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_fold8/SPI1_multitask_profile_fold8_imp_scores.h5
TF-MoDISco results path: /users/amtseng/tfmodisco/results/tfmodisco/multitask_profile/SPI1_multitask_profile_fold8/SPI1_multitask_profile_fold8_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_fold8/SPI1_multitask_profile_fold8_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 [07:50<00:00,  2.42s/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

13129 seqlets

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

Pattern 2/8

453 seqlets

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

Pattern 3/8

402 seqlets

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

Pattern 4/8

164 seqlets

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

Pattern 5/8

127 seqlets

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

Pattern 6/8

57 seqlets

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

Pattern 7/8

36 seqlets

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

Pattern 8/8

34 seqlets

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

Metacluster 2/2

Pattern 1/5

105 seqlets

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

Pattern 2/5

84 seqlets

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

Pattern 3/5

67 seqlets

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

Pattern 4/5

55 seqlets

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

Pattern 5/5

42 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
113129
2453
3402
4164
5127
657
736
834

Metacluster 2/2

#SeqletsForwardReverse
1105
284
367
455
542

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.A7.30503e-18
MA0081.2_SPIB4.8975000000000004e-15
SPI1_HUMAN.H11MO.0.A1.54278e-13
BC11A_HUMAN.H11MO.0.A1.70775e-12
IRF4_HUMAN.H11MO.0.A1.90216e-10
MA0080.5_SPI12.3777e-10Not shown
IRF8_HUMAN.H11MO.0.B3.6552499999999998e-09Not shown
MA0761.2_ETV17.51067e-05Not shown
MA0062.3_GABPA0.00010615Not shown
ETV5_HUMAN.H11MO.0.C0.000588313Not shown

Motif 2/8

Motif IDq-valPWM
MA0645.1_ETV60.207301
MA0081.2_SPIB0.207301
MA0080.5_SPI10.207301
SPI1_HUMAN.H11MO.0.A0.207301
BC11A_HUMAN.H11MO.0.A0.207301
SPIB_HUMAN.H11MO.0.A0.207301Not shown
ELF5_HUMAN.H11MO.0.A0.207301Not shown
MA0076.2_ELK40.309129Not shown
MA0866.1_SOX210.309129Not shown
GABPA_HUMAN.H11MO.0.A0.309129Not shown

Motif 3/8

Motif IDq-valPWM
ETS1_HUMAN.H11MO.0.A0.00697683
MA0763.1_ETV30.00697683
ELK4_HUMAN.H11MO.0.A0.00709197
SPI1_HUMAN.H11MO.0.A0.00709197
ELK1_HUMAN.H11MO.0.B0.00709197
GABPA_HUMAN.H11MO.0.A0.00709197Not shown
BC11A_HUMAN.H11MO.0.A0.00709197Not shown
ELF2_HUMAN.H11MO.0.C0.00709197Not shown
MA0076.2_ELK40.00709197Not shown
ELF1_HUMAN.H11MO.0.A0.00709197Not shown

Motif 4/8

Motif IDq-valPWM
MA0081.2_SPIB0.00168622
SPI1_HUMAN.H11MO.0.A0.00203636
SPIB_HUMAN.H11MO.0.A0.00226272
BC11A_HUMAN.H11MO.0.A0.00226272
MA0080.5_SPI10.00226272
CPEB1_HUMAN.H11MO.0.D0.00226272Not shown
MA0761.2_ETV10.00226272Not shown
MA0062.3_GABPA0.00753989Not shown
MA0645.1_ETV60.010536499999999999Not shown
MA0050.2_IRF10.010536499999999999Not shown

Motif 5/8

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D0.000494851
IRF3_HUMAN.H11MO.0.B0.00504702
PRDM6_HUMAN.H11MO.0.C0.0288127
MA0080.5_SPI10.0288127
MA0645.1_ETV60.0288127
BC11A_HUMAN.H11MO.0.A0.0412817Not shown
ZN394_HUMAN.H11MO.0.C0.0434163Not shown
NFAT5_HUMAN.H11MO.0.D0.048016199999999995Not shown
ETS2_HUMAN.H11MO.0.B0.048016199999999995Not shown
ONEC2_HUMAN.H11MO.0.D0.0533654Not shown

