How to deal with missing values in proteomics data
Missing values prevent the feasibility of methods for analysis, can cause bias, and may negatively impact statistical power. We developed the concept of data-driven selection of an imputation algorithm (DIMA) which optimally selects an imputation method for a given proteomics data set.
Original publication:
Egert J, Brombacher E, Warscheid B, Kreutz, C (2021): DIMA: Data-Driven Selection of an Imputation Algorithm
Check out the paper in Journal of Proteome Research