def calc_statistics(orig_df1, orig_df2, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
df1 = _lib.mh_del_subset(orig_df1)
df1 = _lib.indels_without_mismatches_subset(df1)
df2 = _lib.mh_del_subset(orig_df2)
df2 = _lib.indels_without_mismatches_subset(df2)
if bool(sum(df1['Count']) <= 1000) or bool(sum(df2['Count']) <= 1000):
return
df1['Frequency'] = _lib.normalize_frequency(df1)
df2['Frequency'] = _lib.normalize_frequency(df2)
join_cols = ['Category', 'Genotype Position', 'Length']
mdf = df1.merge(df2, how='outer', on=join_cols, suffixes=['_1', '_2'])
mdf['Frequency_1'].fillna(value=0, inplace=True)
mdf['Frequency_2'].fillna(value=0, inplace=True)
r = pearsonr(mdf['Frequency_1'], mdf['Frequency_2'])[0]
print exp, r
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def get_r_from_subsets(d1, d2):
if sum(d1['Count']) < 100 or sum(d2['Count']) < 100:
return np.nan
d1['Frequency'] = _lib.normalize_frequency(d1)
d2['Frequency'] = _lib.normalize_frequency(d2)
mdf = _lib.merge_crispr_events(d1, d2, '_1', '_2')
return pearsonr(mdf['Frequency_1'], mdf['Frequency_2'])[0]
def featurize(orig_df):
seq, cutsite = _lib.get_sequence_cutsite(orig_df)
mh_lens, gc_fracs, del_lens, freqs = [], [], [], []
dl_freqs = []
DELLEN_LIMIT = 60
df = _lib.mh_del_subset(orig_df)
df = _lib.indels_without_mismatches_subset(df)
df = df[df['Length'] <= DELLEN_LIMIT]
if sum(df['Count']) < 1000:
return None
criteria = (orig_df['Category'] == 'del') & (orig_df['Length'] <= 28)
s = orig_df[criteria]
s['Frequency'] = _lib.normalize_frequency(s)
for del_len in range(1, 28 + 1):
dl_freq = sum(s[s['Length'] == del_len]['Frequency'])
dl_freqs.append(dl_freq)
df['Frequency'] = _lib.normalize_frequency(df)
for del_len in range(1, DELLEN_LIMIT + 1):
left = seq[cutsite - del_len:cutsite]
right = seq[cutsite:cutsite + del_len]
mhs = find_microhomologies(left, right)
for mh in mhs:
mh_len = len(mh) - 1
if mh_len > 0:
gtpos = max(mh)
s = cutsite - del_len + gtpos - mh_len
e = s + mh_len
mh_seq = seq[s:e]
gc_frac = get_gc_frac(mh_seq)
criteria = (df['Length'] == del_len) & (df['Genotype Position']
== gtpos)
freq = sum(df[criteria]['Frequency'])
mh_lens.append(mh_len)
gc_fracs.append(gc_frac)
del_lens.append(del_len)
freqs.append(freq)
return mh_lens, gc_fracs, del_lens, freqs, dl_freqs
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
# Denominator is 1-27 bp dels
df = _lib.crispr_del_27bp_subset(df)
if sum(df['Count']) <= 500:
return
df['Frequency'] = _lib.normalize_frequency(df)
if sum(df['Frequency']) == 0:
return
for del_len in range(1, 27 + 1):
df_lensubset = df[df['Length'] == del_len]
mhyes_freq = sum(df_lensubset[df_lensubset['Microhomology-Based'] ==
'yes']['Frequency'])
mhno_freq = sum(df_lensubset[df_lensubset['Microhomology-Based'] ==
'no']['Frequency'])
alldf_dict['Deletion Length'].append(del_len)
alldf_dict['Microhomology-Based'].append('has MH')
alldf_dict['Frequency'].append(mhyes_freq)
alldf_dict['_Experiment'].append(exp)
alldf_dict['Deletion Length'].append(del_len)
alldf_dict['Microhomology-Based'].append('no MH')
alldf_dict['Frequency'].append(mhno_freq)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
# Denominator is 1-27 bp dels
df = _lib.crispr_del_27bp_subset(df)
if sum(df['Count']) <= 500:
return
df['Frequency'] = _lib.normalize_frequency(df)
if sum(df['Frequency']) == 0:
return
df_s = df[df['Microhomology-Based'] == 'no']
gt0 = sum(df_s[df_s['Genotype Position'] == 0]['Frequency'])
gtN = sum(df_s[df_s['Genotype Position'] == df_s['Length']]['Frequency'])
gtMid = sum(df_s['Frequency']) - gt0 - gtN
alldf_dict['0gt'].append(gt0)
alldf_dict['Ngt'].append(gtN)
alldf_dict['Mid'].append(gtMid)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
df = _lib.mh_del_subset(df)
df = _lib.indels_without_mismatches_subset(df)
df = df[df['Length'] >= 5]
if sum(df['Count']) <= 1000:
return
df['Frequency'] = _lib.normalize_frequency(df)
_predict2.init_model()
