Figure - PMC

Skip to main content

An official website of the United States government

Here's how you know

Here's how you know

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

View full-text article in PMC

. 2018 Apr 30;46(14):e82. doi: 10.1093/nar/gky308

Search in PMC
Search in PubMed
View in NLM Catalog
Add to search

© The Author(s) 2018. Published by Oxford University Press on behalf of Nucleic Acids Research.

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com

PMC Copyright notice

Figure 7. — Evaluation of clustering performance. One third of cells were randomly selected each time and the spectral clustering was repeated 50 times. Spectral clustering was performed on the sampled cells with (A, C) 47 centers or (B, D) nine centers. F1 score (A and B) and G score (C and D) were calculated based on the precision and recall values. We counted each cell pair as true positive (tp) or false positive (fp) based on whether they were correctly clustered together. We also counted true negatives (tn) and false negatives (fn) based on whether a cell pair was correctly assigned to different clusters. Precision is calculated as . Recall is calculated as . Then and . Five scenarios of cell inclusion for F1 and G score calculation are presented: all selected cell pairs (‘all’), cell pairs with more than 250k, 500k, 750k and 1M mapped reads per cell. The mean and standard deviation of F1 and G scores are shown.

Inline graphic — Evaluation of clustering performance. One third of cells were randomly selected each time and the spectral clustering was repeated 50 times. Spectral clustering was performed on the sampled cells with (A, C) 47 centers or (B, D) nine centers. F1 score (A and B) and G score (C and D) were calculated based on the precision and recall values. We counted each cell pair as true positive (tp) or false positive (fp) based on whether they were correctly clustered together. We also counted true negatives (tn) and false negatives (fn) based on whether a cell pair was correctly assigned to different clusters. Precision is calculated as . Recall is calculated as . Then and . Five scenarios of cell inclusion for F1 and G score calculation are presented: all selected cell pairs (‘all’), cell pairs with more than 250k, 500k, 750k and 1M mapped reads per cell. The mean and standard deviation of F1 and G scores are shown.