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: SPI1
DeepSHAP scores path: /users/amtseng/tfmodisco/results/importance_scores/multitask_profile/SPI1_multitask_profile_fold2/SPI1_multitask_profile_fold2_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/SPI1_multitask_profile_fold2/SPI1_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/SPI1_multitask_profile_fold2/SPI1_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%|██████████| 194/194 [03:15<00:00,  1.01s/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 1/8

13151 seqlets

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

Pattern 2/8

408 seqlets

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

Pattern 3/8

364 seqlets

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

Pattern 4/8

123 seqlets

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

Pattern 5/8

108 seqlets

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

Pattern 6/8

50 seqlets

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

Pattern 7/8

47 seqlets

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

Pattern 8/8

36 seqlets

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

Metacluster 2/2

Pattern 1/8

104 seqlets

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

Pattern 2/8

82 seqlets

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

Pattern 3/8

78 seqlets

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

Pattern 4/8

76 seqlets

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

Pattern 5/8

75 seqlets

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

Pattern 6/8

58 seqlets

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

Pattern 7/8

46 seqlets

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

Pattern 8/8

33 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
113151
2408
3364
4123
5108
650
747
836

Metacluster 2/2

#SeqletsForwardReverse
1104
282
378
476
575
658
746
833

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 1/8

Motif IDq-valPWM
SPIB_HUMAN.H11MO.0.A7.644819999999999e-16
MA0081.2_SPIB5.54546e-13
SPI1_HUMAN.H11MO.0.A5.54546e-13
BC11A_HUMAN.H11MO.0.A3.94152e-11
IRF4_HUMAN.H11MO.0.A3.3267400000000003e-10
IRF8_HUMAN.H11MO.0.B9.70793e-10Not shown
MA0080.5_SPI11.75921e-09Not shown
MA0761.2_ETV16.25329e-05Not shown
MA0062.3_GABPA0.00010701Not shown
ETV5_HUMAN.H11MO.0.C0.0006309169999999999Not shown

Motif 2/8

Motif IDq-valPWM
MA0763.1_ETV30.0397083
MA0645.1_ETV60.0397083
MA0474.2_ERG0.0397083
MA0098.3_ETS10.0397083
MA0081.2_SPIB0.0397083
MA0765.2_ETV50.0397083Not shown
MA0598.3_EHF0.0397083Not shown
MA0028.2_ELK10.0397083Not shown
MA0750.2_ZBTB7A0.0397083Not shown
MA0761.2_ETV10.0397083Not shown

Motif 3/8

Motif IDq-valPWM
MA1484.1_ETS20.037835400000000005
MA0760.1_ERF0.037835400000000005
MA0759.1_ELK30.037835400000000005
ELK4_HUMAN.H11MO.0.A0.037835400000000005
MA0136.2_ELF50.037835400000000005
MA0098.3_ETS10.037835400000000005Not shown
MA0156.2_FEV0.037835400000000005Not shown
ETS1_HUMAN.H11MO.0.A0.037835400000000005Not shown
MA0076.2_ELK40.037835400000000005Not shown
MA0763.1_ETV30.037835400000000005Not shown

Motif 4/8

Motif IDq-valPWM
MA1652.1_ZKSCAN50.00963762
CPEB1_HUMAN.H11MO.0.D0.0299858
MA0081.2_SPIB0.0299858
EOMES_HUMAN.H11MO.0.D0.0299858
ETV5_HUMAN.H11MO.0.C0.0456103
MA0645.1_ETV60.0456103Not shown
MA0640.2_ELF30.0456103Not shown
ZN467_HUMAN.H11MO.0.C0.0456103Not shown
PRDM6_HUMAN.H11MO.0.C0.0456103Not shown
IRF3_HUMAN.H11MO.0.B0.0456103Not shown

Motif 5/8

Motif IDq-valPWM
FOXL1_HUMAN.H11MO.0.D0.06580889999999999
SPIC_HUMAN.H11MO.0.D0.0700967
MA0080.5_SPI10.132233
PRDM6_HUMAN.H11MO.0.C0.132233
MA0474.2_ERG0.22926100000000002
MA0038.2_GFI10.22926100000000002Not shown
GFI1_HUMAN.H11MO.0.C0.22926100000000002Not shown
SPI1_HUMAN.H11MO.0.A0.22926100000000002Not shown
ZN394_HUMAN.H11MO.0.C0.22926100000000002Not shown
IRF1_HUMAN.H11MO.0.A0.22926100000000002Not shown

