Research on multi-object detection technology for road scenes based on SDG-YOLOv5.

To resolve the challenges of low detection accuracy and inadequate real-time performance in road scene detection, this article introduces the enhanced algorithm SDG-YOLOv5. The algorithm incorporates the SIoU Loss function to accurately predict the angle loss of bounding boxes, ensuring their directionality during regression and improving both regression accuracy and convergence speed. A novel lightweight decoupled heads (DHs) approach is employed to separate the classification and regression tasks, thereby avoiding conflicts between their focus areas. Moreover, the Global Attention Mechanism Group Convolution (GAMGC), a lightweight strategy, is utilized to enhance the network's capability to process additional contextual information, thereby improving the detection of small targets. Extensive experimental analysis on datasets from Udacity Self Driving Car, BDD100K, and KITTI demonstrates that the proposed algorithm achieves improvements in mAP@.5 of 2.2%, 3.4%, and 1.0% over the original YOLOv5, with a detection speed of 30.3 FPS. These results illustrate that the SDG-YOLOv5 algorithm effectively addresses both detection accuracy and real-time performance in road scene detection.

[Retracted] microRNA­363­3p inhibits cell growth and invasion of non­small cell lung cancer by targeting HMGA2.

Following the publication of this paper, it was drawn to the Editor's attention by a concerned reader that certain of the data shown for the Transwell cell migration and invasion assays in Figs. 2C and 4C were strikingly similar to data appearing in different form in another article by different authors at a different research institution. Owing to the fact that the contentious data in the above article were under consideration for publication elsewhere at a similar time to when it was submitted to Molecular Medicine Reports, the Editor has decided that this paper should be retracted from the Journal. The authors were asked for an explanation to account for these concerns, but the Editorial Office did not receive any reply. The Editor apologizes to the readership for any inconvenience caused. [Molecular Medicine Reports 17: 2712­2718, 2018; DOI: 10.3892/mmr.2017.8131].

Genome-Wide Identification and Comprehensive Analysis of the AP2/ERF Gene Family in Pomegranate Fruit Development and Postharvest Preservation.

Pomegranate (Punica granatum L.) is a kind of fruit with significant economic, ecological and health values. AP2/ERF transcription factors belong to a large group of factors mainly found in plants and play key roles in plant growth and development. However, AP2/ERF genes in pomegranate and their implication in development and postharvest preservation have been little described. In this study, 116 PgAP2/ERF genes in pomegranate were identified and renamed based on their chromosomal distributions. Phylogenetic relationship with genes from other species, structures, duplications, annotations, cis-elements in promoter sequences, and protein-protein interaction networks among PgAP2/ERF proteins were comprehensively explored. Expression analysis revealed several PgAP2/ERFs associated with the phenotypes of pomegranate seed hardness, including PgAP2/ERF5, PgAP2/ERF36, PgAP2/ERF58, and PgAP2/ERF86. Subsequent analysis indicated that many differentially expressed PgAP2/ERF genes are potentially important regulators of pomegranate fruit development. Furthermore, expression of more than one-half of PgAP2/ERFs was repressed in 'Tunisian soft seed' pomegranate fruit under low-temperature cold storage. The results showed that 1-MCP implicated in promoting postharvest preservation of 'Tunisian soft seed' pomegranate upregulated the PgAP2/ERF4, PgAP2/ERF15, PgAP2/ERF26, PgAP2/ERF30, PgAP2/ERF35 and PgAP2/ERF45 genes compared to those under low-temperature cold storage. This indicates that these genes are important candidate genes involved in pomegranate postharvest preservation. In summary, the findings of the present study provide an important basis for characterizing the PgAP2/ERF family genes and provide information on the candidate genes involved in pomegranate fruit development and postharvest preservation.

Positioning Performance of a Sub-Arc-Second Micro-Drive Rotary System.

In the macro/micro dual-drive rotary system, the micro-drive system compensates for the position error of the macro-drive system. To realize the sub-arc-second (i.e., level of 1″-0.1″) positioning of the macro/micro dual-drive rotary system, it is necessary to study the positioning performance of the sub-arc-second micro-drive rotary system. In this paper, we designed a sub-arc-second micro-drive rotary system consisting of a PZT (piezoelectric actuator) and a micro rotary mechanism, and used simulation and experimental methods to study the positioning performance of the system. First, the micro-drive rotary system was developed to provide ultra-precise rotary motion. In this system, the PZT has ultrahigh resolution at a level of 0.1 nanometers in linear motion; a micro rotating mechanism was designed according to the composite motion principle of the flexible hinge, which could transform the linear motion of piezoelectric ceramics into rotating motion accurately. Second, the drive performance was analyzed based on the drive performance experiment. Third, kinematics, simulation, and experiments were carried out to analyze the transformation performance of the system. Finally, the positioning performance equation of the system was established based on the two performance equations, and the maximum rotary displacements and positioning error of the system were calculated. The study results showed that the system can provide precision motion at the sub-arc-second and good linearity of motion. This study has a certain reference value in ultra-precision positioning and micromachining for research on rotary motion systems at the sub-arc-second level.

