Text Mining Gene Selection to Understand Pathological Phenotype Using Biological Big Data

Abstract

Whole transcriptome omics experiments allow for the study of gene regulation at the cellular level. During analysis and interpretation of omics data, false discovery can occur. To minimize false discovery and identify true significant cases, multi-test correction has been introduced to bioinformatics algorithms. The scientific literature offers a huge collection of information that can be parsed using a web Application Programming Interface. Gene selection by text mining can rank information according to its importance while taking into account the most recent updates in scientific literature. The integration of text mining selection in biological big data, such as transcriptome experiments including single cell transcriptome, can achieve an important dimensional reduction of the data without any statistical hypothesis. This avoids false discoveries regarding the molecules of interest. Hydatidiform moles and focal segmental glomerulosclerosis (FSGS) nephropathy are the two examples presented in this chapter, which demonstrate the considerable value of these analytical methods to prove the concept. The best FSGS markers expressed can be displayed by building an interactive online web interface as a web resource based on the glomerular cell transcriptome.

NR0B2 regulation during Primary Sclerosing Cholangitis defines a metabolic and pre-malignant reprogramming of Cholangiocyte

“…Few liver transcriptome experiments were available in PSC disease (Horvath et al, 2014): experiments in which it might be interesting to observe cellular mechanisms consecutives to the symptoms of PSC disorder. The integration of biomedical text mining into high-dimensional omics data such as transcriptome data drastically reduces the error of positive false discovery (Desterke et al, 2021). With the aim of increasing the authenticity of discovery of these mechanisms in human liver transcriptome samples from PSC, a biomedical text-mining pipeline has been developed based on a triad of symptoms characterizing PSC: biliary inflammation, biliary fibrosis and biliary stasis (Lazaridis & LaRusso, 2016).…”

“…Previously, test of distinct biomedical text mining web tools to integrate gene relations with omics data highlighted 'Génie' algorithm (Fontaine, Priller, Barbosa-Silva, & Andrade-Navarro, 2011) as a robust and sensitive machine learning tool to rank best literature associated genes. By textmining (Génie) integration in single cell transcriptome it could be possible to highlighted podocytes markers implicated in Focal Segmental Glomeral Sclerosis (Desterke, Lorenzo, & Candelier, 2021). 'Génie' algorithm also contributed to understand lipidome deregulations during nonalcoholic fatty liver disease (Pirola & Sookoian, 2021).…”

Systematic Reviews to Strengthen Evidence-based Nursing Practice

“…For example, the Task Exchange (28) and Cochrane Crowd (37) tools are platforms that support the working group because they help organize and distribute tasks in large teams involving researchers and citizen science collaborators (27), which implies active participation of citizens (29). Moreover, machine learning tools such as RCT Classifier help collaboratively assess and select the available evidence (30), while text mining tools classify information according to importance, considering the most recent updates in the scientific literature (31,32). Text mining automates information search and retrieval by identifying patterns or correlations between the terms used in databases (33) Cochrane Crowd (37) help identify randomized clinical trials (20).…”