In [1]:
%load_ext autoreload
%autoreload 2
import numpy as np
import pandas as pd
import seaborn as sns
from matplotlib import pyplot as plt
from collections import OrderedDict
In [3]:
from matlas.pwms import ic_scale, adjust_for_ic_scale
from matlas.matches import vdom_pssm
from modisco.visualization import viz_sequence
from matlas.matches import vdom_pssm
In [8]:
motif_name = 'GABPA'
top_k_filters = OrderedDict()
filt_infl_from_loss = OrderedDict()
for fold_no in range(1,11):
aitacdir = "/mnt/lab_data2/msharmin/oc-atlas/DanSkinData/alex_bpnets/{0}/{1}".format(motif_name, fold_no)
filt_infl_from_loss[fold_no] = np.load(aitacdir+"/filt_infl_from_loss.npy")
top_k_filters[fold_no] = np.flip(np.argsort(filt_infl_from_loss[fold_no]))[:15]
print(fold_no, top_k_filters[fold_no])
In [4]:
# import numpy as np
# import seaborn as sns
# motif_name = 'GABPA'
# filter_weights = np.load("/mnt/lab_data2/msharmin/oc-atlas/DanSkinData/alex_bpnets/filters/{0}/{0}_filters.npy".format(
# motif_name))
# filter_weights.shape
Out[4]:
In [6]:
from matplotlib import pyplot as plt
from matlas.pwms import ic_scale, adjust_for_ic_scale
from matlas.matches import vdom_pssm
from modisco.visualization import viz_sequence
from matlas.matches import vdom_pssm
def draw_filter_weights(start_filter, end_filter):
alphabets = np.array(['A', 'C', 'G', 'T'])
fig, axes = plt.subplots(4, 4, figsize=(30,10))
for i in range(start_filter, end_filter):
a = np.copy(filter_weights[:,:,i].T)
r,c = (i-start_filter)//4, i%4
#print(r, c)
ax = sns.heatmap(a, yticklabels=alphabets,
xticklabels=alphabets[np.argmax(a, axis=0)], ax = axes[r, c]
)
ax.set_ylabel("filter{}".format(i))
return None
Raw and mean normalized filter weights¶
In [5]:
from modisco.visualization import viz_sequence
for fold_no in range(1,11):
for i in top_k_filters:
print('filter', i)
mean_norm_weights = np.copy(filter_weights[:,:,i])
mean_norm_weights = mean_norm_weights - mean_norm_weights.mean(1, keepdims=True)
print('raw weights')
viz_sequence.plot_weights(filter_weights[:,:,i])
print('mean normalized weights')
viz_sequence.plot_weights(mean_norm_weights)
break
In [7]:
from matlas.matches import vdom_pssm
from IPython.display import display
from vdom.helpers import (h1, p, li, img, div, b, br, ul, img, a,
details, summary,
table, thead, th, tr, tbody, td, ol)
items_to_display = []
for i in top_k_filters:
filter_name = 'filter{}'.format(i)
mean_norm_weights = np.copy(filter_weights[:,:,i])
mean_norm_weights = mean_norm_weights - mean_norm_weights.mean(1, keepdims=True)
un_query = vdom_pssm(filter_weights[:,:,i])
n_query = vdom_pssm(mean_norm_weights)
items_to_display.append(summary(b(filter_name), p('raw weights'), un_query, 'mean normalized', n_query))
#break
display(details(summary(b("weights of selected filters")), summary(items_to_display)))
weights of selected filters
filter45raw weights
mean normalized
filter56raw weights
mean normalized
filter18raw weights
mean normalized
filter4raw weights
mean normalized
filter52raw weights
mean normalized
filter24raw weights
mean normalized
filter57raw weights
mean normalized
filter43raw weights
mean normalized
filter35raw weights
mean normalized
filter61raw weights
mean normalized
filter23raw weights
mean normalized
filter47raw weights
mean normalized
filter16raw weights
mean normalized
filter62raw weights
mean normalized
filter34raw weights
mean normalized
raw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedraw weights
mean normalizedIn [8]:
from matlas.pwms import ic_scale, adjust_for_ic_scale
from matlas.matches import vdom_pssm
from sklearn.preprocessing import MinMaxScaler
from collections import OrderedDict
