1
|
Inoue Y, Fu T, Luna A. GraphPINE: Graph Importance propagation for interpretable drug response prediction. ARXIV 2025:arXiv:2504.05454v1. [PMID: 40297226 PMCID: PMC12036428] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Subscribe] [Scholar Register] [Indexed: 04/30/2025]
Abstract
Explainability is necessary for many tasks in biomedical research. Recent explainability methods have focused on attention, gradient, and Shapley value. These do not handle data with strong associated prior knowledge and fail to constrain explainability results based on known relationships between predictive features. We propose GraphPINE, a graph neural network (GNN) architecture leveraging domain-specific prior knowledge to initialize node importance optimized during training for drug response prediction. Typically, a manual post-prediction step examines literature (i.e., prior knowledge) to understand returned predictive features. While node importance can be obtained for gradient and attention after prediction, node importance from these methods lacks complementary prior knowledge; GraphPINE seeks to overcome this limitation. GraphPINE differs from other GNN gating methods by utilizing an LSTM-like sequential format. We introduce an importance propagation layer that unifies 1) updates for feature matrix and node importance and 2) uses GNN-based graph propagation of feature values. This initialization and updating mechanism allows for informed feature learning and improved graph representation. We apply GraphPINE to cancer drug response prediction using drug screening and gene data collected for over 5,000 gene nodes included in a gene-gene graph with a drug-target interaction (DTI) graph for initial importance. The gene-gene graph and DTIs were obtained from curated sources and weighted by article count discussing relationships between drugs and genes. GraphPINE achieves a PR-AUC of 0.894 and ROC-AUC of 0.796 across 952 drugs. Code is available at https://anonymous.4open.science/r/GraphPINE-40DE.
Collapse
Affiliation(s)
- Yoshitaka Inoue
- Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN, USA
- Computational Biology Branch, National Library of Medicine, Developmental Therapeutics Branch, National Cancer Institute, Bethesda, MD, USA
| | - Tianfan Fu
- Department of Computer Science, Nanjing University, Nanjing, Jiangsu, China
| | - Augustin Luna
- Computational Biology Branch, National Library of Medicine, Developmental Therapeutics Branch, National Cancer Institute, Bethesda, MD, USA
| |
Collapse
|
2
|
Wang G, Lou X, Guo F, Kwok D, Cao C. EHR-HGCN: An Enhanced Hybrid Approach for Text Classification Using Heterogeneous Graph Convolutional Networks in Electronic Health Records. IEEE J Biomed Health Inform 2024; 28:1668-1679. [PMID: 38133976 DOI: 10.1109/jbhi.2023.3346210] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/24/2023]
Abstract
Text classification is a central part of natural language processing, with important applications in understanding the knowledge behind biomedical texts including electronic health records (EHR). In this article, we propose a novel heterogeneous graph convolutional network method for classifying EHR texts. Our method, called EHR-HGCN, is able to combine context-sensitive word and sentence embeddings with structural sentence-level and word-level relation information to perform text classification. EHR-HGCN reframes EHR text classification as a graph classification task to better capture structural information about the document using a heterogeneous graph. To mine contextual information from a document, EHR-HGCN first applies a bidirectional recurrent neural network (BiRNN) on word embeddings obtained via Global Vectors for word representation (GloVe) to obtain context-sensitive word-level and sentence-level embeddings. To mine structural relationships from the document, EHR-HGCN then constructs a heterogeneous graph over the word and sentence embeddings, where sentence-word and word-word relationships are represented by graph edges. Finally, a heterogeneous graph convolutional neural network is used to classify documents by their graph representation. We evaluate EHR-HGCN on a variety of standard text classification benchmarks and find that EHR-HGCN has higher accuracy and F1-score than other representative machine learning and deep learning methods. We also apply EHR-HGCN to the MedLit benchmark and find it performs with high accuracy and F1-score on the task of section classification in EHR texts. Our ablation experiments show that the heterogeneous graph construction and heterogeneous graph convolutional network are critical to the performance of EHR-HGCN.
