Machine learning for image-based multi-omics analysis of leaf veins.

Veins are a critical component of the plant growth and development system, playing an integral role in supporting and protecting leaves, as well as transporting water, nutrients, and photosynthetic products. A comprehensive understanding of the form and function of veins requires a dual approach that combines plant physiology with cutting-edge image recognition technology. The latest advancements in computer vision and machine learning have facilitated the creation of algorithms that can identify vein networks and explore their developmental progression. Here, we review the functional, environmental, and genetic factors associated with vein networks, along with the current status of research on image analysis. In addition, we discuss the methods of venous phenotype extraction and multi-omics association analysis using machine learning technology, which could provide a theoretical basis for improving crop productivity by optimizing the vein network architecture.

MC-GCN: A Multi-Scale Contrastive Graph Convolutional Network for Unconstrained Face Recognition With Image Sets.

In this paper, a Multi-scale Contrastive Graph Convolutional Network (MC-GCN) method is proposed for unconstrained face recognition with image sets, which takes a set of media (orderless images and videos) as a face subject instead of single media (an image or video). Due to factors such as illumination, posture, media source, etc., there are huge intra-set variances in a face set, and the importance of different face prototypes varies considerably. How to model the attention mechanism according to the relationship between prototypes or images in a set is the main content of this paper. In this work, we formulate a framework based on graph convolutional network (GCN), which considers face prototypes as nodes to build relations. Specifically, we first present a multi-scale graph module to learn the relationship between prototypes at multiple scales. Moreover, a Contrastive Graph Convolutional (CGC) block is introduced to build attention control model, which focuses on those frames with similar prototypes (contrastive information) between pair of sets instead of simply evaluating the frame quality. The experiments on IJB-A, YouTube Face, and an animal face dataset clearly demonstrate that our proposed MC-GCN outperforms the state-of-the-art methods significantly.

Maize-IAS: a maize image analysis software using deep learning for high-throughput plant phenotyping.

BACKGROUND: Maize (Zea mays L.) is one of the most important food sources in the world and has been one of the main targets of plant genetics and phenotypic research for centuries. Observation and analysis of various morphological phenotypic traits during maize growth are essential for genetic and breeding study. The generally huge number of samples produce an enormous amount of high-resolution image data. While high throughput plant phenotyping platforms are increasingly used in maize breeding trials, there is a reasonable need for software tools that can automatically identify visual phenotypic features of maize plants and implement batch processing on image datasets. RESULTS: On the boundary between computer vision and plant science, we utilize advanced deep learning methods based on convolutional neural networks to empower the workflow of maize phenotyping analysis. This paper presents Maize-IAS (Maize Image Analysis Software), an integrated application supporting one-click analysis of maize phenotype, embedding multiple functions: (I) Projection, (II) Color Analysis, (III) Internode length, (IV) Height, (V) Stem Diameter and (VI) Leaves Counting. Taking the RGB image of maize as input, the software provides a user-friendly graphical interaction interface and rapid calculation of multiple important phenotypic characteristics, including leaf sheath points detection and leaves segmentation. In function Leaves Counting, the mean and standard deviation of difference between prediction and ground truth are 1.60 and 1.625. CONCLUSION: The Maize-IAS is easy-to-use and demands neither professional knowledge of computer vision nor deep learning. All functions for batch processing are incorporated, enabling automated and labor-reduced tasks of recording, measurement and quantitative analysis of maize growth traits on a large dataset. We prove the efficiency and potential capability of our techniques and software to image-based plant research, which also demonstrates the feasibility and capability of AI technology implemented in agriculture and plant science.

Concurrent adsorption and micro-electrolysis of Cr(VI) by nanoscale zerovalent iron/biochar/Ca-alginate composite.

