Protein and other biomedical entities such as a gene, chromosome names are key elements in bioinformatics. Identifying them individually from the pdf file is very challenging. Because a text pdf document can contain lots of information, identifying them is not so much easy task. So the main focus in our project is converting the pdf file to humanreadable text file then we will have to find the gene and other entities from the GENIA tagger website database. Using natural language processing GENIA tagger will give us the name of all the protein, gene, and other biomedical entity name. After identifying them, we will save it to database. Then we will visualize the related data.