Link to results

DiChIPMunk: on peaks and on multi-task seqlets and on single-task seqlets

HOMER: on peaks and on multi-task seqlets and on single-task seqlets

MEME: on peaks and on multitask seqlets and on single-task seqlets

import sys
import os
sys.path.append(os.path.abspath("/users/amtseng/tfmodisco/src/"))
from util import figure_to_vdom_image
import motif.read_motifs as read_motifs
from motif.read_motifs import pfm_to_pwm
import plot.viz_sequence as viz_sequence
import numpy as np
import matplotlib.pyplot as plt
import vdom.helpers as vdomh
from IPython.display import display

# Define parameters/fetch arguments
tf_name = os.environ["TFM_TF_NAME"]
multitask_fold = int(os.environ["TFM_MULTITASK_FOLD"])

if "TFM_TASK_INDEX" in os.environ:
    task_index = int(os.environ["TFM_TASK_INDEX"])
    singletask_fold = int(os.environ["TFM_SINGLETASK_FOLD"])
else:
    task_index = None
    singletask_fold = None
    
print("TF name: %s" % tf_name)
print("Multi-task fold: %s" % multitask_fold)
print("Task index: %s" % task_index)
print("Single-task fold: %s" % singletask_fold)

TF name: GABPA
Multi-task fold: 7
Task index: 5
Single-task fold: 5

# Define paths and constants
base_path = "/users/amtseng/tfmodisco/results/classic_motifs/"

multitask_seqlets_dir = os.path.join(
    base_path, "seqlets", "multitask_profile_finetune",
    "%s_multitask_profile_finetune_fold%s" % (tf_name, multitask_fold)
)

if task_index is None:
    peaks_path = os.path.join(base_path, "peaks", tf_name, "%s_peaks_taskall" % tf_name)
    multitask_profile_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_profile_taskall" % tf_name
    )
    multitask_count_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_count_taskall" % tf_name
    )
else:
    peaks_path = os.path.join(base_path, "peaks", tf_name, "%s_peaks_task%d" % (tf_name, task_index))
    multitask_profile_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_profile_task%d" % (tf_name, task_index)
    )
    multitask_count_seqlets_path = os.path.join(
        multitask_seqlets_dir,
        "%s_seqlets_count_task%d" % (tf_name, task_index)
    )
    
    singletask_seqlets_dir = os.path.join(
        base_path, "seqlets", "singletask_profile_finetune",
        "%s_singletask_profile_finetune_fold%s" % (tf_name, singletask_fold),
        "task_%d" % task_index
    )
    singletask_profile_seqlets_path = os.path.join(
        singletask_seqlets_dir,
        "%s_seqlets_profile_task%d" % (tf_name, task_index)
    )
    singletask_count_seqlets_path = os.path.join(
        singletask_seqlets_dir,
        "%s_seqlets_count_task%d" % (tf_name, task_index)
    )

Helper functions

def show_peaks_motif_table(results_path, mode):
    """
    Shows a table of motifs from the given results path.
    `mode` is either `dichipmunk`, `homer`, `meme`, or `memechip`.
    """
    assert mode in ("dichipmunk", "homer", "meme", "memechip")
    if mode == "dichipmunk":
        score_name = "Supporting sequences"
        pfms, score_vals = read_motifs.import_dichipmunk_pfms(results_path)
    elif mode == "homer":
        score_name = "Log enrichment"
        pfms, score_vals = read_motifs.import_homer_pfms(results_path)
    elif mode == "meme":
        score_name = "E-value"
        pfms, score_vals = read_motifs.import_meme_pfms(results_path)
    else:
        score_name = "E-value"
        pfms, score_vals = read_motifs.import_meme_pfms(
            os.path.join(results_path, "meme_out")
        )
        
    colgroup = vdomh.colgroup(
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "40%"})
    )
    header = vdomh.thead(
        vdomh.tr(
            vdomh.th("Motif", style={"text-align": "center"}),
            vdomh.th(score_name, style={"text-align": "center"}),
            vdomh.th("PWM", style={"text-align": "center"})
        )
    )

    body = []
    for i, pfm in enumerate(pfms):
        pwm = pfm_to_pwm(pfm)
        if np.sum(pwm[:, [0, 2]]) < 0.5 * np.sum(pwm):
            # Flip to purine-rich version
            pwm = np.flip(pwm, axis=(0, 1))
        fig = viz_sequence.plot_weights(pwm, figsize=(20, 4), return_fig=True)
        fig.tight_layout()

