Here, we present a protocol to identify nucleotide motifs that predict the pro-inflammatory property of microRNAs (miRNAs) using machine learning. We describe steps for cell culture, miRNA transfection, pro-inflammatory classification, and k-mer discovery. We detail procedures for combining in vitro macrophage assays with exhaustive motif searches and least absolute shrinkage and selection operator (LASSO) regression to define nucleotide sequence features that distinguish pro-inflammatory miRNAs. This workflow enables systematic motif discovery and biomarker prioritization directly from miRNA sequences, streamlining translational applications without extensive functional screening. For complete details on the use and execution of this protocol, please refer to Ren et al. 1 • Cell culture and RNA transfection steps are provided to test miRNA activities • In vitro assay of MIP-2 production defines inflammatory microRNAs • Exhaustive search algorithm identifies nucleotide motifs linked to inflammatory miRNAs Publisher’s note: Undertaking any experimental protocol requires adherence to local institutional guidelines for laboratory safety and ethics. Here, we present a protocol to identify nucleotide motifs that predict the pro-inflammatory property of microRNAs (miRNAs) using machine learning. We describe steps for cell culture, miRNA transfection, pro-inflammatory classification, and k-mer discovery. We detail procedures for combining in vitro macrophage assays with exhaustive motif searches and LASSO regression to define nucleotide sequence features that distinguish pro-inflammatory miRNAs. This workflow enables systematic motif discovery and biomarker prioritization directly from miRNA sequences, streamlining translational applications without extensive functional screening.
Lin et al. (Thu,) studied this question.