Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine

Mathema, Vivek Bhakta; Sen, Partho; Lamichhane, Santosh; Orešič, Matej; Khoomrung, Sakda

doi:10.1016/j.csbj.2023.01.043

Cited by 33 publications

(13 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…41 Several computational or statistical-based techniques have been developed that can successfully integrate with multi-omics data and achieve a great success because of their feature representation capability and end-to-end training paradigm. 13 In addition, network analysis approaches have been developed to identify the key pathways and molecular interactions that drive cancer. 46 Despite the many benefits of cancer big data, there are also several challenges associated with managing and analyzing these datasets (Table 2).…”

Section: Cancer Big Datamentioning

confidence: 99%

“…The database provides a platform for researchers to explore the genomic changes that cause cancer, allowing them to identify potential therapeutic biomarkers and to develop predictive models for patient outcomes 41 . Several computational or statistical‐based techniques have been developed that can successfully integrate with multi‐omics data and achieve a great success because of their feature representation capability and end‐to‐end training paradigm 13 . In addition, network analysis approaches have been developed to identify the key pathways and molecular interactions that drive cancer 46 …”

Section: Cancer Big Datamentioning

confidence: 99%

“…Despite these advances, cancer remains a serious global public health concern 3,9–11 . Artificial intelligence (AI) methods are becoming increasingly popular in the field of cancer research with respect to finding novel therapeutic targets and predicting the efficacy of drugs 12–14 . These techniques help to explore the possible disease mechanism and can assist in the best possible treatment for a patient even before they begin treatment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

From cancer big data to treatment: Artificial intelligence in cancer research

Danishuddin,

Khan,

Kim

2023

The Journal of Gene Medicine

View full text Add to dashboard Cite

In recent years, developing the idea of “cancer big data” has emerged as a result of the significant expansion of various fields such as clinical research, genomics, proteomics and public health records. Advances in omics technologies are making a significant contribution to cancer big data in biomedicine and disease diagnosis. The increasingly availability of extensive cancer big data has set the stage for the development of multimodal artificial intelligence (AI) frameworks. These frameworks aim to analyze high‐dimensional multi‐omics data, extracting meaningful information that is challenging to obtain manually. Although interpretability and data quality remain critical challenges, these methods hold great promise for advancing our understanding of cancer biology and improving patient care and clinical outcomes. Here, we provide an overview of cancer big data and explore the applications of both traditional machine learning and deep learning approaches in cancer genomic and proteomic studies. We briefly discuss the challenges and potential of AI techniques in the integrated analysis of omics data, as well as the future direction of personalized treatment options in cancer.

show abstract

Section: Cancer Big Datamentioning

confidence: 99%

Section: Cancer Big Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

From cancer big data to treatment: Artificial intelligence in cancer research

Danishuddin,

Khan,

Kim

2023

The Journal of Gene Medicine

View full text Add to dashboard Cite

show abstract

“…C OMPLEX diseases often present a multifactorial nature [1]- [3], which has motivated recent advancements in highthroughput omics data acquisition, and further stimulated the growth of multi-omics integration as a rapidly expanding research field. Compared to single-omics studies [4], [5], multi-omics studies enable the capture of complementary information across various molecular layers such as DNA, RNA, and protein, therefore improving the understanding of underlying biological processes and molecular mechanisms involved in complex diseases [6], [7].…”

Section: Introductionmentioning

confidence: 99%

GREMI: an Explainable Multi-omics Integration Framework for Enhanced Disease Prediction and Module Identification

Luo

Liang

Jia

et al. 2023

Preprint

View full text Add to dashboard Cite

By capturing complementary information from multiple omics data, multi-omics integration has demonstrated promising performance in disease prediction. However, with the increasing number of omics data, accurately quantifying the characterization ability of each omics and avoiding mutual interference becomes challenging due to the intricate relationships among omics data. Here, we propose a novel multi-omics integration framework that improves diagnostic prediction. Specifically, our framework involves constructing co-expression and co-methylation networks for each subject, followed by applying multi-level graph attention to incorporate biomolecule interaction information. The true-class-probability strategy is employed to evaluate omics-level confidence for classification, and the loss is designed using an adaptive mechanism to leverage both within- and across-omics information. Extensive experiments demonstrate that the proposed framework outperforms state-of-the-art methods on classification tasks, and indicate that the integration of three omics yields superior performance compared to employing only one or two data types. Code and data are available at https://github.com/Yaolab-fantastic/GRAMI-NET.

show abstract

“…Budholiya et al [53] present a diagnostic system that employs an optimised XGBoost classifier with the aim of predicting the occurrence of heart disease. Ensemble models, combining machine learning and deep learning approaches, provide personalized patient treatment strategies based on medical histories and diagnostics [54]. The versatility of deep learning models is clear, with applications for omics data types, as well as histopathology-based genomic inference, providing perspectives on the integration of different data types to develop decision support tools [55], but few of them have yet demonstrated real-world medical utility [56].…”

Section: Introductionmentioning

confidence: 99%

Comparing the Min–Max–Median/IQR Approach with the Min–Max Approach, Logistic Regression and XGBoost, Maximising the Youden Index

et al. 2023

View full text Add to dashboard Cite

Although linearly combining multiple variables can provide adequate diagnostic performance, certain algorithms have the limitation of being computationally demanding when the number of variables is sufficiently high. Liu et al. proposed the min–max approach that linearly combines the minimum and maximum values of biomarkers, which is computationally tractable and has been shown to be optimal in certain scenarios. We developed the Min–Max–Median/IQR algorithm under Youden index optimisation which, although more computationally intensive, is still approachable and includes more information. The aim of this work is to compare the performance of these algorithms with well-known Machine Learning algorithms, namely logistic regression and XGBoost, which have proven to be efficient in various fields of applications, particularly in the health sector. This comparison is performed on a wide range of different scenarios of simulated symmetric or asymmetric data, as well as on real clinical diagnosis data sets. The results provide useful information for binary classification problems of better algorithms in terms of performance depending on the scenario.

show abstract

Deep learning facilitates multi-data type analysis and predictive biomarker discovery in cancer precision medicine

Cited by 33 publications

References 98 publications

From cancer big data to treatment: Artificial intelligence in cancer research

From cancer big data to treatment: Artificial intelligence in cancer research

GREMI: an Explainable Multi-omics Integration Framework for Enhanced Disease Prediction and Module Identification

Comparing the Min–Max–Median/IQR Approach with the Min–Max Approach, Logistic Regression and XGBoost, Maximising the Youden Index

Contact Info

Product

Resources

About