Motif 6/8

Motif IDq-valPWM
PRDM1_HUMAN.H11MO.0.A0.111121
MA0156.2_FEV0.111121
MA0475.2_FLI10.111121
IRF8_HUMAN.H11MO.0.B0.111121
MA0760.1_ERF0.111121
MA0474.2_ERG0.111121Not shown
MA0098.3_ETS10.111121Not shown
IRF2_HUMAN.H11MO.0.A0.111121Not shown
IRF1_HUMAN.H11MO.0.A0.111121Not shown
MA0028.2_ELK10.111121Not shown

Motif 7/8

Motif IDq-valPWM
CPEB1_HUMAN.H11MO.0.D4.00716e-05
PRDM6_HUMAN.H11MO.0.C0.0231565
MA1125.1_ZNF3840.0231565
FOXL1_HUMAN.H11MO.0.D0.032397
FOXG1_HUMAN.H11MO.0.D0.056032500000000006
ANDR_HUMAN.H11MO.0.A0.105648Not shown
MA0679.2_ONECUT10.105648Not shown
FOXJ3_HUMAN.H11MO.0.A0.117172Not shown
ONEC2_HUMAN.H11MO.0.D0.12414700000000001Not shown
FUBP1_HUMAN.H11MO.0.D0.191158Not shown

Motif 8/8

Motif IDq-valPWM
ERG_HUMAN.H11MO.0.A0.000515654
MAZ_HUMAN.H11MO.0.A0.000515654
ETS1_HUMAN.H11MO.0.A0.0006221390000000001
BC11A_HUMAN.H11MO.0.A0.0006221390000000001
FLI1_HUMAN.H11MO.1.A0.0006221390000000001
ETV5_HUMAN.H11MO.0.C0.0006221390000000001Not shown
VEZF1_HUMAN.H11MO.0.C0.00107834Not shown
GABPA_HUMAN.H11MO.0.A0.00107834Not shown
ZN467_HUMAN.H11MO.0.C0.00107834Not shown
MA0081.2_SPIB0.00107834Not shown

Metacluster 2/2

Motif 1/5

No TOMTOM matches passing threshold

Motif 2/5

No TOMTOM matches passing threshold

Motif 3/5

Motif IDq-valPWM
TAL1_HUMAN.H11MO.0.A0.374207
GATA2_HUMAN.H11MO.1.A0.374207
GATA4_HUMAN.H11MO.0.A0.374207
GFI1_HUMAN.H11MO.0.C0.374207
GATA1_HUMAN.H11MO.1.A0.374207
MA0521.1_Tcf120.374207Not shown
SMAD3_HUMAN.H11MO.0.B0.44888199999999995Not shown
ZN554_HUMAN.H11MO.1.D0.44888199999999995Not shown
GATA1_HUMAN.H11MO.0.A0.44888199999999995Not shown
GATA2_HUMAN.H11MO.0.A0.44888199999999995Not shown

Motif 4/5

Motif IDq-valPWM
MA0081.2_SPIB9.34307e-11
SPIB_HUMAN.H11MO.0.A1.29284e-10
SPI1_HUMAN.H11MO.0.A2.6833099999999995e-10
BC11A_HUMAN.H11MO.0.A2.27891e-09
MA0080.5_SPI12.3373e-09
IRF4_HUMAN.H11MO.0.A6.00639e-09Not shown
IRF8_HUMAN.H11MO.0.B6.00639e-09Not shown
MA0062.3_GABPA0.00023182599999999997Not shown
MA0598.3_EHF0.00023182599999999997Not shown
MA0761.2_ETV10.000477151Not shown

Motif 5/5

Motif IDq-valPWM
MA0081.2_SPIB1.91918e-05
SPI1_HUMAN.H11MO.0.A1.91918e-05
SPIB_HUMAN.H11MO.0.A1.91918e-05
BC11A_HUMAN.H11MO.0.A5.67345e-05
MA0598.3_EHF5.67345e-05
MA0062.3_GABPA5.7215299999999994e-05Not shown
MA0761.2_ETV15.7215299999999994e-05Not shown
ETV5_HUMAN.H11MO.0.C6.39154e-05Not shown
IRF4_HUMAN.H11MO.0.A0.00011184899999999999Not shown
ERG_HUMAN.H11MO.0.A0.00013047299999999998Not shown