seq, cutsite = _lib.get_sequence_cutsite(df)
pred_df = _predict2.predict_mhdel(seq, cutsite)
pred_df = pred_df[pred_df['Length'] >= 5]
pred_df['Predicted_Frequency'] = pred_df['Predicted_Frequency'] / sum(
pred_df['Predicted_Frequency'])
join_cols = ['Category', 'Genotype Position', 'Length']
mdf = df.merge(pred_df, how='outer', on=join_cols)
mdf['Frequency'].fillna(value=0, inplace=True)
mdf['Predicted_Frequency'].fillna(value=0, inplace=True)
obs = mdf['Frequency']
pred = mdf['Predicted_Frequency']
ns_criteria = (mdf['Length'] - mdf['Genotype Position'] == 0)
s = mdf[ns_criteria]
alldf_dict['Predicted Ngt'] += list(s['Predicted_Frequency'])
alldf_dict['Observed Ngt'] += list(s['Frequency'])
alldf_dict['_Experiment'] += [exp] * len(s['Frequency'])
return alldf_dict
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
# Denominator is 3-27 bp dels
# Remove obvious subpopulation of 1 bp, mh vs. no mh
df = _lib.crispr_del_3bp_27bp_subset(df)
if sum(df['Count']) <= 500:
return
df['Frequency'] = _lib.normalize_frequency(df)
# Consider only deletion length 5
df = df[df['Length'] == 5]
df_s = df[df['Microhomology-Based'] == 'no']
gt0 = sum(df_s[df_s['Genotype Position'] == 0]['Frequency'])
gtN = sum(df_s[df_s['Genotype Position'] == df_s['Length']]['Frequency'])
gt0N = gt0 + gtN
mh_freq = sum(df[df['Microhomology-Based'] == 'yes']['Frequency'])
alldf_dict['0N_freq'].append(gt0N)
alldf_dict['MH_freq'].append(mh_freq)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(orig_df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
df = _lib.mh_del_subset(orig_df)
df = _lib.indels_without_mismatches_subset(df)
df = df[df['Length'] >= 5]
if sum(df['Count']) <= 500:
return
df['Frequency'] = _lib.normalize_frequency(df)
_predict2.init_model()
seq, cutsite = _lib.get_sequence_cutsite(df)
pred_df = _predict2.predict_mhdel_cpf1(seq, cutsite)
join_cols = ['Category', 'Genotype Position', 'Length']
mdf = df.merge(pred_df, how='outer', on=join_cols)
mdf['Frequency'].fillna(value=0, inplace=True)
mdf['Predicted_Frequency'].fillna(value=0, inplace=True)
obs = mdf['Frequency']
pred = mdf['Predicted_Frequency']
r = pearsonr(obs, pred)[0]
alldf_dict['gt_r'].append(r)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(orig_df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
df = _lib.crispr_subset(orig_df)
if sum(df['Count']) <= 1000:
return
df['Frequency'] = _lib.normalize_frequency(df)
# Wildtype repair frequency
dlwt = _config.d.DISLIB_WT
row = dlwt[dlwt['name'] == exp].iloc[0]
if row['wt_repairable'] != 'yes':
alldf_dict['wt_obs'].append(np.nan)
alldf_dict['dl'].append(np.nan)
else:
dls = [int(s) for s in row['dls'].split(';')]
gts = [int(s) for s in row['gts'].split(';')]
obs_freq = 0
for dl, gt in zip(dls, gts):
crit = (df['Length'] == dl) & (df['Genotype Position'] == gt)
obs_freq += sum(df[crit]['Frequency'])
alldf_dict['wt_obs'].append(obs_freq)
alldf_dict['dl'].append(set(dls).pop())
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(orig_df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
df = _lib.mh_del_subset(orig_df)
df = _lib.indels_without_mismatches_subset(df)
if sum(df['Count']) <= 1000:
return
df['Frequency'] = _lib.normalize_frequency(df)
_predict2.init_model()
seq, cutsite = _lib.get_sequence_cutsite(df)
pred_df = _predict2.predict_mhdel(seq, cutsite)
join_cols = ['Category', 'Genotype Position', 'Length']
mdf = df.merge(pred_df, how = 'outer', on = join_cols)
mdf['Frequency'].fillna(value = 0, inplace = True)
mdf['Predicted_Frequency'].fillna(value = 0, inplace = True)
obs = mdf['Frequency']
pred = mdf['Predicted_Frequency']
obs_entropy = entropy(obs) / np.log(len(obs))
pred_entropy = entropy(pred) / np.log(len(pred))
alldf_dict['obs gt entropy'].append(obs_entropy)
alldf_dict['pred gt entropy'].append(pred_entropy)
df = orig_df[orig_df['Category'] == 'del']
df = df[df['Length'] <= 28]
df['Frequency'] = _lib.normalize_frequency(df)
