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: MAFK
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/MAFK_multitask_profile_fold7/MAFK_multitask_profile_fold7_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/MAFK_multitask_profile_fold7/MAFK_multitask_profile_fold7_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/MAFK_multitask_profile_fold7/MAFK_multitask_profile_fold7_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%|██████████| 311/311 [05:43<00:00,  1.11s/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")
if tfm_motifs_cache_dir:
    motif_hdf5.close()

Metacluster 1/2

Pattern 1/14

9407 seqlets

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

Pattern 2/14

541 seqlets

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

Pattern 3/14

540 seqlets

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

Pattern 4/14

383 seqlets

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

Pattern 5/14

215 seqlets

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

Pattern 6/14

162 seqlets

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

Pattern 7/14

146 seqlets

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

Pattern 8/14

109 seqlets

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

Pattern 9/14

64 seqlets

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

Pattern 10/14

59 seqlets

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

Pattern 11/14

51 seqlets

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

Pattern 12/14

42 seqlets

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

Pattern 13/14

38 seqlets

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

Pattern 14/14

36 seqlets

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

Metacluster 2/2

Pattern 1/1

62 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
19407
2541
3540
4383
5215
6162
7146
8109
964
1059
1151
1242
1338
1436

Metacluster 2/2

#SeqletsForwardReverse
162

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 1/14

Motif IDq-valPWM
MAFK_HUMAN.H11MO.0.A2.6637499999999996e-09
MA0496.3_MAFK2.6637499999999996e-09
MAFB_HUMAN.H11MO.0.B2.6637499999999996e-09
MA1520.1_MAF2.6637499999999996e-09
MAFG_HUMAN.H11MO.0.A2.6637499999999996e-09
MAFK_HUMAN.H11MO.1.A8.68239e-09Not shown
MAF_HUMAN.H11MO.0.A4.423690000000001e-08Not shown
MA1521.1_MAFA8.71037e-08Not shown
MAFF_HUMAN.H11MO.0.B1.7826299999999999e-07Not shown
MAF_HUMAN.H11MO.1.B7.64964e-06Not shown

Motif 2/14

Motif IDq-valPWM
JUN_HUMAN.H11MO.0.A3.51844e-05
FOSL2_HUMAN.H11MO.0.A3.51844e-05
MA1130.1_FOSL2::JUN0.00011462399999999999
NFE2_HUMAN.H11MO.0.A0.00011462399999999999
MA0099.3_FOS::JUN0.00012329799999999998
JUND_HUMAN.H11MO.0.A0.000136998Not shown
MA1128.1_FOSL1::JUN0.000136998Not shown
MA1141.1_FOS::JUND0.000136998Not shown
NF2L2_HUMAN.H11MO.0.A0.000136998Not shown
MA0150.2_Nfe2l20.000136998Not shown

Motif 3/14

Motif IDq-valPWM
MA0139.1_CTCF1.2416e-15
CTCF_HUMAN.H11MO.0.A1.52571e-12
CTCFL_HUMAN.H11MO.0.A8.22607e-07
MA1102.2_CTCFL0.000288206
MA1568.1_TCF21(var.2)0.0714215
MA1638.1_HAND20.0838645Not shown
SNAI1_HUMAN.H11MO.0.C0.18517Not shown
ZIC3_HUMAN.H11MO.0.B0.250684Not shown
MA1109.1_NEUROD10.411621Not shown
ZIC2_HUMAN.H11MO.0.D0.411621Not shown

Motif 4/14

No TOMTOM matches passing threshold

Motif 5/14

Motif IDq-valPWM
MA0659.2_MAFG3.5091500000000004e-07
MA0117.2_Mafb3.5091500000000004e-07
MA0495.3_MAFF3.5091500000000004e-07
MAFG_HUMAN.H11MO.0.A0.000505632
MAFF_HUMAN.H11MO.0.B0.000505632
MAFK_HUMAN.H11MO.0.A0.000744011Not shown
MA0842.2_NRL0.00142024Not shown
MAF_HUMAN.H11MO.0.A0.023703400000000003Not shown
MA0501.1_MAF::NFE20.023703400000000003Not shown
MAF_HUMAN.H11MO.1.B0.0312807Not shown

Motif 6/14

Motif IDq-valPWM
MXI1_HUMAN.H11MO.0.A0.385842
USF2_HUMAN.H11MO.0.A0.385842
MAX_HUMAN.H11MO.0.A0.385842
MA1587.1_ZNF1350.385842
MBD2_HUMAN.H11MO.0.B0.385842
KLF12_HUMAN.H11MO.0.C0.385842Not shown
BHE41_HUMAN.H11MO.0.D0.385842Not shown
MA0139.1_CTCF0.385842Not shown
CTCF_HUMAN.H11MO.0.A0.385842Not shown
SP4_HUMAN.H11MO.0.A0.385842Not shown

