Integration of transcriptome and machine learning to identify the potential key genes and regulatory networks affecting drip loss in pork

Low level of drip loss (DL) is an important quality characteristic of meat with high economic value. However, the key genes and regulatory networks contributing to DL in pork remain largely unknown. To accurately identify the key genes affecting DL in muscles postmortem, 12 Duroc x (Landrace x Yorkshire) pigs with extremely high (n = 6, H group) and low (n = 6, L group) DL at both 24 and 48 h postmortem were selected for transcriptome sequencing. The analysis of differentially expressed genes and weighted gene co-expression network analysis (WGCNA) were performed to find the overlapping genes using the transcriptome data, and functional enrichment and protein-protein interaction (PPI) network analysis were conducted using the overlapping genes. Moreover, we used machine learning to identify the key genes and regulatory networks related to DL based on the interactive genes of the PPI network. Finally, nine potential key genes (IRS1, ESR1, HSPA6, INSR, SPOP, MSTN, LGALS4, MYLK2, and FRMD4B) mainly associated with the MAPK signaling pathway, the insulin signaling pathway, and the calcium signaling pathway were identified, and a single-gene set enrichment analysis (GSEA) was performed to further annotate the functions of these potential key genes. The GSEA results showed that these genes are mainly related to ubiquitin-mediated proteolysis and oxidative reactions. Taken together, our results indicate that the potential key genes influencing DL are mainly related to insulin signaling mediated differences in glycolysis and ubiquitin-mediated changes in muscle structure and improve the understanding of gene expression and regulation related to DL and contribute to future molecular breeding for improving pork quality. This study contributes to elucidating the molecular mechanism of drip loss in pork and provides potential promising genes for the genetic improvement of drip loss. A low level of drip loss (DL) is critical for the economic value of pork. However, the genetic basis underlying DL remains unclear. In this study, pigs with extremely high and low DL at both 24 and 48 h postmortem were selected, and total RNA from longissimus dorsi (LD) muscles was extracted for transcriptome sequencing. Subsequently, a variety of analytical methods, were integrated to identify the potential key genes and pathways affecting DL. As a result, nine potential key genes (IRS1, ESR1, HSPA6, INSR, SPOP, MSTN, LGALS4, MYLK2, and FRMD4B) mainly associated with the MAPK signaling pathway, insulin signaling pathway, and calcium signaling pathway, were identified, and these genes are primarily related to ubiquitin-mediated proteolysis and oxidation reactions. This study contributes new evidence for elucidating the molecular mechanism of DL and provides potential target genes for precise genetic improvement of DL.