Table 3. Variant extraction results on the Variome corpus.
Results for exact and partial matching are present. Each row shows the performance of each method in terms of true positives (TP), false negatives (FN), false positives (FP), Precision, Recall and F1 measure (F1). The tools are Extractor of Mutations (EMU), OpenMutationMiner (OMM), MutationFinder (MF), tmVar and SNP Extraction Tool for Human Variations (SETH) and their combination (either selecting the longest span Combined_longest or the shortest span Combined_shortest).
Exact | TP | FN | FP | Precision | Recall | F1 | Char Overlap (%) |
---|---|---|---|---|---|---|---|
EMU
OMM MF tmVar SETH Combined_shortest Combined_longest |
66
7 7 81 81 34 78 |
52
111 111 37 37 84 40 |
25
56 10 26 10 76 32 |
0.7253
0.1111 0.4118 0.7570 0.8901 0.3091 0.7091 |
0.5593
0.0593 0.0593 0.6864 0.6864 0.2881 0.661 |
0.6316
0.0773 0.1037 0.7200 0.7751 0.2982 0.6842 |
100.00
100.00 100.00 100.00 100.00 100.00 100.00 |
Partial | TP | FN | FP | Precision | Recall | F1 | Char Overlap (%) |
EMU
OMM MF tmVar SETH Combined_shortest Combined_longest |
90
64 16 107 90 110 110 |
28
54 102 11 28 8 8 |
3
1 1 3 1 3 3 |
0.9677
0.9846 0.9412 0.9727 0.9890 0.9735 0.9735 |
0.7627
0.5424 0.1356 0.9068 0.7627 0.9322 0.9322 |
0.8531
0.6995 0.2370 0.9386 0.8612 0.9524 0.9524 |
82.08
70.01 52.91 81.11 80.99 82.03 83.03 |