79739669_20260330_IC50__LS180_GGFG-VA-VC-Exa_GGFG-DXd — B5 vs Syn — 2026-03-30

B5 vs Syn
Published

March 30, 2026

IC50 & Growth Kinetics — LS180 Conjugates

Analysis of PCM_LSConj data: 8 drugs across 2 plates, 6 timepoints.
Two metrics: Fold-D0 and raw Total Cell Area.
IC50 computed two ways: LL.4 curve fit and direct interpolation at 50% viable.

Show code
from IPython.display import display, Image as IPImage
import os
import zipfile
import re
import pandas as pd
import numpy as np
from scipy.optimize import curve_fit
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')

sns.set_style('whitegrid')
plt.rcParams.update({'figure.figsize': (10, 6), 'font.size': 12})

# =====================================================================
#  USER INPUT — change only this section to run a different experiment
# =====================================================================
BASE_DIR     = '/home/dlee/gitpcm/2911_RnD/IC50_growth_kinetics'
DATA_SUBDIR  = '20260330_IC50__LS180_GGFG-VA-VC-Exa_GGFG-DXd'
TEST_AB      = 'B5'    # test article antibody prefix
ISO_AB       = 'Syn'   # isotype control antibody prefix
R2_THRESHOLD = 0.5     # minimum R² for a "reliable" LL.4 fit
# =====================================================================

DATA_DIR  = os.path.join(BASE_DIR, DATA_SUBDIR)
PLOT_DIR  = os.path.join(DATA_DIR, 'plots')
os.makedirs(PLOT_DIR, exist_ok=True)
plot_counter = [0]

def save_fig(title=''):
    plot_counter[0] += 1
    fname = os.path.join(PLOT_DIR, f'plot_{plot_counter[0]:02d}.png')
    plt.savefig(fname, dpi=120, bbox_inches='tight')
    plt.close()
    display(IPImage(filename=fname))

# Auto-discover zip file and plate layout CSVs in DATA_DIR
zip_files = sorted([f for f in os.listdir(DATA_DIR) if f.endswith('.zip')])
assert len(zip_files) == 1, f'Expected 1 zip in {DATA_DIR}, found {len(zip_files)}: {zip_files}'
ZIP_PATH    = os.path.join(DATA_DIR, zip_files[0])
ZIP_STEM    = os.path.splitext(zip_files[0])[0]
EXTRACT_DIR = os.path.join(DATA_DIR, ZIP_STEM + '_extracted')

PLATE_LAYOUTS = sorted([f for f in os.listdir(DATA_DIR)
                        if re.match(r'Plate\d+_layout\.csv', f)])
assert len(PLATE_LAYOUTS) >= 1, f'No Plate*_layout.csv found in {DATA_DIR}'

print(f'Data dir : {DATA_DIR}')
print(f'Zip      : {ZIP_PATH} ({os.path.exists(ZIP_PATH)})')
print(f'Plates   : {len(PLATE_LAYOUTS)} layout(s) — {PLATE_LAYOUTS}')

Load Data from Zip

Show code
# ===========================================================================
# 1. Extract zip and load confluency data
# ===========================================================================
print('\n=== 1. Extract zip and load confluency data ===')
os.makedirs(EXTRACT_DIR, exist_ok=True)
with zipfile.ZipFile(ZIP_PATH, 'r') as z:
    z.extractall(EXTRACT_DIR)

csv_files = sorted([f for f in os.listdir(EXTRACT_DIR) if f.endswith('.csv')])
print(f'{len(csv_files)} CSV files extracted')

# Flexible pattern: matches _Plate1_D0, _P1_D0, _P1_D07, etc.
fname_pattern = re.compile(r'.*_P(?:late)?(\d+)_D(\d+)\.csv', re.IGNORECASE)

frames = []
seen = set()
for fname in csv_files:
    m = fname_pattern.match(fname)
    if not m:
        continue
    plate_num = int(m.group(1))
    day       = int(m.group(2))
    key = (plate_num, day)
    if key in seen:
        continue
    seen.add(key)
    tmp = pd.read_csv(os.path.join(EXTRACT_DIR, fname), index_col=0)
    tmp.index.name = 'Well'
    tmp = tmp.reset_index()
    tmp['Plate'] = plate_num
    tmp['Day']   = day
    frames.append(tmp)

df_raw = pd.concat(frames, ignore_index=True)
df_raw.rename(columns={'Total cell area': 'TotalCellArea'}, inplace=True)

print(f'Combined raw data: {df_raw.shape[0]} rows  x  {df_raw.shape[1]} cols')
print(f'Plates: {sorted(df_raw.Plate.unique())}   Days: {sorted(df_raw.Day.unique())}')

