11 Machine learning approaches to genomics

    Article metrics

    • 5 Accesses

    ENCODE has applied machine learning approaches to enable integration and exploration of large and diverse data

    Access options

    Rent or Buy article

    Get time limited or full article access on ReadCube.

    from$8.99

    All prices are NET prices.

    Figure 2: Modelling transcription levels from histone modification and transcription-factor-binding patterns.
    Figure 5: Integration of ENCODE data by genome-wide segmentation.
    Figure 7: High-resolution segmentation of ENCODE data by self-organizing maps (SOM).
    Figure 1: Overview of the pipeline for identifying the six types of regions for one cell line.
    Figure 1: Accuracy of the TF model for predicting TSS expression levels.
    Figure 5: Cell line specificity of the TF model.
    Figure 1: TF Co-association
    Supplementary Figure 18: Using a self-organizing map to cluster DHSs by cross-cell-type pattern.
    Supplementary Figure 19
    Supplementary Figure 20: Instance counts of patterns discovered by the SOM (Supp. Fig. 18)
    Figure 1: Schematic of models to predict transcription factor occupancy from sequence and chromatin.
    Figure 2: SVM sequence models better predict binding sites than traditional motif approaches.
    Figure 3: SVM spatial chromatin models better predict binding sites than simpler models.
    Figure 3: Identification and directional classification of novel promoters.
    Supplementary Figure 9: Overlaps between novel promoters, CAGE clusters, and ESTs.
    Supplementary Figure 10: Additional examples of novel promoters identified in K562 cells.

    Rights and permissions

    Reprints and Permissions

    About this article

    Verify currency and authenticity via CrossMark

    Cite this article

    11 Machine learning approaches to genomics. Nature (2019) doi:10.1038/nature28180

    Download citation

    Comments

    By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.