Machine Learning for Protein Name Extraction

A large volume of protein data has been generated as a result of biological research. This vast amount of data is generally stored in the textual form in databases such as Medline. Currently, over 11 million summaries of articles are stored in Medline. However, lack of formal structure in the articles makes difficult to retrieve and process the information stored in these articles. In this paper, we explore the use of machine learning techniques for the information extraction task and present the initial results of the conducted experiments. Particularly, we study using Hidden Markov Models (HMMs) for protein name extraction from the biological texts