Optimized data representation and convolutional neural network model for predicting tumor purity
Sun, G. J.; Jenkins, D. F.; Cingolani, P. E.; Dry, J. R.; Lai, Z.
Show abstract
Here we present a machine learning model, Deep Purity (DePuty) that leverages convolutional neural networks to accurately predict tumor purity from next-generation sequencing data from clinical samples without matched normals. As input, our model utilizes SNP-based copy number and minor allele frequency data formulated as a scatterplot image. With a representation matching that used by expert human annotators, we best an existing algorithm using only ~100 manually curated samples. Our simple, data-efficient approach can serve as a straightforward alternative to traditional, more complex statistical methods, for building performant purity prediction models that enable downstream bioinformatic analysis of tumor variants and absolute copy number alterations relevant to cancer genomics.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- miQC: An adaptive probabilistic framework for quality control of single-cell RNA-sequencing data 94%
- Highly Accurate Cancer Phenotype Prediction with AKLIMATE, a Stacked Kernel Learner Integrating Multimodal Genomic Data and Pathway Knowledge 94%
- Extending differential gene expression testing to handle genome aneuploidy in cancer 93%
Similar papers in this journal
- Validation of genetic variants from NGS data using Deep Convolutional Neural Networks 94%
- Leveraging Permutation Testing to Assess Confidence in Positive-Unlabeled Learning Applied to High-Dimensional Biological Datasets 93%
- driveR: A Novel Method for Prioritizing Cancer Driver Genes Using Somatic Genomics Data 93%
Similar papers in this journal
- Optimizer's dilemma: optimization strongly influences model selection in transcriptomic prediction 95%
- CanDrivR-CS: A Cancer-Specific Machine Learning Framework for Distinguishing Recurrent and Rare Variants 93%
- Deconvolution and Phylogeny Inference of Diverse Variant Types Integrating Bulk DNA-seq with Single-cell RNA-seq 93%
Similar papers in this journal
- Probabilistic mixture models improve calibration of panel-derived tumor mutational burden in the context of both tumor-normal and tumor-only sequencing 94%
- Transformer-based deep learning integrates multi-omic data with cancer pathways 93%
- Autofluorescence Virtual Staining System for H&E Histology and Multiplex Immunofluorescence Applied to Immuno-Oncology Biomarkers in Lung Cancer 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.