Collapse
|
3
|
Wang LH, Liu XM, Liu Y, Li HR, Liu JQI, Yang LB. Emergency entity relationship extraction for water diversion project based on pre-trained model and multi-featured graph convolutional network. PLoS One 2023; 18:e0292004. [PMID: 37812633 PMCID: PMC10561837 DOI: 10.1371/journal.pone.0292004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Accepted: 09/10/2023] [Indexed: 10/11/2023] Open
Abstract
Using information technology to extract emergency decision-making knowledge from emergency plan documents is an essential means to enhance the efficiency and capacity of emergency management. To address the problems of numerous terminologies and complex relationships faced by emergency knowledge extraction of water diversion project, a multi-feature graph convolutional network (PTM-MFGCN) based on pre-trained model is proposed. Initially, through the utilization of random masking of domain-specific terminologies during pre-training, the model's comprehension of the meaning and application of such terminologies within specific fields is enhanced, thereby augmenting the network's proficiency in extracting professional terminologies. Furthermore, by introducing a multi-feature adjacency matrix to capture a broader range of neighboring node information, thereby enhancing the network's ability to handle complex relationships. Lastly, we utilize the PTM-MFGCN to achieve the extraction of emergency entity relationships in water diversion project, thus constructing a knowledge graph for water diversion emergency management. The experimental results demonstrate that PTM-MFGCN exhibits improvements of 2.84% in accuracy, 4.87% in recall, and 5.18% in F1 score, compared to the baseline model. Relevant studies can effectively enhance the efficiency and capability of emergency management, mitigating the impact of unforeseen events on engineering safety.
Collapse
Affiliation(s)
- Li Hu Wang
- School of Management and Economics, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
| | - Xue Mei Liu
- School of Management and Economics, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
- School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
- Collaborative Innovation Centre for Efficient Utilization of Water Resources, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
| | - Yang Liu
- Collaborative Innovation Centre for Efficient Utilization of Water Resources, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
| | - Hai Rui Li
- School of Management and Economics, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
| | - Jia QI Liu
- Collaborative Innovation Centre for Efficient Utilization of Water Resources, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
| | - Li Bo Yang
- School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou, Henan, 450046, China
| |
Collapse
|
4
|
Lin L, Xiong M, Zhang G, Kang W, Sun S, Wu S, Initiative Alzheimer’s Disease Neuroimaging. A Convolutional Neural Network and Graph Convolutional Network Based Framework for AD Classification. SENSORS (BASEL, SWITZERLAND) 2023; 23:1914. [PMID: 36850510 PMCID: PMC9961367 DOI: 10.3390/s23041914] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 12/24/2022] [Revised: 01/29/2023] [Accepted: 02/01/2023] [Indexed: 06/18/2023]
Abstract
The neuroscience community has developed many convolutional neural networks (CNNs) for the early detection of Alzheimer's disease (AD). Population graphs are thought of as non-linear structures that capture the relationships between individual subjects represented as nodes, which allows for the simultaneous integration of imaging and non-imaging information as well as individual subjects' features. Graph convolutional networks (GCNs) generalize convolution operations to accommodate non-Euclidean data and aid in the mining of topological information from the population graph for a disease classification task. However, few studies have examined how GCNs' input properties affect AD-staging performance. Therefore, we conducted three experiments in this work. Experiment 1 examined how the inclusion of demographic information in the edge-assigning function affects the classification of AD versus cognitive normal (CN). Experiment 2 was designed to examine the effects of adding various neuropsychological tests to the edge-assigning function on the mild cognitive impairment (MCI) classification. Experiment 3 studied the impact of the edge assignment function. The best result was obtained in Experiment 2 on multi-class classification (AD, MCI, and CN). We applied a novel framework for the diagnosis of AD that integrated CNNs and GCNs into a unified network, taking advantage of the excellent feature extraction capabilities of CNNs and population-graph processing capabilities of GCNs. To learn high-level anatomical features, DenseNet was used; a set of population graphs was represented with nodes defined by imaging features and edge weights determined by different combinations of imaging or/and non-imaging information, and the generated graphs were then fed to the GCNs for classification. Both binary classification and multi-class classification showed improved performance, with an accuracy of 91.6% for AD versus CN, 91.2% for AD versus MCI, 96.8% for MCI versus CN, and 89.4% for multi-class classification. The population graph's imaging features and edge-assigning functions can both significantly affect classification accuracy.
