A Lightweight and Robust Framework for Circulating Genetically Abnormal Cells (CACs) Identification Using 4-Color Fluorescence In Situ Hybridization (FISH) Image and Deep Refined Learning.

Circulating genetically abnormal cells (CACs) constitute an important biomarker for cancer diagnosis and prognosis. This biomarker offers high safety, low cost, and high repeatability, which can serve as a key reference in clinical diagnosis. These cells are identified by counting fluorescence signals using 4-color fluorescence in situ hybridization (FISH) technology, which has a high level of stability, sensitivity, and specificity. However, there are some challenges in CACs identification, due to the difference in the morphology and intensity of staining signals. In this concern, we developed a deep learning network (FISH-Net) based on 4-color FISH image for CACs identification. Firstly, a lightweight object detection network based on the statistical information of signal size was designed to improve the clinical detection rate. Secondly, the rotated Gaussian heatmap with a covariance matrix was defined to standardize the staining signals with different morphologies. Then, the heatmap refinement model was proposed to solve the fluorescent noise interference of 4-color FISH image. Finally, an online repetitive training strategy was used to improve the model's feature extraction ability for hard samples (i.e., fracture signal, weak signal, and adjacent signals). The results showed that the precision was superior to 96%, and the sensitivity was higher than 98%, for fluorescent signal detection. Additionally, validation was performed using the clinical samples of 853 patients from 10 centers. The sensitivity was 97.18% (CI 96.72-97.64%) for CACs identification. The number of parameters of FISH-Net was 2.24 M, compared to 36.9 M for the popularly used lightweight network (YOLO-V7s). The detection speed was about 800 times greater than that of a pathologist. In summary, the proposed network was lightweight and robust for CACs identification. It could greatly increase the review accuracy, enhance the efficiency of reviewers, and reduce the review turnaround time during CACs identification.

Response Surface Methodology (RSM) Mediated Optimization of Medium Components for Mycelial Growth and Metabolites Production of Streptomyces alfalfae XN-04.

Streptomyces alfalfae XN-04 has been reported for the production of antifungal metabolites effectively to control Fusarium wilt of cotton, caused by Fusarium oxysporum f. sp. vasinfectum (Fov). In this study, we used integrated statistical experimental design methods to investigate the optimized liquid fermentation medium components of XN-04, which can significantly increase the antifungal activity and biomass of XN-04. Seven variables, including soluble starch, KNO3, soybean cake powder, K2HPO4, MgSO4·7H2O, CaCO3 and FeSO4·7H2O, were identified as the best ingredients based on one-factor-at-a-time (OFAT) method. The results of Plackett-Burman Design (PBD) showed that soluble starch, soybean cake powder and K2HPO4 were the most significant variables among the seven variables. The steepest climbing experiment and response surface methodology (RSM) were performed to determine the interactions among these three variables and fine-tune the concentrations. The optimal compositions of medium were as follows: soluble starch (26.26 g/L), KNO3 (1.00 g/L), soybean cake powder (23.54 g/L), K2HPO4 (0.27 g/L), MgSO4·7H2O (0.50 g/L), CaCO3 (1.00 g/L) and FeSO4·7H2O (0.10 g/L). A verification experiment was then carried out under the optimized conditions, and the results revealed the mycelial dry weight of S. alfalfae XN-04 reaching 6.61 g/L. Compared with the initial medium, a 7.47-fold increase in the biomass was achieved using the optimized medium. Moreover, the active ingredient was purified from the methanol extract of S. alfalfae XN-04 mycelium and then identified as roflamycoin (a polyene macrolide antibiotic). The results may provide new insights into the development of S. alfalfae XN-04 fermentation process and the control of the Fusarium wilt of cotton and other plant diseases.

Activation of the VQ Motif-Containing Protein Gene VQ28 Compromised Nonhost Resistance of Arabidopsis thaliana to Phytophthora Pathogens.

