INFLAMeR: a machine learning algorithm based on large-scale perturbation screening identified new lncRNAs regulating differentiation and survival of leukaemia cells

Long non-coding RNAs (lncRNAs) are a diverse group of transcripts with poorly understoodfunctionality. To address this gap, we developed INFLAMeR, an advanced machine learningmodel trained on CRISPRi screening data, to predict functional lncRNAs using comprehensivegenetic features. We experimentally validated the predictions by assessing their impact on cellproliferation and anticancer drug resistance. Among the selected lncRNAs, 85% showedsignificant effects upon knockdown, while low-scoring lncRNAs had no discernible impact.Notably, our study elucidated the functional role of SNHG6 in hematopoietic differentiation.INFLAMeR greatly enhances the prediction of functional lncRNAs, providing valuable insightsinto their regulatory landscape. By integrating INFLAMeR with experimental validation, we canidentify and characterize functional lncRNAs in a cell-type-specific manner, contributing to adeeper understanding of their involvement in cellular processes. Our findings revealed insightsinto lncRNA biology and a framework for improving the identification of functional lncRNAs.