Yonghwa Choi
Researcher
Bioinformatics, Natural Language Understanding
yonghwachoi@oncomaster.co.kr | yonghwachoi@korea.ac.kr | under1210@gmail.com | +82) 10-7220-1210
Company: oncoMASTER Inc.
2022.03 - Present
Precision Medicine R&D Team
Position: Senior Research Engineer
2015.09 - Present
Advisor: Prof. Jaewoo Kang
Data Mining and Information System Lab, Department of Computer Science and Engineering, Korea University, Seoul, South Korea
2011.03 - 2015.08
Computer Science at Korea University, Seoul, South Korea
Clinical Decision Support System (2016 - 2021)
- Developed an antidepressant prescription model based on patients' diseases using `STAHL's Essential Psychopharmacology - The Prescriber's guide`.
- Developed a treatment response prediction model that predicts how much the depression score of a patient will decrease after treatment. [3]
- Collaborated with researchers and doctors from the Department of Psychiatry of Anam Hospital at Korea University to develop a clinical decision support system for Major depressive disorder(MDD).
Natural Language Understanding in Biomedical Articles (2016 - 2021)
- Gathered and processed biomedical and scientific literature for use in multiple research.
- Designed and developed a Chrome extension app that automatically extracts biomedical named entities from a PubMed abstract and generates a relation graph. [9]
- Developed a web demo for a database that contains mutation-gene-drug relation data identified by deep learning-based text mining techniques in PubMed articles. [7, 11]
- Developed a pipeline that processes biomedical and scientific literature into cloze-style Question Answering. [6, 8]
- Developed a web demo and API that extracts and highlights biomedical named entities from biomedical literature. - https://bern.korea.ac.kr/ [4]
- Evaluated manually curated questions based on facts about COVID-19 to develop a real-time Question Answering system and developed a web demo. - https://covidask.korea.ac.kr/ [11]
Opinion-based Question Answering system (2015)
- Gathered opinion-based questions (e.g., "best horror movies?" or "movies to watch with a girlfriend?") and answers from Twitter using Twitter API.
- Developed a web demo for an opinion-based QA system. [13]
EHR DREAM Challenge - Patient Mortality Prediction (2019)
- "Of patients who had at least one hospital visit, can we predict who will pass away within 6 months of their last visit?"
- Mapped medical events (condition, drug exposure, measurement, etc.) to embedding space to capture their relationship without domain knowledge.
- Participated as a leader and ranked 5th.
Multiple Myeloma DREAM Challenge (2017) [2]
- "Identify high-risk patients defined by disease progression (or death) within 18 months from time of diagnosis using RNA- or DNA-based data."
- Gathered gene signatures that are known to be associated with MM in several papers and cancer-related pathways.
- Developed an SVM classifier using important DNA and RNA features, selected from the feature selection process using LASSO.
- Ranked 3rd place in Sub-Challenge 3 (1: DNA-based data / 2: RNA-based data / 3: DNA- and RNA-based data).
