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_fold5/MAFK_multitask_profile_fold5_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/MAFK_multitask_profile_fold5/MAFK_multitask_profile_fold5_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_fold5/MAFK_multitask_profile_fold5_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 [08:28<00:00,  1.63s/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 1/11

10323 seqlets

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

Pattern 2/11

739 seqlets

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

Pattern 3/11

665 seqlets

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

Pattern 4/11

234 seqlets

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

Pattern 5/11

228 seqlets

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

Pattern 6/11

182 seqlets

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

Pattern 7/11

52 seqlets

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

Pattern 8/11

45 seqlets

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

Pattern 9/11

44 seqlets

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

Pattern 10/11

42 seqlets

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

Pattern 11/11

42 seqlets

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

Metacluster 2/2

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
110323
2739
3665
4234
5228
6182
752
845
944
1042
1142

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 1/11

Motif IDq-valPWM
MAFK_HUMAN.H11MO.0.A2.14378e-10
MA1520.1_MAF2.14378e-10
MAFG_HUMAN.H11MO.0.A6.227619999999999e-10
MAFB_HUMAN.H11MO.0.B2.02639e-09
MA0496.3_MAFK3.24269e-09
MA1521.1_MAFA1.55656e-08Not shown
MAF_HUMAN.H11MO.0.A2.41838e-08Not shown
MAFK_HUMAN.H11MO.1.A6.20029e-08Not shown
MAFF_HUMAN.H11MO.0.B9.93924e-08Not shown
MAF_HUMAN.H11MO.1.B5.38147e-06Not shown

Motif 2/11

Motif IDq-valPWM
MA0139.1_CTCF1.0567799999999999e-16
CTCF_HUMAN.H11MO.0.A2.3378200000000002e-12
CTCFL_HUMAN.H11MO.0.A4.4655e-07
MA1102.2_CTCFL0.000291887
MA1568.1_TCF21(var.2)0.07108719999999999
MA1638.1_HAND20.07108719999999999Not shown
SNAI1_HUMAN.H11MO.0.C0.186281Not shown
ZIC3_HUMAN.H11MO.0.B0.25666100000000003Not shown
ZIC2_HUMAN.H11MO.0.D0.406521Not shown
MA1109.1_NEUROD10.414724Not shown

Motif 3/11

Motif IDq-valPWM
MA1141.1_FOS::JUND1.09832e-06
MA1128.1_FOSL1::JUN1.09832e-06
MA1130.1_FOSL2::JUN1.93413e-05
MA0099.3_FOS::JUN7.62485e-05
FOSL2_HUMAN.H11MO.0.A9.03686e-05
MA0477.2_FOSL19.03686e-05Not shown
MA1622.1_Smad2::Smad39.03686e-05Not shown
MA0150.2_Nfe2l29.03686e-05Not shown
MA0591.1_Bach1::Mafk9.03686e-05Not shown
MA0089.2_NFE2L19.14982e-05Not shown

Motif 4/11

Motif IDq-valPWM
MA0753.2_ZNF7400.0125785
ZN740_HUMAN.H11MO.0.D0.0125785
SP2_HUMAN.H11MO.0.A0.0125785
ZN423_HUMAN.H11MO.0.D0.0125785
MA0116.1_Znf4230.0125785
TBX15_HUMAN.H11MO.0.D0.0125785Not shown
MA1630.1_Znf2810.0140704Not shown
SP1_HUMAN.H11MO.1.A0.0140704Not shown
KLF1_HUMAN.H11MO.0.A0.0201463Not shown
EGR2_HUMAN.H11MO.0.A0.0201463Not shown

Motif 5/11

Motif IDq-valPWM
MA0117.2_Mafb6.85796e-07
MA0659.2_MAFG3.37325e-05
MA0495.3_MAFF4.15102e-05
MAFG_HUMAN.H11MO.0.A0.000256056
MAFK_HUMAN.H11MO.0.A0.00027513900000000004
MAFF_HUMAN.H11MO.0.B0.00444655Not shown
MA0842.2_NRL0.00444655Not shown
MAF_HUMAN.H11MO.1.B0.0207451Not shown
MA0501.1_MAF::NFE20.025914499999999997Not shown
ATF2_HUMAN.H11MO.1.B0.0259671Not shown

