DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings

TL;DR

This paper introduces DrugDBEmbed, a supervised Bi-LSTM-based method for generating semantic column encodings in relational databases, improving the accuracy of drug-drug interaction predictions and enabling effective semantic queries.

Contribution

It presents a novel supervised encoding approach for multi-token columns using Bi-LSTM, outperforming unsupervised methods in drug interaction prediction and semantic querying.

Findings

High accuracy in DDI prediction using supervised encodings

Effective semantic query simulation on relational data

Supervised column encodings outperform averaging token vectors

Abstract

Traditional relational databases contain a lot of latent semantic information that have largely remained untapped due to the difficulty involved in automatically extracting such information. Recent works have proposed unsupervised machine learning approaches to extract such hidden information by textifying the database columns and then projecting the text tokens onto a fixed dimensional semantic vector space. However, in certain databases, task-specific class labels may be available, which unsupervised approaches are unable to lever in a principled manner. Also, when embeddings are generated at individual token level, then column encoding of multi-token text column has to be computed by taking the average of the vectors of the tokens present in that column for any given row. Such averaging approach may not produce the best semantic vector representation of the multi-token text column, as observed while encoding paragraphs or documents in natural language processing domain. With these shortcomings in mind, we propose a supervised machine learning approach using a Bi-LSTM based sequence encoder to directly generate column encodings for multi-token text columns of the DrugBank database, which contains gold standard drug-drug interaction (DDI) labels. Our text data driven encoding approach achieves very high Accuracy on the supervised DDI prediction task for some columns and we use those supervised column encodings to simulate and evaluate the Analogy SQL queries on relational data to demonstrate the efficacy of our technique.