obs_dl = []
for del_len in range(1, 28+1):
freq = sum(df[df['Length'] == del_len]['Frequency'])
obs_dl.append(freq)
pred_dl = _predict2.deletion_length_distribution(seq, cutsite)
obs_entropy = entropy(obs_dl) / np.log(len(obs_dl))
pred_entropy = entropy(pred_dl) / np.log(len(pred_dl))
alldf_dict['obs dl entropy'].append(obs_entropy)
alldf_dict['pred dl entropy'].append(pred_entropy)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
# Denominator is ins
df = df[df['Category'] == 'ins']
if sum(df['Count']) <= 500:
return
df['Frequency'] = _lib.normalize_frequency(df)
for ins_len in range(1, 15 + 1):
df_s = df[df['Length'] == ins_len]
criteria = (df_s['Ins Template Length'] >= 6)
frac_templated = sum(df_s[criteria]['Frequency'])
criteria = (df_s['Ins Fivehomopolymer']
== 'yes') & (df_s['Ins Template Length'] < 6)
frac_fivehomopolymer = sum(df_s[criteria]['Frequency'])
criteria = (df_s['Ins Fivehomopolymer']
== 'no') & (df_s['Ins Template Length'] < 6)
frac_other = sum(df_s[criteria]['Frequency'])
alldf_dict['Frac 5hm'].append(frac_fivehomopolymer)
alldf_dict['Frac templated'].append(frac_templated)
alldf_dict['Frac other'].append(frac_other)
alldf_dict['Frac total'].append(sum(df_s['Frequency']))
alldf_dict['Length'].append(ins_len)
alldf_dict['_Experiment'].append(exp)
# Get all insertions longer than 15 bp
df_s = df[df['Length'] > 15]
criteria = (df_s['Ins Template Length'] >= 6)
frac_templated = sum(df_s[criteria]['Frequency'])
criteria = (df_s['Ins Fivehomopolymer']
== 'yes') & (df_s['Ins Template Length'] < 6)
frac_fivehomopolymer = sum(df_s[criteria]['Frequency'])
criteria = (df_s['Ins Fivehomopolymer']
== 'no') & (df_s['Ins Template Length'] < 6)
frac_other = sum(df_s[criteria]['Frequency'])
alldf_dict['Frac 5hm'].append(frac_fivehomopolymer)
alldf_dict['Frac templated'].append(frac_templated)
alldf_dict['Frac other'].append(frac_other)
alldf_dict['Frac total'].append(sum(df_s['Frequency']))
alldf_dict['Length'].append(16)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
longdup_len = int(exp.split('_')[1])
# Denominator is ins
df = _lib.crispr_subset(df)
if sum(df['Count']) <= 500:
return
df['Frequency'] = _lib.normalize_frequency(df)
criteria = (df['Category'] == 'del') & (df['Length'] == longdup_len)
freq = sum(df[criteria]['Frequency'])
alldf_dict['Length'].append(longdup_len)
alldf_dict['Frequency'].append(freq)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
# Denominator is all dels
df = df[df['Category'] == 'del']
if sum(df['Count']) <= 1000:
return
df['Frequency'] = _lib.normalize_frequency(df)
if sum(df['Frequency']) == 0:
return
for del_len in range(1, 80 + 1):
cum_freq = sum(df[df['Length'] <= del_len]['Frequency'])
alldf_dict['Cumulative Frequency'].append(cum_freq)
alldf_dict['Length'].append(del_len)
alldf_dict['_Experiment'].append(exp)
return alldf_dict
def calc_statistics(df, exp, alldf_dict):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
# Denominator is all non-noise categories
df = _lib.notnoise_subset(df)
df['Frequency'] = _lib.normalize_frequency(df)
if sum(df['Frequency']) == 0:
return
# Consider only deletions, anywhere
del_df = _lib.del_subset(df)
# Get left side
for del_pos in range(-10, -1 + 1):
total_freq = sum(
del_df[del_df['Genotype Position'] == del_pos]['Frequency'])
alldf_dict[str(del_pos)].append(total_freq)
# Get right side
for del_pos in range(1, 10 + 1):
criteria = (del_df['Genotype Position'] - del_df['Length'] == del_pos)
total_freq = sum(del_df[criteria]['Frequency'])
alldf_dict[str(del_pos)].append(total_freq)
editing_rate = sum(_lib.crispr_subset(df)['Frequency']) / sum(
df['Frequency'])
alldf_dict['Editing Rate'].append(editing_rate)
alldf_dict['_Experiment'].append(exp)
# Test alternative hypothesis: is asymmetry actually meaningful? If -1 arises from 0gt and sequencing mismatch, and +1 arises from Ngt and sequencing mismatch, then we should see asymmetry in 0gt vs Ngt.
