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: FOXA2
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/FOXA2_multitask_profile_fold2/FOXA2_multitask_profile_fold2_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/FOXA2_multitask_profile_fold2/FOXA2_multitask_profile_fold2_profile_tfm.h5
Importance score key: profile_hyp_scores
Saved TF-MoDISco-derived motifs cache: /users/amtseng/tfmodisco/results/reports/tfmodisco_results//cache/multitask_profile/FOXA2_multitask_profile_fold2/FOXA2_multitask_profile_fold2_profile
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%|██████████| 174/174 [03:27<00:00,  1.19s/it]
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")

Metacluster 1/2

Pattern 1/12

7684 seqlets

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

Pattern 2/12

2654 seqlets

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

Pattern 3/12

1485 seqlets

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

Pattern 4/12

731 seqlets

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

Pattern 5/12

198 seqlets

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

Pattern 6/12

196 seqlets

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

Pattern 7/12

181 seqlets

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

Pattern 8/12

101 seqlets

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

Pattern 9/12

91 seqlets

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

Pattern 10/12

86 seqlets

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

Pattern 11/12

67 seqlets

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

Pattern 12/12

58 seqlets

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

Metacluster 2/2

Pattern 1/1

72 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 1/2

/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
17684
22654
31485
4731
5198
6196
7181
8101
991
1086
1167
1258

Metacluster 2/2

#SeqletsForwardReverse
172

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 1/2

Motif 1/12

Motif IDq-valPWM
FOXA3_HUMAN.H11MO.0.B9.15407e-08
FOXA1_HUMAN.H11MO.0.A9.93192e-08
MA0846.1_FOXC21.24809e-07
FOXA2_HUMAN.H11MO.0.A1.24809e-07
MA0032.2_FOXC13.08156e-07
FOXF2_HUMAN.H11MO.0.D5.7948e-06Not shown
FOXD3_HUMAN.H11MO.0.D5.7948e-06Not shown
MA0847.2_FOXD25.7948e-06Not shown
MA0845.1_FOXB11.58519e-05Not shown
FOXC1_HUMAN.H11MO.0.C1.58519e-05Not shown

Motif 2/12

Motif IDq-valPWM
FOXM1_HUMAN.H11MO.0.A0.00019006400000000002
FOXJ2_HUMAN.H11MO.0.C0.00361918
MA1487.1_FOXE10.00532201
FOXA1_HUMAN.H11MO.0.A0.0054086
FOXF2_HUMAN.H11MO.0.D0.0054086
MA0846.1_FOXC20.00631641Not shown
FOXA2_HUMAN.H11MO.0.A0.00631641Not shown
MA0847.2_FOXD20.00722674Not shown
FOXD3_HUMAN.H11MO.0.D0.00944577Not shown
FOXC1_HUMAN.H11MO.0.C0.00974349Not shown

Motif 3/12

Motif IDq-valPWM
HNF4A_HUMAN.H11MO.0.A1.33371e-05
HNF4G_HUMAN.H11MO.0.B1.33371e-05
MA0677.1_Nr2f68.33784e-05
MA0856.1_RXRG8.33784e-05
MA1550.1_PPARD8.33784e-05
MA0512.2_Rxra8.33784e-05Not shown
MA1537.1_NR2F1(var.2)8.33784e-05Not shown
MA1574.1_THRB8.33784e-05Not shown
MA0115.1_NR1H2::RXRA8.63309e-05Not shown
NR1H2_HUMAN.H11MO.0.D9.84731e-05Not shown

Motif 4/12

Motif IDq-valPWM
CEBPA_HUMAN.H11MO.0.A8.0696e-07
CEBPB_HUMAN.H11MO.0.A8.0696e-07
MA0836.2_CEBPD2.59011e-06
CEBPD_HUMAN.H11MO.0.C7.81179e-06
MA0102.4_CEBPA0.00013062
MA0837.1_CEBPE0.00171189Not shown
MA0466.2_CEBPB0.00171189Not shown
MA0838.1_CEBPG0.0017809999999999998Not shown
DBP_HUMAN.H11MO.0.B0.00239643Not shown
MA0025.2_NFIL30.00239643Not shown

Motif 5/12

Motif IDq-valPWM
JUN_HUMAN.H11MO.0.A2.25367e-05
BACH2_HUMAN.H11MO.0.A0.000100377
FOSB_HUMAN.H11MO.0.A0.000122136
MA0591.1_Bach1::Mafk0.000122136
MA0501.1_MAF::NFE20.000122136
MA1622.1_Smad2::Smad30.000122136Not shown
MA1135.1_FOSB::JUNB0.000122136Not shown
MA1144.1_FOSL2::JUND0.000122136Not shown
FOSL2_HUMAN.H11MO.0.A0.000122136Not shown
FOSL1_HUMAN.H11MO.0.A0.000122136Not shown

