TF-MoDISco results

Summary of motifs

TOMTOM matches to motifs

Sample of seqlets for each motif

In [1]:
import os
import util
from tomtom import match_motifs_to_database
import viz_sequence
import numpy as np
import pandas as pd
import sklearn.cluster
import scipy.cluster.hierarchy
import matplotlib.pyplot as plt
import matplotlib.font_manager as font_manager
import vdom.helpers as vdomh
from IPython.display import display
import tqdm
tqdm.tqdm_notebook()

/users/amtseng/miniconda3/envs/tfmodisco-mini/lib/python3.7/site-packages/ipykernel_launcher.py:14: TqdmDeprecationWarning: This function will be removed in tqdm==5.0.0
Please use `tqdm.notebook.tqdm` instead of `tqdm.tqdm_notebook`
Out[1]:
0it [00:00, ?it/s]
In [2]:
# Plotting defaults
font_manager.fontManager.ttflist.extend(
    font_manager.createFontList(
        font_manager.findSystemFonts(fontpaths="/users/amtseng/modules/fonts")
    )
)
plot_params = {
    "figure.titlesize": 22,
    "axes.titlesize": 22,
    "axes.labelsize": 20,
    "legend.fontsize": 18,
    "xtick.labelsize": 16,
    "ytick.labelsize": 16,
    "font.family": "Roboto",
    "font.weight": "bold"
}
plt.rcParams.update(plot_params)

/users/amtseng/miniconda3/envs/tfmodisco-mini/lib/python3.7/site-packages/ipykernel_launcher.py:4: MatplotlibDeprecationWarning: 
The createFontList function was deprecated in Matplotlib 3.2 and will be removed two minor releases later. Use FontManager.addfont instead.
  after removing the cwd from sys.path.

Define constants and paths

In [3]:
# Define parameters/fetch arguments
preds_path = os.environ["TFM_PRED_PATH"]
shap_scores_path = os.environ["TFM_SHAP_PATH"]
tfm_results_path = os.environ["TFM_TFM_PATH"]
peak_bed_paths = [os.environ["TFM_PEAKS_PATH"]]

print("Predictions path: %s" % preds_path)
print("DeepSHAP scores path: %s" % shap_scores_path)
print("TF-MoDISco results path: %s" % tfm_results_path)
print("Peaks path: %s" % peak_bed_paths[0])

Predictions path: /users/zahoor/TF-Atlas/02-16-2021/predictions/ENCSR240PRQ/profile_predictions.h5
DeepSHAP scores path: /users/zahoor/TF-Atlas/02-16-2021/shap/ENCSR240PRQ/counts_scores_alex_format.h5
TF-MoDISco results path: /users/zahoor/TF-Atlas/02-16-2021/modisco/ENCSR240PRQ/counts/modisco_results.hd5
Peaks path: /users/zahoor/TF-Atlas/data/idr_peaks//ENCFF463FGL.bed.gz
In [4]:
# Define constants
input_length, profile_length = 2114, 1000
shap_score_center_size = 400
profile_display_center_size = 400
hyp_score_key = "hyp_scores"
task_index = None

Helper functions

In [5]:
def extract_profiles_and_coords(
    seqlets_arr, one_hot_seqs, hyp_scores, true_profs, pred_profs, pred_coords,
    input_length, profile_length, input_center_cut_size, profile_center_cut_size,
    task_index=None
):
    """
    From the seqlets object of a TF-MoDISco pattern's seqlets and alignments,
    extracts the predicted and observed profiles of the model, as well as the
    set of coordinates for the seqlets.
    Arguments:
        `seqlets_arr`: a TF-MoDISco pattern's seqlets object array (N-array)
        `one_hot_seqs`: an N x R x 4 array of input sequences, where R is
            the cut centered size
        `hyp_scores`: an N x R x 4 array of hypothetical importance scores
        `true_profs`: an N x T x O x 2 array of true profile counts
        `pred_profs`: an N x T x O x 2 array of predicted profile probabilities
        `pred_coords`: an N x 3 object array of coordinates for the input sequence
            underlying the predictions
        `input_length`: length of original input sequences, I
        `profile_length`: length of profile predictions, O
        `input_center_cut_size`: centered cut size of SHAP scores used
        `profile_center_cut_size`: size to cut profiles to when returning them, P
        `task_index`: index of task to focus on for profiles; if None, returns
            profiles for all tasks
    Returns an N x (T or 1) x P x 2 array of true profile counts, an
    N x (T or 1) x P x 2 array of predicted profile probabilities, an N x Q x 4
    array of one-hot seqlet sequences, an N x Q x 4 array of hypothetical seqlet
    importance scores, and an N x 3 object array of seqlet coordinates, where P
    is the profile cut size and Q is the seqlet length. Returned profiles are
    centered at the same center as the seqlets.
    Note that it is important that the seqlet indices match exactly with the indices
    out of the N. This should be the exact sequences in the original SHAP scores.
    """
    true_seqlet_profs, pred_seqlet_profs, seqlet_seqs, seqlet_hyps, seqlet_coords = [], [], [], [], []
    
    def seqlet_coord_to_profile_coord(seqlet_coord):
        return seqlet_coord + ((input_length - input_center_cut_size) // 2) - ((input_length - profile_length) // 2)
    
    def seqlet_coord_to_input_coord(seqlet_coord):
        return seqlet_coord + ((input_length - input_center_cut_size) // 2)
        