def ic_scale_filter_weights(filter_weights, filter_count=64):
norm_weights = np.copy(filter_weights)
norm_weights = (norm_weights-np.mean(norm_weights))/np.std(norm_weights)
norm_weights[norm_weights>2] = 2.0
norm_weights[norm_weights<-2] = -2.0
ic_scaled_weights = OrderedDict()
for i in range(filter_count):
weights = np.copy(norm_weights[:,:,i])
scaler = MinMaxScaler()
arr = scaler.fit_transform(weights)
#convert to probability
arr = arr / arr.sum(1, keepdims=True) #divide by colsum
arr = arr + 0.01 # add pseudo-counts
probs = arr / arr.sum(1, keepdims=True)
#probs = adjust_for_ic_scale(probs)
try:
ic_scaled_weights['filter{0}'.format(i)] = ic_scale(probs)
except AssertionError:
print('filter{0}'.format(i))
return probs
return ic_scaled_weights
ic_scaled_weights = ic_scale_filter_weights(filter_weights)
filter weights in IC scale¶
All filter weights are standardised and each filter weights are scaled to 0-1 and converted to probability score before IC-scaling
In [10]:
# from IPython.display import display
# from matlas.pwms import ic_scale
# from vdom.helpers import (h1, p, li, img, div, b, br, ul, img, a,
# details, summary,
# table, thead, th, tr, tbody, td, ol)
# items_to_display = []
# for i in range(64):
# filter_name = 'filter{}'.format(i)
# query = vdom_pssm(ic_scaled_weights[filter_name])
# items_to_display.append(summary(filter_name, query))
# display(details(summary(b("filter weights in IC scale")), summary(items_to_display)))
In [9]:
#display(details(summary(b("Click here to see the filter weights in IC scale")), summary(items_to_display)))
#0, 18, 23, 45, 56, 61
selected_items_to_display = []
for i in top_k_filters:
filter_name = 'filter{}'.format(i)
query = vdom_pssm(ic_scaled_weights[filter_name])
selected_items_to_display.append(summary(filter_name, query))
display(details(summary(b("Click here to see the filter weights in IC scale")), summary(selected_items_to_display)))
Click here to see the filter weights in IC scale
filter45
filter56
filter18
filter4
filter52
filter24
filter57
filter43
filter35
filter61
filter23
filter47
filter16
filter62
filter34
importance score of the filtered sequences¶
In [14]:
imp_scores = np.load(aitacdir+"/imp_scores.npy")
rev_imp_scores = np.load(aitacdir+"/rev_imp_scores.npy")
OCR_matrix = np.load(aitacdir+"/OCR_matrix_0.npy")
activations2 = np.load(aitacdir+"/activations2_0.npy")
seq_indices_of_activation = np.load(aitacdir+"/seq_indices_of_activation_0.npy")
already_visited = []
for filter_no in top_k_filters:
filter_name = "filter{}".format(filter_no)
print(filter_name)
activated_seqs = np.argwhere(OCR_matrix[filter_no,:]==1)[:,0]; print(activated_seqs.shape)
activated_scores = imp_scores[activated_seqs]; print(activated_scores.shape)
for i in range(20):
if i in already_visited: continue
print('seq', activated_seqs[i])
viz_sequence.plot_weights(activated_scores[i, 600:746,:],
subticks_frequency=10, figsize=(20,1))
break
break
In [16]:
from matlas.sliding_similarities import aggregate_seqlets
seqlen = imp_scores.shape[1]
for filter_no in [45, 56, 18, 4, 52, 24, 57, 43, 35, 61, 23, 47, 16, 62, 34]:
activated_subseqs = np.argwhere(seq_indices_of_activation[filter_no]!=0); #print(activated_subseqs.shape)
activated_subscores = []
rev_activated_subscores = []
sub_activations = []
rev_sub_activations = []
for i,j,k in zip(activated_subseqs.T[0], activated_subseqs.T[1], activated_subseqs.T[1]+21):
activated_subscores.append(imp_scores[i, j:k, :])
rev_activated_subscores.append(rev_imp_scores[i, (seqlen-k):(seqlen-j), :])
sub_activations.append(activations2[i, filter_no, j])
activated_subscores = np.array(activated_subscores); #print(activated_subscores.shape)
