A variational expectation-maximization framework for balanced multi-scale learning of protein and drug interactions.

Protein functions are characterized by interactions with proteins, drugs, and other biomolecules. Understanding these interactions is essential for deciphering the molecular mechanisms underlying biological processes and developing new therapeutic strategies. Current computational methods mostly predict interactions based on either molecular network or structural information, without integrating them within a unified multi-scale framework. While a few multi-view learning methods are devoted to fusing the multi-scale information, these methods tend to rely intensively on a single scale and under-fitting the others, likely attributed to the imbalanced nature and inherent greediness of multi-scale learning. To alleviate the optimization imbalance, we present MUSE, a multi-scale representation learning framework based on a variant expectation maximization to optimize different scales in an alternating procedure over multiple iterations. This strategy efficiently fuses multi-scale information between atomic structure and molecular network scale through mutual supervision and iterative optimization. MUSE outperforms the current state-of-the-art models not only in molecular interaction (protein-protein, drug-protein, and drug-drug) tasks but also in protein interface prediction at the atomic structure scale. More importantly, the multi-scale learning framework shows potential for extension to other scales of computational drug discovery.

RNF20 Reduces Cell Proliferation and Warburg Effect by Promoting NLRP3 Ubiquitination in Liver Cancer.

The present study explored that the effects and its possible mechanisms of ring finger protein 20 (RNF20) in Postoperative survival rate of liver cancer in clinical. All the serum samples were collected from our hospital. Quantitative polymerase chain reaction (PCR) and microarray analysis, and RNA pull down assay were used in this study. We found that the serum RNF20 mRNA expression level in patients with liver cancer were down-regulated. Postoperative survival rate of RNF20 high expression was higher than that of RNF20 low expression. Then, over-expression of RNF20 diminished liver cancer cell proliferation and metastasis. RNF20 reduced Warburg effect of liver cancer. RNF20 expression regulated NOD-like receptor protein 3 (NLRP3) expression and increased NLRP3 Ubiquitination. NLRP3 participated in the effects of RNF20 on cell proliferation, and not affected on Warburg effect of liver cancer. Our study demonstrated that the serum RNF20 expression level was down-regulated in liver cancer, and promoted postoperative survival rate. RNF20 can reduce cancer progression of liver cancer by NLRP3 signal pathway, suggesting that it may prove to be a potential therapeutic target for postoperative survival rate of liver cancer.