Deep learning in systems medicine

Haiying Wang; Estelle Pujos-Guillot; Blandine Comte; Joao Luis de Miranda; Vojtech Spiwok; Ivan Chorbev; Filippo Castiglione; Paolo Tieri; Steven Watterson; Roisin McAllister; Tiago de Melo Malaquias; Massimiliano Zanin; Taranjit Singh Rai; Huiru Zheng

doi:10.1093/bib/bbaa237

Deep learning in systems medicine

Brief Bioinform. 2021 Mar 22;22(2):1543-1559. doi: 10.1093/bib/bbaa237.

Authors

Affiliations

¹ computer science at Ulster University.
² metabolomic platform dedicated to metabolism studies in nutrition and health in the French National Research Institute for Agriculture, Food and Environment.
³ French National Research Institute for Agriculture, Food and Environment.
⁴ (ESTG/IPP) and a Researcher (CERENA/IST) in optimization methods and process systems engineering.
⁵ Molecular Modelling Researcher applying machine learning to accelerate molecular simulations.
⁶ Faculty for Computer Science and Engineering, University Ss Cyril and Methodius in Skopje, North Macedonia working in the area of eHealth and assistive technologies.
⁷ Computer Scientist working at the National Research Council of Italy.
⁸ National Research Council of Italy (CNR) and a lecturer at Sapienza University in Rome, working in the field of network medicine and computational biology.
⁹ computational biology at Ulster University.
¹⁰ Research Associate working in CTRIC, University of Ulster, Derry, and has worked in clinical and academic roles in the fields of molecular diagnostics and biomarker discovery.
¹¹ Research Associate in CTIRC, Derry, UK.
¹² Researcher working in the Institute for Cross-Disciplinary Physics and Complex Systems, Spain, with an interest on data analysis and integration using statistical physics techniques.
¹³ Lecturer in cellular ageing at the Centre for Stratified Medicine. Dr Rai's research interests are in cellular senescence, which is thought to promote cellular and tissue ageing in disease, and the development of senolytic compounds to restrict this process.
¹⁴ Professor of computer sciences at Ulster University.

Abstract

Systems medicine (SM) has emerged as a powerful tool for studying the human body at the systems level with the aim of improving our understanding, prevention and treatment of complex diseases. Being able to automatically extract relevant features needed for a given task from high-dimensional, heterogeneous data, deep learning (DL) holds great promise in this endeavour. This review paper addresses the main developments of DL algorithms and a set of general topics where DL is decisive, namely, within the SM landscape. It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine. Several key challenges have been highlighted including delivering clinical impact and improving interpretability. We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease. The review offers valuable insights and informs the research in DL and SM.

Keywords: biomarker discovery; data integration; deep learning (DL); disease classification; systems medicine (SM).

Publication types

Research Support, Non-U.S. Gov't
Review

MeSH terms

Algorithms
Biomarkers / metabolism
Deep Learning*
Disease / classification
Electronic Health Records
Genomics
Humans
Metabolomics
Neural Networks, Computer
Precision Medicine / methods
Proteomics
Systems Analysis*
Transcriptome

Substances

Biomarkers