        body.append(
            vdomh.tr(
                vdomh.td(str(i + 1)),
                vdomh.td(str(score_vals[i])),
                vdomh.td(figure_to_vdom_image(fig))
            )
        )

    display(vdomh.table(colgroup, header, vdomh.tbody(*body)))
    plt.close("all")

def show_seqlets_motif_table(profile_results_path, count_results_path, mode):
    """
    Shows a table of motifs from the given results path.
    `mode` is either `dichipmunk`, `homer`, `meme`, or `memechip`
    """
    assert mode in ("dichipmunk", "homer", "meme", "memechip")
    if mode == "dichipmunk":
        score_name = "Supporting sequences"
        p_pfms, p_score_vals = read_motifs.import_dichipmunk_pfms(profile_results_path)
        c_pfms, c_score_vals = read_motifs.import_dichipmunk_pfms(count_results_path)
    elif mode == "homer":
        score_name = "Log enrichment"
        p_pfms, p_score_vals = read_motifs.import_homer_pfms(profile_results_path)
        c_pfms, c_score_vals = read_motifs.import_homer_pfms(count_results_path)
    elif mode == "meme":
        score_name = "E-value"
        p_pfms, p_score_vals = read_motifs.import_meme_pfms(profile_results_path)
        c_pfms, c_score_vals = read_motifs.import_meme_pfms(count_results_path)
    else:
        score_name = "E-value"
        p_pfms, p_score_vals = read_motifs.import_meme_pfms(
            os.path.join(profile_results_path, "meme_out")
        )
        c_pfms, c_score_vals = read_motifs.import_meme_pfms(
            os.path.join(count_results_path, "meme_out")
        )
        
    colgroup = vdomh.colgroup(
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "40%"}),
        vdomh.col(style={"width": "5%"}),
        vdomh.col(style={"width": "40%"})
    )
    header = vdomh.thead(
        vdomh.tr(
            vdomh.th("Motif", style={"text-align": "center"}),
            vdomh.th(score_name + " (profile)", style={"text-align": "center"}),
            vdomh.th("PWM (profile)", style={"text-align": "center"}),
            vdomh.th(score_name + " (count)", style={"text-align": "center"}),
            vdomh.th("PWM (count)", style={"text-align": "center"})
        )
    )

    body = []
    for i in range(max(len(p_pfms), len(c_pfms))):
        rows = [vdomh.td(str(i + 1))]
        if i < len(p_pfms):
            pwm = pfm_to_pwm(p_pfms[i])
            if np.sum(pwm[:, [0, 2]]) < 0.5 * np.sum(pwm):
                # Flip to purine-rich version
                pwm = np.flip(pwm, axis=(0, 1))
            fig = viz_sequence.plot_weights(pwm, figsize=(20, 4), return_fig=True)
            fig.tight_layout()
            rows.extend([
                vdomh.td(str(p_score_vals[i])),
                vdomh.td(figure_to_vdom_image(fig))
            ])
        else:
            rows.extend([vdomh.td(), vdomh.td()])
            
        if i < len(c_pfms):
            pwm = pfm_to_pwm(c_pfms[i])
            if np.sum(pwm[:, [0, 2]]) < 0.5 * np.sum(pwm):
                # Flip to purine-rich version
                pwm = np.flip(pwm, axis=(0, 1))
            fig = viz_sequence.plot_weights(pwm, figsize=(20, 4), return_fig=True)
            fig.tight_layout()
            rows.extend([
                vdomh.td(str(c_score_vals[i])),
                vdomh.td(figure_to_vdom_image(fig))
            ])
        else:
            rows.extend([vdomh.td(), vdomh.td()])
            

        body.append(vdomh.tr(*rows))

    display(vdomh.table(colgroup, header, vdomh.tbody(*body)))
    plt.close("all")

Show benchmark motifs

DiChIPMunk on peaks

show_peaks_motif_table(os.path.join(peaks_path, "dichipmunk"), "dichipmunk")

Motif	Supporting sequences	PWM
1	2000
2	2000
3	2000
4	1999
5	1807
6	1046
7	510
8	365
9	221
10	130

