Skip to main content

Table 3 Baseline model performance on the BioCreative VI precision medicine track corpus

From: Triage of documents containing protein interactions affected by mutations using an NLP based machine learning approach

Data

Precision

Recall

F1

F1 all relevant

AvPr

10f CV (IntAct)

0.7184

0.6321

0.6725

0.5507

0.7577

Validation (TM)

0.6210

0.6897

0.6536

0.6842

0.6551

10f CV (all data)

0.6891

0.6260

0.6561

0.5915

0.7225

  1. AvPr: Average precision; 10f CV: 10-fold Cross-validation; TM: Text Mining set, corpus of abstracts found with the aid of text mining methods
Back to article page

BMC Genomics

ISSN: 1471-2164

Contact us