Collapse
Affiliation(s)
- Lan Lin
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | | | | | | | | | | | | |
Collapse
|
5
|
Yang Y, Lu Y, Yan W. A comprehensive review on knowledge graphs for complex diseases. Brief Bioinform 2023; 24:6931722. [PMID: 36528805 DOI: 10.1093/bib/bbac543] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/22/2022] [Revised: 11/02/2022] [Accepted: 11/10/2022] [Indexed: 12/23/2022] Open
Abstract
In recent years, knowledge graphs (KGs) have gained a great deal of popularity as a tool for storing relationships between entities and for performing higher level reasoning. KGs in biomedicine and clinical practice aim to provide an elegant solution for diagnosing and treating complex diseases more efficiently and flexibly. Here, we provide a systematic review to characterize the state-of-the-art of KGs in the area of complex disease research. We cover the following topics: (1) knowledge sources, (2) entity extraction methods, (3) relation extraction methods and (4) the application of KGs in complex diseases. As a result, we offer a complete picture of the domain. Finally, we discuss the challenges in the field by identifying gaps and opportunities for further research and propose potential research directions of KGs for complex disease diagnosis and treatment.
Collapse
Affiliation(s)
- Yang Yang
- School of Computer Science & Technology, Soochow University, Suzhou 215000, China.,Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 210000, China
| | - Yuwei Lu
- School of Computer Science & Technology, Soochow University, Suzhou 215000, China.,Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing 210000, China
| | - Wenying Yan
- Department of Bioinformatics, School of Biology and Basic Medical Sciences, Medical College of Soochow University, and Center for Systems Biology, Soochow University, Suzhou 215123, China
| |
Collapse
|
6
|
Li Z, Wang M, Peng D, Liu J, Xie Y, Dai Z, Zou X. Identification of Chemical-Disease Associations Through Integration of Molecular Fingerprint, Gene Ontology and Pathway Information. Interdiscip Sci 2022; 14:683-696. [PMID: 35391615 DOI: 10.1007/s12539-022-00511-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/28/2021] [Revised: 03/16/2022] [Accepted: 03/17/2022] [Indexed: 06/14/2023]
Abstract
The identification of chemical-disease association types is helpful not only to discovery lead compounds and study drug repositioning, but also to treat disease and decipher pathomechanism. It is very urgent to develop computational method for identifying potential chemical-disease association types, since wet methods are usually expensive, laborious and time-consuming. In this study, molecular fingerprint, gene ontology and pathway are utilized to characterize chemicals and diseases. A novel predictor is proposed to recognize potential chemical-disease associations at the first layer, and further distinguish whether their relationships belong to biomarker or therapeutic relations at the second layer. The prediction performance of current method is assessed using the benchmark dataset based on ten-fold cross-validation. The practical prediction accuracies of the first layer and the second layer are 78.47% and 72.07%, respectively. The recognition ability for lead compounds, new drug indications, potential and true chemical-disease association pairs has also been investigated and confirmed by constructing a variety of datasets and performing a series of experiments. It is anticipated that the current method can be considered as a powerful high-throughput virtual screening tool for drug researches and developments.
Collapse
Affiliation(s)
- Zhanchao Li
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou, 510006, People's Republic of China.
- NMPA Key Laboratory for Technology Research and Evaluation of Pharmacovigilance, Guangzhou, 510006, People's Republic of China.
- Key Laboratory of Digital Quality Evaluation of Chinese Materia Medica of State Administration of Traditional Chinese Medicine, Guangzhou, 510006, People's Republic of China.
| | - Mengru Wang
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou, 510006, People's Republic of China
| | - Dongdong Peng
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou, 510006, People's Republic of China
| | - Jie Liu
- School of Chemistry and Chemical Engineering, Guangdong Pharmaceutical University, Guangzhou, 510006, People's Republic of China
| | - Yun Xie
- HuiZhou University, Huizhou, 516007, People's Republic of China
| | - Zong Dai
- School of Biomedical Engineering, Sun Yat-Sen University, Guangzhou, 510275, People's Republic of China
| | - Xiaoyong Zou
- School of Chemistry, Sun Yat-Sen University, Guangzhou, 510275, People's Republic of China.
| |
Collapse
|