Merge Plate Layouts

Show code
# ===========================================================================
# 2. Load plate layouts and merge
# ===========================================================================
print('\n=== 2. Load plate layouts and merge ===')
layout_frames = []
for lf in PLATE_LAYOUTS:
    plate_num = int(re.search(r'Plate(\d+)', lf).group(1))
    tmp = pd.read_csv(os.path.join(DATA_DIR, lf))
    tmp.rename(columns={'Cell': 'Well'}, inplace=True)
    tmp['Plate'] = plate_num
    layout_frames.append(tmp)
    print(f'Plate {plate_num} drugs: {sorted(tmp.Drug.unique())}')

layouts = pd.concat(layout_frames, ignore_index=True)
print(f'Layout entries: {len(layouts)}  ({len(PLATE_LAYOUTS)} plates)')

df = df_raw.merge(layouts[['Well', 'Drug', 'Conc', 'Plate']],
                  on=['Well', 'Plate'], how='left')

unmatched = df.Drug.isna().sum()
if unmatched > 0:
    print(f'WARNING: {unmatched} wells did not match a layout entry')
else:
    print('All wells matched their layout.')

print(f'Drugs: {sorted(df.Drug.dropna().unique())}')
print(f'Concentrations: {sorted(df.Conc.dropna().unique())}')

# Auto-derive concentration parameters from the data
nonzero_concs = df.loc[df.Conc > 0, 'Conc']
CONC_MIN   = nonzero_concs.min()
CONC_MAX   = nonzero_concs.max()
PSEUDO_CONC = CONC_MIN / 10.0

df['Conc_orig'] = df['Conc'].copy()
df.loc[df.Conc == 0, 'Conc'] = PSEUDO_CONC
print(f'Conc range: {CONC_MIN:.4g} – {CONC_MAX:.4g} nM')
print(f'Conc==0 replaced with pseudo-conc {PSEUDO_CONC:.4g} nM')

Fold-D0 Normalization

Show code
# ===========================================================================
# 3. Fold-D0 normalization
# ===========================================================================
print('\n=== 3. Fold-D0 normalization ===')
d0_confl = df[df.Day == 0][['Plate', 'Well', 'Confluence']].rename(
    columns={'Confluence': 'Confluence_D0'})
d0_tca = df[df.Day == 0][['Plate', 'Well', 'TotalCellArea']].rename(
    columns={'TotalCellArea': 'TCA_D0'})

df = df.merge(d0_confl, on=['Plate', 'Well'], how='left')
df = df.merge(d0_tca, on=['Plate', 'Well'], how='left')
df['FoldD0'] = df['Confluence'] / df['Confluence_D0']
df['FoldD0_TCA'] = df['TotalCellArea'] / df['TCA_D0']

print('All wells have D0 baseline.' if df.Confluence_D0.isna().sum() == 0
      else f'WARNING: {df.Confluence_D0.isna().sum()} rows missing D0')
print(f'Fold-D0 stats by Day:')
print(df.groupby('Day')['FoldD0'].describe().round(3).to_string())

Drug & Color Setup

Show code
# ===========================================================================
# 4. Drug/color mapping (all 8 drugs together)
# ===========================================================================
all_drugs = sorted(df.Drug.dropna().unique())
drug_colors = dict(zip(all_drugs, sns.color_palette('tab10', len(all_drugs))))
fit_days = [d for d in sorted(df.Day.unique()) if d > 0]
all_days = sorted(df.Day.unique())

print(f'\n{len(all_drugs)} drugs across both plates: {all_drugs}')

Growth Kinetics Plots

Show code
# ===========================================================================
# 5. Growth kinetics plots (per drug, combined plates)
# ===========================================================================
print('\n=== 4. Growth kinetics plots ===')
for drug in all_drugs:
    sub = df[df.Drug == drug].copy()
    concs = sorted(sub.Conc.unique())

    fig, axes = plt.subplots(1, 2, figsize=(16, 5), sharey=False)

    for ax, metric, ylabel in [
        (axes[0], 'FoldD0',        'Fold D0 (Confluence)'),
        (axes[1], 'TotalCellArea', 'Total Cell Area (mm²)'),
    ]:
        for conc in concs:
            csub = sub[sub.Conc == conc]
            means = csub.groupby('Day')[metric].mean()
            sds   = csub.groupby('Day')[metric].std()
            lbl = 'untreated' if conc == PSEUDO_CONC else f'{conc} nM'
            ax.errorbar(means.index, means.values, yerr=sds.values,
                        marker='o', capsize=3, label=lbl)
        ax.set_xlabel('Day')
        ax.set_ylabel(ylabel)
        ax.set_xticks(all_days)
        ax.legend(title='Conc', fontsize=8, title_fontsize=9)

    fig.suptitle(f'{drug} — Growth Kinetics', fontsize=14)
    plt.tight_layout()
    save_fig()

