AFEI: adaptive optimized vertical federated learning for heterogeneous multi-omics data integration.

Vertical federated learning has gained popularity as a means of enabling collaboration and information sharing between different entities while maintaining data privacy and security. This approach has potential applications in disease healthcare, cancer prognosis prediction, and other industries where data privacy is a major concern. Although using multi-omics data for cancer prognosis prediction provides more information for treatment selection, collecting different types of omics data can be challenging due to their production in various medical institutions. Data owners must comply with strict data protection regulations such as European Union (EU) General Data Protection Regulation. To share patient data across multiple institutions, privacy and security issues must be addressed. Therefore, we propose an adaptive optimized vertical federated-learning-based framework adaptive optimized vertical federated learning for heterogeneous multi-omics data integration (AFEI) to integrate multi-omics data collected from multiple institutions for cancer prognosis prediction. AFEI enables participating parties to build an accurate joint evaluation model for learning more information related to cancer patients from different perspectives, based on the distributed and encrypted multi-omics features shared by multiple institutions. The experimental results demonstrate that AFEI achieves higher prediction accuracy (6.5% on average) than using single omics data by utilizing the encrypted multi-omics data from different institutions, and it performs almost as well as prognosis prediction by directly integrating multi-omics data. Overall, AFEI can be seen as an efficient solution for breaking down barriers to multi-institutional collaboration and promoting the development of cancer prognosis prediction.

Downregulation of lncRNA IGF2-AS-encoded peptide induces trophoblast - cycle arrest.

RESEARCH QUESTION: lncRNA IGF2-AS may be related to early pregnancy loss. Does lncRNA IGF2-AS affect trophoblast cell growth? The aim of the present study was to verify that lncRNA IGF2-AS encodes a polypeptide, IGF2-AS-168aa, and to study its role in the pathogenesis of trophoblasts. DESIGN: A small interfering RNA targeted to the IGF2-AS gene (si-IGF2-AS) was designed and transfected into JEG-3 and JAR cells for in-vitro gene silencing. Quantitative polymerase chain reaction and western blotting were used to determine lncRNA IGF2-AS levels in experimental cells. After IGF2-AS suppression, MTT assay was used to assess cell proliferation and apoptosis was determined by flow cytometry. Target gRNA IGF2-AS-gRNA was designed for knockout conducted the corresponding mRNA. HEK293T cells were transfected with the identified positive clone vectors. Finally, IGF2-AS-168aa was analysed by western blotting after the protein-coding region of the IGF2-AS gene was knocked out by CRISPR/Cas9 gene-editing technology. RESULTS: lncRNA IGF2-AS and IGF2-AS-168aa were significantly downregulated in JEG-3 and JAR cells transfected with si-IGF2-AS (lncRNA IGF2-AS: JAR: NC versus small interfering RNA (siRNA)-1: P = 0.019 NC versus siRNA-2: P = 0.013; JEG-3: NC versus siRNA-1: P = 0.001 NC versus siRNA-2: P = 0.004) (IGF2-AS-168aa: JAR: NC versus siRNA-1: P = 0.030 NC versus siRNA-2: P = 0.018; JEG-3: NC versus siRNA-1: P = 0.004 NC versus siRNA-2: P = 0.001). IGF2-AS gene was incapable of encoding IGF2-AS-168aa after the coding region was successfully knocked out in HEK293T cells. Flow cytometry and the MTT assay revealed that IGF2-AS gene silencing led to cell cycle block in the G1 phase, markedly decreasing cell proliferation and increasing apoptosis. CONCLUSION: The IGF2-AS gene encoded a peptide with a potential function in trophoblast cell cycle arrest.

Deep learning-based ovarian cancer subtypes identification using multi-omics data.

