CAtboost-based method for predicting MEthyLatIon stAtes(English)

• a CatBoost gradient boosting method for predicting the missing methylation states based on the locally paired similarity of intercellular methylation patterns. On real single-cell methylation data sets, CaMelia yields significant imputation performance gains. Furthermore, applying the imputed data to the downstream analysis of cell-type identification, it is found that CaMelia helps to discover more intercellular differentially methylated loci that were masked by the sparsity in raw data, and the clustering results demonstrate that CaMelia could preserve cell-cell relationships and improve the identification of cell types and cell subpopulations
• Genomics, Epigenetics
• https://doi.org…rmatics/btab029