Bias-invariant RNA-sequencing metadata annotation

TY - JOUR

T1 - Bias-invariant RNA-sequencing metadata annotation

AU - Wartmann, Hannes

AU - Heins, Sven

AU - Kloiber, Karin

AU - Bonn, Stefan

N1 - © The Author(s) 2021. Published by Oxford University Press GigaScience.

PY - 2021/9/22

Y1 - 2021/9/22

N2 - BACKGROUND: Recent technological advances have resulted in an unprecedented increase in publicly available biomedical data, yet the reuse of the data is often precluded by experimental bias and a lack of annotation depth and consistency. Missing annotations makes it impossible for researchers to find datasets specific to their needs.FINDINGS: Here, we investigate RNA-sequencing metadata prediction based on gene expression values. We present a deep-learning-based domain adaptation algorithm for the automatic annotation of RNA-sequencing metadata. We show, in multiple experiments, that our model is better at integrating heterogeneous training data compared with existing linear regression-based approaches, resulting in improved tissue type classification. By using a model architecture similar to Siamese networks, the algorithm can learn biases from datasets with few samples.CONCLUSION: Using our novel domain adaptation approach, we achieved metadata annotation accuracies up to 15.7% better than a previously published method. Using the best model, we provide a list of >10,000 novel tissue and sex label annotations for 8,495 unique SRA samples. Our approach has the potential to revive idle datasets by automated annotation making them more searchable.

AB - BACKGROUND: Recent technological advances have resulted in an unprecedented increase in publicly available biomedical data, yet the reuse of the data is often precluded by experimental bias and a lack of annotation depth and consistency. Missing annotations makes it impossible for researchers to find datasets specific to their needs.FINDINGS: Here, we investigate RNA-sequencing metadata prediction based on gene expression values. We present a deep-learning-based domain adaptation algorithm for the automatic annotation of RNA-sequencing metadata. We show, in multiple experiments, that our model is better at integrating heterogeneous training data compared with existing linear regression-based approaches, resulting in improved tissue type classification. By using a model architecture similar to Siamese networks, the algorithm can learn biases from datasets with few samples.CONCLUSION: Using our novel domain adaptation approach, we achieved metadata annotation accuracies up to 15.7% better than a previously published method. Using the best model, we provide a list of >10,000 novel tissue and sex label annotations for 8,495 unique SRA samples. Our approach has the potential to revive idle datasets by automated annotation making them more searchable.

U2 - 10.1093/gigascience/giab064

DO - 10.1093/gigascience/giab064

M3 - SCORING: Journal article

C2 - 34553213

VL - 10

SP - giab064

JO - GIGASCIENCE

JF - GIGASCIENCE

SN - 2047-217X

IS - 9

ER -