detecting Sequence Critical fOr Phase sEparation

Welcome to dSCOPE

Recently, more and more experimental studies have proved that liquid-liquid phase separation (LLPS) regulates the formation of membraneless organelles in cells. Phase separation mediates intracellular biological processes, such as signal transduction, transcriptional regulation, stress response, etc.. Although the mechanism details for LLPS is still unclear, it is identified that a number of particular sequence patterns in proteins are critical for regulating LLPS.

dSCOPE is a web server developed for detecting sequences critical for phase separation related proteins. Based on random forest algorithm, the predictor achieved promising performances with three bright spots as follows: ⅰ) Multiple features are extracted to build the prediction model; ⅱ) Various sequence and structural properties including phase separation region, disorder, exposed & buried, polar, low complexity region, charge, secondary structure, prion-like region, surface accessibility, hydropathy, subcellular location are visualized; ⅲ) Pre-predicted key regions of phase separation for human proteome are provided.

Algorithm for prediction of key regions for phase separation

•  Sliding window and feature extraction to build models.

•  Feature extraction including disorder, exposed & buried, polar, low complexity region, charge, prion-like region, surface accessibility, hydropathy, and four sequence coding features.

•  Random forest is utilized to predict key regions.

Prediction results of dSCOPE

•  The predicted sequence region crucial for phase separation.

•  The subcellular location of the protein is displayed.

•  The sequence and structural characteristics of the protein are also available.