Machine Learning for Integrating Data in Biology and Medicine: Principles, Practice, and Opportunities

By Marinka Zitnik, Francis Nguyen, Jure Leskovec, Anna Goldenberg, Michael M. Hoffman. 2018

586 citations recorded by the source corpus.

New technologies have enabled the investigation of biology and human health at an unprecedented scale and in multiple dimensions. These dimensions include myriad properties describing genome, epigenome, transcriptome, microbiome, phenotype, and lifestyle. No single data type, however, can capture the complexity of all the factors relevant to understanding a phenomenon such as a disease. Integrative methods that combine data from multiple technologies have thus emerged as critical statistical and computational approaches. The key challenge in developing such approaches is the identification of effective models to provide a comprehensive and relevant systems view. An ideal method can answer a biological or medical question, identifying important features and predicting outcomes, by harnessing heterogeneous data across several dimensions of biological variation. In this Review, we describe the principles of data integration and discuss current methods and available implementations. We provide examples of successful data integration in biology and medicine. Finally, we discuss current challenges in biomedical integrative methods and our perspective on the future development of the field.

Subfields: Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

Citations in the corpus

How Machine Learning will Transform Biomedicine (2020, unknown): “…x-rays (McKinney et al., 2020; Wu et al., 2019), discover new antibiotics (Stokes et al., 2020), predict onset of gestational diabetes from electronic health records (Artzi et al., 2020), and identify clusters of patients that share a molecular signature of treatment response (Zitnik et al., 2019).”
Evaluation of artificial intelligence techniques in disease diagnosis and prediction (2023, background): “AI technologies are increasingly used in medicine to succeed and gain more accurate knowledge about dangerous disorders and diseases [71, 72].”
Network medicine framework for identifying drug-repurposing opportunities for COVID-19 (2020, methodology): “Here, we implement three network-medicine drug-repurposing algorithms that rely on artificial intelligence (AI) (15, 16), network diffusion”
Graph Representation Learning in Biomedicine and Healthcare (2021, unknown): “…17,18 ; graph neural networks 19–21 (GNNs); representation learning for homogeneous and heterogeneous graphs 22–24 , solely heterogeneous graphs 25 and dynamic graphs 26 ; data fusion 27 ; network propagation 28 ; topological data analysis 29 (TDA); and the creation of biomedical networks 9,29–32 .”
Machine learning applications in drug development (2019, methodology): “Integrating multi-view data in a drug development method has been shown to increase its accuracy [94–96].”
Empowering Biomedical Discovery with AI Agents (2024, unknown): “Much human eﬀort in building systems for biomedical research is dedicated to gathering and preparing such data for use in ML models (e.g., speciﬁc to a particular modality, such as graphs, time series, or discrete sequences [193]).”
High-performance medicine: the convergence of human and artificial intelligence (2019, background): “While this debate of whether it is acceptable to use nontransparent algorithms for patient care is unsettled, it is notable that many aspects of the practice of medicine are unexplained, such as prescription of a drug without a known mechanism of action.”
Interpretable bilinear attention network with domain adaptation improves drug–target prediction (2022, unknown): “The learned drug and protein representation vectors are combined with a simple concatenation; (4) MolTrans16, a deep learning model adapting transformer architecture to encode drug and protein information, and a CNN-based interactive module to learn sub-structural interaction.”
Integration strategies of multi-omics data for machine learning analysis (2021, background): “Zitnik et al. (2019) [17] differentiated two types of integration.”
The promise of artificial intelligence: a review of the opportunities and challenges of artificial intelligence in healthcare. (2021, methodology): “26 AI is therefore already augmenting our understanding of biology and pathology, with future application of these algorithms as clinical decision support tools requiring further acquisition of both -omics and phenotype data.”