    # For each seqlet, fetch the true/predicted profiles
    for seqlet in seqlets_arr:
        coord_index = seqlet.coor.example_idx
        seqlet_start = seqlet.coor.start
        seqlet_end = seqlet.coor.end
        seqlet_rc = seqlet.coor.is_revcomp
        
        # Get indices of profile to cut out
        seqlet_center = (seqlet_start + seqlet_end) // 2
        prof_center = seqlet_coord_to_profile_coord(seqlet_center)
        prof_start = prof_center - (profile_center_cut_size // 2)
        prof_end = prof_start + profile_center_cut_size
        
        if task_index is None or true_profs.shape[1] == 1:
            # Use all tasks if the predictions only have 1 task to begin with
            task_start, task_end = None, None
        else:
            task_start, task_end = task_index, task_index + 1
            
        true_prof = true_profs[coord_index, task_start:task_end, prof_start:prof_end]  # (T or 1) x P x 2
        pred_prof = pred_profs[coord_index, task_start:task_end, prof_start:prof_end]  # (T or 1) x P x 2
        
        true_seqlet_profs.append(true_prof)
        pred_seqlet_profs.append(pred_prof)
        
        # The one-hot-sequences and hypothetical scores are assumed to already by cut/centered,
        # so the indices match the seqlet indices
        if seqlet_rc:
            seqlet_seqs.append(np.flip(one_hot_seqs[coord_index, seqlet_start:seqlet_end], axis=(0, 1)))
            seqlet_hyps.append(np.flip(hyp_scores[coord_index, seqlet_start:seqlet_end], axis=(0, 1)))
        else:
            seqlet_seqs.append(one_hot_seqs[coord_index, seqlet_start:seqlet_end])
            seqlet_hyps.append(hyp_scores[coord_index, seqlet_start:seqlet_end])
            
        # Get the coordinates of the seqlet based on the input coordinates
        inp_start = seqlet_coord_to_input_coord(seqlet_start)
        inp_end = seqlet_coord_to_input_coord(seqlet_end)
        chrom, start, _ = pred_coords[coord_index]
        seqlet_coords.append([chrom, start + inp_start, start + inp_end])
    
    return np.stack(true_seqlet_profs), np.stack(pred_seqlet_profs), np.stack(seqlet_seqs), np.stack(seqlet_hyps), np.array(seqlet_coords, dtype=object)
In [6]:
def plot_profiles(seqlet_true_profs, seqlet_pred_profs, kmeans_clusters=5):
    """
    Plots the given profiles with a heatmap.
    Arguments:
        `seqlet_true_profs`: an N x O x 2 NumPy array of true profiles, either as raw
            counts or probabilities (they will be normalized)
        `seqlet_pred_profs`: an N x O x 2 NumPy array of predicted profiles, either as
            raw counts or probabilities (they will be normalized)
        `kmeans_cluster`: when displaying profile heatmaps, there will be this
            many clusters
    """
    assert len(seqlet_true_profs.shape) == 3
    assert seqlet_true_profs.shape == seqlet_pred_profs.shape
    num_profs, width, _ = seqlet_true_profs.shape

    # First, normalize the profiles along the output profile dimension
    def normalize(arr, axis=0):
        arr_sum = np.sum(arr, axis=axis, keepdims=True)
        arr_sum[arr_sum == 0] = 1  # If 0, keep 0 as the quotient instead of dividing by 0
        return arr / arr_sum
    true_profs_norm = normalize(seqlet_true_profs, axis=1)
    pred_profs_norm = normalize(seqlet_pred_profs, axis=1)

    # Compute the mean profiles across all examples
    true_profs_mean = np.mean(true_profs_norm, axis=0)
    pred_profs_mean = np.mean(pred_profs_norm, axis=0)

    # Perform k-means clustering on the predicted profiles, with the strands pooled
    kmeans_clusters = max(5, num_profs // 50)  # Set number of clusters based on number of profiles, with minimum
    kmeans = sklearn.cluster.KMeans(n_clusters=kmeans_clusters)
    cluster_assignments = kmeans.fit_predict(
        np.reshape(pred_profs_norm, (pred_profs_norm.shape[0], -1))
    )

    # Perform hierarchical clustering on the cluster centers to determine optimal ordering
    kmeans_centers = kmeans.cluster_centers_
    cluster_order = scipy.cluster.hierarchy.leaves_list(
        scipy.cluster.hierarchy.optimal_leaf_ordering(
            scipy.cluster.hierarchy.linkage(kmeans_centers, method="centroid"), kmeans_centers
        )
    )

    # Order the profiles so that the cluster assignments follow the optimal ordering
    cluster_inds = []
    for cluster_id in cluster_order:
        cluster_inds.append(np.where(cluster_assignments == cluster_id)[0])
    cluster_inds = np.concatenate(cluster_inds)

