Table 2.

We defined 10 different labels for tokens within mutation mentions: reference sequence (A); mutation position (P); mutation type (T); wild-type (W); mutant (M); frame shift (F); frame shift position (S); duplication time (D); SNP (R); other inside mutation tokens (I)

Mutation types	A	P	T	W	M	F	S	D	R	I
Substitution	•	•	•	•	•					•
Deletion	•	•	•		•					•
Insertion	•	•	•		•					•
Insertion/deletion	•	•	•		•					•
Duplication	•	•	•	•				•		•
Frame shift	•	•	•	•	•	•	•			•
RS number									•

Each mutation type has its own set of labels (e.g. substitution corresponds to six labels).