rev_activated_subscores = np.array(rev_activated_subscores); #print(rev_activated_subscores.shape)
sub_activations = np.array(sub_activations)
sub_act_ind = np.flip(np.argsort(sub_activations))
activated_subscores = activated_subscores[sub_act_ind]
rev_activated_subscores = rev_activated_subscores[sub_act_ind]
avg_activated_subscores = aggregate_seqlets(activated_subscores[:100],
rev_activated_subscores[:100], 'sum'); #print(avg_activated_subscores.shape)
print('Aggregated importance scores using direct sum for filter-{}'.format(filter_no))
viz_sequence.plot_weights(avg_activated_subscores)
# print("filter{}".format(filter_no))
# print('running average')
# viz_sequence.plot_weights(avg_activated_subscores)
# viz_sequence.plot_weights(aggregate_seqlets(activated_subscores, rev_activated_subscores, 'old'))
#break
aitac motifs¶
In [10]:
from matlas.matches import DenovoAitac
motif_name = 'GABPA'
obs = OrderedDict()
for fold_no in range(1,11):
aitacdir = "/mnt/lab_data2/msharmin/oc-atlas/DanSkinData/alex_bpnets/{0}/{1}".format(motif_name, fold_no)
ob = DenovoAitac(aitacdir, filt_infl_from_loss[fold_no], len(top_k_filters[fold_no]))
ob.fetch_tomtom_matches(
meme_db="/mnt/lab_data/kundaje/users/msharmin/annotations/HOCOMOCOv11_core_pwms_HUMAN_mono.renamed.nonredundant.annotated.meme",
database_name="HOCOMOCO.nonredundant.annotated",
save_report=True, tomtom_dir= "{0}/{1}_tomtomout".format(aitacdir, "HOCOMOCO.nonredundant.annotated"))
# ob.load_matched_motifs(database_name="HOCOMOCO.nonredundant.annotated")
# ob.get_motif_per_celltype(match_threshold=0.05, database_name="HOCOMOCO.nonredundant.annotated")
# pattern_tab, pattern_dict = ob.visualize_pattern_table()
# tf_tab, tf_dict = ob.visualize_tf_table("Aitac")
# obs[fold_no] = ob
ith_influence_in_aitac = mean(change of across_task_correlation(label, prediction) between original vs. leave-one-out)
ith_influence_in_profile = mean(change of nll between original vs. leave-one-out)
ith_influence_in_binary = mean(change of loss between original vs. leave-one-out)
In [13]:
from vdom.helpers import (b, summary, details)
from IPython.display import display
ob_tofold = OrderedDict()
pattern_tab_tofold, pattern_dict_tofold = OrderedDict(), OrderedDict()
tf_tab_tofold, tf_dict_tofold = OrderedDict(), OrderedDict()
for fold_no in range(1,11):
aitacdir = "/mnt/lab_data2/msharmin/oc-atlas/DanSkinData/alex_bpnets/{0}/{1}".format(motif_name, fold_no)
ob = DenovoAitac(aitacdir, filt_infl_from_loss[fold_no], len(top_k_filters[fold_no]))
ob.load_matched_motifs(database_name="HOCOMOCO.nonredundant.annotated")
ob.get_motif_per_celltype(match_threshold=0.05, database_name="HOCOMOCO.nonredundant.annotated")
pattern_tab, pattern_dict = ob.visualize_pattern_table()
tf_tab, tf_dict = ob.visualize_tf_table("Aitac")
ob_tofold[fold_no] = ob
pattern_tab_tofold[fold_no], pattern_dict_tofold[fold_no] = pattern_tab, pattern_dict
tf_tab_tofold[fold_no], tf_dict_tofold[fold_no] = tf_tab, tf_dict
display(details(summary('Click here for ', b('Denovo Patterns'), ' by ', b('{}'.format('Aitac')),
' in ', b(motif_name), 'for fold-', b(str(fold_no)),
": #{}".format(len(pattern_dict)),
), pattern_tab))
#break
Click here for Denovo Patterns by Aitac in GABPAfor fold 1: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter21 |  | 0.012158171528416008 | |
| filter14 |  | 0.004646432232007024 | |
| filter38 |  | 0.0036944003840172013 | |
| filter11 | HCLUST-185_EGR1.UNK.0.A |  | 0.002735360262923564 |
| filter0 |  | 0.002564695543201924 | |
| filter52 |  | 0.002294969040943912 | |
| filter27 |  | 0.0018666101327697868 | |
| filter7 |  | 0.0015726890526587354 | |
