ACBD3 Bioinformatic Analysis and Protein Expression in Breast Cancer Cells

Conditional generative adversarial network driven radiomic prediction of mutation status based on magnetic resonance imaging of breast cancer

BACKGROUND

Breast Cancer (BC) is a highly heterogeneous and complex disease. Personalized treatment options require the integration of multi-omic data and consideration of phenotypic variability. Radiogenomics aims to merge medical images with genomic measurements but encounter challenges due to unpaired data consisting of imaging, genomic, or clinical outcome data. In this study, we propose the utilization of a well-trained conditional generative adversarial network (cGAN) to address the unpaired data issue in radiogenomic analysis of BC. The generated images will then be used to predict the mutations status of key driver genes and BC subtypes.

METHODS

We integrated the paired MRI and multi-omic (mRNA gene expression, DNA methylation, and copy number variation) profiles of 61 BC patients from The Cancer Imaging Archive (TCIA) and The Cancer Genome Atlas (TCGA). To facilitate this integration, we employed a Bayesian Tensor Factorization approach to factorize the multi-omic data into 17 latent features. Subsequently, a cGAN model was trained based on the matched side-view patient MRIs and their corresponding latent features to predict MRIs for BC patients who lack MRIs. Model performance was evaluated by calculating the distance between real and generated images using the Fréchet Inception Distance (FID) metric. BC subtype and mutation status of driver genes were obtained from the cBioPortal platform, where 3 genes were selected based on the number of mutated patients. A convolutional neural network (CNN) was constructed and trained using the generated MRIs for mutation status prediction. Receiver operating characteristic area under curve (ROC-AUC) and precision-recall area under curve (PR-AUC) were used to evaluate the performance of the CNN models for mutation status prediction. Precision, recall and F1 score were used to evaluate the performance of the CNN model in subtype classification.

RESULTS

The FID of the images from the well-trained cGAN model based on the test set is 1.31. The CNN for TP53, PIK3CA, and CDH1 mutation prediction yielded ROC-AUC values 0.9508, 0.7515, and 0.8136 and PR-AUC are 0.9009, 0.7184, and 0.5007, respectively for the three genes. Multi-class subtype prediction achieved precision, recall and F1 scores of 0.8444, 0.8435 and 0.8336 respectively. The source code and related data implemented the algorithms can be found in the project GitHub at https://github.com/mattthuang/BC_RadiogenomicGAN .

CONCLUSION

Our study establishes cGAN as a viable tool for generating synthetic BC MRIs for mutation status prediction and subtype classification to better characterize the heterogeneity of BC in patients. The synthetic images also have the potential to significantly augment existing MRI data and circumvent issues surrounding data sharing and patient privacy for future BC machine learning studies.

Investigating the clinical role and prognostic value of genes related to insulin-like growth factor signaling pathway in thyroid cancer

BACKGROUND

Thyroid cancer (THCA) is the most common endocrine malignancy having a female predominance. The insulin-like growth factor (IGF) pathway contributed to the unregulated cell proliferation in multiple malignancies. We aimed to explore the IGF-related signature for THCA prognosis.

METHOD

The TCGA-THCA dataset was collected from the Cancer Genome Atlas (TCGA) for screening of key prognostic genes. The limma R package was applied for differentially expressed genes (DEGs) and the clusterProfiler R package was used for the Gene Ontology (GO) and KEGG analysis of DEGs. Then, the un/multivariate and least absolute shrinkage and selection operator (Lasso) Cox regression analysis was used for the establishment of RiskScore model. Receiver Operating Characteristic (ROC) analysis was used to verify the model's predictive performance. CIBERSORT and MCP-counter algorithms were applied for immune infiltration analysis. Finally, we analyzed the mutation features and the correlation between the RiskScore and cancer hallmark pathway by using the GSEA.

RESULT

We obtained 5 key RiskScore model genes for patient's risk stratification from the 721 DEGs. ROC analysis indicated that our model is an ideal classifier, the high-risk patients are associated with the poor prognosis, immune infiltration, high tumor mutation burden (TMB), stronger cancer stemness and stronger correlation with the typical cancer-activation pathways. A nomogram combined with multiple clinical features was developed and exhibited excellent performance upon long-term survival quantitative prediction.

CONCLUSIONS

We constructed an excellent prognostic model RiskScore based on IGF-related signature and concluded that the IGF signal pathway may become a reliable prognostic phenotype in THCA intervention.

Identification of ACBD3 as a new molecular biomarker in pan-cancers through bioinformatic analysis: a preclinical study

BACKGROUND

Acyl-CoA-binding domain-containing 3 (ACBD3) is a multifunctional protein, that plays essential roles in cellular signaling and membrane domain organization. Although the precise roles of ACBD3 in various cancers remain unclear. Thus, we aimed to determine the diverse roles of ACBD3 in pan-cancers.

METHODS

Relevant clinical and RNA-sequencing data for normal tissues and 33 tumors from The Cancer Genome Atlas (TCGA) database, the Human Protein Atlas, and other databases were applied to investigate ACBD3 expression in various cancers. ACBD3-binding and ACBD3-related target genes were obtained from the STRING and GEPIA2 databases. The possible functions of ACBD3-binding genes were explored using Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses. We also applied the diagnostic value and survival prognosis analysis of ACBD3 in pan-cancers using R language. The mutational features of ACBD3 in various TCGA cancers were obtained from the cBioPortal database.

RESULTS

When compared with normal tissues, ACBD3 expression was statistically upregulated in eleven cancers and downregulated in three cancers. ACBD3 expression was remarkably different among various pathological stages of tumors, immune and molecular subtypes of cancers, cancer phosphorylation levels, and immune cell infiltration. The survival of four tumors was correlated with the expression level of ACBD3, including pancreatic adenocarcinoma, adrenocortical carcinoma, sarcoma, and glioma. The high accuracy in diagnosing multiple tumors and its correlation with prognosis indicated that ACBD3 may be a potential biomarker of pan-cancers.

CONCLUSION

According to our pan-cancer analysis, ACBD3 may serve as a remarkable prognostic and diagnostic biomarker of pan-cancers as well as contribute to tumor development. ACBD3 may also provide new directions for cancer treatment targets in the future.