Knowledge Extraction and Extrapolation Using Ancient and Modern Biomedical Literature

Extraction of knowledge from biomedical literature is one of the major problems for researchers. This primarily involves identification of novel associations between biological objects (genes, proteins, diseases, medicines etc.). These associations are commonly extracted by mining biomedical resources such as the PUBMED which contains a large volume of information. An automated approach towards this end will reduce a substantial amount of time for biomedical researchers. In this paper we discuss a methodology to extract such associations and to assign a significance measure to the generated hypotheses. The computed significance value for the extracted knowledge can be considered as association strength between biological objects. The generated hypotheses with large significance can be considered for further experimental validation by biologists. In this paper we conduct two different validation studies of the results, which provide justification for the approach that was followed to generate the hypotheses.