@article{Jung2024,

title = {Interpretable prediction of drug-drug interactions via text embedding in biomedical literature},

author = {Sunwoo Jung and Sunyong Yoo},

url = {https://www.sciencedirect.com/science/article/pii/S0010482524015816},

doi = {10.1016/j.compbiomed.2024.109496},

isbn = {0010-4825},

year  = {2025},

date = {2025-02-01},

urldate = {2025-02-01},

journal = {Computers in Biology and Medicine},

volume = {185},

pages = {109496},

abstract = {Polypharmacy is a promising approach for treating diseases, especially those with complex symptoms. However, it can lead to unexpected drug-drug interactions (DDIs), potentially reducing efficacy and triggering adverse drug reactions (ADRs). Predicting the risk of DDIs is crucial for ensuring safe drug use, particularly by identifying the types of DDIs and the mechanisms involved. Therefore, this study used biomedical literature to proposed hierarchical attention-based deep learning models to predict DDIs and their types. The proposed model consists of two components: drug embedding and DDI prediction. The drug embedding module extracts representation vectors that effectively capture drug properties using sentence and sequence embedding methods. For sentence embedding, a pre-trained biomedical language model is used to map drug-related sentences into vector space. For sequence embedding, sentence embedding vectors are sequentially fed into bidirectional long short-term memory with a hierarchical attention network, enabling the analysis of sentences relevant to DDI prediction while accounting for the order of the sentences. Finally, DDI prediction is performed using a deep neural network based on the sequence embedding vectors of a drug pair. Our model achieved high performances in the accuracy (0.85–0.90), AUROC (0.98–0.99), and AUPR (0.63–0.95) performance across 164 DDI types. Additionally, the proposed model showed improvements in up to 11 % in AUROC, and 8 % in AUPR. Furthermore, model interprets predictions by leveraging attention mechanisms and drug similarity. The results indicated that the model considered various factors beyond similarity to predict DDIs. These findings may help prevent unforeseen medical accidents and reduce healthcare costs by predicting detailed drug interaction types.},

note = {Correspondence to Sunyong Yoo},

keywords = {ADR, Artificial Intelligence, Attention mechanism, Bioinformatics, DDI, Deep learning, Text mining},

pubstate = {published},

tppubtype = {article}

}

@article{정선우2024drug,

title = {Drug-Drug Interaction Prediction Model Based on Deep Learning Using Drug Information Document Embedding},

author = {정선우 and 유선용},

url = {https://www.dbpia.co.kr/pdf/pdfView.do?nodeId=NODE11852157&googleIPSandBox=false&mark=0&minRead=10&ipRange=false&b2cLoginYN=false&icstClss=010000&isPDFSizeAllowed=true&nodeHistoryTotalCnt=2&accessgl=Y&language=ko_KR&hasTopBanner=true},

doi = {10.5626/JOK.2024.51.6.503},

issn = {2833-6296},

year  = {2024},

date = {2024-01-02},

urldate = {2024-01-02},

journal = {Journal of KIISE},

volume = {51},

number = {6},

pages = {503–512},

abstract = {다약제는 암, 고혈압, 천식 등 다양한 질병에 대하여 유망한 접근법이다. 일반적으로 병원에 방문하는 환자는 2종 이상의 약물을 처방받는다. 그러나 다약제의 사용은 개별 약물이 목표하는 작용 외에 예상치 못한 상호작용을 유발할 수 있다. 약물 간 상호작용을 사전에 예측하는 것은 안전한 약물 사용을 위한 매우 중요한 과제이다. 본 연구에서는 다약제 사용 시 발생 가능한 약물 간 상호작용 예측을 위해 개별 약물 정보를 포함한 문서를 이용하여 약물을 표현하는 문서 임베딩 기반의 딥러닝 예측 모델을 제안한다. 약물 정보 문서는 DrugBank 데이터를 이용해 약물의 설명, 적응증, 약력학 정보, 작용 기전, 독성 속성을 결합해 구축한다. 그 후 Doc2Vec, BioSentVec 언어 모델을 통해 약물 문서로부터 약물 표현 벡터를 생성한다. 두 약물 표현 벡터는 한 쌍으로 묶여 딥러닝 기반 예측 모델에 입력되고, 해당 모델은 두 약물 간 상호작용을 예측한다. 본 논문에서는 언어 임베딩 모델의 성능 비교, 데이터의 불균형도 조절 등 다양한 조건의 변화에 따른 실험 결과의 차이를 분석하여 약물 간 상호작용 예측을 위한 최적의 모델을 구축하는 것을 목표로 한다. 제안된 모델은 약물 처방 과정, 신약 개발의 임상 과정 등에서 약물간 상호작용 사전 예측을 위하여 활용될 수 있을 것으로 기대된다.},

note = {Correspondence to Sunyong Yoo},

keywords = {ADR, DDI, Deep learning, Text mining},

pubstate = {published},

tppubtype = {article}

}

@article{10.3389/fphar.2020.584875,

title = {A Deep Learning-Based Approach for Identifying the Medicinal Uses of Plant-Derived Natural Compounds},

author = {Sunyong Yoo and Hyung Chae Yang and Seongyeong Lee and Jaewook Shin and Seyoung Min and Eunjoo Lee and Minkeun Song and Doheon Lee},

url = {https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2020.584875},

doi = {10.3389/fphar.2020.584875},

issn = {1663-9812},

year  = {2020},

date = {2020-01-01},

urldate = {2020-01-01},

journal = {Frontiers in Pharmacology},

volume = {11},

pages = {584875},

abstract = {Medicinal plants and their extracts have been used as important sources for drug discovery. In particular, plant-derived natural compounds, including phytochemicals, antioxidants, vitamins, and minerals, are gaining attention as they promote health and prevent disease. Although several in vitro methods have been developed to confirm the biological activities of natural compounds, there is still considerable room to reduce time and cost. To overcome these limitations, several in silico methods have been proposed for conducting large-scale analysis, but they are still limited in terms of dealing with incomplete and heterogeneous natural compound data. Here, we propose a deep learning-based approach to identify the medicinal uses of natural compounds by exploiting massive and heterogeneous drug and natural compound data. The rationale behind this approach is that deep learning can effectively utilize heterogeneous features to alleviate incomplete information. Based on latent knowledge, molecular interactions, and chemical property features, we generated 686 dimensional features for 4,507 natural compounds and 2,882 approved and investigational drugs. The deep learning model was trained using the generated features and verified drug indication information. When the features of natural compounds were applied as input to the trained model, potential efficacies were successfully predicted with high accuracy, sensitivity, and specificity.},

keywords = {Bioinformatics, Chemical property, Deep learning, Molecular interaction, Natural product, Network analysis, Text mining},

pubstate = {published},

tppubtype = {article}

}