BACKGROUND: Identifying molecular subtypes of ovarian cancer is important. Compared to identify subtypes using single omics data, the multi-omics data analysis can utilize more information. Autoencoder has been widely used to construct lower dimensional representation for multi-omics feature integration. However, learning in the deep architectures in Autoencoder is difficult for achieving satisfied generalization performance. To solve this problem, we proposed a novel deep learning-based framework to robustly identify ovarian cancer subtypes by using denoising Autoencoder. RESULTS: In proposed method, the composite features of multi-omics data in the Cancer Genome Atlas were produced by denoising Autoencoder, and then the generated low-dimensional features were input into k-means for clustering. At last based on the clustering results, we built the light-weighted classification model with L1-penalized logistic regression method. Furthermore, we applied the differential expression analysis and WGCNA analysis to select target genes related to molecular subtypes. We identified 34 biomarkers and 19 KEGG pathways associated with ovarian cancer. CONCLUSIONS: The independent test results in three GEO datasets proved the robustness of our model. The literature reviewing show 19 (56%) biomarkers and 8(42.1%) KEGG pathways identified based on the classification subtypes have been proved to be associated with ovarian cancer. The outcomes indicate that our proposed method is feasible and can provide reliable results.

Aberrant methylation of IGF2-AS promoter in early pregnancy loss.

OBJECTIVE: The present study aimed to evaluate insulin-like growth factor 2 antisense (IGF2-AS) in the villi of human embryos and compared its expression between normal pregnancy and early pregnancy loss (EPL). MATERIALS AND METHODS: The present study conducted a microarray analysis to identify the expression profiles of lncRNAs in villi from EPL and normal controls (controls, n = 10 and EPL patients, n = 10). Embryonic villi were collected from women who underwent artificial abortion. QPCR was used to confirm the results. The DNA methylation patterns were analyzed using pyrosequencing and bisulfite sequencing polymerase chain reaction. The percentage of methylation was compared in chorionic villi from the two groups. RESULTS: A total of 57 deregulated differentially expressed lncRNAs were detected, of which 33 were upregulated, and 24 were downregulated. The expression of lncRNA IGF2-AS was downregulated significantly in EPL villi compared with the normal villi. Negative regulation of IGF2-AS may be involved in the development of EPL. Methprimer predicted that IGF2-AS promoter had CpG islands and dense CG sites. Increased methylation at CpG islands present in IGF2-AS gene promoter was observed in EPL villi. CONCLUSION: An increase in methylation of IGF2-AS likely leads to its downregulation in chorionic villi of EPL. The findings suggest that a deficiency of IGF2-AS in the villi is associated with human EPL.

Pulsatilla decoction inhibits Candida albicans proliferation and adhesion in a mouse model of vulvovaginal candidiasis via the Dectin-1 signaling pathway.

ETHNOPHARMACOLOGICAL RELEVANCE: Pulsatilla decoction (PD) is a classical prescription in Traditional Chinese Medicine (TCM) and has been reported to have inhibitory effects on Candida albicans proliferation. STUDY AIM: To investigate the therapeutic effects of PD in the treatment of Vulvovaginal candidiasis (VVC) and elucidate the potential mechanism. MATERIALS AND METHODS: Female BALB/c mice (N = 90) were randomized to six treatment groups, including the Control group, Model group, three PD groups and Fluconazole group which served as a positive control (20 mg/kg weekly). The three PD groups (low dose group, medium dose group and high dose group) were given a daily intragastric gavage of PD at doses of 5, 10 and 20 g/kg, respectively. Five animals from each group were euthanized on Day 4, Day 7 and Day 14 after treatment. Colony forming unit (CFU) was measured by the serial dilution method. The degree of infection was assessed by Gram staining, Periodic acid schiff (PAS) staining, Hematoxylin and eosin (H&E) staining and Scanning electron microscopy (SEM). The serum inflammation levels were determined by a Luminex assay. Gene and protein expression levels of components of the Dectin-1 signaling pathway were determined by Real-time PCR, Western-blot and immunohistochemistry, respectively. RESULTS: The administration of PD significantly decreased the fungal load from Day 7 post-infection onwards and decreased the number of visible microorganisms based on findings from Gram staining, PAS staining and SEM. H&E staining indicated that the impaired histological profiles were improved in all three PD groups. PD led to a significantly lower level of IL-23 in the serum; the levels of IL-10 and TNF-α were also decreased, although the differences were not significant. Furthermore, a substantial downregulation of Dectin-1, CARD9 and NF-κB mRNA levels and Dectin-1, Syk, CARD9 and NF-κB protein levels was observed after the administration of PD. CONCLUSION: This study suggests that PD exerts inhibitory effects on C. albicans proliferation, adhesion and inflammation and simultaneously downregulates the expression levels of important genes and proteins associated with the Dectin-1 pathway, highlighting the potential application of PD to improve the clinical management of VVC.