def compare_hmmscores(fasta, hmm1, hmm2):
'''Return a dataframe whose columns are the accession
numbers in fasta and the corresponding hmm scores from
the hmm output files, hmm1 and hmm2, respectively.'''
acc_all = bioinf.get_accession(fasta)
[acc1, score1] = get_acc_and_scores(hmm1)
[acc2, score2] = get_acc_and_scores(hmm2)
hmm1_scores,hmm2_scores = [],[]
for i in range(len(acc_all)):
try:
hmm1_scores.append(score1[acc1.index(acc_all[i])])
except:
hmm1_scores.append(0) # Assign a score of 0 if it's below the threshold
try:
hmm2_scores.append(score2[acc2.index(acc_all[i])])
except:
hmm2_scores.append(0)
store = pd.DataFrame([acc_all, hmm1_scores, hmm2_scores]).transpose()
store.columns = ['accession', 'hmm1_scores', 'hmm2_scores']
return store
from sklearn.preprocessing import OneHotEncoder
from sklearn.model_selection import KFold
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix
import warnings
warnings.filterwarnings("ignore")
import bioinformatics as bioinf
# Prepare sequences and data
#=====================================================#
GH13_df = pd.read_csv('results_final/ncbi_subtypes.csv')
GH13_SH = GH13_df[(GH13_df.ncbi_pred_class == 0)]
accession_SH = GH13_SH.Accession.tolist()
accession_all = bioinf.get_accession('fasta/initial_blast/nrblast_all.fasta')
GH13 = [1 if x in accession_SH else 0 for x in accession_all]
# class labels
y = pd.Series(GH13)
GH13_not_SH = y[y == 0]
GH13_yes_SH = y[y == 1]
# Derive features for machine learning with one-hot encoding
#============================================================#
cat_domain_fasta = 'fasta/GH13_positions_only/GH13_cat.fasta'
sequence_df = bioinf.fasta_to_df(cat_domain_fasta)
X_features = pd.DataFrame() # empty dataframe for storing features
for i in range(len(sequence_df.columns)):
# Convert amino acids to integers
X_resid = list(sequence_df.iloc[:, i])
from keras.callbacks import ReduceLROnPlateau
import os
import tensorflow as tf
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import classification_report
from sklearn.preprocessing import label_binarize
from sklearn.metrics import roc_curve
from sklearn.metrics import auc
from sklearn.metrics import confusion_matrix
from keras.models import load_model
# load train and test dataset
h, sequences = bioinf.split_fasta('fasta/GH13_positions_only/GH13_cat.fasta')
heads=bioinf.get_accession('fasta/GH13_positions_only/GH13_cat.fasta')
subtype = list(pd.read_csv('results_final/ncbi_subtypes.csv')['ncbi_pred_class'])
lb = LabelBinarizer()
y = lb.fit_transform(subtype)
y = to_categorical(y)
cat_domain_fasta = 'fasta/GH13_positions_only/GH13_cat.fasta'
sequence_df = bioinf.fasta_to_df(cat_domain_fasta)
max_length = len(sequence_df.columns)
embedding_dim = 11
top_classes=2
tokenizer = Tokenizer(char_level=True)
tokenizer.fit_on_texts(sequences)
X_seq = tokenizer.texts_to_sequences(sequences)
X_seq = sequence.pad_sequences(X_seq, maxlen=max_length)
#X_train, X_test, y_train, y_test = train_test_split(X_seq, y, test_size=.2)
store.append(looplength)
# Save results as DataFrame
result = pd.DataFrame(store)
result.columns = ['A1', 'A2', 'A3', 'A4', 'B1', 'B2', 'B3', 'B4']
return result
# Calculate loop lengths
msafile = 'fasta/structure_based_alignment/cel7_nr99_structaln.fasta'
looplength = get_gh7looplength(msafile, trecel7a_pos=0)
# Write results to spreadhseet
looplength.index = range(1, len(looplength)+1)
looplength['accession'] = bioinf.get_accession(msafile)
looplength.to_csv('results_final/looplength.csv')
# Data preprocessing: prepare data for machine learning
#================================================================#
# Retreive data
looplength = pd.read_csv('results_final/looplength.csv', index_col=0)
subtype = pd.read_csv('results_final/cel7_subtypes.csv', index_col=0)
looplength.index = range(len(looplength))
subtype.index = range(len(subtype))
output = 'results_final/cbm_blast_output.txt'
blast_cline = NcbiblastpCommandline(cmd=blastp_exe,
query=trecel7a_cbm,
db='cbm_database/cel7_cbm',
evalue=1e-3,
outfmt=7,
num_alignments=2000,
out=output)
stdout, stderr = blast_cline(
) # evalue of 1e-3 or less corresponds to bit score of 30 or more
# CBM data for all sequences
ex = pd.read_csv(
'results_final/cbm_blast_output.csv') # csv derived from txt file output
accession_cbm = list(ex['subject'])
accession_all = bioinf.get_accession(
'fasta/initial_blast/cel7_nr99_full_length.fasta')
has_cbm = [1 if x in accession_cbm else 0 for x in accession_all]
df = pd.DataFrame([accession_all, has_cbm], index=['accession',
'has_cbm']).transpose()
df.to_csv('results_final/has_cbm.csv')
# CBM distribution
df['subtype'] = pd.read_excel(
'results_final/cel7_subtypes.xlsx')['ncbi_pred_class']
df_cbh = df[df['subtype'] == 1]
df_egl = df[df['subtype'] == 0]
cbh_cbm = df_cbh.has_cbm.value_counts()[1]
cbh_nocbm = df_cbh.has_cbm.value_counts()[0]
egl_cbm = df_egl.has_cbm.value_counts()[1]
egl_nocbm = df_egl.has_cbm.value_counts()[0]