The impact of different negative training data on regulatory sequence predictions.

Regulatory regions, like promoters and enhancers, cover an estimated 5-15% of the human genome. Changes to these sequences are thought to underlie much of human phenotypic variation and a substantial proportion of genetic causes of disease. However, our understanding of their functional encoding in DNA is still very limited. Applying machine or deep learning methods can shed light on this encoding and gapped k-mer support vector machines (gkm-SVMs) or convolutional neural networks (CNNs) are commonly trained on putative regulatory sequences. Here, we investigate the impact of negative sequence selection on model performance. By training gkm-SVM and CNN models on open chromatin data and corresponding negative training dataset, both learners and two approaches for negative training data are compared. Negative sets use either genomic background sequences or sequence shuffles of the positive sequences. Model performance was evaluated on three different tasks: predicting elements active in a cell-type, predicting cell-type specific elements, and predicting elements' relative activity as measured from independent experimental data. Our results indicate strong effects of the negative training data, with genomic backgrounds showing overall best results. Specifically, models trained on highly shuffled sequences perform worse on the complex tasks of tissue-specific activity and quantitative activity prediction, and seem to learn features of artificial sequences rather than regulatory activity. Further, we observe that insufficient matching of genomic background sequences results in model biases. While CNNs achieved and exceeded the performance of gkm-SVMs for larger training datasets, gkm-SVMs gave robust and best results for typical training dataset sizes without the need of hyperparameter optimization.

Abstract licence: CC BY

1. 3.

   A User's Guide to the Encyclopedia of DNA Elements (ENCODE) · 2011

2. 5.

   The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets · 2015

3. 11.

   Area under Precision-Recall Curves for Weighted and Unweighted Data · 2014

4. 13.

   pROC: an open-source package for R and S+ to analyze and compare ROC curves · 2011

5. 17.

   uShuffle: A useful tool for shuffling biological sequences while preserving the k-let counts · 2008

6. 18.

   G+C content dominates intrinsic nucleosome occupancy · 2009

7. 29.

   GC-Rich Sequence Elements Recruit PRC2 in Mammalian ES Cells · 2010

8. 33.

   Analysis of Genomic Sequence Motifs for Deciphering Transcription Factor Binding and Transcriptional Regulation in Eukaryotic Cells · 2016

9. 36.

   Basset: learning the regulatory code of the accessible genome with deep convolutional neural networks · 2016

31 more references, whose wording the paper’s licence keeps private.

• CADD v1.7: using protein language models, regulatory CNNs and other nucleotide-level scores to improve genome-wide variant predictions · 2024

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.