Research


As a research lab in Korea University, DMIS Lab focuses on AI-driven Drug Discovery, Bio Text-Mining and Web & Social Data Mining. Below are some example works introduced by lab members. More papers related to each of these topics can be found in the publications section.

AI-driven Drug Discovery and Precision Medicine

DMIS Lab aims to develop a full-scale machine learning algorithm that would facilitate data-driven drug discovery and support precision medicine.

  • Community assessment of cancer drug combination screens identifies strategies for synergy prediction (2019, biorxiv, link)
  • In Silico Drug Combination Discovery for Personalized Cancer Therapy (2018, BMC Systems Biology, link)
  • BTNET : Boosted tree based gene regulatory network inference algorithm using time-course measurement data (2018, BMC Systems Biology, link)

Biomedical Text Mining

As there is a large amount of biomedical corpus, DMIS Lab is currently developing several applications such as Bio-NER, Bio-relation extraction etc. that to help researchers make efficient use of bio-literature.

  • BioBERT: a pre-trained biomedical language representation model for biomedical text mining (2019, arxiv)
  • Drug drug interaction extraction from the literature using a recursive neural network (2018, PLOS ONE, link)
  • BEST: Next-Generation Biomedical Entity Search Tool for Knowledge Discovery from Biomedical Literature (2016, PLOS ONE, link)

Financial Data Mining

DMIS Lab aims to find viable signals with predictability in future market trends and develop algorithms for efficient business trades.

  • Global Stock Market Prediction Based on Stock Chart Images Using Deep Q-Network(2019, arxiv, link)

Web & Social Data Mining

Other topics such as POI recommendation, Machine Comprehension are currently being explored by DMIS Lab.

  • Predicting Multiple Demographic Attributes with Task Specific Embedding and Attention Network (2019, SDM19, link)
  • Content-Aware Point-of-Interest Embedding Model for Successive POI Recommendation (2018, IJCAI, link)
  • Ranking Paragraphs for Improving Answer Recall in Open-Domain Question Answering (2018, EMNLP, link)
  • Learning User Preferences and Understanding Calendar Contexts for Event Scheduling (2018, CIKM, link)