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: GABPA
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/GABPA_multitask_profile_fold6/GABPA_multitask_profile_fold6_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/GABPA_multitask_profile_fold6/GABPA_multitask_profile_fold6_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/GABPA_multitask_profile_fold6/GABPA_multitask_profile_fold6_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%|██████████| 104/104 [01:39<00:00,  1.04it/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

4940 seqlets

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

Pattern 2/10

627 seqlets

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

Pattern 3/10

499 seqlets

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

Pattern 4/10

280 seqlets

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

Pattern 5/10

243 seqlets

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

Pattern 6/10

181 seqlets

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

Pattern 7/10

49 seqlets

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

Pattern 8/10

45 seqlets

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

Pattern 9/10

40 seqlets

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

Pattern 10/10

31 seqlets

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

Metacluster 2/2

Pattern 1/6

534 seqlets

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

Pattern 2/6

439 seqlets

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

Pattern 3/6

404 seqlets

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

Pattern 4/6

255 seqlets

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

Pattern 5/6

151 seqlets

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

Pattern 6/6

38 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
14940
2627
3499
4280
5243
6181
749
845
940
1031

Metacluster 2/2

#SeqletsForwardReverse
1534
2439
3404
4255
5151
638

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
MA0076.2_ELK43.26522e-07
MA0750.2_ZBTB7A3.26522e-07
ETV1_HUMAN.H11MO.0.A1.16377e-06
ELF1_HUMAN.H11MO.0.A1.3965200000000002e-06
GABPA_HUMAN.H11MO.0.A1.3965200000000002e-06
ELK1_HUMAN.H11MO.0.B2.42135e-06Not shown
MA0765.2_ETV52.42135e-06Not shown
ELF2_HUMAN.H11MO.0.C3.5311400000000002e-06Not shown
ELK4_HUMAN.H11MO.0.A9.33607e-06Not shown
MA0763.1_ETV37.39792e-05Not shown

Motif 2/10

Motif IDq-valPWM
GABPA_HUMAN.H11MO.0.A0.00273576
MA0645.1_ETV60.0136856
MA0475.2_FLI10.0178066
MA0474.2_ERG0.0178066
ELF2_HUMAN.H11MO.0.C0.0178066
MA0772.1_IRF70.0178066Not shown
MA0098.3_ETS10.0178066Not shown
MA0763.1_ETV30.0178066Not shown
ELF1_HUMAN.H11MO.0.A0.0178066Not shown
MA0760.1_ERF0.0181975Not shown

Motif 3/10

Motif IDq-valPWM
ZNF76_HUMAN.H11MO.0.C2.48748e-22
ZN143_HUMAN.H11MO.0.A2.4585300000000002e-21
THA11_HUMAN.H11MO.0.B1.0503700000000002e-18
MA1573.1_THAP113.11785e-09
MA0088.2_ZNF1430.0204601
P63_HUMAN.H11MO.0.A0.0851966Not shown
STAT3_HUMAN.H11MO.0.A0.0851966Not shown
MA1625.1_Stat5b0.191023Not shown
MA0525.2_TP630.21053899999999998Not shown
MA0519.1_Stat5a::Stat5b0.22038899999999997Not shown

Motif 4/10

Motif IDq-valPWM
MA1513.1_KLF150.064778
EGR4_HUMAN.H11MO.0.D0.064778
MA1102.2_CTCFL0.064778
SP3_HUMAN.H11MO.0.B0.0784586
ZN219_HUMAN.H11MO.0.D0.0784586
MA0753.2_ZNF7400.0784586Not shown
SP1_HUMAN.H11MO.0.A0.0784586Not shown
TAF1_HUMAN.H11MO.0.A0.0784586Not shown
SP1_HUMAN.H11MO.1.A0.0784586Not shown
MXI1_HUMAN.H11MO.0.A0.0784586Not shown

Motif 5/10

Motif IDq-valPWM
MA0765.2_ETV50.30345900000000003
MBD2_HUMAN.H11MO.0.B0.30345900000000003
MA0686.1_SPDEF0.30345900000000003
MA0136.2_ELF50.30345900000000003
MA0475.2_FLI10.30345900000000003
MA0474.2_ERG0.30345900000000003Not shown
MA0156.2_FEV0.30345900000000003Not shown
MA0028.2_ELK10.30345900000000003Not shown
MA1483.1_ELF20.30345900000000003Not shown
MA0762.1_ETV20.30345900000000003Not shown

Motif 6/10

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A6.22308e-05
MA1475.1_CREB3L4(var.2)9.8077e-05
USF2_HUMAN.H11MO.0.A9.8077e-05
SP1_HUMAN.H11MO.0.A0.00020507099999999998
SP3_HUMAN.H11MO.0.B0.00038513699999999997
MA0605.2_ATF30.00150183Not shown
MA0609.2_CREM0.00150183Not shown
ATF2_HUMAN.H11MO.2.C0.00150909Not shown
MA0656.1_JDP2(var.2)0.0024863000000000003Not shown
ATF1_HUMAN.H11MO.0.B0.00253883Not shown