LL.4 Model & Interpolation Functions

Show code
# ===========================================================================
# 6. LL.4 fitting functions
# ===========================================================================
print('\n=== 5. LL.4 model ===')

def ll4(x, slope, lower, upper, ec50):
    return lower + (upper - lower) / (1.0 + (x / ec50) ** slope)


def compute_r2(y_obs, y_pred):
    ss_res = np.sum((y_obs - y_pred) ** 2)
    ss_tot = np.sum((y_obs - np.mean(y_obs)) ** 2)
    if ss_tot == 0:
        return 0.0
    return 1.0 - ss_res / ss_tot


def fit_ll4(conc, response, p0=None):
    """Two-pass LL.4 fit with residual-based outlier removal.

    Pass 1: fit all data.
    Pass 2: remove points whose residuals fall outside 1.5x IQR, then refit.
    This catches concentration groups that are anomalous relative to the
    dose-response trend (e.g. cell fragmentation artefacts at high conc).
    """
    conc = np.asarray(conc, dtype=float)
    response = np.asarray(response, dtype=float)
    mask = (conc > 0) & np.isfinite(response)
    conc, response = conc[mask], response[mask]
    if len(conc) < 4 or len(np.unique(conc)) < 3:
        return None, None

    cmin, cmax = conc.min(), conc.max()
    if p0 is None:
        p0 = [1.0, np.min(response), np.max(response), np.median(conc)]

    bounds = (
        [0.01,   -np.inf, -np.inf, cmin * 0.01],
        [np.inf,  np.inf,  np.inf, cmax * 100 ]
    )

    try:
        popt, _ = curve_fit(ll4, conc, response, p0=p0,
                            maxfev=10000, bounds=bounds)
    except Exception:
        return None, None

    # Residual-based outlier removal (1.5x IQR on residuals)
    residuals = response - ll4(conc, *popt)
    q1, q3 = np.percentile(residuals, 25), np.percentile(residuals, 75)
    iqr = q3 - q1
    keep = (residuals >= q1 - 1.5 * iqr) & (residuals <= q3 + 1.5 * iqr)

    n_removed = (~keep).sum()
    if n_removed > 0 and keep.sum() >= 4 and len(np.unique(conc[keep])) >= 3:
        conc_clean, resp_clean = conc[keep], response[keep]
        cmin2, cmax2 = conc_clean.min(), conc_clean.max()
        bounds2 = (
            [0.01,   -np.inf, -np.inf, cmin2 * 0.01],
            [np.inf,  np.inf,  np.inf, cmax2 * 100 ]
        )
        p0_2 = list(popt)
        try:
            popt, _ = curve_fit(ll4, conc_clean, resp_clean, p0=p0_2,
                                maxfev=10000, bounds=bounds2)
            y_pred = ll4(conc_clean, *popt)
            r2 = compute_r2(resp_clean, y_pred)
            return popt, r2
        except Exception:
            pass

    y_pred = ll4(conc, *popt)
    r2 = compute_r2(response, y_pred)
    return popt, r2


def classify_ic50(row):
    if row['R2'] < R2_THRESHOLD:
        return 'poor fit'
    if row['IC50_nM'] < CONC_MIN * 0.5:
        return f'<{CONC_MIN} nM'
    if row['IC50_nM'] > CONC_MAX * 2:
        return f'>{CONC_MAX} nM'
    return f"{row['IC50_nM']:.2f}"


def interpolate_ic50(concs, pct_viable, target=50.0):
    """
    Find concentration where mean %Viable crosses `target` (default 50%).
    Linear interpolation on log10(conc).
    Drops trailing high-conc points where the curve reverses upward
    (artefact from cell fragmentation).
    Returns NaN if the curve never crosses the target.
    """
    means = pct_viable.groupby(concs).mean()
    c = np.array(means.index, dtype=float)
    v = np.array(means.values, dtype=float)
    order = np.argsort(c)
    c, v = c[order], v[order]

