small scale of perb_score in the output from scRank and order of the rank

Question

[alwayshope]

Dear guys,

May I know the reasonable of the small values in the output perb_score, and the order of the cells, seems the larger the rank, the more perturbation the response of the cell to the stimulation.

I tried my data, has similar results to the tutorial data. Very small perb_score(5e-6) and score of rank1 are lower than score rank5, not as the usual rank1 has the highest perb_score.

Slot "cell_type_rank":
            perb_score rank top_rank% fill method
resistant 1.101223e-06    1         0    0 scRank
sensitive 2.566986e-06    2         1    1 scRank