TF-MoDISco results

Summary of motifs

TOMTOM matches to motifs

In [1]:
import os
import sys
sys.path.append(os.path.abspath("/users/amtseng/tfmodisco/src/"))
from tfmodisco.run_tfmodisco import import_shap_scores, import_tfmodisco_results
from motif.read_motifs import pfm_info_content, pfm_to_pwm, trim_motif_by_ic
from motif.match_motifs import match_motifs_to_database
from util import figure_to_vdom_image
import plot.viz_sequence as viz_sequence
import numpy as np
import h5py
import matplotlib.pyplot as plt
import vdom.helpers as vdomh
from IPython.display import display

Define constants and paths

In [2]:
# Define parameters/fetch arguments
tf_name = os.environ["TFM_TF_NAME"]
shap_scores_path = os.environ["TFM_SHAP_PATH"]
tfm_results_path = os.environ["TFM_TFM_PATH"]
hyp_score_key = os.environ["TFM_HYP_SCORE_KEY"]
if "TFM_MOTIF_CACHE" in os.environ:
    tfm_motifs_cache_dir = os.environ["TFM_MOTIF_CACHE"]
else:
    tfm_motifs_cache_dir = None

print("TF name: %s" % tf_name)
print("DeepSHAP scores path: %s" % shap_scores_path)
print("TF-MoDISco results path: %s" % tfm_results_path)
print("Importance score key: %s" % hyp_score_key)
print("Saved TF-MoDISco-derived motifs cache: %s" % tfm_motifs_cache_dir)

TF name: NR3C1-reddytime
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/NR3C1-reddytime_multitask_profile_fold6/NR3C1-reddytime_multitask_profile_fold6_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/NR3C1-reddytime_multitask_profile_fold6/NR3C1-reddytime_multitask_profile_fold6_count_tfm.h5
Importance score key: count_hyp_scores
Saved TF-MoDISco-derived motifs cache: /users/amtseng/tfmodisco/results/reports/tfmodisco_results//cache/multitask_profile/NR3C1-reddytime_multitask_profile_fold6/NR3C1-reddytime_multitask_profile_fold6_count
In [3]:
# Define paths and constants
input_length = 2114
shap_score_center_size = 400
In [4]:
if tfm_motifs_cache_dir:
    os.makedirs(tfm_motifs_cache_dir, exist_ok=True)

Import SHAP scores and TF-MoDISco results

In [5]:
# Import SHAP coordinates and one-hot sequences
hyp_scores, _, one_hot_seqs, shap_coords = import_shap_scores(shap_scores_path, hyp_score_key, center_cut_size=shap_score_center_size)
# This cuts the sequences/scores off just as how TF-MoDISco saw them, but the coordinates are uncut

Importing SHAP scores: 100%|██████████| 186/186 [01:28<00:00,  2.09it/s]
In [6]:
# Import the TF-MoDISco results object
tfm_obj = 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 [7]:
plot_slice = slice(int(shap_score_center_size / 4), int(3 * shap_score_center_size / 4))
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])[plot_slice], subticks_frequency=100)

Plot TF-MoDISco results

Plot all motifs by metacluster

In [8]:
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())
if tfm_motifs_cache_dir:
    motif_hdf5 = h5py.File(os.path.join(tfm_motifs_cache_dir, "all_motifs.h5"), "w")
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(figure_to_vdom_image(pfm_fig))
            ),
            vdomh.tr(
                vdomh.td("Hypothetical contributions (hCWM)"),
                vdomh.td(figure_to_vdom_image(hcwm_fig))
            ),
            vdomh.tr(
                vdomh.td("Actual contributions (CWM)"),
                vdomh.td(figure_to_vdom_image(cwm_fig))
            )
        )
        display(motif_table)
        plt.close("all")  # Remove all standing figures
        
        # Trim motif based on information content
        short_trimmed_pfm = trim_motif_by_ic(pfm, pfm)
        motif_pfms_short[-1].append(short_trimmed_pfm)
        
        # Expand trimming to +/- 4bp on either side
        trimmed_pfm = trim_motif_by_ic(pfm, pfm, pad=4)
        trimmed_hcwm = trim_motif_by_ic(pfm, hcwm, pad=4)
        trimmed_cwm = trim_motif_by_ic(pfm, cwm, pad=4)
        
        motif_pfms[-1].append(trimmed_pfm)
        motif_hcwms[-1].append(trimmed_hcwm)
        motif_cwms[-1].append(trimmed_cwm)
        
        num_seqlets[-1].append(len(seqlets))
        
        if tfm_motifs_cache_dir:
            # Save results and figures
            motif_id = "%d_%d" % (metacluster_i, pattern_i)
            pfm_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_pfm_full.png"))
            hcwm_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_hcwm_full.png"))
            cwm_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_cwm_full.png"))
            motif_dset = motif_hdf5.create_group(motif_id)
            motif_dset.create_dataset("pfm_full", data=pfm, compression="gzip")
            motif_dset.create_dataset("hcwm_full", data=hcwm, compression="gzip")
            motif_dset.create_dataset("cwm_full", data=cwm, compression="gzip")
            motif_dset.create_dataset("pfm_trimmed", data=trimmed_pfm, compression="gzip")
            motif_dset.create_dataset("hcwm_trimmed", data=trimmed_hcwm, compression="gzip")
            motif_dset.create_dataset("cwm_trimmed", data=trimmed_cwm, compression="gzip")
            motif_dset.create_dataset("pfm_short_trimmed", data=short_trimmed_pfm, compression="gzip")
if tfm_motifs_cache_dir:
    motif_hdf5.close()

