Simple and efficient machine learning frameworks for identifying protein-protein interaction relevant articles and experimental methods used to study the interactions

Table 6 Runs submitted for IMT

Run number	Label	Algorithm	Number of features
1	j48-21	J48	All (21 features)
2	rc-21	Random Committee	All (21 features)
3	rf-21	Random Forest	All (21 features)
4	j48-14	J48	14 features
5	rf-12	Random Forest	12 features
6	rc-12	Random Committee	12 features
7	rc-14	Random Committee	14 features
8	rf-7	Random Forest	7 features
9	nbt-7	Naïve Bayes Tree	7 features
10	rf-15	Random Forest	15 features

For the BioCreative III challenge, each participating team was allowed to submit 10 runs for IMT. Five runs could be submitted offline and the other five runs could be submitted online, using XML-RPC. Runs 1-5 were submitted offline, while runs 6-10 were submitted online. For all runs, we combined the training and the development data. We submitted 10 runs, listed here.

ISSN: 1471-2105