DiChIPMunk on multi-task seqlets

show_seqlets_motif_table(
    os.path.join(multitask_profile_seqlets_path, "dichipmunk"),
    os.path.join(multitask_count_seqlets_path, "dichipmunk"),
    "dichipmunk"
)

Motif	Supporting sequences (profile)	PWM (profile)	Supporting sequences (count)	PWM (count)
1	20000		6524
2			313
3			655

DiChIPMunk on single-task seqlets

if task_index is not None:
    show_seqlets_motif_table(
        os.path.join(singletask_profile_seqlets_path, "dichipmunk"),
        os.path.join(singletask_count_seqlets_path, "dichipmunk"),
        "dichipmunk"
    )

Motif	Supporting sequences (profile)	PWM (profile)	Supporting sequences (count)	PWM (count)
1	15699		11560

HOMER on peaks

show_peaks_motif_table(os.path.join(peaks_path, "homer"), "homer")

Motif	Log enrichment	PWM
1	-7939.571858
2	-1788.822853
3	-1660.693387
4	-914.598152
5	-863.044493
6	-572.214855
7	-521.641909
8	-461.11506
9	-454.79595
10	-373.373894
11	-372.842297
12	-331.064574
13	-229.517552
14	-224.51258
15	-215.063493
16	-194.156278
17	-118.960414

HOMER on multi-task seqlets

show_seqlets_motif_table(
    os.path.join(multitask_profile_seqlets_path, "homer"),
    os.path.join(multitask_count_seqlets_path, "homer"),
    "homer"
)

/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)

Motif	Log enrichment (profile)	PWM (profile)	Log enrichment (count)	PWM (count)
1	-13069.989165		-12441.220882
2	-1555.321075		-1389.882715
3	-715.282067		-377.353021
4	-544.316381		-222.448885
5	-535.481498		-113.017577
6	-494.719767		-102.525241
7	-473.33683		-61.773667
8	-404.805538		-29.293631
9	-205.398428		-11.974012
10	-180.267212
11	-167.084418
12	-144.868579
13	-104.003281
14	-73.494493

HOMER on single-task seqlets

if task_index is not None:
    show_seqlets_motif_table(
        os.path.join(singletask_profile_seqlets_path, "homer"),
        os.path.join(singletask_count_seqlets_path, "homer"),
        "homer"
    )

Motif	Log enrichment (profile)	PWM (profile)	Log enrichment (count)	PWM (count)
1	-15705.879251		-14866.278748
2	-1253.820187		-1524.737825
3	-822.74562		-419.956277
4	-369.295503		-234.13868
5	-236.509789		-188.330331
6	-224.463685		-92.912832
7	-138.779474		-50.636738
8	-81.081168		-30.891148
9	-64.648259
10	-57.655887

MEMEChIP on peaks

show_peaks_motif_table(os.path.join(peaks_path, "memechip"), "memechip")

Motif	E-value	PWM
1	0.0
2	1.7e-236
3	5.8e-58
4	5.4e-32
5	1.5e-20
6	1.8e-17
7	2.6e-14
8	8.2e-07
9	7e-08
10	0.03

MEME on multi-task seqlets

show_seqlets_motif_table(
    os.path.join(multitask_profile_seqlets_path, "meme"),
    os.path.join(multitask_count_seqlets_path, "meme"),
    "meme"
)

Motif	E-value (profile)	PWM (profile)	E-value (count)	PWM (count)
1	0.0		0.0
2	2.1e-58		4.2e-61
3	4.8e-41		0.18
4	3.4e-09		130000.0
5	3.4e-09		7100.0
6	3.4e-09		900000.0
7	3.4e-09		900000.0
8	3.4e-09		900000.0
9	3.4e-09		1200000.0
10	3.4e-09		1500000.0

MEME on single-task seqlets

if task_index is not None:
    show_seqlets_motif_table(
        os.path.join(singletask_profile_seqlets_path, "meme"),
        os.path.join(singletask_count_seqlets_path, "meme"),
        "meme"
    )

Motif	E-value (profile)	PWM (profile)	E-value (count)	PWM (count)
1	0.0		0.0
2	1.5e-177		1.1e-19
3	1.2e-05		0.0021
4	28000.0		3700.0
5	31000.0		6600.0
6	190000.0		790000.0
7	210000.0		880000.0
8	250000.0		1500000.0
9	670000.0		1700000.0
10	1100000.0		2000000.0