    # Compute a matrix of profiles, normalized to the maximum height, ordered by clusters
    def make_profile_matrix(flat_profs, order_inds):
        matrix = flat_profs[order_inds]
        maxes = np.max(matrix, axis=1, keepdims=True)
        maxes[maxes == 0] = 1  # If 0, keep 0 as the quotient instead of dividing by 0
        return matrix / maxes
    true_matrix = make_profile_matrix(true_profs_norm, cluster_inds)
    pred_matrix = make_profile_matrix(pred_profs_norm, cluster_inds)

    # Create a figure with the right dimensions
    mean_height = 4
    heatmap_height = min(num_profs * 0.004, 8)
    fig_height = mean_height + (2 * heatmap_height)
    fig, ax = plt.subplots(
        3, 2, figsize=(16, fig_height), sharex=True,
        gridspec_kw={
            "width_ratios": [1, 1],
            "height_ratios": [mean_height / fig_height, heatmap_height / fig_height, heatmap_height / fig_height]
        }
    )

    # Plot the average predictions
    ax[0, 0].plot(true_profs_mean[:, 0], color="darkslateblue")
    ax[0, 0].plot(-true_profs_mean[:, 1], color="darkorange")
    ax[0, 1].plot(pred_profs_mean[:, 0], color="darkslateblue")
    ax[0, 1].plot(-pred_profs_mean[:, 1], color="darkorange")

    # Set axes on average predictions
    max_mean_val = max(np.max(true_profs_mean), np.max(pred_profs_mean))
    mean_ylim = max_mean_val * 1.05  # Make 5% higher
    ax[0, 0].set_title("True profiles")
    ax[0, 0].set_ylabel("Average probability")
    ax[0, 1].set_title("Predicted profiles")
    for j in (0, 1):
        ax[0, j].set_ylim(-mean_ylim, mean_ylim)
        ax[0, j].label_outer()

    # Plot the heatmaps
    ax[1, 0].imshow(true_matrix[:, :, 0], interpolation="nearest", aspect="auto", cmap="Blues")
    ax[1, 1].imshow(pred_matrix[:, :, 0], interpolation="nearest", aspect="auto", cmap="Blues")
    ax[2, 0].imshow(true_matrix[:, :, 1], interpolation="nearest", aspect="auto", cmap="Oranges")
    ax[2, 1].imshow(pred_matrix[:, :, 1], interpolation="nearest", aspect="auto", cmap="Oranges")

    # Set axes on heatmaps
    for i in (1, 2):
        for j in (0, 1):
            ax[i, j].set_yticks([])
            ax[i, j].set_yticklabels([])
            ax[i, j].label_outer()
    width = true_matrix.shape[1]
    delta = 100
    num_deltas = (width // 2) // delta
    labels = list(range(max(-width // 2, -num_deltas * delta), min(width // 2, num_deltas * delta) + 1, delta))
    tick_locs = [label + max(width // 2, num_deltas * delta) for label in labels]
    for j in (0, 1):
        ax[2, j].set_xticks(tick_locs)
        ax[2, j].set_xticklabels(labels)
        ax[2, j].set_xlabel("Distance from peak summit (bp)")

    fig.tight_layout()
    plt.show()
In [7]:
def get_summit_distances(coords, peak_table):
    """
    Given a set of coordinates, computes the distance of the center of each
    coordinate to the nearest summit.
    Arguments:
        `coords`: an N x 3 object array of coordinates
        `peak_table`: a 6-column table of peak data, as imported by
            `import_peak_table`
    Returns and N-array of integers, which is the distance of each coordinate
    midpoint to the nearest coordinate.
    """
    chroms = coords[:, 0]
    midpoints = (coords[:, 1] + coords[:, 2]) // 2
    dists = []
    for i in range(len(coords)):
        chrom = chroms[i]
        midpoint = midpoints[i]
        rows = peak_table[peak_table["chrom"] == chrom]
        dist_arr = (midpoint - rows["summit"]).values
        min_dist = dist_arr[np.argmin(np.abs(dist_arr))]
        dists.append(min_dist)
    return np.array(dists)
In [8]:
def plot_summit_dists(summit_dists):
    """
    Plots the distribution of seqlet distances to summits.
    Arguments:
        `summit_dists`: the array of distances as returned by
            `get_summit_distances`
    """
    plt.figure(figsize=(8, 6))
    num_bins = max(len(summit_dists) // 30, 20)
    plt.hist(summit_dists, bins=num_bins, color="purple")
    plt.title("Histogram of distance of seqlets to peak summits")
    plt.xlabel("Signed distance from seqlet center to nearest peak summit (bp)")
    plt.show()

Import SHAP scores, profile predictions, and TF-MoDISco results

In [9]:
# Import SHAP coordinates and one-hot sequences
hyp_scores, _, one_hot_seqs, shap_coords = util.import_shap_scores(shap_scores_path, hyp_score_key, center_cut_size=shap_score_center_size, remove_non_acgt=False)
# This cuts the sequences/scores off just as how TF-MoDISco saw them, but the coordinates are uncut

Importing SHAP scores: 100%|██████████| 60/60 [00:16<00:00,  3.66it/s]
In [10]:
# Import the set of all profiles and their coordinates
true_profs, pred_profs, all_pred_coords = util.import_profiles(preds_path)



















In [11]:



    


# Import the set of peaks
peak_table = util.import_peak_table(peak_bed_paths)



    













