Prediction of CD44 Structure by Deep Learning-Based Protein Modeling

CD44 is a cell surface glycoprotein transmembrane receptor that involved in cell–cell and cell–matrix interactions. It crucially associates with several molecules composing the extracellular matrix, main one of which hyaluronic acid. ubiquitously expressed various types cells regulation important signaling pathways, thus playing key role physiological pathological processes. Structural information about is, therefore, fundamental for understanding mechanism action this developing effective treatments against its aberrant expression dysregulation frequently associated conditions. To date, only structure hyaluronan-binding domain (HABD) has been experimentally determined. elucidate nature CD44s, most isoform, we employed recently developed deep-learning-based tools D-I-TASSER, AlphaFold2, RoseTTAFold an initial structural prediction full-length receptor, accompanied by molecular dynamics simulations on promising model. All three approaches correctly predicted HABD, AlphaFold2 outperforming D-I-TASSER comparison crystallographic HABD confidence predicting helix. Low regions were also predicted, largely corresponded to disordered CD44s. These allow perform unconventional activity.