    # Trim trailing reversals: if response goes UP at high concentrations,
    # drop those points (likely fragmentation artefact)
    while len(v) > 2 and v[-1] > v[-2]:
        c, v = c[:-1], v[:-1]

    for i in range(len(v) - 1):
        if (v[i] >= target and v[i+1] < target) or \
           (v[i] <= target and v[i+1] > target):
            log_c1, log_c2 = np.log10(c[i]), np.log10(c[i+1])
            frac = (target - v[i]) / (v[i+1] - v[i])
            return 10 ** (log_c1 + frac * (log_c2 - log_c1))

    if v[-1] < target and v[0] >= target:
        return c[-1]
    return np.nan


print(f'LL.4 defined.  R² threshold = {R2_THRESHOLD}')
print('Interpolation IC50 function defined.')
print('Residual-based outlier removal (1.5x IQR) active for curve fitting.')

Dose-Response Fitting & Plotting (Both Metrics)

Show code
# ===========================================================================
# 7. Dose-response fitting & plotting — BOTH metrics
# ===========================================================================
METRICS = {
    'FoldD0': {
        'col': 'FoldD0',
        'ylabel_dr': 'Fold D0 (Confluence)',
        'ylabel_pv': '% Viable (Fold-D0 normalized)',
    },
    'TotalCellArea': {
        'col': 'TotalCellArea',
        'ylabel_dr': 'Total Cell Area (mm²)',
        'ylabel_pv': '% Viable (TCA normalized)',
    },
}

all_ic50_tables = {}

for metric_name, minfo in METRICS.items():
    col = minfo['col']
    print(f'\n{"="*60}')
    print(f'=== METRIC: {metric_name} ===')
    print(f'{"="*60}')

    # --- 7a. Dose-response plots (raw metric) ---
    print(f'\n--- Dose-response plots ({metric_name}) ---')
    fit_params_dr = {}
    ic50_dr_records = []

    for drug in all_drugs:
        for day in fit_days:
            sub = df[(df.Drug == drug) & (df.Day == day)].copy()
            sub = sub.dropna(subset=['Conc', col])
            if sub.empty:
                continue
            popt, r2 = fit_ll4(sub.Conc.values, sub[col].values)
            if popt is not None:
                fit_params_dr[(drug, day)] = popt
                ic50_dr_records.append({
                    'Drug': drug, 'Day': day,
                    'IC50_nM': popt[3], 'Slope': popt[0],
                    'Lower': popt[1], 'Upper': popt[2], 'R2': r2,
                })
            else:
                ic50_dr_records.append({
                    'Drug': drug, 'Day': day,
                    'IC50_nM': np.nan, 'Slope': np.nan,
                    'Lower': np.nan, 'Upper': np.nan, 'R2': np.nan,
                })

    for day in fit_days:
        fig, ax = plt.subplots(figsize=(12, 7))
        for drug in all_drugs:
            sub = df[(df.Drug == drug) & (df.Day == day)].copy()
            sub = sub.dropna(subset=[col])
            if sub.empty:
                continue
            means = sub.groupby('Conc')[col].mean()
            sds   = sub.groupby('Conc')[col].std()
            ax.errorbar(means.index, means.values, yerr=sds.values,
                        fmt='o', capsize=3, color=drug_colors[drug], label=drug)
            key = (drug, day)
            if key in fit_params_dr:
                popt = fit_params_dr[key]
                x_pred = np.geomspace(PSEUDO_CONC, means.index.max(), 200)
                y_pred = ll4(x_pred, *popt)
                ax.plot(x_pred, y_pred, '-', color=drug_colors[drug], linewidth=1.5)

        ax.set_xscale('log')
        ax.set_xlabel('Concentration (nM, log scale)')
        ax.set_ylabel(minfo['ylabel_dr'])
        ax.set_title(f'Day {day} — Dose Response ({metric_name})')
        ax.legend(fontsize=8, loc='best')
        plt.tight_layout()
        save_fig()

    df_ic50_dr = pd.DataFrame(ic50_dr_records)
    df_ic50_dr['Reliable'] = (
        (df_ic50_dr['R2'] >= R2_THRESHOLD) &
        (df_ic50_dr['IC50_nM'] >= CONC_MIN * 0.5) &
        (df_ic50_dr['IC50_nM'] <= CONC_MAX * 2)
    )
    df_ic50_dr['Status'] = df_ic50_dr.apply(classify_ic50, axis=1)

    print(f'\n  IC50 ({metric_name} direct): {df_ic50_dr.Reliable.sum()} reliable '
          f'of {len(df_ic50_dr)}')

