“…Therefore, in order to minimize this effect, the synthetic genome modeling approach was repeated for individual tissue types which were represented by at least 16 high-quality cell lines (as defined by F-measure of greater than or equal to 0.8) using the same parameters described above. All of the analyses were performed using Python version 3.6 using multiple packages including pandas (Reback et al, 2020), NumPy (C. R. Harris et al, 2020), the sklearn.metrics, sklearn.utils, resample modules in SciKits (Buitinck et al, 2013), Matplotlib (Hunter, 2007), seaborn (Waskom et al, 2020), and scipy (SciPy 1.0 Contributors et al, 2020).…”