Motif 7/14

Motif IDq-valPWM
MAFG_HUMAN.H11MO.0.A0.00015622799999999998
MAFK_HUMAN.H11MO.0.A0.00015622799999999998
MAFF_HUMAN.H11MO.0.B0.0011830999999999999
MA0496.3_MAFK0.00238121
MAFK_HUMAN.H11MO.1.A0.00238211
MAF_HUMAN.H11MO.0.A0.00238211Not shown
MAF_HUMAN.H11MO.1.B0.00238211Not shown
MA1520.1_MAF0.00865146Not shown
MAFB_HUMAN.H11MO.0.B0.0170524Not shown
FOXD3_HUMAN.H11MO.0.D0.020615099999999997Not shown

Motif 8/14

No TOMTOM matches passing threshold

Motif 9/14

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D4.8303300000000006e-06
MA1125.1_ZNF3840.000848635
MA0679.2_ONECUT10.0079505
HXC10_HUMAN.H11MO.0.D0.0079505
FOXG1_HUMAN.H11MO.0.D0.0079505
FOXL1_HUMAN.H11MO.0.D0.0079505Not shown
LMX1A_HUMAN.H11MO.0.D0.0186236Not shown
ARI3A_HUMAN.H11MO.0.D0.0186236Not shown
FOXJ3_HUMAN.H11MO.0.A0.088148Not shown
PRDM6_HUMAN.H11MO.0.C0.088148Not shown

Motif 10/14

Motif IDq-valPWM
MA0117.2_Mafb0.0344848
MAF_HUMAN.H11MO.0.A0.0344848
MAF_HUMAN.H11MO.1.B0.08353719999999999
MAFK_HUMAN.H11MO.0.A0.0888829
MAFG_HUMAN.H11MO.0.A0.134909
MA0842.2_NRL0.176508Not shown
MAFF_HUMAN.H11MO.0.B0.227404Not shown
MAFG_HUMAN.H11MO.1.A0.25683Not shown
MA0659.2_MAFG0.285991Not shown
TEAD4_HUMAN.H11MO.0.A0.285991Not shown

Motif 11/14

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D2.9586500000000002e-05
MA1125.1_ZNF3840.0253175
PRDM6_HUMAN.H11MO.0.C0.0253175
FOXL1_HUMAN.H11MO.0.D0.028814
FOXG1_HUMAN.H11MO.0.D0.0598751
ANDR_HUMAN.H11MO.0.A0.06488569999999999Not shown
MA0679.2_ONECUT10.08530030000000001Not shown
ZFP28_HUMAN.H11MO.0.C0.08530030000000001Not shown
FOXJ3_HUMAN.H11MO.0.A0.08530030000000001Not shown
HXC10_HUMAN.H11MO.0.D0.0854072Not shown

Motif 12/14

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A1.60762e-07
TBX15_HUMAN.H11MO.0.D2.2656099999999999e-07
SP1_HUMAN.H11MO.0.A2.2656099999999999e-07
KLF16_HUMAN.H11MO.0.D2.45508e-07
SP3_HUMAN.H11MO.0.B2.45508e-07
PATZ1_HUMAN.H11MO.0.C2.73439e-07Not shown
ZN467_HUMAN.H11MO.0.C4.54878e-07Not shown
MAZ_HUMAN.H11MO.0.A6.32215e-07Not shown
WT1_HUMAN.H11MO.0.C2.28475e-06Not shown
VEZF1_HUMAN.H11MO.0.C3.51459e-06Not shown

Motif 13/14

Motif IDq-valPWM
PO3F3_HUMAN.H11MO.0.D0.176467
MA0465.2_CDX20.176467
MA0756.1_ONECUT20.20915599999999998
SHOX_HUMAN.H11MO.0.D0.20915599999999998
VSX1_HUMAN.H11MO.0.D0.20915599999999998
MA0507.1_POU2F20.20915599999999998Not shown
MA0787.1_POU3F20.20915599999999998Not shown
MA0790.1_POU4F10.20915599999999998Not shown
MA0495.3_MAFF0.20915599999999998Not shown
PO4F1_HUMAN.H11MO.0.D0.20915599999999998Not shown

Motif 14/14

Motif IDq-valPWM
BACH2_HUMAN.H11MO.0.A0.00022019700000000002
BACH1_HUMAN.H11MO.0.A0.00043079699999999996
MA0150.2_Nfe2l20.000453591
MAFF_HUMAN.H11MO.1.B0.000641394
NFE2_HUMAN.H11MO.0.A0.000706412
MA1633.1_BACH10.00102789Not shown
NF2L2_HUMAN.H11MO.0.A0.00177167Not shown
MAFG_HUMAN.H11MO.1.A0.00625712Not shown
MA0501.1_MAF::NFE20.00625712Not shown
MA0591.1_Bach1::Mafk0.00727677Not shown

Metacluster 2/2

Motif 1/1

Motif IDq-valPWM
MAFK_HUMAN.H11MO.0.A9.921889999999999e-05
MAFG_HUMAN.H11MO.0.A0.00010678
MA0117.2_Mafb0.00013605100000000002
MAF_HUMAN.H11MO.1.B0.000169956
MAF_HUMAN.H11MO.0.A0.000307572
MA1520.1_MAF0.00038368Not shown
MA0496.3_MAFK0.00038368Not shown
MAFF_HUMAN.H11MO.0.B0.00047808599999999996Not shown
MA0495.3_MAFF0.0009775810000000002Not shown
MA1521.1_MAFA0.0009775810000000002Not shown