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_fold10/SPI1_multitask_profile_fold10_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/SPI1_multitask_profile_fold10/SPI1_multitask_profile_fold10_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_fold10/SPI1_multitask_profile_fold10_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 [08:25<00:00,  2.60s/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 1/6

12819 seqlets

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

Pattern 2/6

746 seqlets

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

Pattern 3/6

301 seqlets

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

Pattern 4/6

41 seqlets

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

Pattern 5/6

41 seqlets

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

Pattern 6/6

33 seqlets

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

Metacluster 2/2

Pattern 1/8

140 seqlets

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

Pattern 2/8

97 seqlets

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

Pattern 3/8

74 seqlets

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

Pattern 4/8

63 seqlets

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

Pattern 5/8

44 seqlets

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

Pattern 6/8

44 seqlets

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

Pattern 7/8

35 seqlets

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

Pattern 8/8

34 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
112819
2746
3301
441
541
633

Metacluster 2/2

#SeqletsForwardReverse
1140
297
374
463
544
644
735
834

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 1/6

Motif IDq-valPWM
SPIB_HUMAN.H11MO.0.A4.84649e-16
MA0081.2_SPIB1.80321e-14
SPI1_HUMAN.H11MO.0.A1.97573e-12
BC11A_HUMAN.H11MO.0.A1.39503e-11
IRF4_HUMAN.H11MO.0.A1.9152900000000003e-10
MA0080.5_SPI18.993220000000001e-10Not shown
IRF8_HUMAN.H11MO.0.B3.7043899999999994e-09Not shown
MA0761.2_ETV17.418130000000001e-05Not shown
MA0062.3_GABPA0.000104896Not shown
ETV5_HUMAN.H11MO.0.C0.000616785Not shown

Motif 2/6

Motif IDq-valPWM
MA0483.1_Gfi1b0.0897918

Motif 3/6

Motif IDq-valPWM
MA0687.1_SPIC0.157575
MA0081.2_SPIB0.157575
MA0645.1_ETV60.157575
SPI1_HUMAN.H11MO.0.A0.157575
MA0080.5_SPI10.157575
SPIB_HUMAN.H11MO.0.A0.175275Not shown
IRF8_HUMAN.H11MO.0.B0.31945Not shown
MA0763.1_ETV30.31945Not shown
MA0098.3_ETS10.31945Not shown
MA0028.2_ELK10.31945Not shown

Motif 4/6

Motif IDq-valPWM
MA0080.5_SPI12.45865e-06
BC11A_HUMAN.H11MO.0.A2.51476e-06
SPIB_HUMAN.H11MO.0.A2.5235499999999998e-06
SPI1_HUMAN.H11MO.0.A4.131690000000001e-06
MA0081.2_SPIB1.07639e-05
IRF4_HUMAN.H11MO.0.A3.39648e-05Not shown
IRF8_HUMAN.H11MO.0.B5.32361e-05Not shown
MA0050.2_IRF10.00103813Not shown
MA0687.1_SPIC0.0055762Not shown
IRF2_HUMAN.H11MO.0.A0.00670039Not shown

Motif 5/6

Motif IDq-valPWM
IRF3_HUMAN.H11MO.0.B1.32712e-05
BC11A_HUMAN.H11MO.0.A0.00104137
MA0080.5_SPI10.00104137
CPEB1_HUMAN.H11MO.0.D0.00115329
VEZF1_HUMAN.H11MO.0.C0.00117863
SPIB_HUMAN.H11MO.0.A0.00242012Not shown
SPI1_HUMAN.H11MO.0.A0.00253393Not shown
ZN467_HUMAN.H11MO.0.C0.0039893Not shown
ZN341_HUMAN.H11MO.0.C0.0039893Not shown
IRF8_HUMAN.H11MO.0.B0.0039893Not shown

Motif 6/6

Motif IDq-valPWM
IRF3_HUMAN.H11MO.0.B0.0372586
BC11A_HUMAN.H11MO.0.A0.0372586
CPEB1_HUMAN.H11MO.0.D0.0409659
MA0482.2_GATA40.0409659
MA0080.5_SPI10.0409659
NFAC1_HUMAN.H11MO.0.B0.0428399Not shown
MA0081.2_SPIB0.0430922Not shown
PRDM6_HUMAN.H11MO.0.C0.0430922Not shown
FLI1_HUMAN.H11MO.0.A0.0430922Not shown
ZFP82_HUMAN.H11MO.0.C0.06833489999999999Not shown

Metacluster 2/2

Motif 1/8

No TOMTOM matches passing threshold

Motif 2/8

Motif IDq-valPWM
MA0081.2_SPIB1.80528e-08
SPIB_HUMAN.H11MO.0.A1.80528e-08
SPI1_HUMAN.H11MO.0.A3.00209e-08
BC11A_HUMAN.H11MO.0.A1.1114e-07
MA0080.5_SPI11.33368e-07
IRF8_HUMAN.H11MO.0.B3.1918400000000003e-06Not shown
IRF4_HUMAN.H11MO.0.A4.5518999999999996e-06Not shown
MA0598.3_EHF0.000704135Not shown
MA0473.3_ELF10.00118056Not shown
MA0062.3_GABPA0.00118056Not shown

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
MA0645.1_ETV60.195109
MA0528.2_ZNF2630.195109
MA0471.2_E2F60.195109
ERG_HUMAN.H11MO.0.A0.195109
SP1_HUMAN.H11MO.0.A0.195109
MA0764.2_ETV40.20761999999999997Not shown
ZBT17_HUMAN.H11MO.0.A0.20761999999999997Not shown
GABPA_HUMAN.H11MO.0.A0.20761999999999997Not shown
SP1_HUMAN.H11MO.1.A0.20761999999999997Not shown
MA0136.2_ELF50.20761999999999997Not shown

Motif 7/8

Motif IDq-valPWM
MA0598.3_EHF0.000594441
MA0473.3_ELF10.0016472000000000001
MA0062.3_GABPA0.00240446
ETV5_HUMAN.H11MO.0.C0.00375179
ETV2_HUMAN.H11MO.0.B0.00375179
ERG_HUMAN.H11MO.0.A0.00375179Not shown
MA0081.2_SPIB0.00375179Not shown
MA0761.2_ETV10.00375179Not shown
ETS1_HUMAN.H11MO.0.A0.00375179Not shown
SPI1_HUMAN.H11MO.0.A0.00375179Not shown

Motif 8/8

Motif IDq-valPWM
VEZF1_HUMAN.H11MO.0.C0.11277899999999999
PLAG1_HUMAN.H11MO.0.D0.11277899999999999
COT2_HUMAN.H11MO.1.A0.11277899999999999
ETV5_HUMAN.H11MO.0.C0.11277899999999999
ZN816_HUMAN.H11MO.0.C0.174869
OSR2_HUMAN.H11MO.0.C0.174869Not shown
ERG_HUMAN.H11MO.0.A0.174869Not shown
ETS1_HUMAN.H11MO.0.A0.19178699999999999Not shown
MA0062.3_GABPA0.19178699999999999Not shown
RARA_HUMAN.H11MO.2.A0.196525Not shown