In [12]:



    


# Subset the predicted profiles/coordinates to the task-specific SHAP coordinates/scores
shap_coords_table = pd.DataFrame(shap_coords, columns=["chrom", "start", "end"])
pred_coords_table = pd.DataFrame(all_pred_coords, columns=["chrom", "start", "end"])

subset_inds = pred_coords_table.reset_index().drop_duplicates(["chrom", "start", "end"]).merge(
    shap_coords_table.reset_index(), on=["chrom", "start", "end"]
).sort_values("index_y")["index_x"].values

true_profs = true_profs[subset_inds]
pred_profs = pred_profs[subset_inds]
pred_coords = all_pred_coords[subset_inds]

# Make sure the coordinates all match
assert np.all(pred_coords == shap_coords)



    













In [13]:



    


# Import the TF-MoDISco results object
tfm_obj = util.import_tfmodisco_results(tfm_results_path, hyp_scores, one_hot_seqs, shap_score_center_size)



    















Plot some SHAP score tracks
Plot the central region of some randomly selected actual importance scores













In [14]:



    


for index in np.random.choice(hyp_scores.shape[0], size=5, replace=False):
    viz_sequence.plot_weights((hyp_scores[index] * one_hot_seqs[index])[100:300], subticks_frequency=100)



    















    

















    

















    

















    

















    






























Plot TF-MoDISco results
Plot all motifs by metacluster













In [15]:



    


motif_pfms, motif_hcwms, motif_cwms = [], [], []  # Save the trimmed PFMs, hCWMs, and CWMs
motif_pfms_short = []  # PFMs that are even more trimmed (for TOMTOM)
num_seqlets = []  # Number of seqlets for each motif
motif_seqlets = []  # Save seqlets of each motif
metaclusters = tfm_obj.metacluster_idx_to_submetacluster_results
num_metaclusters = len(metaclusters.keys())
for metacluster_i, metacluster_key in enumerate(metaclusters.keys()):
    metacluster = metaclusters[metacluster_key]
    display(vdomh.h3("Metacluster %d/%d" % (metacluster_i + 1, num_metaclusters)))
    patterns = metacluster.seqlets_to_patterns_result.patterns
    if not patterns:
        break
    motif_pfms.append([])
    motif_hcwms.append([])
    motif_cwms.append([])
    motif_pfms_short.append([])
    num_seqlets.append([])
    motif_seqlets.append([])
    num_patterns = len(patterns)
    for pattern_i, pattern in enumerate(patterns):
        seqlets = pattern.seqlets
        display(vdomh.h4("Pattern %d/%d" % (pattern_i + 1, num_patterns)))
        display(vdomh.p("%d seqlets" % len(seqlets)))
        
        pfm = pattern["sequence"].fwd
        hcwm = pattern["task0_hypothetical_contribs"].fwd
        cwm = pattern["task0_contrib_scores"].fwd
        
        pfm_fig = viz_sequence.plot_weights(pfm, subticks_frequency=10, return_fig=True)
        hcwm_fig = viz_sequence.plot_weights(hcwm, subticks_frequency=10, return_fig=True)
        cwm_fig = viz_sequence.plot_weights(cwm, subticks_frequency=10, return_fig=True)
        pfm_fig.tight_layout()
        hcwm_fig.tight_layout()
        cwm_fig.tight_layout()
        
        motif_table = vdomh.table(
            vdomh.tr(
                vdomh.td("Sequence (PFM)"),
                vdomh.td(util.figure_to_vdom_image(pfm_fig))
            ),
            vdomh.tr(
                vdomh.td("Hypothetical contributions (hCWM)"),
                vdomh.td(util.figure_to_vdom_image(hcwm_fig))
            ),
            vdomh.tr(
                vdomh.td("Actual contributions (CWM)"),
                vdomh.td(util.figure_to_vdom_image(cwm_fig))
            )
        )
        display(motif_table)
        plt.close("all")  # Remove all standing figures
        
        # Trim motif based on total contribution
        score = np.sum(np.abs(cwm), axis=1)
        trim_thresh = np.max(score) * 0.2  # Cut off anything less than 20% of max score
        pass_inds = np.where(score >= trim_thresh)[0]
        
        short_trimmed_pfm = pfm[np.min(pass_inds): np.max(pass_inds) + 1]
        motif_pfms_short[-1].append(short_trimmed_pfm)
        
        # Expand trimming to +/- 4bp on either side
        start, end = max(0, np.min(pass_inds) - 4), min(len(cwm), np.max(pass_inds) + 4 + 1)
        trimmed_pfm = pfm[start:end]
        trimmed_hcwm = hcwm[start:end]
        trimmed_cwm = cwm[start:end]
        
        motif_pfms[-1].append(trimmed_pfm)
        motif_hcwms[-1].append(trimmed_hcwm)
        motif_cwms[-1].append(trimmed_cwm)
        
        num_seqlets[-1].append(len(seqlets))
        
        seqlet_true_profs, seqlet_pred_profs, seqlet_seqs, seqlet_hyps, seqlet_coords = extract_profiles_and_coords(
            seqlets, one_hot_seqs, hyp_scores, true_profs, pred_profs, pred_coords,
            input_length, profile_length, shap_score_center_size,
            profile_display_center_size, task_index=task_index
        )
        