Motif 6/12

Motif IDq-valPWM
MA0856.1_RXRG0.00165914
MA0512.2_Rxra0.00165914
MA0855.1_RXRB0.00165914
MA0677.1_Nr2f60.00165914
NR4A3_HUMAN.H11MO.0.D0.00165914
RXRG_HUMAN.H11MO.0.B0.00212238Not shown
PPARG_HUMAN.H11MO.1.A0.00212238Not shown
RXRA_HUMAN.H11MO.1.A0.00212238Not shown
PPARA_HUMAN.H11MO.1.B0.00222729Not shown
MA1574.1_THRB0.00334101Not shown

Motif 7/12

Motif IDq-valPWM
HNF4G_HUMAN.H11MO.0.B0.00106558
HNF4A_HUMAN.H11MO.0.A0.00106558
MA0484.2_HNF4G0.0011936
MA0114.4_HNF4A0.00124259
MA0856.1_RXRG0.00124259
MA0512.2_Rxra0.00124259Not shown
MA0855.1_RXRB0.00124259Not shown
MA0677.1_Nr2f60.00124259Not shown
RXRG_HUMAN.H11MO.0.B0.00325142Not shown
MA1574.1_THRB0.00494626Not shown

Motif 8/12

Motif IDq-valPWM
MA0466.2_CEBPB3.39684e-06
MA0837.1_CEBPE3.39684e-06
MA0838.1_CEBPG2.7474699999999996e-05
CEBPB_HUMAN.H11MO.0.A0.000192914
CEBPD_HUMAN.H11MO.0.C0.00267864
CEBPA_HUMAN.H11MO.0.A0.00276505Not shown
DBP_HUMAN.H11MO.0.B0.00452825Not shown
MA0836.2_CEBPD0.00695915Not shown
NFIL3_HUMAN.H11MO.0.D0.00750405Not shown
CEBPE_HUMAN.H11MO.0.A0.00836963Not shown

Motif 9/12

Motif IDq-valPWM
MA0837.1_CEBPE3.22468e-05
MA0466.2_CEBPB3.22468e-05
MA0838.1_CEBPG0.000116926
CEBPB_HUMAN.H11MO.0.A0.00355302
MA0639.1_DBP0.00475517
HLF_HUMAN.H11MO.0.C0.00512155Not shown
CEBPD_HUMAN.H11MO.0.C0.00512155Not shown
CEBPE_HUMAN.H11MO.0.A0.0054412Not shown
DBP_HUMAN.H11MO.0.B0.0054412Not shown
MA0843.1_TEF0.00628931Not shown

Motif 10/12

Motif IDq-valPWM
MA0837.1_CEBPE1.14608e-07
MA0466.2_CEBPB1.14608e-07
MA0838.1_CEBPG2.11805e-06
CEBPD_HUMAN.H11MO.0.C0.000460552
CEBPE_HUMAN.H11MO.0.A0.000696003
CEBPB_HUMAN.H11MO.0.A0.000696003Not shown
BATF_HUMAN.H11MO.1.A0.0008506830000000001Not shown
HLF_HUMAN.H11MO.0.C0.0008506830000000001Not shown
CEBPA_HUMAN.H11MO.0.A0.00381244Not shown
NFIL3_HUMAN.H11MO.0.D0.00381244Not shown

Motif 11/12

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D0.000124176
FOXL1_HUMAN.H11MO.0.D0.00283241
ANDR_HUMAN.H11MO.0.A0.00283241
MA1125.1_ZNF3840.00878488
FOXG1_HUMAN.H11MO.0.D0.0104221
PRDM6_HUMAN.H11MO.0.C0.0181299Not shown
MA0679.2_ONECUT10.0353654Not shown
FOXJ3_HUMAN.H11MO.0.A0.0402908Not shown
FUBP1_HUMAN.H11MO.0.D0.0402908Not shown
ONEC2_HUMAN.H11MO.0.D0.0497144Not shown

Motif 12/12

Motif IDq-valPWM
FOXA1_HUMAN.H11MO.0.A0.000268787
FOXA2_HUMAN.H11MO.0.A0.0009613089999999999
FOXM1_HUMAN.H11MO.0.A0.0009613089999999999
FOXF2_HUMAN.H11MO.0.D0.00185284
MA1487.1_FOXE10.00577589
MA0847.2_FOXD20.00615999Not shown
FOXJ2_HUMAN.H11MO.0.C0.0073826000000000004Not shown
FOXA3_HUMAN.H11MO.0.B0.012584Not shown
FOXL1_HUMAN.H11MO.0.D0.016214199999999998Not shown
MA0846.1_FOXC20.017925299999999998Not shown

Metacluster 2/2

Motif 1/1

Motif IDq-valPWM
MA0593.1_FOXP20.000101191
MA0849.1_FOXO60.00039292300000000005
FOXD1_HUMAN.H11MO.0.D0.000624546
FOXF2_HUMAN.H11MO.0.D0.000624546
MA0846.1_FOXC20.000624546
MA0042.2_FOXI10.000624546Not shown
MA0848.1_FOXO40.000624546Not shown
FOXP2_HUMAN.H11MO.0.C0.0007089739999999999Not shown
MA1606.1_Foxf10.000760751Not shown
FOXC1_HUMAN.H11MO.0.C0.000807335Not shown