rpotter6298
89 lines
3.5 KiB
Python
89 lines
3.5 KiB
Python
"""
|
|
Generate sample_sequencing_plan.xlsx
|
|
Labels every sample as Already sequenced / To be sequenced / Skip
|
|
at the chosen concentration threshold, with colour-coded rows.
|
|
"""
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
from openpyxl import load_workbook
|
|
from openpyxl.styles import PatternFill
|
|
|
|
THRESHOLD = 0.25
|
|
OUT_FILE = "sample_sequencing_plan.xlsx"
|
|
|
|
PILOT_IDS = {("A", n) for n in [1, 2, 3, 4, 5, 6]} | \
|
|
{("B", n) for n in [1, 2, 15, 16, 17, 18]}
|
|
|
|
FILLS = {
|
|
"Already sequenced": PatternFill("solid", fgColor="C6EFCE"), # green
|
|
"To be sequenced": PatternFill("solid", fgColor="FFEB9C"), # yellow
|
|
"Skip": PatternFill("solid", fgColor="FFC7CE"), # red/pink
|
|
}
|
|
|
|
# ── load data ─────────────────────────────────────────────────────────────────
|
|
patients = pd.read_excel("patients.xlsx", usecols=["Number", "Exf"])
|
|
patients = patients.dropna(subset=["Number"])
|
|
patients["Number"] = patients["Number"].astype(int)
|
|
patients["Exf"] = patients["Exf"].astype(int)
|
|
|
|
def parse_conc(v):
|
|
if isinstance(v, str): return np.nan
|
|
try: return float(v)
|
|
except: return np.nan
|
|
|
|
qa = pd.read_excel("BEA25P077_RP.xlsx", sheet_name="A-samples")
|
|
qb = pd.read_excel("BEA25P077_RP.xlsx", sheet_name="B-samples")
|
|
qa["conc_val"] = qa["conc (ng/ul)"].apply(parse_conc)
|
|
qb["conc_val"] = qb["Conc [ng/ul]"].apply(parse_conc)
|
|
qa["Number"] = pd.to_numeric(qa["ID"].str.extract(r"^(\d+)A")[0], errors="coerce")
|
|
qb["Number"] = pd.to_numeric(qb["ID"].str.extract(r"^(\d+)B")[0], errors="coerce")
|
|
qa = qa.dropna(subset=["Number"]); qa["Number"] = qa["Number"].astype(int); qa["tissue"] = "A"
|
|
qb = qb.dropna(subset=["Number"]); qb["Number"] = qb["Number"].astype(int); qb["tissue"] = "B"
|
|
qa = qa.merge(patients, on="Number", how="left")
|
|
qb = qb.merge(patients, on="Number", how="left")
|
|
|
|
# ── build plan ────────────────────────────────────────────────────────────────
|
|
rows = []
|
|
for _, r in pd.concat([qa, qb], ignore_index=True).iterrows():
|
|
tissue, num, conc = r["tissue"], r["Number"], r["conc_val"]
|
|
if (tissue, num) in PILOT_IDS:
|
|
status = "Already sequenced"
|
|
elif pd.isna(conc) or conc < THRESHOLD:
|
|
status = "Skip"
|
|
else:
|
|
status = "To be sequenced"
|
|
rows.append({
|
|
"Sample": f"{num}{tissue}_G2",
|
|
"Patient": num,
|
|
"Tissue": tissue,
|
|
"Conc (ng/ul)": conc,
|
|
"Status": status,
|
|
})
|
|
|
|
df = pd.DataFrame(rows).sort_values(["Tissue", "Patient"])
|
|
|
|
# ── write Excel ───────────────────────────────────────────────────────────────
|
|
df.to_excel(OUT_FILE, index=False)
|
|
|
|
wb = load_workbook(OUT_FILE)
|
|
ws = wb.active
|
|
|
|
# auto-width columns
|
|
for col_cells in ws.columns:
|
|
width = max(len(str(c.value)) if c.value is not None else 0 for c in col_cells)
|
|
ws.column_dimensions[col_cells[0].column_letter].width = width + 4
|
|
|
|
# colour every row based on Status (Status is the last column)
|
|
status_col = df.columns.get_loc("Status") + 1 # 1-indexed
|
|
for row in ws.iter_rows(min_row=2):
|
|
status = row[status_col - 1].value
|
|
fill = FILLS.get(status)
|
|
if fill:
|
|
for cell in row:
|
|
cell.fill = fill
|
|
|
|
wb.save(OUT_FILE)
|
|
print(f"Saved {OUT_FILE} ({len(df)} samples)")
|
|
print(df["Status"].value_counts().to_string())
|