    # --- 7b. %Viable calculation ---
    pv_col = f'PctViable_{metric_name}'
    untx_mean = (
        df[df.Conc_orig == 0]
        .groupby(['Plate', 'Drug', 'Day'])[col]
        .mean()
        .reset_index()
        .rename(columns={col: f'UntxMean_{metric_name}'})
    )
    untx_col = f'UntxMean_{metric_name}'
    df = df.merge(untx_mean, on=['Plate', 'Drug', 'Day'], how='left')
    df[pv_col] = 100.0 * df[col] / df[untx_col]

    # --- 7c. Interpolated IC50 (no curve fitting) ---
    interp_records = []
    for drug in all_drugs:
        for day in fit_days:
            sub = df[(df.Drug == drug) & (df.Day == day)].copy()
            sub = sub.dropna(subset=['Conc', pv_col])
            if sub.empty:
                continue
            ic50_interp = interpolate_ic50(sub.Conc, sub[pv_col], target=50.0)
            interp_records.append({
                'Drug': drug, 'Day': day, 'IC50_interp': ic50_interp,
            })
    df_interp = pd.DataFrame(interp_records)
    all_ic50_tables[f'{metric_name}_interpolated'] = df_interp

    print(f'\n  Interpolated IC50 ({metric_name}): '
          f'{df_interp.IC50_interp.notna().sum()} of {len(df_interp)} crossed 50%')

    # --- 7d. %Viable IC50 fitting (LL.4) ---
    fit_params_pv = {}
    ic50_pv_records = []

    for drug in all_drugs:
        for day in fit_days:
            sub = df[(df.Drug == drug) & (df.Day == day)].copy()
            sub = sub.dropna(subset=['Conc', pv_col])
            if sub.empty:
                continue
            popt, r2 = fit_ll4(sub.Conc.values, sub[pv_col].values)
            if popt is not None:
                fit_params_pv[(drug, day)] = popt
                ic50_pv_records.append({
                    'Drug': drug, 'Day': day,
                    'IC50_nM': popt[3], 'Slope': popt[0],
                    'Lower': popt[1], 'Upper': popt[2], 'R2': r2,
                })
            else:
                ic50_pv_records.append({
                    'Drug': drug, 'Day': day,
                    'IC50_nM': np.nan, 'Slope': np.nan,
                    'Lower': np.nan, 'Upper': np.nan, 'R2': np.nan,
                })

    # --- 7e. %Viable dose-response plots with interpolated IC50 markers ---
    for day in fit_days:
        fig, ax = plt.subplots(figsize=(12, 7))
        for drug in all_drugs:
            sub = df[(df.Drug == drug) & (df.Day == day)].copy()
            sub = sub.dropna(subset=[pv_col])
            if sub.empty:
                continue
            means = sub.groupby('Conc')[pv_col].mean()
            sds   = sub.groupby('Conc')[pv_col].std()
            ax.errorbar(means.index, means.values, yerr=sds.values,
                        fmt='o', capsize=3, color=drug_colors[drug], label=drug)

            # Overlay LL.4 fitted curve if available
            key = (drug, day)
            if key in fit_params_pv:
                popt = fit_params_pv[key]
                x_pred = np.geomspace(PSEUDO_CONC, means.index.max(), 200)
                y_pred = ll4(x_pred, *popt)
                ax.plot(x_pred, y_pred, '-', color=drug_colors[drug], linewidth=1.5)
            else:
                sorted_means = means.sort_index()
                ax.plot(sorted_means.index, sorted_means.values, '-',
                        color=drug_colors[drug], linewidth=1, alpha=0.6)

            # Mark interpolated IC50 with a diamond
            row = df_interp[(df_interp.Drug == drug) & (df_interp.Day == day)]
            if not row.empty and pd.notna(row.IC50_interp.values[0]):
                ic50_val = row.IC50_interp.values[0]
                ax.plot(ic50_val, 50, 'D', color=drug_colors[drug],
                        markersize=10, markeredgecolor='black', markeredgewidth=1,
                        zorder=5)

        ax.set_xscale('log')
        ax.set_xlabel('Concentration (nM, log scale)')
        ax.set_ylabel(minfo['ylabel_pv'])
        ax.set_title(f'Day {day} — %Viable ({metric_name}) — diamonds = interpolated IC50')
        ax.axhline(50, color='red', ls='--', alpha=0.7, label='50% viable')
        ax.axhline(100, color='grey', ls='--', alpha=0.3)
        ax.legend(fontsize=8, loc='best')
        plt.tight_layout()
        save_fig()