def detect_0gt_microhomology(row):
# Returns a frequency
if row['Category'] != 'del':
return 0
cutsite = int(row['_Cutsite'])
seq = row['_Sequence Context']
gt_pos = int(row['Genotype Position'])
del_len = int(row['Length'])
left = seq[cutsite - del_len:cutsite]
right = seq[cutsite:cutsite + del_len]
if len(left) != len(right):
return 0
mhs = []
mh = [0]
for idx, (c1, c2) in enumerate(zip(left, right)):
if c1 == c2:
mh.append(idx + 1)
else:
mhs.append(mh)
mh = [idx + 1]
mhs.append(mh)
for mh in mhs:
if gt_pos in mh:
if 0 in mh:
return row['Frequency']
return 0
freq_0gt = sum(del_df.apply(detect_0gt_microhomology, axis=1))
alldf_dict['0gt Frequency'].append(freq_0gt)
criteria = (del_df['Genotype Position'] - del_df['Length'] == 0)
freq_Ngt = sum(del_df[criteria]['Frequency'])
alldf_dict['Ngt Frequency'].append(freq_Ngt)
return
def calc_statistics(orig_df, exp, rate_model, bp_model, alldf_dict, rs, data_nm):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
df = _lib.mh_del_subset(orig_df)
df = _lib.indels_without_mismatches_subset(df)
if sum(df['Count']) <= 1000:
return
obs_d = defaultdict(list)
df = orig_df
# Grab observed deletions, MH and MH-less
for del_len in range(1, 59+1):
crit = (df['Category'] == 'del') & (df['Indel with Mismatches'] != 'yes') & (df['Length'] == del_len)
s = df[crit]
mh_s = s[s['Microhomology-Based'] == 'yes']
for idx, row in mh_s.iterrows():
obs_d['Count'].append(row['Count'])
obs_d['Genotype Position'].append(row['Genotype Position'])
obs_d['Length'].append(row['Length'])
obs_d['Category'].append('del')
mhless_s = s[s['Microhomology-Based'] != 'yes']
obs_d['Length'].append(del_len)
obs_d['Count'].append(sum(mhless_s['Count']))
obs_d['Genotype Position'].append('e')
obs_d['Category'].append('del')
obs_df = pd.DataFrame(obs_d)
# Grab observed 1 bp insertions
ins_crit = (orig_df['Category'] == 'ins') & (orig_df['Length'] == 1) & (orig_df['Indel with Mismatches'] != 'yes')
ins_df = orig_df[ins_crit]
truncated_ins_d = defaultdict(list)
for ins_base in list('ACGT'):
crit = (ins_df['Inserted Bases'] == ins_base)
tot_count = sum(ins_df[crit]['Count'])
truncated_ins_d['Count'].append(tot_count)
truncated_ins_d['Inserted Bases'].append(ins_base)
truncated_ins_d['Category'].append('ins')
truncated_ins_d['Length'].append(1)
ins_df = pd.DataFrame(truncated_ins_d)
obs_df = obs_df.append(ins_df, ignore_index = True)
obs_df['Frequency'] = _lib.normalize_frequency(obs_df)
crispr_subset = _lib.crispr_subset(orig_df)
frac_explained = sum(obs_df['Count']) / sum(crispr_subset['Count'])
# print frac_explained
# Save this for aggregate plotting
alldf_dict['Fraction Explained'].append(frac_explained)
# Predict MH dels and MH-less dels
_predict2.init_model()
seq, cutsite = _lib.get_sequence_cutsite(orig_df)
pred_df = _predict2.predict_indels(seq, cutsite,
rate_model, bp_model)
mdf = obs_df.merge(pred_df, how = 'outer', on = ['Category', 'Genotype Position', 'Inserted Bases', 'Length'])
mdf['Frequency'].fillna(value = 0, inplace = True)
mdf['Predicted_Frequency'].fillna(value = 0, inplace = True)
r = pearsonr(mdf['Frequency'], mdf['Predicted_Frequency'])[0]
