Table 1 Literature mining approaches for mutation extraction. The additional materials sections (Additional file 1) provides a more detailed description of each method.
From: Extraction of human kinase mutations from literature, databases and genotyping studies
Collection of existing mutation extraction approaches | ||
|---|---|---|
Method | Main characteristics and descriptive keywords of the approach | Ref |
MEMA | Uses regular expressions, gene and protein mention detection, co-mention proximity, OMIM validation | [19] |
MuteXt | Uses regular expressions, GPCR and NR mention detection, co-mention proximity, sequence check | [27] |
Yip et al. | Uses regular expressions, protein mention detection, SwissProt validation, extensive sequence check | [28] |
CoagMDB | Uses regular expressions, serine protease mention detection, sequence check | [41] |
Mutation GraB | Uses regular expressions, protein mention detection, graph shorted distance, sequence check | [20] |
Mutation Miner | Uses regular expressions, protein mention detection, sentence co-mention | [21] |
MuGeX | Uses regular expressions, protein mention detection, protein and DNA mutation disambiguation | [24] |
VTag | Machine learning (CRF) detection of acquired sequence variations mentions (mutations, translocations, deletions) | [26] |
OSIRISv1.2 | Detection of human gene variations corresponding to SNPs | [42] |
MutationFinder | Uses regular expressions and patterns, protein mutations, complex language expressions | [23] |