    df_ic50_pv = pd.DataFrame(ic50_pv_records)
    df_ic50_pv['Reliable'] = (
        (df_ic50_pv['R2'] >= R2_THRESHOLD) &
        (df_ic50_pv['IC50_nM'] >= CONC_MIN * 0.5) &
        (df_ic50_pv['IC50_nM'] <= CONC_MAX * 2)
    )
    df_ic50_pv['Status'] = df_ic50_pv.apply(classify_ic50, axis=1)

    print(f'  IC50 (%Viable {metric_name}): {df_ic50_pv.Reliable.sum()} reliable '
          f'of {len(df_ic50_pv)}')

    all_ic50_tables[f'{metric_name}_direct'] = df_ic50_dr
    all_ic50_tables[f'{metric_name}_pctViable'] = df_ic50_pv

Trellis: Test vs Isotype by Linker-Payload

Show code
# ===========================================================================
# 7f. Trellis: Test vs Isotype per Linker-Payload, one subplot per Day
# ===========================================================================
print('\n=== Trellis: dose-response by LP ===')

def _parse_drug(name):
    for ab in [TEST_AB, ISO_AB]:
        if name.startswith(ab + '-'):
            return ab, name[len(ab)+1:]
    return None, None

_drug_ab = {d: _parse_drug(d) for d in all_drugs}
_test_drugs = {lp: d for d, (ab, lp) in _drug_ab.items() if ab == TEST_AB}
_iso_drugs  = {lp: d for d, (ab, lp) in _drug_ab.items() if ab == ISO_AB}
_matched_lps = sorted(set(_test_drugs) & set(_iso_drugs))
print(f'  Matched LPs: {_matched_lps}')

for metric_name, minfo in METRICS.items():
    col = minfo['col']
    pv_col = f'PctViable_{metric_name}'

    for lp in _matched_lps:
        test_drug = _test_drugs[lp]
        iso_drug  = _iso_drugs[lp]

        # Pre-scan: find the global y-range across all days for this LP
        all_vals = []
        for day in fit_days:
            for drug in [test_drug, iso_drug]:
                sub = df[(df.Drug == drug) & (df.Day == day)].dropna(subset=[pv_col])
                if not sub.empty:
                    means = sub.groupby('Conc')[pv_col].mean()
                    sds   = sub.groupby('Conc')[pv_col].std().fillna(0)
                    all_vals.extend((means + sds).tolist())
                    all_vals.extend((means - sds).tolist())
        if not all_vals:
            continue
        y_lo = min(all_vals)
        y_hi = max(all_vals)
        margin = (y_hi - y_lo) * 0.08
        ylim = (y_lo - margin, y_hi + margin)

        ncols = len(fit_days)
        fig, axes = plt.subplots(1, ncols, figsize=(4 * ncols, 5), sharey=True)
        if ncols == 1:
            axes = [axes]

        for ax, day in zip(axes, fit_days):
            for drug, lstyle, mrkr in [(test_drug, '-', 'o'), (iso_drug, '--', 's')]:
                sub = df[(df.Drug == drug) & (df.Day == day)].dropna(subset=[pv_col])
                if sub.empty:
                    continue
                means = sub.groupby('Conc')[pv_col].mean()
                sds   = sub.groupby('Conc')[pv_col].std()
                ax.errorbar(means.index, means.values, yerr=sds.values,
                            fmt=mrkr, capsize=3, color=drug_colors[drug],
                            label=drug)

                key = (drug, day)
                if key in fit_params_pv:
                    popt = fit_params_pv[key]
                    x_pred = np.geomspace(PSEUDO_CONC, means.index.max(), 200)
                    y_pred = ll4(x_pred, *popt)
                    ax.plot(x_pred, y_pred, lstyle, color=drug_colors[drug],
                            linewidth=1.5)

            ax.set_xscale('log')
            ax.set_ylim(ylim)
            ax.set_title(f'Day {day}', fontsize=11)
            ax.set_xlabel('Conc (nM)')
            ax.axhline(50, color='red', ls=':', alpha=0.5)
            ax.axhline(100, color='grey', ls=':', alpha=0.3)
            if ax is axes[0]:
                ax.set_ylabel(minfo['ylabel_pv'])
            ax.legend(fontsize=7, loc='best')

        fig.suptitle(f'{lp} — %Viable ({metric_name}) — {TEST_AB} vs {ISO_AB}',
                     fontsize=14, y=1.02)
        plt.tight_layout()
        save_fig()

