The testing of pharmacological hypotheses becomes faster and more accurate, but at the same time more difficult than even two decades ago. It takes more time to collect and analyse disease mechanisms and experimental facts in various specialized resources. We discuss a new approach to aggregating individual pieces of information about a single disease using Elsevier's automated text mining technology. The developed algorithm allows for the collection of published facts in a unified format starting only with the name of the disease. A special template, which combines research and clinical descriptions of diseases was developed. The approach was tested, and information was collected for 55 rare monogenic diseases. Clinical, molecular, and pharmacological characteristics of diseases with supporting references from the literature are available in the form of tables and files. Manually curated templates for 10 rare diseases, including top ranked Cystic Fibrosis and Huntington's disease were published to demonstrate the results of the described approach.

Brain cancers are ones of most aggressive and difficult to treat cancers. Despite numerous studies of the cellular mechanisms of gliomas, it is difficult to stop tumor growth. A complex genetic and epigenetic nature of many gliomas and poorly known pathways of human neuron precursors maturation suggest turning to big data analysis to find new insights and directions for drug development. We developed in silico molecular models and predicted molecular switches in signaling cascades that maintain multipotency of neuronal precursor cells in diffuse intrinsic pontine glioma (DIPG) driven by the H3K27M mutation and mutations in the TP53 gene. Oncogenes and biomarkers were predicted based on transcriptomics and mutational genomics data from a cohort of 30 patients with DIPG analyzed using Elsevier artificial intelligence methods and a collection of manually curated cancer hallmark pathways. The molecular models of DIPG with mutations in TP53 and histone 3 gene describe the mechanism of oligodendrocyte dedifferentiation due to activation of transcriptional factors OLIG2, SOX2, and POU5F1, epithelial-to-mesenchymal transition via strong EGFR and TGFR signaling, enhanced cell response to hypoxia via HIF1A signaling and enhanced angiogenesis by VEGFA overexpression. Using in silico analysis, we identified drugs capable of inhibiting mutant TP53: vorinostat, cisplatin, paclitaxel, and statins were top-ranked drugs. The predicted drugs and oncogenes had individual patient-level differences that can be visualized with created DIPG model and may be useful for future research in the field of personalized medicine.