Deep-Learning Model for Tumor-Type Prediction Using Targeted Clinical Genomic Sequencing Data.
Madison DarmofalShalabh SumanGurnit AtwalMichael ToomeyJie-Fu ChenJason C ChangEfsevia VakianiMarjorie G ZaudererAnoop Balakrishnan RemaAijazuddin SyedNikolaus SchultzMichael F BergerQuaid D MorrisPublished in: Cancer discovery (2024)
We describe a highly accurate tumor-type prediction model, designed specifically for clinical implementation. Our model relies only on widely used cancer gene panel sequencing data, predicts across 38 distinct cancer types, and supports integration of patient-specific nongenomic information for enhanced decision support in challenging diagnostic situations. See related commentary by Garg, p. 906. This article is featured in Selected Articles from This Issue, p. 897.
Keyphrases
- papillary thyroid
- deep learning
- squamous cell
- copy number
- single cell
- big data
- healthcare
- primary care
- high resolution
- gene expression
- childhood cancer
- artificial intelligence
- genome wide
- quality improvement
- convolutional neural network
- squamous cell carcinoma
- drug delivery
- health information
- young adults
- mass spectrometry