Motif 6/8

Motif IDq-valPWM
NFAT5_HUMAN.H11MO.0.D0.0224822
IRF3_HUMAN.H11MO.0.B0.08375110000000001
MNX1_HUMAN.H11MO.0.D0.08375110000000001
VEZF1_HUMAN.H11MO.1.C0.148109
PRDM1_HUMAN.H11MO.0.A0.148109
ZFP82_HUMAN.H11MO.0.C0.148109Not shown
ZN394_HUMAN.H11MO.0.C0.16319Not shown
MA0508.3_PRDM10.191064Not shown
MZF1_HUMAN.H11MO.0.B0.191064Not shown
MA0081.2_SPIB0.191064Not shown

Motif 7/8

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D3.14904e-05
MA1125.1_ZNF3840.02713
PRDM6_HUMAN.H11MO.0.C0.02713
FOXL1_HUMAN.H11MO.0.D0.030451699999999998
FOXG1_HUMAN.H11MO.0.D0.0568395
ANDR_HUMAN.H11MO.0.A0.126591Not shown
MA0679.2_ONECUT10.126591Not shown
FOXJ3_HUMAN.H11MO.0.A0.126591Not shown
ONEC2_HUMAN.H11MO.0.D0.150001Not shown
FUBP1_HUMAN.H11MO.0.D0.220025Not shown

Motif 8/8

Motif IDq-valPWM
IRF4_HUMAN.H11MO.0.A1.47704e-06
IRF8_HUMAN.H11MO.0.B1.47704e-06
MA0081.2_SPIB5.52026e-05
BC11A_HUMAN.H11MO.0.A5.52026e-05
SPIB_HUMAN.H11MO.0.A0.000122734
IRF1_HUMAN.H11MO.0.A0.000134245Not shown
SPI1_HUMAN.H11MO.0.A0.000173237Not shown
IRF2_HUMAN.H11MO.0.A0.000199872Not shown
IRF3_HUMAN.H11MO.0.B0.000269586Not shown
STAT1_HUMAN.H11MO.1.A0.00031490099999999997Not shown

Metacluster 2/2

Motif 1/8

Motif IDq-valPWM
SPIB_HUMAN.H11MO.0.A1.9024799999999998e-12
MA0081.2_SPIB2.4441e-12
BC11A_HUMAN.H11MO.0.A3.08521e-10
SPI1_HUMAN.H11MO.0.A3.08521e-10
IRF4_HUMAN.H11MO.0.A7.067750000000001e-10
IRF8_HUMAN.H11MO.0.B1.76649e-09Not shown
MA0080.5_SPI15.00872e-09Not shown
MA0761.2_ETV10.000226806Not shown
MA0062.3_GABPA0.000302108Not shown
ETV5_HUMAN.H11MO.0.C0.000786349Not shown

Motif 2/8

No TOMTOM matches passing threshold

Motif 3/8

No TOMTOM matches passing threshold

Motif 4/8

No TOMTOM matches passing threshold

Motif 5/8

No TOMTOM matches passing threshold

Motif 6/8

Motif IDq-valPWM
NKX61_HUMAN.H11MO.0.B0.474358
FOXC2_HUMAN.H11MO.0.D0.474358
GATA4_HUMAN.H11MO.0.A0.474358
DLX3_HUMAN.H11MO.0.C0.474358
GATA1_HUMAN.H11MO.1.A0.474358
GATA2_HUMAN.H11MO.1.A0.474358Not shown

Motif 7/8

Motif IDq-valPWM
ETV5_HUMAN.H11MO.0.C9.93826e-06
BC11A_HUMAN.H11MO.0.A9.93826e-06
MA0081.2_SPIB9.93826e-06
SPI1_HUMAN.H11MO.0.A9.93826e-06
SPIB_HUMAN.H11MO.0.A1.67462e-05
IRF4_HUMAN.H11MO.0.A6.25841e-05Not shown
MA0062.3_GABPA6.25841e-05Not shown
MA0761.2_ETV18.78928e-05Not shown
MA0598.3_EHF9.17284e-05Not shown
IRF8_HUMAN.H11MO.0.B0.000158725Not shown

Motif 8/8

Motif IDq-valPWM
SPIB_HUMAN.H11MO.0.A3.53513e-05
SPI1_HUMAN.H11MO.0.A3.53513e-05
MA0081.2_SPIB0.000183511
MA0080.5_SPI10.000401315
BC11A_HUMAN.H11MO.0.A0.000481011
IRF4_HUMAN.H11MO.0.A0.000481724Not shown
IRF3_HUMAN.H11MO.0.B0.00203516Not shown
IRF8_HUMAN.H11MO.0.B0.00223771Not shown
MA0761.2_ETV10.00273814Not shown
MA0473.3_ELF10.0033108000000000005Not shown