Integrative Analysis of Next-Generation Sequencing for Next-Generation Cancer Research toward Artificial Intelligence
Problem
Large-scale next-generation sequencing data in cancer research creates big-data challenges, requiring sophisticated analysis to characterize tumors and tumor subtypes.
Why it matters
Better predictive models of tumor characteristics and subtypes are needed to advance cancer research.
What the AI did
The paper reviews machine learning and deep learning methods for NGS data analysis, discussing how deep neural networks outperform other approaches and the potential of graph neural networks.
Results
not stated in source
Impact
The evidence supports only a review of computational methodologies for NGS cancer data, not a demonstrated result.
Record
| Venue | Cancers |
|---|---|
| Published | 2021 |
| Work type | article |
| Authors | Youngjun Park, Dominik Heider, Anne-Christin Hauschild |
| Citations | 41 (OpenAlex, at import time) |
| References | 166 |
| Model or method | deep neural networks; graph neural networks (as reviewed approaches) |
| Organization | not stated in source |
| Primary source | https://doi.org/10.3390/cancers13133148 |
| Open access | gold |
| Keywords | next-generation sequencing, cancer, machine learning, deep neural networks, graph neural networks, omics |
Importance rating
major — millions of lives, an industry or a field
Large-scale NGS data analysis is described as indispensable for tumor characterization, heterogeneity, and drug discovery across cancer research; review only, no quantified scale or demonstrated result.