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: JUND
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/JUND_multitask_profile_fold1/JUND_multitask_profile_fold1_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/JUND_multitask_profile_fold1/JUND_multitask_profile_fold1_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/JUND_multitask_profile_fold1/JUND_multitask_profile_fold1_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%|██████████| 350/350 [04:30<00:00,  1.30it/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 1/2

Pattern 1/10

5940 seqlets

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

Pattern 2/10

1621 seqlets

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

Pattern 3/10

1056 seqlets

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

Pattern 4/10

664 seqlets

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

Pattern 5/10

608 seqlets

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

Pattern 6/10

398 seqlets

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

Pattern 7/10

358 seqlets

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

Pattern 8/10

106 seqlets

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

Pattern 9/10

94 seqlets

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

Pattern 10/10

65 seqlets

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

Metacluster 2/2

Pattern 1/8

152 seqlets

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

Pattern 2/8

145 seqlets

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

Pattern 3/8

121 seqlets

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

Pattern 4/8

114 seqlets

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

Pattern 5/8

110 seqlets

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

Pattern 6/8

102 seqlets

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

Pattern 7/8

101 seqlets

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

Pattern 8/8

66 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

#SeqletsForwardReverse
15940
21621
31056
4664
5608
6398
7358
8106
994
1065

Metacluster 2/2

#SeqletsForwardReverse
1152
2145
3121
4114
5110
6102
7101
866

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 1/10

Motif IDq-valPWM
JUN_HUMAN.H11MO.0.A3.63283e-07
FOSL2_HUMAN.H11MO.0.A3.63283e-07
FOSL1_HUMAN.H11MO.0.A1.4672299999999999e-06
FOSB_HUMAN.H11MO.0.A2.1983599999999997e-06
JUND_HUMAN.H11MO.0.A2.1983599999999997e-06
MA1130.1_FOSL2::JUN2.44262e-06Not shown
MA0099.3_FOS::JUN2.6763799999999998e-06Not shown
MA1141.1_FOS::JUND5.2040699999999995e-06Not shown
MA1128.1_FOSL1::JUN5.2040699999999995e-06Not shown
MA1622.1_Smad2::Smad35.62039e-06Not shown

Motif 2/10

Motif IDq-valPWM
MA0605.2_ATF36.30542e-07
MA1475.1_CREB3L4(var.2)6.30542e-07
MA1131.1_FOSL2::JUN(var.2)2.06176e-06
JDP2_HUMAN.H11MO.0.D2.06176e-06
ATF2_HUMAN.H11MO.2.C2.6810400000000005e-06
MA1127.1_FOSB::JUN2.6810400000000005e-06Not shown
MA1145.1_FOSL2::JUND(var.2)2.6810400000000005e-06Not shown
MA0656.1_JDP2(var.2)2.6810400000000005e-06Not shown
ATF7_HUMAN.H11MO.0.D2.9858099999999997e-06Not shown
MA1139.1_FOSL2::JUNB(var.2)3.6455800000000006e-06Not shown

Motif 3/10

Motif IDq-valPWM
ATF4_HUMAN.H11MO.0.A0.00022166400000000002
MA1636.1_CEBPG(var.2)0.00022166400000000002
MA0833.2_ATF40.00022166400000000002
CEBPG_HUMAN.H11MO.0.B0.000237242
CEBPD_HUMAN.H11MO.0.C0.00041579400000000004
CEBPB_HUMAN.H11MO.0.A0.000418876Not shown
DDIT3_HUMAN.H11MO.0.D0.0004538Not shown
MA0025.2_NFIL30.000779365Not shown
MA0837.1_CEBPE0.00107196Not shown
MA0466.2_CEBPB0.00107196Not shown

Motif 4/10

No TOMTOM matches passing threshold

Motif 5/10

Motif IDq-valPWM
COT2_HUMAN.H11MO.1.A0.27515500000000004
MA1632.1_ATF20.27515500000000004
MAFK_HUMAN.H11MO.1.A0.27515500000000004
RXRG_HUMAN.H11MO.0.B0.27515500000000004
CREB3_HUMAN.H11MO.0.D0.27515500000000004
MA0490.2_JUNB0.27515500000000004Not shown
MA0842.2_NRL0.27515500000000004Not shown
MA1128.1_FOSL1::JUN0.27515500000000004Not shown
MA0066.1_PPARG0.27515500000000004Not shown
STF1_HUMAN.H11MO.0.B0.27515500000000004Not shown

