A method for automatically extracting infectious disease-related primers and probes from the literature

BACKGROUND: Primer and probe sequences are the main components of nucleic acid-based detection systems. Biologists use primers and probes for different tasks, some related to the diagnosis and prescription of infectious diseases. The biological literature is the main information source for empirically validated primer and probe sequences. Therefore, it is becoming increasingly important for researchers to navigate this important information. In this paper, we present a four-phase method for extracting and annotating primer/probe sequences from the literature. These phases are: (1) convert each document into a tree of paper sections, (2) detect the candidate sequences using a set of finite state machine-based recognizers, (3) refine problem sequences using a rule-based expert system, and (4) annotate the extracted sequences with their related organism/gene information. RESULTS: We tested our approach using a test set composed of 297 manuscripts. The extracted sequences and their organism/gene annotations were manually evaluated by a panel of molecular biologists. The results of the evaluation show that our approach is suitable for automatically extracting DNA sequences, achieving precision/recall rates of 97.98% and 95.77%, respectively. In addition, 76.66% of the detected sequences were correctly annotated with their organism name. The system also provided correct gene-related information for 46.18% of the sequences assigned a correct organism name. CONCLUSIONS: We believe that the proposed method can facilitate routine tasks for biomedical researchers using molecular methods to diagnose and prescribe different infectious diseases. In addition, the proposed method can be expanded to detect and extract other biological sequences from the literature. The extracted information can also be used to readily update available primer/probe databases or to create new databases from scratch. The present work has been funded, in part, by the European Commission through the ACGT integrated project (FP6-2005-IST-026996) and the ACTION-Grid support action (FP7-ICT-2007-2-224176), the Spanish Ministry of Science and Innovation through the OntoMineBase project (ref. TSI2006-13021-C02-01), the ImGraSec project (ref. TIN2007-61768), FIS/AES PS09/00069 and COMBIOMED-RETICS, and the Comunidad de Madrid, Spain. Sí