Trellis: Therapeutic Index by Concentration

Show code
# ===========================================================================
# 7g. Trellis: Therapeutic Index (Syn/B5) per concentration, per LP × Day
# ===========================================================================
print('\n=== Trellis: TI by concentration ===')

for metric_name, minfo in METRICS.items():
    pv_col = f'PctViable_{metric_name}'

    # Pre-scan: compute TI at every concentration for every LP × day
    # to find per-LP y-range
    _ti_data = {}  # (lp, day) -> (conc_array, ti_array)
    _lp_yranges = {}  # lp -> (ymin, ymax)

    for lp in _matched_lps:
        test_drug = _test_drugs[lp]
        iso_drug  = _iso_drugs[lp]
        all_ti = []

        for day in fit_days:
            sub_t = df[(df.Drug == test_drug) & (df.Day == day)].dropna(subset=[pv_col])
            sub_i = df[(df.Drug == iso_drug)  & (df.Day == day)].dropna(subset=[pv_col])
            if sub_t.empty or sub_i.empty:
                continue
            mean_t = sub_t.groupby('Conc')[pv_col].mean()
            mean_i = sub_i.groupby('Conc')[pv_col].mean()
            shared_concs = sorted(set(mean_t.index) & set(mean_i.index))
            if not shared_concs:
                continue
            concs = np.array(shared_concs)
            ti = np.array([mean_i[c] / mean_t[c] if mean_t[c] != 0 else np.nan
                           for c in shared_concs])
            _ti_data[(lp, day)] = (concs, ti)
            all_ti.extend(ti[np.isfinite(ti)].tolist())

        if all_ti:
            _lp_yranges[lp] = (min(all_ti), max(all_ti))

    if not _lp_yranges:
        print(f'  No TI data for {metric_name}')
        continue

    nrows = len(_matched_lps)
    ncols = len(fit_days)
    fig, axes = plt.subplots(nrows, ncols,
                             figsize=(3.5 * ncols, 3.5 * nrows),
                             squeeze=False)

    for row, lp in enumerate(_matched_lps):
        if lp not in _lp_yranges:
            continue
        y_lo, y_hi = _lp_yranges[lp]
        margin = (y_hi - y_lo) * 0.1 if y_hi > y_lo else 0.5
        ylim = (y_lo - margin, y_hi + margin)

        for col, day in enumerate(fit_days):
            ax = axes[row][col]
            key = (lp, day)
            if key in _ti_data:
                concs, ti = _ti_data[key]
                ax.plot(concs, ti, 'o-', color=drug_colors.get(_test_drugs[lp], 'steelblue'),
                        markersize=5, linewidth=1.2)

            ax.axhline(1, color='red', ls='--', alpha=0.6)
            ax.set_xscale('log')
            ax.set_ylim(ylim)

            if row == 0:
                ax.set_title(f'Day {day}', fontsize=11)
            if col == 0:
                ax.set_ylabel(f'{lp}\nTI ({ISO_AB}/{TEST_AB})', fontsize=9)
            else:
                ax.set_yticklabels([])
            if row == nrows - 1:
                ax.set_xlabel('Conc (nM)')
            else:
                ax.set_xticklabels([])

    fig.suptitle(f'Therapeutic Index by Concentration — %Viable ({metric_name})\n'
                 f'TI = {ISO_AB} / {TEST_AB}  (red dashed = TI 1)',
                 fontsize=14, y=1.02)
    plt.tight_layout()
    save_fig()

IC50 Summary Tables (Curve Fit)

Show code
# ===========================================================================
# 8. Summary tables — side-by-side comparison
# ===========================================================================
print('\n' + '='*60)
print('=== IC50 SUMMARY — COMPARISON ===')
print('='*60)

for label, df_tbl in all_ic50_tables.items():
    if 'interpolated' in label:
        continue  # handled separately below
    # Reliable IC50 pivot
    pivot = df_tbl[df_tbl.Reliable].pivot_table(
        index='Drug', columns='Day', values='IC50_nM')
    print(f'\n--- {label} — IC50 (nM), reliable only (R²≥{R2_THRESHOLD}, in range) ---')
    if pivot.empty:
        print('  (no reliable fits)')
    else:
        print(pivot.round(2).to_string())

