A new machine learning based computational framework identifies therapeutic targets and unveils influential genes in pancreatic islet cells

Abstract

Pancreatic islets comprise a group of cells that produce hormones regulating blood glucose levels. Particularly, the alpha and beta islet cells produce glucagon and insulin to stabilize blood glucose. When beta islet cells are dysfunctional, insulin is not secreted, inducing a glucose metabolic disorder. Identifying effective therapeutic targets against the disease is a complicated task and is yet not conclusive. To close the wide gap between understanding the molecular mechanism of pancreatic islet cells and providing effective therapeutic targets, we present a computational framework to identify potential therapeutic targets against pancreatic disorders. First, we downloaded three transcriptome expression profiling datasets pertaining to pancreatic islet cells (GSE87375, GSE79457, GSE110154) from the Gene Expression Omnibus database. For each dataset, we extracted expression profiles for two cell types. We then provided the extracted expression profile along with the cell types to our proposed constrained optimization problem of a support vector machine and to other existing methods, selecting important genes from the expression profiles. Finally, we performed (1) an evaluation from a classification perspective showing the superiority of our methods against the baseline; and (2) an enrichment analysis showing that our methods achieved better outcomes. Results for the three datasets included 44 unique genes and 10 unique transcription factors (SP1, HDAC1, EGR1, E2F1, AR, STAT6, RELA, SP3, NFKB1, and ESR1) that have been reported related to pancreatic islet functions, diseases, and therapeutic targets.

GENEvaRX: A Novel AI-Driven Method and Web Tool Can Identify Critical Genes and Effective Drugs for Lichen Planus

“…For lasso, the glmnet package [34] was used to select genes associated with non-zero coefficients, as these refer to the important genes. For the three baseline methods (i.e., SAM, limma, and t-test), we employed the p.adjust function coupled with the "BH" option to compute adjusted p-values, setting a threshold of p < 0.01 as in [22,35].…”

“…(1) We introduce a computational framework based on machine learning to extract more biological knowledge pertaining to LP. Our framework consists of three new variants of support vector machines (SVM) coupled with enrichment analysis tools, including Enrichr and Metascape [21,22] .…”

“…In Equation 1, the constrained optimization problem is different from the soft margin SVM in [22], as it includes additional constraint ԡW ԡ ଵ λ , shrinking weights for genes with less prediction power closer to zero. That leads to increased sparsity for weight vector w. (…”