        motif_seqlets[-1].append((seqlet_seqs, seqlet_hyps))

        assert np.allclose(np.sum(seqlet_seqs, axis=0) / len(seqlet_seqs), pattern["sequence"].fwd)
        # ^Sanity check: PFM derived from seqlets match the PFM stored in the pattern
        plot_profiles(
            # Flatten to NT x O x 2
            np.reshape(seqlet_true_profs, (-1, seqlet_true_profs.shape[2], seqlet_true_profs.shape[3])),
            np.reshape(seqlet_pred_profs, (-1, seqlet_pred_profs.shape[2], seqlet_pred_profs.shape[3]))
        )
        
        summit_dists = get_summit_distances(seqlet_coords, peak_table)
        plot_summit_dists(summit_dists)



    















    







Metacluster 1/2










    







Pattern 1/2










    







8098 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 2/2










    







288 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Metacluster 2/2










    







Pattern 1/19










    







489 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 2/19










    







317 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 3/19










    







256 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 4/19










    







259 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 5/19










    







213 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 6/19










    







169 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 7/19










    







103 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 8/19










    







89 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 9/19










    







91 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 10/19










    







90 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 11/19










    







65 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 12/19










    







98 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 13/19










    







61 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 14/19










    







63 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 15/19










    







61 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 16/19










    







77 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 17/19










    







42 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 18/19










    







37 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    

















    







Pattern 19/19










    







56 seqlets










    







Sequence (PFM)
Hypothetical contributions (hCWM)
Actual contributions (CWM)










    

















    






























Summary of motifs
Motifs are trimmed based on information content, and presented in descending order by number of supporting seqlets. The motifs are separated by metacluster. The motifs are presented as hCWMs. The forward orientation is defined as the orientation that is richer in purines.













In [16]:



    


colgroup = vdomh.colgroup(
    vdomh.col(style={"width": "5%"}),
    vdomh.col(style={"width": "5%"}),
    vdomh.col(style={"width": "45%"}),
    vdomh.col(style={"width": "45%"})
)
header = vdomh.thead(
    vdomh.tr(
        vdomh.th("#", style={"text-align": "center"}),
        vdomh.th("Seqlets", style={"text-align": "center"}),
        vdomh.th("Forward", style={"text-align": "center"}),
        vdomh.th("Reverse", style={"text-align": "center"})
    )
)

for i in range(len(motif_hcwms)):
    display(vdomh.h3("Metacluster %d/%d" % (i + 1, num_metaclusters)))
    body = []
    for j in range(len(motif_hcwms[i])):
        motif = motif_hcwms[i][j]
        if np.sum(motif[:, [0, 2]]) > 0.5 * np.sum(motif):
            # Forward is purine-rich, reverse-complement is pyrimidine-rich
            f, rc = motif, np.flip(motif, axis=(0, 1))
        else:
            f, rc = np.flip(motif, axis=(0, 1)), motif
            
        f_fig = viz_sequence.plot_weights(f, figsize=(20, 4), return_fig=True)
        f_fig.tight_layout()
        rc_fig = viz_sequence.plot_weights(rc, figsize=(20, 4), return_fig=True)
        rc_fig.tight_layout()

        body.append(
            vdomh.tr(
                vdomh.td(str(j + 1)),
                vdomh.td(str(num_seqlets[i][j])),
                vdomh.td(util.figure_to_vdom_image(f_fig)),
                vdomh.td(util.figure_to_vdom_image(rc_fig))
            )
        )
    display(vdomh.table(colgroup, header, vdomh.tbody(*body)))
    plt.close("all")



    















    







Metacluster 1/2










    







#SeqletsForwardReverse
18098
2288










    







Metacluster 2/2










    






/users/amtseng/TF-Atlas/3M/reports/viz_sequence.py:152: RuntimeWarning: More than 20 figures have been opened. Figures created through the pyplot interface (`matplotlib.pyplot.figure`) are retained until explicitly closed and may consume too much memory. (To control this warning, see the rcParam `figure.max_open_warning`).
  fig = plt.figure(figsize=figsize)










    







#SeqletsForwardReverse
1489
2317
3256
4259
5213
6169
7103
889
991
1090
1165
1298
1361
1463
1561
1677
1742
1837
1956























Top TOMTOM matches for each motif
Here, the TF-MoDISco motifs are plotted as hCWMs, but the TOMTOM matches are shown as PWMs.













