Table 3.
Predictive performance of the KNN model in identifying the human‐infecting viruses from a reported human blood DNA virome study. a Raw read in the study. 1 kb, 1,000 bp
| Length of read/contig (L) | Number of reads/contigs | Proportion of correct predictions | Overall predictive accuracy | ||
|---|---|---|---|---|---|
| Human‐infecting | Other | Human‐infecting | Other | ||
| L = 150 bpa | 14,010,527 | 231,801 | 0.81 | 0.84 | 0.82 |
| L < 1 kb | 222 | 75 | 0.84 | 0.15 | 0.67 |
| 1 kb ≤ L < 3 kb | 61 | 9 | 0.93 | 0 | 0.81 |
| 3 kb ≤ L < 5 kb | 13 | 3 | 0.92 | 0 | 0.75 |
| 5 kb ≤ L < 10 kb | 10 | 0 | 1 | 0 | 1 |
| L ≥ 10 kb | 3 | 0 | 1 | 0 | 1 |
This article is being made freely available through PubMed Central as part of the COVID-19 public health emergency response. It can be used for unrestricted research re-use and analysis in any form or by any means with acknowledgement of the original source, for the duration of the public health emergency.