| filter25 |  | 0.0014848836262653215 | |
| filter23 |  | 0.001476194889957789 | |
| filter55 |  | 0.0014064015665623925 | |
| filter26 |  | 0.0012881647732582784 | |
| filter4 |  | 0.0012143171288241169 | |
| filter17 |  | 0.00108436244177528 | |
| filter54 |  | 0.0009589449341359715 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 2: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter33 |  | 0.01607828391467118 | |
| filter58 |  | 0.008313042639806279 | |
| filter9 |  | 0.0030336345049428257 | |
| filter30 |  | 0.002567477963026992 | |
| filter7 |  | 0.0018705542178636537 | |
| filter60 |  | 0.0017018873324692939 | |
| filter42 |  | 0.0010090865955668235 | |
| filter50 | HCLUST-176_CBFB.UNK.0.A |  | 0.0007512629987262855 |
| filter2 |  | 0.0007456645474280032 | |
| filter46 | HCLUST-185_EGR1.UNK.0.A |  | 0.000671235593341321 |
| filter54 |  | 0.0006237393084835333 | |
| filter10 |  | 0.0005506679933512276 | |
| filter21 |  | 0.0005339955596034493 | |
| filter16 | HCLUST-127_FOXJ2.UNK.0.A, HCLUST-121_AR.UNK.0.A |  | 0.0005338595965256131 |
| filter4 |  | 0.0003812964377732778 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 3: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter61 |  | 0.0241975708651069 | |
| filter40 |  | 0.0120133534590629 | |
| filter47 |  | 0.0022175155858746723 | |
| filter3 | HCLUST-185_EGR1.UNK.0.A |  | 0.0014477433908615034 |
| filter37 |  | 0.001319633457032853 | |
| filter17 |  | 0.001068502114926573 | |
| filter8 | HCLUST-127_FOXJ2.UNK.0.A, HCLUST-121_AR.UNK.0.A |  | 0.0009843019741547637 |
| filter38 |  | 0.0005531907330856901 | |
| filter19 |  | 0.0004643575887528594 | |
| filter53 |  | 0.00045777627595309497 | |
| filter41 |  | 0.0003990157198807458 | |
| filter42 |  | 0.0003803383106884995 | |
| filter60 |  | 0.0003633639576703852 | |
| filter22 |  | 0.0003107487310415468 | |
| filter21 |  | 0.0002932906274264451 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 4: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter12 |  | 0.022725787197082428 | |
| filter3 |  | 0.0033010977792876785 | |
| filter4 |  | 0.0023411398228286593 | |
| filter20 |  | 0.002122195481879739 | |
| filter19 | HCLUST-166_NANOG.UNK.0.A |  | 0.0014721681787709653 |
| filter58 |  | 0.001198504854090217 | |
| filter26 |  | 0.0011863372367746409 | |
| filter17 | HCLUST-185_EGR1.UNK.0.A, HCLUST-68_ZNF341.UNK.0.A |  | 0.0007430883949555256 |
| filter48 |  | 0.0005685315014072121 | |
| filter54 |  | 0.0005176952765088244 | |
| filter61 |  | 0.0004227253807400986 | |
| filter15 |  | 0.0004178638728340347 | |
| filter37 |  | 0.00041766462285837126 | |
| filter39 |  | 0.0003595229726167596 | |
| filter30 |  | 0.00031471317133933415 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 5: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter20 |  | 0.01476561669015209 | |
| filter12 |  | 0.014545523103798273 | |
| filter53 |  | 0.005871722872809147 | |
| filter62 |  | 0.005286434094971864 | |
| filter41 |  | 0.0018207590344454369 | |
| filter48 |  | 0.0016766765534342728 | |
| filter21 | HCLUST-176_CBFB.UNK.0.A |  | 0.0013693896557745414 |
| filter19 | HCLUST-185_EGR1.UNK.0.A |  | 0.0012370154301657916 |
| filter9 |  | 0.0008298574831412477 | |
| filter7 |  | 0.0007951216690805334 | |
| filter5 |  | 0.0004528637987301055 | |
| filter18 |  | 0.0003912096776142643 | |
| filter45 |  | 0.000352125669511754 | |
| filter33 |  | 0.0003500002591125758 | |
| filter16 |  | 0.0003268682165258089 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 6: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter24 |  | 0.019604486554778738 | |
| filter42 |  | 0.008300697856733727 | |