In [17]:



    


num_matches_to_keep = 10
num_matches_to_show = 5

header = vdomh.thead(
    vdomh.tr(
        vdomh.th("Motif ID", style={"text-align": "center"}),
        vdomh.th("q-val", style={"text-align": "center"}),
        vdomh.th("PWM", style={"text-align": "center"})
    )
)

for i in range(len(motif_pfms)):
    display(vdomh.h3("Metacluster %d/%d" % (i + 1, num_metaclusters)))
    
    # Compute TOMTOM matches for all motifs in the metacluster at once
    tomtom_matches = match_motifs_to_database(motif_pfms_short[i], top_k=num_matches_to_keep)
    
    for j in range(len(motif_pfms[i])):
        display(vdomh.h4("Motif %d/%d" % (j + 1, len(motif_pfms[i]))))
        viz_sequence.plot_weights(motif_hcwms[i][j])
    
        body = []
        for k, (match_name, match_pfm, match_qval) in enumerate(tomtom_matches[j]):
            fig = viz_sequence.plot_weights(util.pfm_to_pwm(match_pfm), return_fig=True)
            fig.tight_layout()
            if k < num_matches_to_show:
                body.append(
                    vdomh.tr(
                        vdomh.td(match_name),
                        vdomh.td(str(match_qval)),
                        vdomh.td(util.figure_to_vdom_image(fig))
                    )
                )
            else:
                body.append(
                    vdomh.tr(
                        vdomh.td(match_name),
                        vdomh.td(str(match_qval)),
                        vdomh.td("Not shown")
                    )
                )
        if not body:
            display(vdomh.p("No TOMTOM matches passing threshold"))
        else:
            display(vdomh.table(header, vdomh.tbody(*body)))
        plt.close("all")



    















    







Metacluster 1/2










    







Motif 1/2










    

















    







Motif IDq-valPWM
MA0139.1_CTCF2.7198500000000002e-18
CTCF_HUMAN.H11MO.0.A3.8271199999999996e-14
CTCFL_HUMAN.H11MO.0.A1.3863200000000002e-07
MA1102.2_CTCFL5.9620299999999996e-05
MA1568.1_TCF21(var.2)0.129708
MA1638.1_HAND20.16672599999999999Not shown
ZIC3_HUMAN.H11MO.0.B0.17998599999999998Not shown
SNAI1_HUMAN.H11MO.0.C0.17998599999999998Not shown
ZIC2_HUMAN.H11MO.0.D0.293892Not shown
MA0155.1_INSM10.310781Not shown










    







Motif 2/2










    

















    







Motif IDq-valPWM
MA0139.1_CTCF0.33426100000000003
CTCF_HUMAN.H11MO.0.A0.33426100000000003
MA0502.2_NFYB0.47273999999999994










    







Metacluster 2/2










    







Motif 1/19










    

















    







Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A3.81201e-10
SP3_HUMAN.H11MO.0.B2.069e-09
SP1_HUMAN.H11MO.0.A8.6936e-09
KLF3_HUMAN.H11MO.0.B8.10525e-06
KLF16_HUMAN.H11MO.0.D9.602310000000002e-06
TBX15_HUMAN.H11MO.0.D9.602310000000002e-06Not shown
PATZ1_HUMAN.H11MO.0.C1.79408e-05Not shown
SP1_HUMAN.H11MO.1.A4.63685e-05Not shown
WT1_HUMAN.H11MO.0.C9.391389999999999e-05Not shown
MA1513.1_KLF150.000254797Not shown










    







Motif 2/19










    

















    







Motif IDq-valPWM
MYOD1_HUMAN.H11MO.0.A0.053172300000000006
SP1_HUMAN.H11MO.0.A0.053172300000000006
MA0830.2_TCF40.053172300000000006
SP2_HUMAN.H11MO.0.A0.05791990000000001
ZFX_HUMAN.H11MO.1.A0.0819663
MA0146.2_Zfx0.0916421Not shown
RFX1_HUMAN.H11MO.0.B0.09710869999999999Not shown
HEN1_HUMAN.H11MO.0.C0.09710869999999999Not shown
ASCL1_HUMAN.H11MO.0.A0.09710869999999999Not shown
MYOG_HUMAN.H11MO.0.B0.12464700000000001Not shown










    







Motif 3/19










    

















    







Motif IDq-valPWM
MA1655.1_ZNF3410.24165100000000003
SMAD3_HUMAN.H11MO.0.B0.271054
PTF1A_HUMAN.H11MO.0.B0.314322
ZN341_HUMAN.H11MO.0.C0.314322
ZN341_HUMAN.H11MO.1.C0.314322
NFE2_HUMAN.H11MO.0.A0.345447Not shown
MA1522.1_MAZ0.345447Not shown
MA1593.1_ZNF3170.345447Not shown
SP2_HUMAN.H11MO.0.A0.345447Not shown
SP4_HUMAN.H11MO.0.A0.345447Not shown










    







Motif 4/19










    

















    







Motif IDq-valPWM
EGR2_HUMAN.H11MO.0.A0.00612324
VEZF1_HUMAN.H11MO.0.C0.00612324
WT1_HUMAN.H11MO.0.C0.014976499999999998
FLI1_HUMAN.H11MO.0.A0.014976499999999998
SP2_HUMAN.H11MO.0.A0.014976499999999998
ZN341_HUMAN.H11MO.0.C0.014976499999999998Not shown
SP3_HUMAN.H11MO.0.B0.014976499999999998Not shown
ZN263_HUMAN.H11MO.0.A0.033550800000000006Not shown
PATZ1_HUMAN.H11MO.0.C0.0345931Not shown
MA0163.1_PLAG10.0393228Not shown










    







Motif 5/19










    

















    