Motif 6/10

Motif IDq-valPWM
CTCF_HUMAN.H11MO.0.A0.00032198
CTCFL_HUMAN.H11MO.0.A0.00033403199999999995
MA1102.2_CTCFL0.000542416
MA0139.1_CTCF0.00177335
MA0830.2_TCF40.038968800000000005
USF2_HUMAN.H11MO.0.A0.053713699999999996Not shown
MXI1_HUMAN.H11MO.0.A0.053713699999999996Not shown
MA1648.1_TCF12(var.2)0.059272500000000006Not shown
SNAI1_HUMAN.H11MO.0.C0.063151Not shown
PLAL1_HUMAN.H11MO.0.D0.063151Not shown

Motif 7/10

Motif IDq-valPWM
FOSL1_HUMAN.H11MO.0.A0.12100699999999999
MA0591.1_Bach1::Mafk0.126394
ZN554_HUMAN.H11MO.1.D0.151252
FOSL2_HUMAN.H11MO.0.A0.182614
NFE2_HUMAN.H11MO.0.A0.182614
MA1583.1_ZFP570.182614Not shown
KLF9_HUMAN.H11MO.0.C0.182614Not shown
MA0003.4_TFAP2A0.23386300000000002Not shown
MA1631.1_ASCL1(var.2)0.23386300000000002Not shown
JUND_HUMAN.H11MO.0.A0.23386300000000002Not shown

Motif 8/10

Motif IDq-valPWM
MA0150.2_Nfe2l20.237605
MA0591.1_Bach1::Mafk0.237605
MA0003.4_TFAP2A0.237605
MA1511.1_KLF100.237605
BACH1_HUMAN.H11MO.0.A0.295286
MA1107.2_KLF90.295286Not shown
NFE2_HUMAN.H11MO.0.A0.493065Not shown
FOSL1_HUMAN.H11MO.0.A0.493065Not shown

Motif 9/10

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D5.8603999999999997e-05
MA1125.1_ZNF3840.0121348
FOXL1_HUMAN.H11MO.0.D0.0174714
PRDM6_HUMAN.H11MO.0.C0.0174714
FOXG1_HUMAN.H11MO.0.D0.030477999999999998
ANDR_HUMAN.H11MO.0.A0.0608389Not shown
FOXJ3_HUMAN.H11MO.0.A0.0661172Not shown
MA0679.2_ONECUT10.0661172Not shown
FUBP1_HUMAN.H11MO.0.D0.0854618Not shown
ONEC2_HUMAN.H11MO.0.D0.09481619999999999Not shown

Motif 10/10

Motif IDq-valPWM
ZFP28_HUMAN.H11MO.0.C0.19541
FOSB_HUMAN.H11MO.0.A0.19541
MA0655.1_JDP20.19541
FOSL2_HUMAN.H11MO.0.A0.19541
FOSL1_HUMAN.H11MO.0.A0.19541
MA1144.1_FOSL2::JUND0.202535Not shown
MA1138.1_FOSL2::JUNB0.202535Not shown
MA1135.1_FOSB::JUNB0.202535Not shown
MA0496.3_MAFK0.202535Not shown
MA1132.1_JUN::JUNB0.202535Not shown

Metacluster 2/2

Motif 1/8

No TOMTOM matches passing threshold

Motif 2/8

No TOMTOM matches passing threshold

Motif 3/8

Motif IDq-valPWM
ZN331_HUMAN.H11MO.0.C0.158748
ZN121_HUMAN.H11MO.0.C0.348269

Motif 4/8

No TOMTOM matches passing threshold

Motif 5/8

No TOMTOM matches passing threshold

Motif 6/8

No TOMTOM matches passing threshold

Motif 7/8

Motif IDq-valPWM
MA1615.1_Plagl10.338913

Motif 8/8

Motif IDq-valPWM
MA0491.2_JUND0.0009326810000000001
MA1633.1_BACH10.0009326810000000001
MA0490.2_JUNB0.0009326810000000001
MA0477.2_FOSL10.0009326810000000001
MA1130.1_FOSL2::JUN0.0009326810000000001
MA1634.1_BATF0.0009326810000000001Not shown
BACH2_HUMAN.H11MO.0.A0.0009326810000000001Not shown
MA0835.2_BATF30.0009326810000000001Not shown
MA0462.2_BATF::JUN0.0009326810000000001Not shown
MA1144.1_FOSL2::JUND0.0009326810000000001Not shown