MPRA DragoNN

readme.md

name	model_weights	weights_url	license	sha1	dragonn_version	gist_id
MRPA DragoNN	mpra_model.weights.hd5	https://github.com/irvhsu/cs273b-project/blob/master/notebooks/models/models/from_paper.weights.h5?raw=true	unrestricted	be007a27de30d0eaf330e23fa37fc628259dfaf4	0.1.3	33300cd4bb7e061b50bc25fd85b27d6f

CS 273B Final Project

Title: Predicting regulatory activities from massively parallel reporter assays

Description: We trained a deep convolutional neural net on MRPA data from Ernst et. al., 2016 [1]. The input of the model is a one-hot encoded vector of 145 bp DNA sequences. The model predicts the MPRA assay activities, normalized in the way described in the paper, then squashed into [-1, 1]. The study examines two cell lines, HepG2 and K562, and two promoters per cell line, minP and SV40P. For a given sequence, our model predicts a length 4 vector of outputs corresponding to the predicted activity in (HepG2, minP), (K562, minP), (HepG2, SV40P), and (K562, SV40P). Please see our preprint [2] and our git repository [3] for more details on our model and validation that our model learns biologically relevant information.

[1] Ernst J, Melnikov A, Zhang X, Wang L, Rogov P, Mikkelsen T, Kellis M. Genome-scale high-resolution mapping of activating and repressive nucleotides in regulatory regions. Nature Biotechnology, 34:1180-1190, 2016. [2] Joe Paggi, Andrew Lamb, Kevin Tian, Irving Hsu, Pierre-Louis Cedoz, Prasad Kawthekar. bioRxiv 099879; doi: https://doi.org/10.1101/099879 [3] https://github.com/irvhsu/cs273b-project

mpra_model.arch.json

{
    "layers": [
        {
            "trainable": true, 
            "b_constraint": null, 
            "name": "Convolution2D", 
            "custom_name": "convolution2d", 
            "cache_enabled": true, 
            "activation": "relu", 
            "W_constraint": null, 
            "nb_col": 13, 
            "input_shape": [
                1, 
                4, 
                145
            ], 
            "dim_ordering": "th", 
            "subsample": [
                1, 
                1
            ], 
            "init": "he_normal", 
            "nb_filter": 100, 
            "border_mode": "valid", 
            "b_regularizer": {
                "l2": 0.0, 
                "name": "WeightRegularizer", 
                "l1": 0
            }, 
            "W_regularizer": {
                "l2": 0.0, 
                "name": "WeightRegularizer", 
                "l1": 0
            }, 
            "activity_regularizer": null, 
            "nb_row": 4
        }, 
        {
            "cache_enabled": true, 
            "trainable": true, 
            "name": "Dropout", 
            "custom_name": "dropout", 
            "p": 0.1
        }, 
        {
            "trainable": true, 
            "b_constraint": null, 
            "name": "Convolution2D", 
            "custom_name": "convolution2d", 
            "cache_enabled": true, 
            "activation": "relu", 
            "W_constraint": null, 
            "nb_col": 13, 
            "input_shape": [
                1, 
                4, 
                145
            ], 
            "dim_ordering": "th", 
            "subsample": [
                1, 
                1
            ], 
            "init": "he_normal", 
            "nb_filter": 100, 
            "border_mode": "valid", 
            "b_regularizer": {
                "l2": 0.0, 
                "name": "WeightRegularizer", 
                "l1": 0
            }, 
            "W_regularizer": {
                "l2": 0.0, 
                "name": "WeightRegularizer", 
                "l1": 0
            }, 
            "activity_regularizer": null, 
            "nb_row": 1
        }, 
        {
            "cache_enabled": true, 
            "trainable": true, 
            "name": "Dropout", 
            "custom_name": "dropout", 
            "p": 0.1
        }, 
        {
            "name": "MaxPooling2D", 
            "custom_name": "maxpooling2d", 
            "cache_enabled": true, 
            "trainable": true, 
            "dim_ordering": "th", 
            "pool_size": [
                1, 
                40
            ], 
            "strides": [
                1, 
                40
            ], 
            "border_mode": "valid"
        }, 
        {
            "cache_enabled": true, 
            "trainable": true, 
            "name": "Flatten", 
            "custom_name": "flatten"
        }, 
        {
            "W_constraint": null, 
            "b_constraint": null, 
            "name": "Dense", 
            "custom_name": "dense", 
            "activity_regularizer": null, 
            "trainable": true, 
            "cache_enabled": true, 
            "init": "glorot_uniform", 
            "input_dim": null, 
            "b_regularizer": null, 
            "W_regularizer": null, 
            "activation": "linear", 
            "output_dim": 4
        }
    ], 
    "class_mode": "categorical", 
    "optimizer": {
        "beta_1": 0.8999999761581421, 
        "epsilon": 1e-08, 
        "beta_2": 0.9990000128746033, 
        "lr": 0.0010000000474974513, 
        "name": "Adam"
    }, 
    "name": "Sequential", 
    "loss": "mean_squared_error"
}