Skip to content

[DRAFT][DANGER] Reworked pyplot usage + formatting + code readability #2

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
AlexanderButyaev wants to merge 3 commits into
base: main
Choose a base branch
from
Open

[DRAFT][DANGER] Reworked pyplot usage + formatting + code readability #2

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c0a4b5c
test MPLBACKEND Agg before everything
AlexanderButyaev Sep 17, 2025
28588df
removed plt/global change of mpl backend + use Figure / FigureCanvasA…
AlexanderButyaev Sep 19, 2025
7d3aaf4
reworked almost all plot related stuff
AlexanderButyaev Sep 22, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
276 changes: 197 additions & 79 deletions DashML/Basecall/Basecall_Bias.py
View file
Open in desktop

Large diffs are not rendered by default.

424 changes: 280 additions & 144 deletions DashML/Basecall/Basecall_Plot.py
View file
Open in desktop

Large diffs are not rendered by default.

1,129 changes: 852 additions & 277 deletions DashML/GUI/DT.py
View file
Open in desktop

Large diffs are not rendered by default.

87 changes: 54 additions & 33 deletions DashML/Landscape/Cluster/Centroid_Analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,7 @@
import platform
import numpy as np
import pandas as pd
import matplotlib
matplotlib.use("Agg")
import matplotlib.pyplot as plt

import seaborn as sns
from scipy.cluster.hierarchy import dendrogram, linkage
from sklearn.cluster import AgglomerativeClustering, KMeans
Expand All @@ -13,57 +11,80 @@
from kmodes.kmodes import KModes


pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)
pd.set_option("display.max_columns", None)
pd.set_option("display.max_rows", None)

if platform.system() == 'Linux':
if platform.system() == "Linux":
##### server #####
data_path = "/home/jwbear/projects/def-jeromew/jwbear/dendrogram/Out/"
save_path = "/home/jwbear/projects/def-jeromew/jwbear/dendrogram/Dendrogram/Dendrogram_Out/"
save_path = (
"/home/jwbear/projects/def-jeromew/jwbear/dendrogram/Dendrogram/Dendrogram_Out/"
)
else:
data_path = sys.path[1] + "/DashML/Deconvolution/Dendrogram/Putative_Structures/"
out_path = sys.path[1] + "/DashML/Deconvolution/Out/"
save_path = sys.path[1] + "/DashML/Deconvolution/Dendrogram/Putative_Structures/"


def get_mfe_distances(seq='HCV'):
def get_mfe_distances(seq="HCV"):
# native conformation mfes from RNAeval
df_native = pd.read_csv(data_path + "native_mfes.txt", names=['sequence', 'mfe'],
dtype={'sequence':str, 'mfe': float},
skipinitialspace=True)
df_native = pd.read_csv(
data_path + "native_mfes.txt",
names=["sequence", "mfe"],
dtype={"sequence": str, "mfe": float},
skipinitialspace=True,
)
# putative conformations mfes from RNAeval, multiple can take average?
df_putative = pd.read_csv(data_path + "putative_mfes.txt", names=['sequence', 'cluster_type', 'cluster_number', 'mfe'],
dtype={'sequence':str, 'cluster_type': str, 'cluster_number':int, 'mfe': float},
skipinitialspace=True)
#cluster sizes
df_counts = pd.read_csv("/Users/timshel/structure_landscapes/DashML/Deconvolution/Dendrogram/Clusters/"
"cluster_counts.csv", names=['sequence', 'cluster_type', 'cluster_number', 'cluster_size'],
dtype={'sequence': str, 'cluster_type': str, 'cluster_number': int, 'cluster_size': int},
skipinitialspace=True)
df_putative = pd.read_csv(
data_path + "putative_mfes.txt",
names=["sequence", "cluster_type", "cluster_number", "mfe"],
dtype={
"sequence": str,
"cluster_type": str,
"cluster_number": int,
"mfe": float,
},
skipinitialspace=True,
)
# cluster sizes
df_counts = pd.read_csv(
"/Users/timshel/structure_landscapes/DashML/Deconvolution/Dendrogram/Clusters/"
"cluster_counts.csv",
names=["sequence", "cluster_type", "cluster_number", "cluster_size"],
dtype={
"sequence": str,
"cluster_type": str,
"cluster_number": int,
"cluster_size": int,
},
skipinitialspace=True,
)

#merge data
df_counts['mfe'] = 0
df_putative['cluster_size'] = 0
df = df_putative.merge(df_counts, on=['sequence', 'cluster_type', 'cluster_number'], how='left')
df.drop(columns=['mfe_y', 'cluster_size_x'], inplace=True)
df.rename(columns={'mfe_x':'mfe', 'cluster_size_y': 'cluster_size'}, inplace=True)
df = df.sort_values(by=['sequence', 'cluster_type', 'cluster_number'])
# merge data
df_counts["mfe"] = 0
df_putative["cluster_size"] = 0
df = df_putative.merge(
df_counts, on=["sequence", "cluster_type", "cluster_number"], how="left"
)
df.drop(columns=["mfe_y", "cluster_size_x"], inplace=True)
df.rename(columns={"mfe_x": "mfe", "cluster_size_y": "cluster_size"}, inplace=True)
df = df.sort_values(by=["sequence", "cluster_type", "cluster_number"])

# get delta(native mfe, cluster mfe)
# todo add seq variable loop
native_mfe = df_native.loc[df_native['sequence']==seq, 'mfe'][0]
df['native_mfe'] = native_mfe
native_mfe = df_native.loc[df_native["sequence"] == seq, "mfe"][0]
df["native_mfe"] = native_mfe
# negative means mfe of cluster is more stable than native conformation
# a more negative mfe is more stable
# a more positive mfe is less stable
# native should be most negative, more negative the better in clusters
df['delta_native'] = np.subtract(np.abs(df['native_mfe']),np.abs(df['mfe']))
df["delta_native"] = np.subtract(np.abs(df["native_mfe"]), np.abs(df["mfe"]))
print(df)

#get_mfe_distances()
#sys.exit(0)

# get_mfe_distances()
# sys.exit(0)


#get_cluster_hamming_distance()
#distance_matrix()
# get_cluster_hamming_distance()
# distance_matrix()
Loading