Multimodal Genotype and Phenotype Data Integration to Improve Partial Data-Based Longitudinal Prediction

Journal of computational biology: A journal of computational molecular cell biology

article

Alireza Ganjdanesh¹  Jipeng Zhang²  Sarah Yan³  Wei Chen²  Heng Huang¹ 

[1] Department of Electrical and Computer Engineering, University of Pittsburgh;Department of Biostatistics, University of Pittsburgh;West Windsor-Plainsboro High School South, Princeton Junction;Department of Pediatrics, UPMC Children’s Hospital of Pittsburgh;Department of Human Genetics, University of Pittsburgh

关键词: age-related macular degeneration;    genotype;    imaging genetics;    longitudinal prediction;    mutual learning;    phenotype;   

DOI  :  10.1089/cmb.2022.0378

学科分类：生物科学（综合）

来源: Mary Ann Liebert, Inc. Publishers

【 摘 要 】

Multimodal data analysis has attracted ever-increasing attention in computational biology and bioinformatics community recently. However, existing multimodal learning approaches need all data modalities available at both training and prediction stages, thus they cannot be applied to many real-world biomedical applications, which often have a missing modality problem as the collection of all modalities is prohibitively costly. Meanwhile, two diagnosis-related pieces of information are of main interest during the examination of a subject regarding a chronic disease (with longitudinal progression): their current status (diagnosis) and how it will change before next visit (longitudinal outcome). Correct responses to these queries can identify susceptible individuals and provide the means of early interventions for them. In this article, we develop a novel adversarial mutual learning framework for longitudinal disease progression prediction, allowing us to leverage multiple data modalities available for training to train a performant model that uses a single modality for prediction. Specifically, in our framework, a single-modal model (which utilizes the main modality) learns from a pretrained multimodal model (which accepts both main and auxiliary modalities as input) in a mutual learning manner to (1) infer outcome-related representations of the auxiliary modalities based on its own representations for the main modality during adversarial training and (2) successfully combine them to predict the longitudinal outcome. We apply our method to analyze the retinal imaging genetics for the early diagnosis of age-related macular degeneration (AMD) disease, that is, simultaneous assessment of the severity of AMD at the time of the current visit and the prognosis of the condition at the subsequent visit. Our experiments using the Age-Related Eye Disease Study dataset show that our method is more effective than baselines at classifying patients' current and forecasting their future AMD severity.

【 授权许可】

Unknown