Motif IDq-valPWM
MA0154.4_EBF10.10613399999999999
CTCFL_HUMAN.H11MO.0.A0.10613399999999999
COE1_HUMAN.H11MO.0.A0.118415
MA0872.1_TFAP2A(var.3)0.16738699999999998
MA0815.1_TFAP2C(var.3)0.16738699999999998
MA0814.2_TFAP2C(var.2)0.16738699999999998Not shown
MA1569.1_TFAP2E0.203347Not shown
CTCF_HUMAN.H11MO.0.A0.20468599999999998Not shown
MA0813.1_TFAP2B(var.3)0.21808899999999998Not shown
AP2B_HUMAN.H11MO.0.B0.27812Not shown










    







Motif 6/19










    

















    







Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00044650699999999996
SP1_HUMAN.H11MO.0.A0.00570338
SP3_HUMAN.H11MO.0.B0.00705191
WT1_HUMAN.H11MO.0.C0.0131352
PATZ1_HUMAN.H11MO.0.C0.0161727
ZN341_HUMAN.H11MO.0.C0.0161727Not shown
MAZ_HUMAN.H11MO.0.A0.0593207Not shown
ZFX_HUMAN.H11MO.1.A0.0593207Not shown
MA1615.1_Plagl10.0593207Not shown
KLF3_HUMAN.H11MO.0.B0.0593207Not shown










    







Motif 7/19










    

















    







Motif IDq-valPWM
RREB1_HUMAN.H11MO.0.D0.03843680000000001
MA0073.1_RREB10.03843680000000001
MA0479.1_FOXH10.218156
KLF16_HUMAN.H11MO.0.D0.22471100000000002










    







Motif 8/19










    

















    







Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A2.2858799999999998e-07
SP1_HUMAN.H11MO.0.A5.67481e-07
SP3_HUMAN.H11MO.0.B2.8948200000000003e-06
KLF16_HUMAN.H11MO.0.D6.85715e-06
PATZ1_HUMAN.H11MO.0.C8.67293e-06
WT1_HUMAN.H11MO.0.C4.97314e-05Not shown
TBX15_HUMAN.H11MO.0.D0.000158526Not shown
MAZ_HUMAN.H11MO.0.A0.000158704Not shown
ZN467_HUMAN.H11MO.0.C0.000456929Not shown
KLF15_HUMAN.H11MO.0.A0.00049342Not shown










    







Motif 9/19










    

















    







Motif IDq-valPWM
KLF5_HUMAN.H11MO.0.A0.0914722
ARNT2_HUMAN.H11MO.0.D0.11396500000000001
KLF1_HUMAN.H11MO.0.A0.143045
HAND1_HUMAN.H11MO.1.D0.267389
MA1511.1_KLF100.267389
NR0B1_HUMAN.H11MO.0.D0.409402Not shown










    







Motif 10/19










    

















    







Motif IDq-valPWM
PRD14_HUMAN.H11MO.0.A0.314077










    







Motif 11/19










    

















    







No TOMTOM matches passing threshold










    







Motif 12/19










    

















    







Motif IDq-valPWM
ZN467_HUMAN.H11MO.0.C0.173982
MAZ_HUMAN.H11MO.0.A0.177896
NKX25_HUMAN.H11MO.0.B0.18005
ZFX_HUMAN.H11MO.1.A0.293675
MA0734.2_GLI20.293675
KLF9_HUMAN.H11MO.0.C0.293675Not shown
NR2C1_HUMAN.H11MO.0.C0.293675Not shown
ZN263_HUMAN.H11MO.0.A0.293675Not shown
SP4_HUMAN.H11MO.1.A0.293675Not shown
FLI1_HUMAN.H11MO.1.A0.293675Not shown










    







Motif 13/19










    

















    







Motif IDq-valPWM
VEZF1_HUMAN.H11MO.0.C1.03201e-05
ZN341_HUMAN.H11MO.0.C1.06104e-05
MAZ_HUMAN.H11MO.0.A1.42004e-05
SP2_HUMAN.H11MO.0.A3.3423800000000003e-05
ZN467_HUMAN.H11MO.0.C3.8631300000000004e-05
SP1_HUMAN.H11MO.0.A7.86239e-05Not shown
PATZ1_HUMAN.H11MO.0.C0.00033368300000000004Not shown
WT1_HUMAN.H11MO.0.C0.000342025Not shown
SP3_HUMAN.H11MO.0.B0.000342025Not shown
TBX15_HUMAN.H11MO.0.D0.000480391Not shown










    







Motif 14/19










    

















    







No TOMTOM matches passing threshold










    







Motif 15/19










    

















    







Motif IDq-valPWM
GLI2_HUMAN.H11MO.0.D0.174807
MA1102.2_CTCFL0.174807
KLF8_HUMAN.H11MO.0.C0.174807
ZN322_HUMAN.H11MO.0.B0.34937399999999996
PRDM4_HUMAN.H11MO.0.D0.34937399999999996
MA1516.1_KLF30.44835699999999995Not shown
ZN263_HUMAN.H11MO.1.A0.44835699999999995Not shown
MA1600.1_ZNF6840.44835699999999995Not shown
CTCFL_HUMAN.H11MO.0.A0.474918Not shown










    







Motif 16/19










    

















    







Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A8.666059999999999e-05
SP3_HUMAN.H11MO.0.B0.000101145
SP1_HUMAN.H11MO.0.A0.00025669999999999995
KLF16_HUMAN.H11MO.0.D0.0005091809999999999
ARNT2_HUMAN.H11MO.0.D0.000938936
PATZ1_HUMAN.H11MO.0.C0.000938936Not shown
MA1653.1_ZNF1480.00151805Not shown
TBX15_HUMAN.H11MO.0.D0.00174349Not shown
KLF15_HUMAN.H11MO.0.A0.00290533Not shown
WT1_HUMAN.H11MO.0.C0.00291208Not shown










    







Motif 17/19










    

















    







Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.011078200000000002
SP3_HUMAN.H11MO.0.B0.01726
THAP1_HUMAN.H11MO.0.C0.01726
ZN467_HUMAN.H11MO.0.C0.01726
MA0104.4_MYCN0.01726
MA0147.3_MYC0.01726Not shown
ZFX_HUMAN.H11MO.1.A0.01726Not shown
SP1_HUMAN.H11MO.0.A0.0176348Not shown
WT1_HUMAN.H11MO.0.C0.0213233Not shown
MA1615.1_Plagl10.0213233Not shown










    







Motif 18/19










    

















    







Motif IDq-valPWM
MA1628.1_Zic1::Zic20.405215
PAX5_HUMAN.H11MO.0.A0.405215










    







Motif 19/19










    

















    







Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A1.6466800000000001e-06
SP1_HUMAN.H11MO.0.A1.6466800000000001e-06
ZN467_HUMAN.H11MO.0.C1.6466800000000001e-06
SP3_HUMAN.H11MO.0.B1.6698400000000001e-06
MAZ_HUMAN.H11MO.0.A1.6698400000000001e-06
KLF16_HUMAN.H11MO.0.D1.0843599999999999e-05Not shown
TBX15_HUMAN.H11MO.0.D1.23453e-05Not shown
WT1_HUMAN.H11MO.0.C1.23453e-05Not shown
PATZ1_HUMAN.H11MO.0.C1.23453e-05Not shown
VEZF1_HUMAN.H11MO.0.C1.23453e-05Not shown























Sample of seqlets supporting each motif
Here, the motifs are presented as hCWMs, along with the actual importance scores of a random sample of seqlets that support the motif.













In [18]:



    


num_seqlets_to_show = 10

colgroup = vdomh.colgroup(
    vdomh.col(style={"width": "50%"}),
    vdomh.col(style={"width": "50%"})
)

header = vdomh.thead(
    vdomh.tr(
        vdomh.th("Motif hCWM", style={"text-align": "center"}),
        vdomh.th("Seqlets", style={"text-align": "center"})
    )
)

for i in range(len(motif_hcwms)):
    display(vdomh.h3("Metacluster %d/%d" % (i + 1, num_metaclusters)))
    
    for j in range(len(motif_hcwms[i])):
        display(vdomh.h4("Motif %d/%d" % (j + 1, len(motif_hcwms[i]))))
        
        motif_fig = viz_sequence.plot_weights(motif_hcwms[i][j], figsize=(20, 4), return_fig=True)
        motif_fig.tight_layout()
        
        seqlet_seqs, seqlet_hyps = motif_seqlets[i][j]
        
        sample_size = min(num_seqlets_to_show, len(seqlet_seqs))
        sample_inds = np.random.choice(len(seqlet_seqs), size=sample_size, replace=False)
        sample = []
        for k in sample_inds:
            fig = viz_sequence.plot_weights(seqlet_hyps[k] * seqlet_seqs[k], subticks_frequency=10, return_fig=True)
            fig.tight_layout()
            sample.append(util.figure_to_vdom_image(fig))
        body = vdomh.tbody(vdomh.tr(vdomh.td(util.figure_to_vdom_image(motif_fig)), vdomh.td(*sample)))
        display(vdomh.table(colgroup, header, body))
        plt.close("all")



    















    







Metacluster 1/2










    







Motif 1/2










    







Motif hCWMSeqlets










    







Motif 2/2










    







Motif hCWMSeqlets










    







Metacluster 2/2










    







Motif 1/19










    







Motif hCWMSeqlets










    







Motif 2/19










    







Motif hCWMSeqlets










    







Motif 3/19










    







Motif hCWMSeqlets










    







Motif 4/19










    







Motif hCWMSeqlets










    







Motif 5/19










    







Motif hCWMSeqlets










    







Motif 6/19










    







Motif hCWMSeqlets










    







Motif 7/19










    







Motif hCWMSeqlets










    







Motif 8/19










    







Motif hCWMSeqlets










    







Motif 9/19










    







Motif hCWMSeqlets










    







Motif 10/19










    







Motif hCWMSeqlets










    







Motif 11/19










    







Motif hCWMSeqlets










    







Motif 12/19










    







Motif hCWMSeqlets










    







Motif 13/19










    







Motif hCWMSeqlets










    







Motif 14/19










    







Motif hCWMSeqlets










    







Motif 15/19










    







Motif hCWMSeqlets










    







Motif 16/19










    







Motif hCWMSeqlets










    







Motif 17/19










    







Motif hCWMSeqlets










    







Motif 18/19










    







Motif hCWMSeqlets










    







Motif 19/19










    







Motif hCWMSeqlets