Genomic prediction of pig growth traits based on machine learning.

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.

circRNA on animal skeletal muscle development regulation.

Circular RNA (circRNA) is a type of closed circular RNA molecules formed by reverse splicing, which exists widely in organisms and has become a research hotspot in non-coding RNAs in recent years. Skeletal muscle plays the role of coordinating movement and maintaining normal metabolism and endocrine in organisms. With the development of sequencing and bioinformatics analysis technology, the functions and regulation mechanisms of circRNAs in skeletal muscle development have been gradually revealed. In this review, we summarize the types of molecular regulatory mechanisms, the classical research ideas and the functional research methods of circRNAs, and the research progress of circRNAs involved in normal development of skeletal muscle and regulation of skeletal muscle disease, in order to provide a reference to further study of the genetic mechanisms of circRNAs in the regulation of skeletal muscle development.

Mannose-mediated inhibitory effects of PA-MSHA on invasion and metastasis of hepatocellular carcinoma via EGFR/Akt/IκBß/NF-κB pathway.

BACKGROUND & AIMS: Elevation of high-mannose glycans is a common feature of malignant cells and has been suggested to be the basis for alternative cancer therapy for several years. Here we want to investigate the antitumour effect of pseudomonas aeruginosa-mannosesensitive haemagglutinin (PA-MSHA), a genetically engineered heat-inactivated PA strain with mannose-sensitive binding activity, on hepatocellular carcinoma (HCC). METHODS: Tumourigenicity and metastatic potentials of HCC were studied after PA-MSHA treatment by utilizing the in vitro/in vivo model of HCC. Expression of apoptosis-associated proteins and epithelial-mesenchymal transition (EMT) related genes were evaluated, and possible signalling pathways involved were investigated. RESULTS: PA-MSHA induced significant cell proliferation inhibition and cell cycle arrest of HCC through decreasing the levels of cyclins D1, cyclins E, CDK2, CDK4, proliferating cell nuclear antigen (PCNA), and increasing the level of p21 and p27. Moreover, PA-MSHA suppressed the invasion, migration and adhesion of HCC through inhibiting epithelial-mesenchymal transition (EMT). PA-MSHA also inhibited EGFR/Akt/IκBß/NF-κB pathway and overexpression of NF-κB significantly abrogated PA-MSHA induced EMT inhibition. In addition, competitive inhibition of the mannose binding activity of PA-MSHA by D-mannose significantly blocked its effect on cell cycle arrest and EMT. PA-MSHA also abrogated lung metastasis of HCC and significantly inhibited tumour growth in the in vivo study. CONCLUSIONS: Our study demonstrated the essential role of EGFR/Akt/IκBß/NF-κB pathway in the inhibitory effect of PA-MSHA on invasion and metastasis of HCC through suppressing EMT, and revealed an attractive prospect of PA-MSHA as a novel candidate agent in the treatment of HCC.