def main():
# Reads in a data set
df, tar, grp, _, _ = data_reader.read_main(raw=True)
# Code for DS 4 (GuihuaSun)
"""
missing = ['110608_TGCTCG_s_5', '110608_TGCTCG_s_1', '110608_TCGTCG_s_6', '110608_TCGTCG_s_5', '110602_TGCTCG_s_4', '110602_TGCTCG_s_3', '110602_TCGTCG_s_4', '110602_TCGTCG_s_3']
df = df.drop(missing)
tar = tar.drop(missing)
grp = grp.drop(missing)
#lst = extract_mirnas_r_guihuasun(df, ss, gs_name="_4")
"""
# Running extract_mirnas_r
ss = pd.DataFrame([tar, grp])
ss = ss.rename({
ss.axes[0][0]: 'groups',
ss.axes[0][1]: 'block'
},
axis='index').transpose()
df = df.transpose()
lst = extract_mirnas_r(df, ss, gs_name="_3")
# Creating gmt file
path = r'%s' % getcwd().replace('\\', '/') + "/Out/"
create_gmt_file(lst, path, new=True)
def test_make_density_plot():
df, _, _, length, _ = data_reader.read_main(raw=False)
features = df.axes[1]
samples = df.axes[0]
df = MiRNAScaler.choose_scaling(df, length)
df = pd.DataFrame(df, index=samples, columns=features)
df = df.transpose()
#make_density_plot(df)
latexify(columns=2)
make_full_density_plot(df, 'Density Plot of Hepmark Tissue')
def main():
# Import data
df, tar, grp, lengths, _ = data_reader.read_main(raw=True)
# Log transform keeping all columns as they will be used in the gsea.
df = df_utils.transform_sequence_to_microarray(df.T, all=True)
# Handling for microarray set 0 as this does not require log transformation
"""
df1, _, _ = data_reader.read_number(1)
df2, _, _ = data_reader.read_number(2)
df_len = len(df)
df = df_utils.merge_frames([df,df1,df2], drop=False)
df = df.head(df_len)
"""
sample = df.T
ss = gseapy.ssgsea(data=sample
, gene_sets='Out/gmt_hepmark.gmt'
, no_plot=True
, outdir='Out/gsea_hepmark'
, min_size=10)
# "When you run the gene set enrichment analysis, the GSEA software automatically normalizes
# the enrichment scores for variation in gene set size, as described in GSEA Statistics.
# Nevertheless, the normalization is not very accurate for extremely small or extremely
# large gene sets. For example, for gene sets with fewer than 10 genes, just 2 or 3 genes
# can generate significant results. Therefore, by default, GSEA ignores gene sets that
# contain fewer than 25 genes or more than 500 genes; defaults that are appropriate for
# datasets with 10,000 to 20,000 features. To change these default values, use the Max Size
# and Min Size parameters on the Run GSEA Page; however, keep in mind the possibility of
# inflated scorings for very small gene sets and inaccurate normalization for large ones."
# Setup df file
rows = []
for s in ss.resultsOnSamples:
row = [s]
for val in ss.resultsOnSamples[s]:
row.append(val)
rows.append(row)
columns = ['index']
columns.extend([x for x in ss.resultsOnSamples[s].axes[0]])
# NB : Do not use the res2d as this is the normalized score
# Create es file
df_out = pd.DataFrame(rows, columns = columns)
df_out.set_index('index', inplace=True)
path = r'%s' % getcwd().replace('\\','/') + "/Out/enrichment_scores/"
df_out.to_csv(path+"es_test.csv")
from sklearn import svm
from sklearn.metrics import roc_curve, auc
import matplotlib.pyplot as plt
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import GridSearchCV
from sklearn.model_selection import LeaveOneOut
from scipy import interp
import scaler as MiRNAScaler
from sklearn.ensemble import BaggingClassifier, AdaBoostClassifier
from sklearn.metrics import classification_report
from sklearn.feature_selection import RFECV
from sklearn.ensemble import RandomForestClassifier
from tqdm import tqdm
# Import data
df, target, group, lengths, es = data_reader.read_main()
features = df.axes[1]
samples = df.axes[0]
# Scale data
print(df.shape)
X = MiRNAScaler.choose_scaling(df, lengths)
df = pd.DataFrame(X, index=samples, columns=features)
print("DF shape", X.shape)
# Set seed for reproducability
np.random.seed(0)
n_samples, n_features = X.shape
import df_utils
from sklearn.preprocessing import StandardScaler
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import roc_curve, auc, roc_auc_score
from sklearn.metrics import accuracy_score
import matplotlib.pyplot as plt
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import GridSearchCV
from scipy import interp
import scaler as MiRNAScaler
from sklearn.neighbors import KNeighborsClassifier
from utils import latexify
from sklearn import svm
# Import data
df, target, group, lengths, _ = data_reader.read_main(raw=False)
features = df.axes[1]
samples = df.axes[0]
# Scale data
print(df.shape)
X = MiRNAScaler.choose_scaling(df, lengths)
df = pd.DataFrame(X, index=samples, columns=features)
print("DF shape", X.shape)
# Transform labels to real values
y = np.array([0 if l == 'Normal' else 1 if l == 'Tumor' else 2 for l in target])
df["target"] = y
# Set seed for reproducability
"""
Vegard Bjørgan 2019
Analyze one or more data sets and the effects of scaling miRNAs in a box plot
"""
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import data_reader
import scaler as MiRNAScaler
# Import data
df, tar, grp, _, _ = data_reader.read_main()
# Scale data
features = df.axes[1].values
#df[features] = MiRNAScaler.standard_scaler(df)
#df[features] = MiRNAScaler.robust_scaler(df)
df[features] = MiRNAScaler.minmax_scaler(df)
#df[features] = MiRNAScaler.quantile_scaler(df)
#df[features] = MiRNAScaler.individual_scaler(df.values)
data = []
row = []
for sample in df.axes[0]:
data.append(df.loc[sample])
row.append(sample)
# Extract 10 miRNA og show them in a box plot
last = 0