Motif 6/11

Motif IDq-valPWM
MAFK_HUMAN.H11MO.0.A0.00134614
MAF_HUMAN.H11MO.1.B0.00134614
MAFG_HUMAN.H11MO.0.A0.00134614
MAF_HUMAN.H11MO.0.A0.00134614
MA0496.3_MAFK0.00134614
MA1520.1_MAF0.00134614Not shown
MA1521.1_MAFA0.00139128Not shown
MAFK_HUMAN.H11MO.1.A0.00139128Not shown
MAFF_HUMAN.H11MO.0.B0.0048442Not shown
MAFB_HUMAN.H11MO.0.B0.00800963Not shown

Motif 7/11

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D7.072300000000001e-05
MA1125.1_ZNF3840.0148132
PRDM6_HUMAN.H11MO.0.C0.0148132
MA0679.2_ONECUT10.0412
FOXL1_HUMAN.H11MO.0.D0.0412
FOXG1_HUMAN.H11MO.0.D0.0412Not shown
FOXJ3_HUMAN.H11MO.0.A0.0412Not shown
ZFP28_HUMAN.H11MO.0.C0.06302440000000001Not shown
HXC10_HUMAN.H11MO.0.D0.06340269999999999Not shown
ANDR_HUMAN.H11MO.0.A0.06340269999999999Not shown

Motif 8/11

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A4.2774400000000005e-08
SP1_HUMAN.H11MO.0.A5.41139e-08
SP3_HUMAN.H11MO.0.B5.41139e-08
TBX15_HUMAN.H11MO.0.D6.0744e-08
KLF16_HUMAN.H11MO.0.D2.50545e-07
PATZ1_HUMAN.H11MO.0.C9.97578e-07Not shown
MAZ_HUMAN.H11MO.0.A1.02228e-06Not shown
ZN467_HUMAN.H11MO.0.C1.06814e-06Not shown
WT1_HUMAN.H11MO.0.C2.24664e-06Not shown
VEZF1_HUMAN.H11MO.0.C6.038430000000001e-06Not shown

Motif 9/11

Motif IDq-valPWM
MA0591.1_Bach1::Mafk7.745449999999999e-06
NFE2_HUMAN.H11MO.0.A4.4147700000000004e-05
BACH2_HUMAN.H11MO.0.A6.391779999999999e-05
BACH1_HUMAN.H11MO.0.A0.000264074
MAFF_HUMAN.H11MO.1.B0.000657644
MA1633.1_BACH10.000664732Not shown
MA0150.2_Nfe2l20.00077653Not shown
MA0478.1_FOSL20.00157819Not shown
MAFG_HUMAN.H11MO.1.A0.00189943Not shown
MA0501.1_MAF::NFE20.00371855Not shown

Motif 10/11

Motif IDq-valPWM
MA0139.1_CTCF8.30299e-05
CTCF_HUMAN.H11MO.0.A0.000717605
CTCFL_HUMAN.H11MO.0.A0.015388399999999998

Motif 11/11

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D8.17451e-06
MA1125.1_ZNF3840.00361036
MA0679.2_ONECUT10.0299486
FOXG1_HUMAN.H11MO.0.D0.0299486
PRDM6_HUMAN.H11MO.0.C0.030597500000000003
FOXL1_HUMAN.H11MO.0.D0.030597500000000003Not shown
HXC10_HUMAN.H11MO.0.D0.030597500000000003Not shown
FOXJ3_HUMAN.H11MO.0.A0.10296099999999998Not shown
ONEC2_HUMAN.H11MO.0.D0.10296099999999998Not shown
LMX1A_HUMAN.H11MO.0.D0.10296099999999998Not shown