Nonhost resistance refers to resistance of a plant species to all genetic variants of a non-adapted pathogen. Such resistance has the potential to become broad-spectrum and durable crop disease resistance. We previously employed Arabidopsis thaliana and a forward genetics approach to identify plant mutants susceptible to the nonhost pathogen Phytophthora sojae, which resulted in identification of the T-DNA insertion mutant esp1 (enhanced susceptibility to Phytophthora). In this study, we report the identification of VQ motif-containing protein 28 (VQ28), whose expression was highly up-regulated in the mutant esp1. Stable transgenic A. thaliana plants constitutively overexpressing VQ28 compromised nonhost resistance (NHR) against P. sojae and P. infestans, and supported increased infection of P. parasitica. Transcriptomic analysis showed that overexpression of VQ28 resulted in six differentially expressed genes (DEGs) that are involved in the response to abscisic acid (ABA). High performance liquid chromatography-mass spectrometry (HPLC-MS) detection showed that the contents of endogenous ABA, salicylic acid (SA), and jasmonate (JA) were enriched in VQ28 overexpression lines. These findings suggest that overexpression of VQ28 may lead to an imbalance in plant hormone homeostasis. Furthermore, transient overexpression of VQ28 in Nicotiana benthamiana rendered plants more susceptible to Phytophthora pathogens. Deletion mutant analysis showed that the C-terminus and VQ-motif were essential for plant susceptibility. Taken together, our results suggest that VQ28 negatively regulates plant NHR to Phytophthora pathogens.

An efficient fluorescence in situ hybridization (FISH)-based circulating genetically abnormal cells (CACs) identification method based on Multi-scale MobileNet-YOLO-V4.

Background: Circulating tumor cells (CTCs) acting as "liquid biopsy" of cancer are cells that have been shed from the primary tumor, which cause the development of a secondary tumor in a distant organ site, leading to cancer metastasis. Recent research suggests that CTCs with abnormalities in gene copy numbers in mononuclear cell-enriched peripheral blood samples, namely circulating genetically abnormal cells (CACs), could be used as a non-invasive decision tool to detect patients with benign pulmonary nodules. Such cells are identified by counting the fluorescence signals of fluorescence in situ hybridization (FISH). However, owing to the rarity of CACs in the blood, identification of CACs using this technique is time-consuming and is a drawback of this method. Methods: This study has proposed an efficient and automatic FISH-based CACs identification approach which is based on a combination of the high accuracy of You Only Look Once (YOLO)-V4 and the lightweight and rapidness of MobileNet-V3. The backbone of YOLO-V4 was replaced with MobileNet-V3 to improve the detection efficiency and prevent overfitting, and the architecture of YOLO-V4 was optimized by utilizing a new feature map with a larger scale to enable the enhanced detection ability for small targets. Results: We trained and tested the proposed model using a dataset containing more than 7,000 cells based on five-fold cross-validation. All the images in the dataset were 2,448×2,048 (pixels) in size. The number of cells in each image was >70. The accuracy of four-color fluorescence signals detection for our proposed model were all approximately 98%, and the mean average precision (mAP) were close to 100%. The final outcome of the developed method was the type of cells, i.e., normal cells, CACs, gaining cells or deletion cells. The method had a CACs identification accuracy of 93.86% (similar to an expert pathologist), and a detection speed that was about 500 times greater than that of a pathologist. Conclusions: The developed method could greatly increase the review accuracy, enhance the efficiency of reviewers, and reduce the review turnaround time during CACs identification.

Evaluation of the Biocontrol Potential of Purpureocillium lilacinum QLP12 against Verticillium dahliae in Eggplant.

A fungus with broad spectrum antifungal activity was isolated from the soil in Qinling Mountain, Shaanxi Province, in China. The fungus was identified as Purpureocillium lilacinum based on ITS rDNA gene analysis. The strain, coded as QLP12, showed high inhibition activity on fungal mycelium growth in vitro, especially to Mucor piriformis, Trichothecium roseum, Rhizoctonia solani, and Verticillium dahliae, and its potential for biocontrol efficacy of eggplant. Verticillium wilt disease caused by Verticillium dahliae among 10 fungal species tested was explored. In greenhouse experiments, QLP12 showed an excellent growth-promoting effect on eggplant seed germination (76.7%), bud growth (79.4%), chlorophyll content (47.83%), root activity (182.02%), and so on. QLP12 can colonize the eggplant interior and also develop in rhizosphere soil. In greenhouse, the incidence of Verticillium wilt decreased by 83.82% with pretreated QLP12 fermentation broth in the soil. In the field, QLP12 showed prominent biocontrol effects on Verticillium wilt by reducing the disease index over the whole growth period, a decline of 40.1%. This study showed that the strain QLP12 is not only an effective biocontrol agent for controlling Verticillium wilt of eggplant, but also a plant growth-promoting fungus that deserves to be further developed.