This study introduced a new approach for simultaneously enhancing Cr(VI) removal performance and mitigating release of dissolved Fe during nanoscale zero-valent iron (nZVI)-mediated reactions. After entrapping nZVI-impregnated biochar (BC) in the matrix of calcium-alginate (CA) bead, the physicochemical characterization of nZVI/BC/CA composites revealed that nZVI/BC particles were embedded inside CA having a spherical shape and several cracks on its outer layer. The multi-functionality of nZVI/BC/CA composites consisting of reductant (nZVI), porous adsorbent (BC), and external screening layer (CA) enhanced the removal of Cr(VI) with the maximum adsorption capacity of 86.4 mg/g (based on the Langmuir isotherm) and little release of dissolved Fe. With the XPS analysis and fitting results of kinetics (pseudo second order) and isotherms (Redlich-Peterson model), plausible removal mechanisms of Cr(VI) were simultaneous adsorption and micro-electrolysis reactions by nZVI/BC/CA composites. The practical applicability of nZVI/BC/CA composites was further demonstrated through the fixed-bed column experiments. These results provide new insights into the design of high-performance engineered biochar for wastewater treatment.

[Dental education for college students based on WeChat public platform].

The authors proposed a model for dental education based on WeChat public platform. In this model, teachers send various kinds of digital teaching information such as PPT，word and video to the WeChat public platform and students share the information for preview before class and differentiate the key-point knowledge from those information for in-depth learning in class. Teachers also send reference materials for expansive learning after class. Questionaire through the WeChat public platform is used to evaluate teaching effect of teachers and improvement may be taken based on the feedback questionnaire. A discussion and interaction based on WeCchat between students and teacher can be aroused on a specific topic to reach a proper solution. With technique development of mobile terminal, mobile class will come true in near future.

STK4 (MST1) deficiency in two siblings with autoimmune cytopenias: A novel mutation.

Combined immunodeficiencies (CIDs) are heterogeneous group of disorders characterized by abrogated/impaired T cell development and/or functions that resulted from diverse genetic defects. In addition to the susceptibility to infections with various microorganisms, the patients may have lymphoproliferation, autoimmunity, inflammation, allergy and malignancy. Recently, three groups have independently reported patients having mutations in STK4 gene that cause a novel autosomal recessive (AR) CID. We describe here two siblings with a novel STK4 mutation identified during the evaluation of a group of patients with features highly overlapping with those of DOCK-8 deficiency, a form of AR hyperimmunoglobulin E syndrome. The patients' clinical features include autoimmune cytopenias, viral skin (molluscum contagiosum and perioral herpetic infection) and bacterial infections, mild onychomycosis, mild atopic and seborrheic dermatitis, lymphopenia (particularly CD4 lymphopenia), and intermittent mild neutropenia. Determination of the underlying defect and reporting the patients are required for the description of the phenotypic spectrum of each immunodeficiency.

IL-12Rß1 deficiency: mutation update and description of the IL12RB1 variation database.

IL-12Rß1 deficiency is an autosomal recessive disorder characterized by predisposition to recurrent and/or severe infections caused by otherwise poorly pathogenic mycobacteria and salmonella. IL-12Rß1 is a receptor chain of both the IL-12 and the IL-23 receptor and deficiency of IL-12Rß1 thus abolishes both IL-12 and IL-23 signaling. IL-12Rß1 deficiency is caused by bi-allelic mutations in the IL12RB1 gene. Mutations resulting in premature stop codons, such as nonsense, frame shift, and splice site mutations, represent the majority of IL-12Rß1 deficiency causing mutations (66%; 46/70). Also every other morbid mutation completely inactivates the IL-12Rß1 protein. In addition to disease-causing mutations, rare and common variations with unknown functional effect have been reported in IL12RB1. All these variants have been deposited in the online IL12RB1 variation database (www.LOVD.nl/IL12RB1). In this article, we review the function of IL-12Rß1 and molecular genetics of human IL12RB1.

Hereditary C1q deficiency: a new family with C1qA deficiency.

Hereditary deficiency of complement component C1q is a rare genetic disorder with susceptibility to recurrent infections with polysaccharide-containing encapsulated microorganisms and a high prevalence of autoimmune diseases, most often systemic lupus erythematosus (SLE). Here, we report a 29-month-old boy who presented with facial rash and history of early death of a sibling with infections, who was found to have a selective deficiency of C1q. The facial rash was composed of patchy erythematous plaques and centrally hypopigmented macules and desquamation. Two siblings had died of severe bacterial infections and his uncle had died of meningitis. Molecular study disclosed a homozygous point mutation in the C1qA chain gene. Five members of the family, including the parents and three healthy siblings, were heterozygous for this mutation.