| filter26 |  | 0.005561082098466412 | |
| filter20 |  | 0.0025179019230436267 | |
| filter4 |  | 0.002509759747396084 | |
| filter35 |  | 0.001674854923046387 | |
| filter23 |  | 0.0010959570751264461 | |
| filter59 |  | 0.0009661794588734711 | |
| filter1 |  | 0.0009076734132858928 | |
| filter16 |  | 0.0008164559621340168 | |
| filter61 |  | 0.0007918088238510803 | |
| filter17 | HCLUST-185_EGR1.UNK.0.A |  | 0.0007911315829968562 |
| filter14 | HCLUST-68_ZNF341.UNK.0.A, HCLUST-1_GATA1.UNK.0.A |  | 0.0007636639954181004 |
| filter12 |  | 0.0007149301697975292 | |
| filter49 |  | 0.0005991829793066263 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 7: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter45 |  | 0.016489458846274088 | |
| filter56 |  | 0.0071794140824270785 | |
| filter18 |  | 0.006763104842485965 | |
| filter4 |  | 0.00226459386723026 | |
| filter52 |  | 0.0014455899894864664 | |
| filter24 |  | 0.0013307982479046684 | |
| filter57 |  | 0.0009709997026450573 | |
| filter43 | HCLUST-185_EGR1.UNK.0.A, HCLUST-68_ZNF341.UNK.0.A |  | 0.0007984892106282671 |
| filter35 |  | 0.0007438435758384045 | |
| filter61 | HCLUST-121_AR.UNK.0.A |  | 0.0006917976388044464 |
| filter23 |  | 0.0006895361006770493 | |
| filter47 |  | 0.0004905510970899681 | |
| filter16 |  | 0.00045740756493263545 | |
| filter62 |  | 0.00040114731355204097 | |
| filter34 |  | 0.0003538655137844069 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 8: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter26 |  | 0.018677824853274964 | |
| filter12 |  | 0.009326091436807356 | |
| filter10 |  | 0.0048498071047010346 | |
| filter25 |  | 0.00360668462074044 | |
| filter35 |  | 0.00276519384641043 | |
| filter8 |  | 0.002319249224056114 | |
| filter50 | HCLUST-185_EGR1.UNK.0.A |  | 0.0014981231310598258 |
| filter4 |  | 0.0009138258768458728 | |
| filter21 |  | 0.0008713732480695554 | |
| filter1 | HCLUST-176_CBFB.UNK.0.A |  | 0.0008383305149276209 |
| filter18 |  | 0.0008187513398026262 | |
| filter29 |  | 0.0007953641231948824 | |
| filter49 |  | 0.0006877977147447425 | |
| filter41 |  | 0.000608482759628662 | |
| filter59 |  | 0.0005599507584787912 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 9: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter20 |  | 0.022610587812912388 | |
| filter19 |  | 0.004625078721480363 | |
| filter1 |  | 0.0024810233125579237 | |
| filter38 | HCLUST-47_REST.UNK.0.A |  | 0.0015066811140562767 |
| filter40 |  | 0.001462942785006624 | |
| filter8 |  | 0.0014435565361294845 | |
| filter15 |  | 0.0013175922940217445 | |
| filter45 | HCLUST-185_EGR1.UNK.0.A |  | 0.0008751941570383457 |
| filter59 |  | 0.0005170985102031899 | |
| filter52 |  | 0.000512010106109997 | |
| filter61 |  | 0.0004812091778644074 | |
| filter6 |  | 0.0004663236798240322 | |
| filter44 | HCLUST-14_HOXA13.UNK.0.A |  | 0.0004138636629550604 |
| filter17 |  | 0.0004038094188369986 | |
| filter7 | HCLUST-120_AIRE.UNK.0.A, HCLUST-127_FOXJ2.UNK.0.A |  | 0.00036873326461513275 |
Click here for Denovo Patterns by Aitac in GABPAfor fold 10: #15
| Pattern Name | TF Name(s) | Aitac | Influence |
|---|---|---|---|
| filter8 |  | 0.038050179982820447 | |
| filter2 |  | 0.028632375881360392 | |
| filter1 |  | 0.010766665145937175 | |
| filter35 |  | 0.003392821110765835 | |
| filter39 |  | 0.0026492186131869804 | |
| filter14 |  | 0.0018516416275111349 | |
| filter52 |  | 0.0014056097130946037 | |
| filter18 | HCLUST-185_EGR1.UNK.0.A |  | 0.0009746202007266615 |
| filter10 | HCLUST-68_ZNF341.UNK.0.A |  | 0.0006976170575984161 |
| filter22 |  | 0.0006924676239367729 | |
| filter17 |  | 0.0006825297187301067 | |
