Week 4: Dataset Building

Activities performed in this week

• Understand the drugbank dataset.
• Read about convolutional neural nets.
• Write code for extracting name of the drug from the drug bank ID present in the name of the smile files which were downloaded.
• Carried out exhaustive testing actitities to validate the results obtained in above activity.
• Fixed some of the issues which were discovered in the above actitity.
• Tried running the padel software on the smile files downloaded and found out that it was not working. Upon RCA it was identified that the extension of the smile files should have been smi instead of smiles.
• Updated the code to parse the xml files in DDI Corpus into pandas dataframe for semeval 2013.