Metacluster 1/1

Pattern 1/12

7227 seqlets

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

Pattern 2/12

3338 seqlets

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

Pattern 3/12

1393 seqlets

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

Pattern 4/12

762 seqlets

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

Pattern 5/12

368 seqlets

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

Pattern 6/12

304 seqlets

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

Pattern 7/12

270 seqlets

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

Pattern 8/12

180 seqlets

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

Pattern 9/12

141 seqlets

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

Pattern 10/12

41 seqlets

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

Pattern 11/12

39 seqlets

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

Pattern 12/12

37 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 [9]:
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()
        
        if tfm_motifs_cache_dir:
            # Save results and figures
            motif_id = "%d_%d" % (i, j)
            f_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_hcwm_trimmed_fwd.png"))
            rc_fig.savefig(os.path.join(tfm_motifs_cache_dir, motif_id + "_hcwm_trimmed_rev.png"))

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

Metacluster 1/1

/users/amtseng/tfmodisco/src/plot/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
17227
23338
31393
4762
5368
6304
7270
8180
9141
1041
1139
1237

Top TOMTOM matches for each motif

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

In [10]:
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
    out_dir = os.path.join(tfm_motifs_cache_dir, "tomtom", "metacluster_%d" % i) if tfm_motifs_cache_dir else None
    tomtom_matches = match_motifs_to_database(motif_pfms_short[i], top_k=num_matches_to_keep, temp_dir=out_dir)
    
    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(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(figure_to_vdom_image(fig))
                    )
                )
                if tfm_motifs_cache_dir:
                    # Save results and figures
                    motif_id = "%d_%d" % (i, j)
                    fig.savefig(os.path.join(out_dir, motif_id + ("_hit-%d.png" % (k + 1))))
            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 1/1

Motif 1/12

Motif IDq-valPWM
GCR_HUMAN.H11MO.0.A4.43512e-09
PRGR_HUMAN.H11MO.0.A4.95399e-07
ANDR_HUMAN.H11MO.1.A1.47997e-06
MA0727.1_NR3C20.00014361700000000002
MA0113.3_NR3C10.00022757299999999998
PRGR_HUMAN.H11MO.1.A0.00893681Not shown
MA0007.3_Ar0.014920500000000001Not shown
GCR_HUMAN.H11MO.1.A0.0337985Not shown
MA1508.1_IKZF10.339807Not shown
MA1623.1_Stat20.44161300000000003Not shown

Motif 2/12

Motif IDq-valPWM
FOSB_HUMAN.H11MO.0.A5.98581e-06
FOSL1_HUMAN.H11MO.0.A5.98581e-06
JUN_HUMAN.H11MO.0.A5.98581e-06
MA0099.3_FOS::JUN5.98581e-06
MA1144.1_FOSL2::JUND5.98581e-06
FOSL2_HUMAN.H11MO.0.A5.98581e-06Not shown
MA1130.1_FOSL2::JUN5.98581e-06Not shown
MA1138.1_FOSL2::JUNB6.097140000000001e-06Not shown
MA1135.1_FOSB::JUNB6.097140000000001e-06Not shown
MA0478.1_FOSL26.097140000000001e-06Not shown

Motif 3/12

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A5.682569999999999e-10
CEBPD_HUMAN.H11MO.0.C4.86219e-07
CEBPA_HUMAN.H11MO.0.A1.0777999999999999e-05
MA0836.2_CEBPD1.0777999999999999e-05
MA0102.4_CEBPA0.000121577
MA0837.1_CEBPE0.000257277Not shown
MA0466.2_CEBPB0.000266059Not shown
MA0838.1_CEBPG0.000388247Not shown
MA0025.2_NFIL30.00056279Not shown
DBP_HUMAN.H11MO.0.B0.0015375999999999999Not shown

Motif 4/12

Motif IDq-valPWM
FOXA1_HUMAN.H11MO.0.A2.5419299999999997e-06
FOXM1_HUMAN.H11MO.0.A2.5419299999999997e-06
FOXA2_HUMAN.H11MO.0.A4.544219999999999e-06
FOXF2_HUMAN.H11MO.0.D1.6554400000000002e-05
FOXA3_HUMAN.H11MO.0.B3.74977e-05
FOXD3_HUMAN.H11MO.0.D4.68721e-05Not shown
MA0846.1_FOXC25.2065500000000005e-05Not shown
MA0847.2_FOXD26.0743100000000005e-05Not shown
FOXC1_HUMAN.H11MO.0.C8.09908e-05Not shown
FOXJ2_HUMAN.H11MO.0.C0.00138914Not shown