| filter45 |  | 0.000633379434201547 | |
| filter31 | HCLUST-31_ZNF449.UNK.0.A |  | 0.0005235241341638256 |
| filter27 |  | 0.0004420152752339149 | |
| filter26 |  | 0.00041597865620691623 |
In [14]:
for fold_no in range(1,11):
display(details(summary('Click here for ', b('Motifs'), ' by ', b('{}'.format('Aitac')),
' in ', b(motif_name), 'for fold-', b(str(fold_no)),
": #{}".format(len(tf_dict_tofold[fold_no])),
), tf_tab_tofold[fold_no]))
Click here for Motifs by Aitac in GABPAfor fold-1: #1
| TF Name | Pattern(s) | ||||||
|---|---|---|---|---|---|---|---|
| HCLUST-185_EGR1.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-2: #4
| TF Name | Pattern(s) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| HCLUST-176_CBFB.UNK.0.A |
| |||||||||
| HCLUST-185_EGR1.UNK.0.A |
| |||||||||
| HCLUST-127_FOXJ2.UNK.0.A |
| |||||||||
| HCLUST-121_AR.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-3: #3
| TF Name | Pattern(s) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| HCLUST-185_EGR1.UNK.0.A |
| |||||||||
| HCLUST-127_FOXJ2.UNK.0.A |
| |||||||||
| HCLUST-121_AR.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-4: #3
| TF Name | Pattern(s) | ||||||
|---|---|---|---|---|---|---|---|
| HCLUST-166_NANOG.UNK.0.A |
| ||||||
| HCLUST-185_EGR1.UNK.0.A |
| ||||||
| HCLUST-68_ZNF341.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-5: #2
| TF Name | Pattern(s) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HCLUST-176_CBFB.UNK.0.A |
| ||||||||||||
| HCLUST-185_EGR1.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-6: #3
| TF Name | Pattern(s) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| HCLUST-185_EGR1.UNK.0.A |
| |||||||||
| HCLUST-68_ZNF341.UNK.0.A |
| |||||||||
| HCLUST-1_GATA1.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-7: #3
| TF Name | Pattern(s) | ||||||
|---|---|---|---|---|---|---|---|
| HCLUST-185_EGR1.UNK.0.A |
| ||||||
| HCLUST-68_ZNF341.UNK.0.A |
| ||||||
| HCLUST-121_AR.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-8: #2
| TF Name | Pattern(s) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| HCLUST-185_EGR1.UNK.0.A |
| |||||||||
| HCLUST-176_CBFB.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-9: #5
| TF Name | Pattern(s) | ||||||
|---|---|---|---|---|---|---|---|
| HCLUST-47_REST.UNK.0.A |
| ||||||
| HCLUST-185_EGR1.UNK.0.A |
| ||||||
| HCLUST-14_HOXA13.UNK.0.A |
| ||||||
| HCLUST-120_AIRE.UNK.0.A |
| ||||||
| HCLUST-127_FOXJ2.UNK.0.A |
|
Click here for Motifs by Aitac in GABPAfor fold-10: #3
| TF Name | Pattern(s) | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| HCLUST-185_EGR1.UNK.0.A |
| |||||||||
| HCLUST-68_ZNF341.UNK.0.A |
| |||||||||
| HCLUST-31_ZNF449.UNK.0.A |
|
Rsat motif clustering¶
In [52]:
motif_name = 'GABPA'
aitacdir = "/mnt/lab_data2/msharmin/oc-atlas/DanSkinData/fold_a_alex/{}".format(motif_name)
from matlas.pwms import get_motifDB_id_maps, reduce_pwm_redundancy
memefile = "{0}/filter_motifs_pwm.meme".format(aitacdir)
motif_id_maps = get_motifDB_id_maps(database_name=memefile)
file_prefix = "/mnt/lab_data2/msharmin/oc-atlas/DanSkinData/fold_a_alex/{}/aitac".format(motif_name)
reduce_pwm_redundancy(
motif_id_maps,
out_pwm_file="{}.hclust_pwms.tmp".format(file_prefix),
pwmtype="probabilities", #probabilities
tmp_prefix=file_prefix,
pseudocount=PSEUDOCOUNT,
ic_thresh=IC_THRESHOLD,
cor_thresh=0.6,
ncor_thresh=0.4,
num_threads=28)
In [60]:
from matlas.reports import generate_merged_pwm_plots
from matlas.pwms import read_pwm_file, load_cisbp_maps
mergeddict = read_pwm_file("{}.hclust_pwms.tmp".format(file_prefix))
tab, tabledict = generate_merged_pwm_plots(mergeddict, motif_id_maps)
In [16]:
#display(tab)
In [ ]: