Artificial Intelligence and Cancer Drug Development.

BACKGROUND: The development of cancer drugs is among the most focused "bench to bedside activities" to improve human health. Because of the amount of data publicly available to cancer research, drug development for cancers has significantly benefited from big data and Artificial Intelligence (AI). In the meantime, challenges, like curating the data of low quality, remain to be resolved. OBJECTIVES: This review focused on the recent advancements and challenges of AI in developing cancer drugs. METHODS: We discussed target validation, drug repositioning, de novo design, and compounds' synthetic strategies. RESULTS AND CONCLUSION: AI can be applied to all stages during drug development, and some excellent reviews detailing the applications of AI in specific stages are available.

The emerging role of microRNA-4487/6845-3p in Alzheimer's disease pathologies is induced by Aß25-35 triggered in SH-SY5Y cell.

BACKGROUND: Accumulation of amyloid ß-peptide (Aß) is implicated in the pathogenesis and development of Alzheimer's disease (AD). Neuron-enriched miRNA was aberrantly regulated and may be associated with the pathogenesis of AD. However, regarding whether miRNA is involved in the accumulation of Aß in AD, the underlying molecule mechanism remains unclear. Therefore, we conduct a systematic identification of the promising role of miRNAs in Aß deposition, and shed light on the molecular mechanism of target miRNAs underlying SH-SY5Y cells treated with Aß-induced cytotoxicity. RESULTS: Statistical analyses of microarray data revealed that 155 significantly upregulated and 50 significantly downregulated miRNAs were found on the basis of log2 | Fold Change | ≥ 0.585 and P < 0.05 filter condition through 2588 kinds of mature miRNA probe examined. PCR results show that the expression change trend of the selected six miRNAs (miR-6845-3p, miR-4487, miR-4534, miR-3622-3p, miR-1233-3p, miR-6760-5p) was consistent with the results of the gene chip. Notably, Aß25-35 downregulated hsa-miR-4487 and upregulated hsa-miR-6845-3p in SH-SY5Y cell lines associated with Aß-mediated pathophysiology. Increase of hsa-miR-4487 could inhibit cells apoptosis, and diminution of hsa-miR-6845-3p could attenuate axon damage mediated by Aß25-35 in SH-SY5Y. CONCLUSIONS: Together, these findings suggest that dysregulation of hsa-miR-4487 and hsa-miR-6845-3p contributed to the pathogenesis of AD associated with Aß25-35 mediated by triggering cell apoptosis and synaptic dysfunction. It might be beneficial to understand the pathogenesis and development of clinical diagnosis and treatment of AD. Further, our well-designed validation studies will test the miRNAs signature as a prognostication tool associated with clinical outcomes in AD.

Increased AURKA promotes cell proliferation and predicts poor prognosis in bladder cancer.

BACKGROUND: Bladder cancer (BC) is the most common cancer of the urinary bladder and upper tract, in which the clinical management is limited. AURKA (aurora kinase A) has been identified as an oncogene in cancer development; however, its potential role and underlying mechanisms in the progression of BC remain unknown. RESULTS: In this study, we evaluated Aurora kinase A (AURKA) expression in patient samples by performing gene expression profiling, and found that AURKA expression levels were significantly higher in BC tissues than in normal tissues. Increased AURKA in BC was strongly associated with stage and grade. Moreover, BC patients with elevated AURKA achieved poor overall survival rates. The experiments in vitro comprehensively validated the critical role of AURKA in promoting BC cell proliferation using the methods of gene overexpression and gene silencing. Furthermore, we proved that AURKA inhibitor MLN8237 arrested BC cell growth and induced apoptosis. CONCLUSIONS: These findings implicate AURKA acting as an effective biomarker for BC detection and prognosis, as well as therapeutic target.

Comprehensive annotation of bidirectional promoters identifies co-regulation among breast and ovarian cancer genes.

A "bidirectional gene pair" comprises two adjacent genes whose transcription start sites are neighboring and directed away from each other. The intervening regulatory region is called a "bidirectional promoter." These promoters are often associated with genes that function in DNA repair, with the potential to participate in the development of cancer. No connection between these gene pairs and cancer has been previously investigated. Using the database of spliced-expressed sequence tags (ESTs), we identified the most complete collection of human transcripts under the control of bidirectional promoters. A rigorous screen of the spliced EST data identified new bidirectional promoters, many of which functioned as alternative promoters or regulated novel transcripts. Additionally, we show a highly significant enrichment of bidirectional promoters in genes implicated in somatic cancer, including a substantial number of genes implicated in breast and ovarian cancers. The repeated use of this promoter structure in the human genome suggests it could regulate co-expression patterns among groups of genes. Using microarray expression data from 79 human tissues, we verify regulatory networks among genes controlled by bidirectional promoters. Subsets of these promoters contain similar combinations of transcription factor binding sites, including evolutionarily conserved ETS factor binding sites in ERBB2, FANCD2, and BRCA2. Interpreting the regulation of genes involved in co-expression networks, especially those involved in cancer, will be an important step toward defining molecular events that may contribute to disease.