Motif 5/12

Motif IDq-valPWM
MA1145.1_FOSL2::JUND(var.2)5.315e-05
MA1133.1_JUN::JUNB(var.2)5.315e-05
JDP2_HUMAN.H11MO.0.D5.315e-05
MA1139.1_FOSL2::JUNB(var.2)5.315e-05
MA0840.1_Creb55.315e-05
MA0656.1_JDP2(var.2)5.315e-05Not shown
MA1140.2_JUNB(var.2)5.315e-05Not shown
MA1127.1_FOSB::JUN5.315e-05Not shown
ATF7_HUMAN.H11MO.0.D5.315e-05Not shown
ATF2_HUMAN.H11MO.2.C5.315e-05Not shown

Motif 6/12

Motif IDq-valPWM
TEAD4_HUMAN.H11MO.0.A0.0560112
PRGR_HUMAN.H11MO.0.A0.0560112
P73_HUMAN.H11MO.1.A0.0560112
HXB2_HUMAN.H11MO.0.D0.0560112
MA0808.1_TEAD30.0560112
HSF1_HUMAN.H11MO.0.A0.0560112Not shown
HSF2_HUMAN.H11MO.0.A0.0560112Not shown
HSF4_HUMAN.H11MO.0.D0.06955Not shown
GCR_HUMAN.H11MO.0.A0.0771492Not shown
TEAD1_HUMAN.H11MO.0.A0.10341700000000001Not shown

Motif 7/12

Motif IDq-valPWM
PRGR_HUMAN.H11MO.0.A0.00327989
GCR_HUMAN.H11MO.0.A0.0161959
ANDR_HUMAN.H11MO.1.A0.0569503
MA0727.1_NR3C20.0569503
MA0113.3_NR3C10.0569503
PRGR_HUMAN.H11MO.1.A0.0569503Not shown
MA0808.1_TEAD30.267543Not shown
HSF1_HUMAN.H11MO.0.A0.357543Not shown
MA1508.1_IKZF10.357543Not shown
HSF2_HUMAN.H11MO.0.A0.357543Not shown

Motif 8/12

Motif IDq-valPWM
GCR_HUMAN.H11MO.0.A7.0528e-06
MA0727.1_NR3C22.4595e-05
ANDR_HUMAN.H11MO.1.A4.13328e-05
MA0113.3_NR3C14.13328e-05
PRGR_HUMAN.H11MO.0.A0.00016037200000000002
MA0007.3_Ar0.012014700000000001Not shown
GCR_HUMAN.H11MO.1.A0.310792Not shown

Motif 9/12

Motif IDq-valPWM
FOXD2_HUMAN.H11MO.0.D0.0040051999999999996
FOXB1_HUMAN.H11MO.0.D0.0781424
MA0032.2_FOXC10.40103
MA0845.1_FOXB10.40103
MA0791.1_POU4F30.40103
MA0683.1_POU4F20.445208Not shown
FOXJ2_HUMAN.H11MO.0.C0.464232Not shown
MA0847.2_FOXD20.464232Not shown
PO4F3_HUMAN.H11MO.0.D0.469659Not shown
FOXA2_HUMAN.H11MO.0.A0.481572Not shown

Motif 10/12

Motif IDq-valPWM
MA0041.1_Foxd30.0142591
FOXJ2_HUMAN.H11MO.0.C0.022988599999999998
MA1103.2_FOXK20.0325328
MA0047.3_FOXA20.0325328
MA1683.1_FOXA30.0325328
MA0593.1_FOXP20.0325328Not shown
FOXF1_HUMAN.H11MO.0.D0.0325328Not shown
MA0846.1_FOXC20.0325328Not shown
MA1606.1_Foxf10.0325328Not shown
FOXD2_HUMAN.H11MO.0.D0.0325328Not shown

Motif 11/12

Motif IDq-valPWM
CEBPB_HUMAN.H11MO.0.A0.00294388
MA1636.1_CEBPG(var.2)0.00331745
MA0833.2_ATF40.00360471
DDIT3_HUMAN.H11MO.0.D0.00569438
MA0025.2_NFIL30.00641117
CEBPD_HUMAN.H11MO.0.C0.00641117Not shown
CEBPA_HUMAN.H11MO.0.A0.00641117Not shown
BATF_HUMAN.H11MO.1.A0.00986429Not shown
NFIL3_HUMAN.H11MO.0.D0.00986429Not shown
MA0837.1_CEBPE0.00986429Not shown

Motif 12/12

Motif IDq-valPWM
MA0837.1_CEBPE7.468430000000001e-06
MA0466.2_CEBPB7.468430000000001e-06
MA0838.1_CEBPG2.55903e-05
CEBPB_HUMAN.H11MO.0.A0.00133651
CEBPE_HUMAN.H11MO.0.A0.00236558
CEBPD_HUMAN.H11MO.0.C0.00271936Not shown
NFIL3_HUMAN.H11MO.0.D0.00275731Not shown
MA0025.2_NFIL30.00607191Not shown
BATF_HUMAN.H11MO.1.A0.00875647Not shown
MA0836.2_CEBPD0.019840700000000003Not shown