ LFSR-AFR.

Identification of Target Chicken Populations by Machine Learning Models Using the Minimum Number of SNPs.

A marker combination capable of classifying a specific chicken population could improve commercial value by increasing consumer confidence with respect to the origin of the population. This would facilitate the protection of native genetic resources in the market of each country. In this study, a total of 283 samples from 20 lines, which consisted of Korean native chickens, commercial native chickens, and commercial broilers with a layer population, were analyzed to determine the optimal marker combination comprising the minimum number of markers, using a 600 k high-density single nucleotide polymorphism (SNP) array. Machine learning algorithms, a genome-wide association study (GWAS), linkage disequilibrium (LD) analysis, and principal component analysis (PCA) were used to distinguish a target (case) group for comparison with control chicken groups. In the processing of marker selection, a total of 47,303 SNPs were used for classifying chicken populations; 96 LD-pruned SNPs (50 SNPs per LD block) served as the best marker combination for target chicken classification. Moreover, 36, 44, and 8 SNPs were selected as the minimum numbers of markers by the AdaBoost (AB), Random Forest (RF), and Decision Tree (DT) machine learning classification models, which had accuracy rates of 99.6%, 98.0%, and 97.9%, respectively. The selected marker combinations increased the genetic distance and fixation index (Fst) values between the case and control groups, and they reduced the number of genetic components required, confirming that efficient classification of the groups was possible by using a small number of marker sets. In a verification study including additional chicken breeds and samples (12 lines and 182 samples), the accuracy did not significantly change, and the target chicken group could be clearly distinguished from the other populations. The GWAS, PCA, and machine learning algorithms used in this study can be applied efficiently, to determine the optimal marker combination with the minimum number of markers that can distinguish the target population among a large number of SNP markers.

Video Stabilization Based on Feature Trajectory Augmentation and Selection and Robust Mesh Grid Warping.

We propose a video stabilization algorithm, which extracts a guaranteed number of reliable feature trajectories for robust mesh grid warping. We first estimate feature trajectories through a video sequence and transform the feature positions into rolling-free smoothed positions. When the number of the estimated trajectories is insufficient, we generate virtual trajectories by augmenting incomplete trajectories using a low-rank matrix completion scheme. Next, we detect feature points on a large moving object and exclude them so as to stabilize camera movements, rather than object movements. With the selected feature points, we set a mesh grid on each frame and warp each grid cell by moving the original feature positions to the smoothed ones. For robust warping, we formulate a cost function based on the reliability weights of each feature point and each grid cell. The cost function consists of a data term, a structure-preserving term, and a regularization term. By minimizing the cost function, we determine the robust mesh grid warping and achieve the stabilization. Experimental results demonstrate that the proposed algorithm reconstructs videos more stably than the conventional algorithms.