Combining targeted sequencing and ultra-low-pass whole-genome sequencing for accurate somatic copy number alteration detection.

This study investigated the feasibility of combining targeted sequencing and ultra-low-pass whole-genome sequencing (ULP-WGS) for improved somatic copy number alteration (SCNA) detection, due to its role in tumorigenesis and prognosis. Cerebrospinal fluid and matched blood samples were obtained from 29 patients with brain metastasis derived from lung cancer. Samples were subjected to targeted sequencing (genomic coverage: 300 kb) and 2×ULP-WGS. The SCNA was detected by the CTLW_CNV, Control-FreeC, and CNVkit methods and their accuracy was analyzed. Eighteen tumor samples showed consistent SCNA results between the three methods, while a small fraction of samples resulted in different SCNA estimations. Further analysis indicated that consistency of SCNA highly correlated with the difference of baseline depth (normalized depth of regions without SCNA events) estimation between methods. Conflict Index showed that CTLW_CNV significantly improved the accuracy of SCNA detection through precise baseline depth estimation. CTLW_CNV combines targeted sequencing and ULP-WGS for improved SCNA detection. The improvement in detection accuracy is mainly due to a refined baseline depth estimation, guided by single-nucleotide polymorphism allele frequencies within the deeply sequenced region (targeted sequencing). This method is especially suitable for tumor samples with biased aneuploidy, a previously under-estimated genomic characteristic across different cancer types.

Systematical identifications of prognostic meaningful lung adenocarcinoma subtypes and the underlying mutational and expressional characters.

BACKGROUND: Lung adenocarcinoma (LUAD) is one of the most common cancer types, threatening the human health around the world. However, the high heterogeneity and complexity of LUAD limit the benefits of targeted therapies. This study aimed to identify the key prognosis impacting genes and relevant subtypes for LUAD. METHODS: We recognized significant mutations and prognosis-relevant genes based on the omics data of 515 LUAD samples from The Cancer Genome Atlas. Mutation significance was estimated by MutSigCV. Prognosis analysis was based on the cox proportional hazards regression (Coxph) model. Specifically, the Coxph model was combined with a causal regulatory network to help reveal which genes play master roles among numerous prognosis impacting genes. Based on expressional profiles of the master genes, LUAD patients were clustered into different sub-types by a consensus clustering method and the importance of master genes were further evaluated by random forest. RESULTS: Significant mutations did not influence the prognosis directly. However, a collection of prognosis relevant genes were recognized, where 75 genes like GAPDH and GGA2 which are involved in mTOR signaling, lysosome or other key pathways are further identified as the master ones. Interestingly, the master gene expressions help separate LUAD patients into two sub-types displaying remarkable differences in expressional profiles, prognostic outcomes and genomic mutations in certain genes, like SMARCA4 and COL11A1. Meanwhile, the subtypes were re-discovered from two additional LUAD cohorts based on the top-10 important master genes. CONCLUSIONS: This study can promote precision treatment of LUAD by providing a comprehensive description on the key prognosis-relevant genes and an alternative way to classify LUAD subtypes.

Screening key lncRNAs for human lung adenocarcinoma based on machine learning and weighted gene co-expression network analysis.