Motif 7/10

Motif IDq-valPWM
MA0062.3_GABPA3.85256e-05
MA0473.3_ELF13.85256e-05
MA0761.2_ETV14.2630200000000004e-05
ETS1_HUMAN.H11MO.0.A0.00013167299999999998
ERG_HUMAN.H11MO.0.A0.00013167299999999998
MA0598.3_EHF0.00013167299999999998Not shown
FLI1_HUMAN.H11MO.1.A0.00027994799999999997Not shown
MA0764.2_ETV40.000302573Not shown
ETV4_HUMAN.H11MO.0.B0.000359803Not shown
ETV5_HUMAN.H11MO.0.C0.000445953Not shown

Motif 8/10

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D4.7039799999999996e-05
PRDM6_HUMAN.H11MO.0.C0.00963444
MA1125.1_ZNF3840.0393405
FOXL1_HUMAN.H11MO.0.D0.052460400000000004
FOXG1_HUMAN.H11MO.0.D0.0729666
ANDR_HUMAN.H11MO.0.A0.07910439999999999Not shown
FOXJ3_HUMAN.H11MO.0.A0.13641Not shown
MA0080.5_SPI10.13641Not shown
FUBP1_HUMAN.H11MO.0.D0.152321Not shown
MA0679.2_ONECUT10.157236Not shown

Motif 9/10

Motif IDq-valPWM
MA0598.3_EHF0.00419126
MA1508.1_IKZF10.00419126
EHF_HUMAN.H11MO.0.B0.00625936
ETV6_HUMAN.H11MO.0.D0.00625936
ETV2_HUMAN.H11MO.0.B0.0098278
MA0764.2_ETV40.0124612Not shown
MA0473.3_ELF10.0126861Not shown
ELF3_HUMAN.H11MO.0.A0.0179871Not shown
ETS1_HUMAN.H11MO.0.A0.0227495Not shown
ETV4_HUMAN.H11MO.0.B0.0245484Not shown

Motif 10/10

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00109503
SP1_HUMAN.H11MO.0.A0.00148926
SP3_HUMAN.H11MO.0.B0.008032899999999999
RFX1_HUMAN.H11MO.0.B0.00935064
USF2_HUMAN.H11MO.0.A0.026542400000000004
MA1513.1_KLF150.026542400000000004Not shown
MA0162.4_EGR10.026542400000000004Not shown
KLF3_HUMAN.H11MO.0.B0.026542400000000004Not shown
ZBT7B_HUMAN.H11MO.0.D0.036603500000000004Not shown
EGR1_HUMAN.H11MO.0.A0.036603500000000004Not shown

Metacluster 2/2

Motif 1/6

Motif IDq-valPWM
MBD2_HUMAN.H11MO.0.B0.020456099999999998
SP2_HUMAN.H11MO.0.A0.020456099999999998
MA0146.2_Zfx0.043381699999999995
USF2_HUMAN.H11MO.0.A0.052482799999999996
MA1513.1_KLF150.052482799999999996
SP1_HUMAN.H11MO.0.A0.052482799999999996Not shown
KLF3_HUMAN.H11MO.0.B0.05682140000000001Not shown
MA1102.2_CTCFL0.0725481Not shown
MXI1_HUMAN.H11MO.0.A0.0725481Not shown
SP3_HUMAN.H11MO.0.B0.0798713Not shown

Motif 2/6

Motif IDq-valPWM
MA0076.2_ELK45.38989e-06
MA0750.2_ZBTB7A2.03407e-05
ELK4_HUMAN.H11MO.0.A2.0729400000000002e-05
ELF1_HUMAN.H11MO.0.A4.6839300000000004e-05
MA0765.2_ETV55.78375e-05
GABPA_HUMAN.H11MO.0.A9.898360000000001e-05Not shown
ELF2_HUMAN.H11MO.0.C9.98717e-05Not shown
ELK1_HUMAN.H11MO.0.B0.000139412Not shown
ETV1_HUMAN.H11MO.0.A0.0009819339999999998Not shown
ETS1_HUMAN.H11MO.0.A0.0009819339999999998Not shown

Motif 3/6

No TOMTOM matches passing threshold

Motif 4/6

Motif IDq-valPWM
SP2_HUMAN.H11MO.0.A0.00246538
MA0146.2_Zfx0.00373133
SP1_HUMAN.H11MO.1.A0.00638773
ETV1_HUMAN.H11MO.0.A0.012663500000000001
SP1_HUMAN.H11MO.0.A0.0130238
SP3_HUMAN.H11MO.0.B0.014266Not shown
MBD2_HUMAN.H11MO.0.B0.014266Not shown
KLF6_HUMAN.H11MO.0.A0.014266Not shown
GABPA_HUMAN.H11MO.0.A0.014266Not shown
ZN341_HUMAN.H11MO.0.C0.0198072Not shown

Motif 5/6

No TOMTOM matches passing threshold

Motif 6/6

Motif IDq-valPWM
SP1_HUMAN.H11MO.0.A0.0404073
SP2_HUMAN.H11MO.0.A0.0404073
THAP1_HUMAN.H11MO.0.C0.0404073
MA1615.1_Plagl10.0404073
SP3_HUMAN.H11MO.0.B0.0404073
MXI1_HUMAN.H11MO.0.A0.0404073Not shown
MBD2_HUMAN.H11MO.0.B0.051609Not shown
AP2B_HUMAN.H11MO.0.B0.07742080000000001Not shown
ZFX_HUMAN.H11MO.1.A0.0800653Not shown
ZFX_HUMAN.H11MO.0.A0.107958Not shown