Table 3.

Basic statistics of the SNPPhenA corpus in terms of test and train parts

Item	Train	Test	Total
Files	270	90	360
Sentences	1940	685	2625
Key sentences	362	121	483
SNP	691	244	935
Phenotypes	496	158	654
SNP-Phenotype association candidates	935	365	1300
Neutral candidates	142	166	308
Negative candidates	91	29	120
Positive candidates	702	170	872