SSF-DDI: a deep learning method utilizing drug sequence and substructure features for drug-drug interaction prediction.

BACKGROUND: Drug-drug interactions (DDI) are prevalent in combination therapy, necessitating the importance of identifying and predicting potential DDI. While various artificial intelligence methods can predict and identify potential DDI, they often overlook the sequence information of drug molecules and fail to comprehensively consider the contribution of molecular substructures to DDI. RESULTS: In this paper, we proposed a novel model for DDI prediction based on sequence and substructure features (SSF-DDI) to address these issues. Our model integrates drug sequence features and structural features from the drug molecule graph, providing enhanced information for DDI prediction and enabling a more comprehensive and accurate representation of drug molecules. CONCLUSION: The results of experiments and case studies have demonstrated that SSF-DDI significantly outperforms state-of-the-art DDI prediction models across multiple real datasets and settings. SSF-DDI performs better in predicting DDI involving unknown drugs, resulting in a 5.67% improvement in accuracy compared to state-of-the-art methods.

B-LBConA: a medical entity disambiguation model based on Bio-LinkBERT and context-aware mechanism.

BACKGROUND: The main task of medical entity disambiguation is to link mentions, such as diseases, drugs, or complications, to standard entities in the target knowledge base. To our knowledge, models based on Bidirectional Encoder Representations from Transformers (BERT) have achieved good results in this task. Unfortunately, these models only consider text in the current document, fail to capture dependencies with other documents, and lack sufficient mining of hidden information in contextual texts. RESULTS: We propose B-LBConA, which is based on Bio-LinkBERT and context-aware mechanism. Specifically, B-LBConA first utilizes Bio-LinkBERT, which is capable of learning cross-document dependencies, to obtain embedding representations of mentions and candidate entities. Then, cross-attention is used to capture the interaction information of mention-to-entity and entity-to-mention. Finally, B-LBConA incorporates disambiguation clues about the relevance between the mention context and candidate entities via the context-aware mechanism. CONCLUSIONS: Experiment results on three publicly available datasets, NCBI, ADR and ShARe/CLEF, show that B-LBConA achieves a signifcantly more accurate performance compared with existing models.

Methylation-Mediated Silencing of RBP7 Promotes Breast Cancer Progression through PPAR and PI3K/AKT Pathway.

Retinoid-binding protein7 (RBP7) is a member of the cellular retinol-binding protein (CRBP) family, which is involved in the pathogenesis of breast cancer. The study aims to illustrate the prognostic value and the potential regulatory mechanisms of RBP7 expression in breast cancer. Bioinformatics analysis with the TCGA and CPTAC databases revealed that the mRNA and protein expression levels of RBP7 in normal were higher compared to breast cancer tissues. Survival analysis displayed that the lower expression of RBP7, the worse the prognosis in ER-positive (ER+) breast cancer patients. Genomic analysis showed that low expression of RBP7 correlates with its promoter hypermethylation in breast cancer. Functional enrichment analysis demonstrated that downregulation of RBP7 expression may exert its biological influence on breast cancer through the PPAR pathway and the PI3K/AKT pathway. In summary, we identified RBP7 as a novel biomarker that is helpful for the prognosis of ER+ breast cancer patients. Promoter methylation of RBP7 is involved in its gene silencing in breast cancer, thus regulating the occurrence and development of ER+ breast cancer through the PPAR and PI3K/AKT pathways.

XBP1 impacts lung adenocarcinoma progression by promoting plasma cell adaptation to the tumor microenvironment.

Background: The activation of X-box binding protein 1 (XBP1) plays an essential role in the unfolded protein response (UPR) of the endoplasmic reticulum (ER). XBP1 is commonly expressed in various tumors and is closely related to tumorigenesis and progression. However, the role of XBP1 in lung adenocarcinoma (LUAD), especially the prognostic value of its alternative splicing isoforms, remains largely unknown. Methods: The LUAD datasets were retrieved from the The Cancer Genome Atlas, ArrayExpress and Gene Expression Omnibus. GEPIA2 and meta-analysis were employed to explore the prognostic value, and bioinformatics analysis with the TIMER2.0 database was used to investigate immune cell infiltration. We performed single-cell analyses to identify cell types with high XBP1 expression. In addition, polymerase chain reaction (PCR) and DNA sequencing were performed to verify the authenticity of the new spliceosome. Results: In this study, we found that high expression of XBP1 was significantly associated with a good prognosis, and XBP1 expression was significantly positively correlated with B cell infiltration in LUAD. In addition, we found that high-level expression of a novel splicing isoform, XBP1 (XBP1-003), improved the prognosis of LUAD. Protein structural analysis demonstrated that XBP1-003 has several specific protein domains that are different from those of other XBP1 isoforms, indicating a unique function of this isoform in LUAD. Conclusion: All these results suggest that XBP1 plays an antitumorigenic role in LUAD through alternative splicing, which may be related to the adaptation of plasma cells. This sheds new light on the potential strategy for LUAD prognosis evaluation and immunotherapy.