Deep matching for neural IR in NAVER(2021.08 - 2021.11)
- Adapted and implemented ANCE and DANCE learning methods to ColBERT model
- "ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT"; Omar Khattab and Matei Zaharia; arXiv 2020
- "Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval"; Lee Xiong et al.; arXiv 2020
- "More Robust Dense Retrieval with Contrastive Dual Learning"; Yizhi Li et al.; ICTIR 2021
[1] "Integrated clinical and genomic models using machine-learning methods to predict the efficacy of paclitaxel-based chemotherapy in patients with advanced gastric cancer"; Yonghwa Choi*, Jangwoo Lee, Keewon Shin, Ji Won Lee, Ju Won Kim, Soohyeon Lee, Yoon Ji Choi, Kyong Hwa Park, Jwa Hoon Kim; BMC Cancer 2024
[2] "Evaluation of crowdsourced mortality prediction models as a framework for assessing artificial intelligence in medicine"; Timothy Bergquist, Thomas Schaffter, Yao Yan, Thomas Yu, Justin Prosser, Jifan Gao, Guanhua Chen, Łukasz Charzewski, Zofia Nawalany, Ivan Brugere, Renata Retkute, Alidivinas Prusokas, Augustinas Prusokas, Yonghwa Choi, Sanghoon Lee, Junseok Choe, Inggeol Lee, Sunkyu Kim, Jaewoo Kang, Sean D. Mooney*, Justin Guinney* and the Patient Mortality Prediction DREAM Challenge Consortium; JAMIA 2023
[3] "ARPNet: Antidepressant Response Prediction Model for Major Depressive Disorder"; Buru Chang*, Yonghwa Choi*, Minji Jeon, Junhyun Lee, Aram Kim, Byung-Joo Ham and Jaewoo Kang; Genes 2019
[4] "A Neural Named Entity Recognition and Multi-Type Normalization Tool for Biomedical Text Mining"; Donghyeon Kim*, Jinhyuk Lee, Chan Ho So, Hwisang Jeon, Minbyul Jeong, Yonghwa Choi, Wonjin Yoon, Mujeen Sung and Jaewoo Kang; IEEE Access 2019
[5] "ReSimNet: Drug Response Similarity Prediction based on a Siamese Neural Network"; Minji Jeon*, Donghyeon Park*, Jinhyuk Lee, Hwisang Jeon, Miyoung Ko, Sunyku Kim, Yonghwa Choi and Jaewoo Kang; Bioinformatics 2019
[6] "Can Machines Learn to Comprehend Scientific Literature?"; Donghyeon Park*, Yonghwa Choi, Daehan Kim, Minhwan Yu, Seongsoon Kim and Jaewoo Kang; IEEE Access 2019
[7] "Deep learning of mutation-gene-drug relations from the literature"; Kyubum Lee*, Byounggun Kim*, Yonghwa Choi, Sunkyu Kim, Wonho Shin, Sunwon Lee, Sungjoon Park, Seongsoon Kim, Aik Choon Tan and Jaewoo Kang; BMC Bioinformatics 2018
[8] "A Pilot Study of Biomedical Text Comprehension using an Attention-Based Deep Neural Reader: Design and Experimental Analysis"; Seongsoon Kim*, Donghyeon Park*, Yonghwa Choi*; Kyubum Lee, Byounggun Kim, Minji Jeon, Jihye Kim, Aik Choon Tan, Jaewoo Kang; JMIR Medical Informatics 2018
[9] "HiPub: translating PubMed and PMC texts to networks for knowledge discovery"; Kyubum Lee*, Wonho Shin, Byounggun Kim, Sunwon Lee, Yonghwa Choi, Sunkyu Kim, Minji Jeon, Aik Choon Tan and Jaewoo Kang; BIOINFORMATICS Vol. 32 Issue 18 Aug 2016
[10] "Artificial intelligence–based prediction of PD-1/PD-L1 immunotherapy benefit across six advanced cancers"; Yonghwa Choi*, Jisoo Hong, Doyoon Kim, Jinah Choi, Yoonji Kim, Cheul-Hun Seong, Woo Young Jang, Yoon Ji Choi, Jason K. Sa; 2025 AACR-KCA Joint Conference on Precision Medicine in Cancer; Nov 14-15 2025 (Poster)
[11] "Answering Questions on COVID-19 in Real-Time"; Jinhyuk Lee*, Sean S. Yi, Minbyul Jeong, Mujeen Sung, Wonjin Yoon, Yonghwa Choi, Mi-Young Ko, Jaewoo Kang; 1st Workshop on NLP for COVID-19 at EMNLP 2020; December 2020
[12] "Deep Learning of Mutation-Gene-Drug Relations from the Literature for Precision Medicine"; Kyubum Lee*, Byounggun Kim*, Yonghwa Choi, Sunkyu Kim, Wonho Shin, Sunwon Lee, Sungjoon Park, Seongsoon Kim, Aik Choon Tan, and Jaewoo Kang; Intelligent Systems for Molecular Biology and European Conference on Computational Biology (ISMB/ECCB 2017); Prague, Czech Republic; July 21-25 2017 (Poster)
[13] "SEMO: Searching Majority Opinions on Movies using SNS and QA Threads"; Jukyong Lee*, Yonghwa Choi, Suhkyung Kim, Seongsoon Kim and Jaewoo Kang; The 25th International World Wide Web Conference (WWW 2016); Montreal, Canada; Apr 11-15 2016 (Demo)