BACKGROUND: Lung adenocarcinoma (LUAD) accounts for a significant proportion of lung cancer and there have been few diagnostic and therapeutic targets for LUAD due to the lack of specific biomarker. The aim of this study was to identify key long non-coding RNAs (lncRNAs) for LUAD. METHODS: The lncRNA and mRNA expression profiles of a large group of patients with LUAD were obtained from The Cancer Genome Atlas (TCGA). The differentially expressed lncRNAs (DElncRNAs) and mRNAs (DEmRNAs) were identified. The optimal diagnostic lncRNA biomarkers for LUAD were identified by using feature selection procedure and classification model. We established classification models including random forests, decision tree and support vector machine to distinguish LUAD and normal tissues. The lncRNAs-mRNAs co-expression networks and module identification were established by weighted gene co-expression network analysis (WGCNA). Functional annotation of pink and green modules was performed. The expression of selected DElncRNAs were validated by qRT-PCR. RESULTS: A total of 1364 DEmRNAs (468 down-regulated and 896 up-regulated mRNAs) and 260 DElncRNAs (88 down-regulated and 172 up-regulated lncRNAs) between LUAD and normal tissue were obtained. LANCL1-AS1, MIR3945HG, LINC01270, RP5-1061H20.4, BLACAT1, LINC01703, CTD-2227E11.1 and RP1-244F24.1 were identified as optimal diagnostic lncRNA biomarkers for LUAD. The area under curve (AUC) of the random forests model, decision tree model and SVM model were 0.999, 0.937 and 0.999, and the specificity and sensitivity of the three model were 98.3% and 99.8%, 93.2% and 99% and 100% and 98.4%, respectively. Co-expression networks analysis showed that RP11-389C8.2, CTD-2510F5.4 and TMPO-AS1 were co-expressed with 44, 242 and 241 mRNAs, respectively. Cell cycle, DNA replication and p53 signaling pathway were three significantly enriched pathways. The qRT-PCR results were consistent with our integrated analysis, generally. The GSE32863 and GSE104854 validation was consistent with our integrated analysis, generally. CONCLUSION: Our study identified eight DElncRNAs as potential diagnostic biomarkers of LUAD. Functional annotation of green module provided new evidences for exploring the precise roles of lncRNA in LUAD.

microRNA-363-3p inhibits cell growth and invasion of non­small cell lung cancer by targeting HMGA2.

Lung cancer is the second most common cancer and is the leading cause of cancer-related death worldwide. For decades, increasing evidence revealed that microRNAs may contribute to non­small cell lung cancer (NSCLC) carcinogenesis and progression and could provide novel therapeutic targets for treatments of patients with NSCLC. Accumulated studies indicate that microRNA (miR)­363­3p serves important roles in tumorigenesis and tumor development; however, the role of miR­363­3p in NSCLC is still unclear. The current study reported that miR­363­3p exhibited reduced expression in NSCLC tissues and cell lines. Reduced miR­363­3p expression was correlated with tumor node metastasis classification and distant metastasis of NSCLC patients. Notably, miR­363­3p re­expression significantly suppressed cell proliferation and invasion of NSCLC. Furthermore, bioinformatics analysis, luciferase reporter assay, reverse transcription­quantitative polymerase chain reaction and western blotting indicated that (high mobility group AT-hook 2) HMGA2 was a direct target gene of miR­363­3p. HMGA2 was increased in NSCLC tissues and inversely associated with HMGA2 expression. Moreover, HMGA2 underexpression had similar effects to miR­363­3p overexpression in NSCLC cells. Thus, the current study suggested that miR­363­3p may act as a tumor suppressor in NSCLC and that the miR­363­3p could be investigated as a therapeutic target for the patients with this disease.

Endogenous microRNA-424 predicts clinical outcome and its inhibition acts as cancer suppressor in human non-small cell lung cancer.

PURPOSE: We examined the expression, clinical correlation and functional mechanisms of endogenous microRNA-424 (miR-424) in human non-small cell lung cancer (NSCLC). METHODS: Expression pattern of endogenous miR-424 was examined by qRT-PCR in clinical samples obtained from 233 NSCLC patients. Correlations between differential miR-424 expression level (low vs. high) and NSCLC patients' clinicopathological parameters or survival were statistically examined. In in vitro NSCLC H596 and SW900 cells, miR-424 was either upregulated or downregulation by lentiviral transduction. Their effects on cancer cell viability, proliferation, and cell-cycle transition were also examined. RESULTS: MiR-424 expression was not different between NSCLC tumors and healthy lung tissues. However, it is much upregulated in NSCLC tumors associated with patients at advanced clinical stages. Statistical analyses demonstrated that high endogenous miR-424 expression in NSCLC tumors was significantly correlated with patients' advanced clinical stages, aggressive tumor metastasis, and short survival. In addition, Cox regression model predicted that endogenous miR-424 might be an independent prognostic marker in NSCLC. In in vitro NSCLC cell lines, miR-424 downregulation had a significant suppressing effect on cancer proliferation and G1 to S phase cell-cycle transition. On the other hand, miR-424 upregulation had no effect on NSCLC in vitro. CONCLUSION: High endogenous miR-424 expression in tumors may predict poor prognosis of patients with NSCLC. Inhibiting endogenous miR-424 may also serve an effective cancer suppressor in NSCLC.