Search

When differential evolutionary algorithm is used in solving complex optimization problems, capability ol global search is decreased in the later evolution period, and the ability of global search is weakened and algorithm can easily fall inlo local optimum. In response to these problems, stagnation factor and similarity factor are defined. Scaling factor F is adaptive adjusted according to the stagnation factor. Similarity between individuals is determined by the similarity factor, the gene reconstruction is taken. So that the problem of decrease of population diversity can be alleviated. The improved algorithm is applied to standard test function optimization and vehicle routing problem, the results show thai improved differential evolution algorithm has belter global search ability. And the algorithm is suitable for solving complex optimization problems. [ABSTRACT FROM AUTHOR]

This study aimed to assess and compare the performance of different machine learning models in predicting selected pig growth traits and genomic estimated breeding values (GEBV) using automated machine learning, with the goal of optimizing whole-genome evaluation methods in pig breeding. The research employed genomic information, pedigree matrices, fixed effects, and phenotype data from 9968 pigs across multiple companies to derive four optimal machine learning models: deep learning (DL), random forest (RF), gradient boosting machine (GBM), and extreme gradient boosting (XGB). Through 10-fold cross-validation, predictions were made for GEBV and phenotypes of pigs reaching weight milestones (100 kg and 115 kg) with adjustments for backfat and days to weight. The findings indicated that machine learning models exhibited higher accuracy in predicting GEBV compared to phenotypic traits. Notably, GBM demonstrated superior GEBV prediction accuracy, with values of 0.683, 0.710, 0.866, and 0.871 for B100, B115, D100, and D115, respectively, slightly outperforming other methods. In phenotype prediction, GBM emerged as the best-performing model for pigs with B100, B115, D100, and D115 traits, achieving prediction accuracies of 0.547, followed by DL at 0.547, and then XGB with accuracies of 0.672 and 0.670. In terms of model training time, RF required the most time, while GBM and DL fell in between, and XGB demonstrated the shortest training time. In summary, machine learning models obtained through automated techniques exhibited higher GEBV prediction accuracy compared to phenotypic traits. GBM emerged as the overall top performer in terms of prediction accuracy and training time efficiency, while XGB demonstrated the ability to train accurate prediction models within a short timeframe. RF, on the other hand, had longer training times and insufficient accuracy, rendering it unsuitable for predicting pig growth traits and GEBV.

Objective: To evaluate the expression and clinical significance of Endostatin, vascular endothelial growth factor (VEGF) and fibroblast growth factor basic-2 (FGF-2) in the laryngeal squamous cell carcinoma (LSCC)., Methods: The expression of Endostatin, VEGF and FGF-2 in 50 specimens of LSCC, 40 specimens of para-carcinoma and 10 specimens of normal laryngeal tissues were examined by Flow cytometry., Results: Compared with para-carcinoma and normal laryngeal tissues, the expression level and positive rate of Endostatin, VEGF, FGF-2 in LSCC were different in statistics (P < 0.05); the expression level and positive rate of endostatin, VEGF, FGF-2 in LSCC are obviously higher than those in para-carcinoma and normal laryngeal tissues. The expression level and positive rate of Endostatin, VEGF, FGF-2 were no difference in statistics between para-carcinoma and normal laryngeal tissues (P > 0.05). The expression level and positive rate of Endostatin, VEGF, FGF-2 in LSCC were associated with lymphoid metastasis and clinical stage, not associated with age, sex and clinical group., Conclusions: Endostatin, VEGF and FGF-2 play important role in the incidence, development and prognosis of the LSCC.

Objective: To study the mechanism of STAT3 antisense oligonucleotide (STAT3 AS-ON) in combination with DDP in the treatment of laryngeal cancer., Methods: STAT3 AS-ON, DDP, or STAT3 AS-ON + DDP was added into culture media. The expression and phosphorylation levels of STAT3 protein in Hep-2 cells were measured by Western Blot. The expression of Cyclin D1 and Bcl-xL was also detected by Western Blot. The cell proliferation was assayed by methyl thiazolyl tetrazolium (MTT). Flow cytometry was performed to analyze the cell cycle and apoptosis., Results: STAT3 was highly expressed and phosphorylated in Hep-2 cells. Transfection of STAT3 AS-ON suppressed the expression and phosphorylation levels of STAT3 protein. Forty-eight hours after transfection, the proliferation of Hep-2 cells was inhibited in a dose-dependent manner. Inhibitory effects appeared at 24 h after transfection of STAT3 AS-ON, and became more obvious after 36 h. Seventy-two hours after transfection, the rate of apoptosis in STAT3 AS-ON + DDP group, DDP group, STAT3 AS-ON group, STAT3 S-ON group, lipidosome group and control group was 32.9%, 13.5%, 28.1%, 3.2%, 2.4%, 1.8% respectively. After the treatment of Hep-2 cells with STAT3 AS-ON and DDP for 72 h, the ratio of G1 phase was up-regulated from 55.7% to 74.9%, while that of S phase was own-regulate from 33.6% to 6.9%., Conclusions: STAT3 AS-ON and DDP could suppress the growth of laryngeal cancer cells and induce significant apoptosis of laryngeal cancer cells. Combined use of them had a synergic effect, obviously inhibiting the activation of STAT3 signaling transduction pathway of laryngeal cancer cells. Selective inhibition of specific signaling pathway may provide a new therapeutic approach for treating laryngeal cancers.