TY - JOUR
T1 - Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine
AU - Mathema, Vivek Bhakta
AU - Sen, Partho
AU - Lamichhane, Santosh
AU - Orešič, Matej
AU - Khoomrung, Sakda
N1 - Publisher Copyright:
© 2023 The Authors
PY - 2023/1
Y1 - 2023/1
N2 - Cancer progression is linked to gene-environment interactions that alter cellular homeostasis. The use of biomarkers as early indicators of disease manifestation and progression can substantially improve diagnosis and treatment. Large omics datasets generated by high-throughput profiling technologies, such as microarrays, RNA sequencing, whole-genome shotgun sequencing, nuclear magnetic resonance, and mass spectrometry, have enabled data-driven biomarker discoveries. The identification of differentially expressed traits as molecular markers has traditionally relied on statistical techniques that are often limited to linear parametric modeling. The heterogeneity, epigenetic changes, and high degree of polymorphism observed in oncogenes demand biomarker-assisted personalized medication schemes. Deep learning (DL), a major subunit of machine learning (ML), has been increasingly utilized in recent years to investigate various diseases. The combination of ML/DL approaches for performance optimization across multi-omics datasets produces robust ensemble-learning prediction models, which are becoming useful in precision medicine. This review focuses on the recent development of ML/DL methods to provide integrative solutions in discovering cancer-related biomarkers, and their utilization in precision medicine.
AB - Cancer progression is linked to gene-environment interactions that alter cellular homeostasis. The use of biomarkers as early indicators of disease manifestation and progression can substantially improve diagnosis and treatment. Large omics datasets generated by high-throughput profiling technologies, such as microarrays, RNA sequencing, whole-genome shotgun sequencing, nuclear magnetic resonance, and mass spectrometry, have enabled data-driven biomarker discoveries. The identification of differentially expressed traits as molecular markers has traditionally relied on statistical techniques that are often limited to linear parametric modeling. The heterogeneity, epigenetic changes, and high degree of polymorphism observed in oncogenes demand biomarker-assisted personalized medication schemes. Deep learning (DL), a major subunit of machine learning (ML), has been increasingly utilized in recent years to investigate various diseases. The combination of ML/DL approaches for performance optimization across multi-omics datasets produces robust ensemble-learning prediction models, which are becoming useful in precision medicine. This review focuses on the recent development of ML/DL methods to provide integrative solutions in discovering cancer-related biomarkers, and their utilization in precision medicine.
KW - Cancer
KW - Deep learning
KW - Oncogene
KW - Precision medicine
KW - Reinforcement learning
KW - Systems medicine
UR - http://www.scopus.com/inward/record.url?scp=85147607641&partnerID=8YFLogxK
U2 - 10.1016/j.csbj.2023.01.043
DO - 10.1016/j.csbj.2023.01.043
M3 - Review Article or Literature Review
AN - SCOPUS:85147607641
SN - 2001-0370
VL - 21
SP - 1372
EP - 1382
JO - Computational and Structural Biotechnology Journal
JF - Computational and Structural Biotechnology Journal
ER -