# Merge observed and predicted, double check correlation
# Store in a way that I can plot it.
data_nm_out_dir = out_dir + data_nm + '/'
util.ensure_dir_exists(data_nm_out_dir)
exp_out_dir = data_nm_out_dir + exp + '/'
util.ensure_dir_exists(exp_out_dir)
out_fn = exp_out_dir + '%.3f.csv' % (r)
mdf.to_csv(out_fn)
# Store in alldf_dict
alldf_dict['_Experiment'].append(exp)
alldf_dict['rs'].append(rs)
return alldf_dict
def calc_statistics(orig_df, exp, rate_model, bp_model, alldf_dict, rs):
# Calculate statistics on df, saving to alldf_dict
# Deletion positions
df = _lib.mh_del_subset(orig_df)
df = _lib.indels_without_mismatches_subset(df)
if sum(df['Count']) <= 1000:
return
ins_crit = (orig_df['Category'] == 'ins') & (orig_df['Length'] == 1)
ins_df = orig_df[ins_crit]
truncated_ins_d = defaultdict(list)
for ins_base in list('ACGT'):
crit = (ins_df['Inserted Bases'] == ins_base)
tot_count = sum(ins_df[crit]['Count'])
truncated_ins_d['Count'].append(tot_count)
truncated_ins_d['Inserted Bases'].append(ins_base)
truncated_ins_d['Category'].append('ins')
truncated_ins_d['Length'].append(1)
ins_df = pd.DataFrame(truncated_ins_d)
df = df.append(ins_df, ignore_index=True)
df['Frequency'] = _lib.normalize_frequency(df)
_predict2.init_model()
seq, cutsite = _lib.get_sequence_cutsite(orig_df)
pred_df = _predict2.predict_mhdel(seq, cutsite)
# Predict rate of 1 bp insertions
# Featurize first
del_score = _predict2.total_deletion_score(seq, cutsite)
dlpred = _predict2.deletion_length_distribution(seq, cutsite)
norm_entropy = entropy(dlpred) / np.log(len(dlpred))
ohmapper = {
'A': [1, 0, 0, 0],
'C': [0, 1, 0, 0],
'G': [0, 0, 1, 0],
'T': [0, 0, 0, 1]
}
fivebase = seq[cutsite - 1]
onebp_features = ohmapper[fivebase] + [norm_entropy] + [del_score]
onebp_features = np.array(onebp_features).reshape(1, -1)
rate_1bpins = float(rate_model.predict(onebp_features))
# Predict 1 bp genotype frequencies
pred_1bpins_d = defaultdict(list)
for ins_base in bp_model[fivebase]:
freq = bp_model[fivebase][ins_base]
freq *= rate_1bpins / (1 - rate_1bpins)
pred_1bpins_d['Category'].append('ins')
pred_1bpins_d['Length'].append(1)
pred_1bpins_d['Inserted Bases'].append(ins_base)
pred_1bpins_d['Predicted_Frequency'].append(freq)
pred_1bpins_df = pd.DataFrame(pred_1bpins_d)
pred_df = pred_df.append(pred_1bpins_df, ignore_index=True)
pred_df['Predicted_Frequency'] /= sum(pred_df['Predicted_Frequency'])
join_cols = ['Category', 'Genotype Position', 'Length', 'Inserted Bases']
mdf = df.merge(pred_df, how='outer', on=join_cols)
mdf['Frequency'].fillna(value=0, inplace=True)
mdf['Predicted_Frequency'].fillna(value=0, inplace=True)
obs = mdf['Frequency']
pred = mdf['Predicted_Frequency']
r = pearsonr(obs, pred)[0]
alldf_dict['gt_r'].append(r)
obs_entropy = entropy(obs) / np.log(len(obs))
pred_entropy = entropy(pred) / np.log(len(pred))
alldf_dict['obs entropy'].append(obs_entropy)
alldf_dict['pred entropy'].append(pred_entropy)
alldf_dict['_Experiment'].append(exp)
alldf_dict['rs'].append(rs)
return alldf_dict