# --- Interpolated IC50 tables (the simple midpoint method) ---
print('\n' + '='*60)
print('=== INTERPOLATED IC50 (no curve fitting) ===')
print('='*60)

for metric_name in METRICS:
    label = f'{metric_name}_interpolated'
    df_interp_tbl = all_ic50_tables[label]
    pivot = df_interp_tbl.pivot_table(
        index='Drug', columns='Day', values='IC50_interp')
    print(f'\n--- {metric_name} — Interpolated IC50 (nM) at 50% viable ---')
    print(pivot.round(2).to_string())

# Side-by-side: interpolated vs curve-fit (FoldD0)
print('\n--- FoldD0: Interpolated vs LL.4 curve-fit IC50 ---')
interp = all_ic50_tables['FoldD0_interpolated'][['Drug', 'Day', 'IC50_interp']]
fitted = all_ic50_tables['FoldD0_pctViable']
fitted_rel = fitted[fitted.Reliable][['Drug', 'Day', 'IC50_nM']].rename(
    columns={'IC50_nM': 'IC50_LL4'})
compare = interp.merge(fitted_rel, on=['Drug', 'Day'], how='outer')
compare = compare.dropna(subset=['IC50_interp', 'IC50_LL4'], how='all')
compare['Diff_%'] = ((compare.IC50_interp - compare.IC50_LL4) /
                      compare.IC50_LL4 * 100).round(1)
print(compare.round(2).to_string(index=False))

Interpolated IC50 Tables

Show code
# ===========================================================================
# 9. IC50 bar plots (reliable, both metrics side by side)
# ===========================================================================
for label, df_tbl in [
    ('FoldD0 %Viable', all_ic50_tables['FoldD0_pctViable']),
    ('TotalCellArea %Viable', all_ic50_tables['TotalCellArea_pctViable']),
]:
    plot_df = df_tbl[df_tbl.Reliable].dropna(subset=['IC50_nM']).copy()
    if plot_df.empty:
        continue
    fig, ax = plt.subplots(figsize=(14, 6))
    drug_order = sorted(plot_df.Drug.unique())
    x = np.arange(len(drug_order))
    day_vals = sorted(plot_df.Day.unique())
    width = 0.8 / max(len(day_vals), 1)
    cmap = sns.color_palette('tab10', len(day_vals))

    for i, day in enumerate(day_vals):
        day_data = plot_df[plot_df.Day == day]
        vals = []
        for drug in drug_order:
            row = day_data[day_data.Drug == drug]
            vals.append(row.IC50_nM.values[0] if len(row) > 0 else np.nan)
        ax.bar(x + i * width, vals, width, label=f'Day {day}', color=cmap[i])

    ax.set_xticks(x + width * (len(day_vals) - 1) / 2)
    ax.set_xticklabels(drug_order, rotation=45, ha='right', fontsize=9)
    ax.set_ylabel('IC50 (nM)')
    ax.set_yscale('log')
    ax.set_title(f'IC50 by Drug and Day — {label}')
    ax.legend()
    plt.tight_layout()
    save_fig()

IC50 Bar Plots

Show code
# ===========================================================================
# 10. Export
# ===========================================================================
print('\n=== 10. Export ===')
out_long = os.path.join(DATA_DIR, f'{ZIP_STEM}_long_foldD0.csv')
df.to_csv(out_long, index=False)
print(f'Saved long data: {out_long}')

for label, df_tbl in all_ic50_tables.items():
    out = os.path.join(DATA_DIR, f'{ZIP_STEM}_IC50_{label}.csv')
    df_tbl.to_csv(out, index=False)
    print(f'Saved: {out}')

print(f'\nTotal plots saved: {plot_counter[0]}')
print('Done.')
Show code
# ===========================================================================
# 11. Therapeutic Windows — Relative IC50 (midpoint between plateaus)
# ===========================================================================
print(f'\n=== 11. Therapeutic Windows ({TEST_AB} vs {ISO_AB}) ===')
print(f'    IC50 = relative IC50: conc at midpoint between untreated & max-dose plateaus')

def parse_drug(name, test_ab, iso_ab):
    """Return (antibody, linker-payload) or (None, None) if not matching."""
    for ab in [test_ab, iso_ab]:
        prefix = ab + '-'
        if name.startswith(prefix):
            return ab, name[len(prefix):]
    return None, None


def relative_ic50(concs, responses):
    """
    Relative IC50: concentration where response = midpoint between
    the untreated plateau (lowest conc) and the max-dose plateau (highest conc).
    Interpolates on log10(conc). Returns (ic50, target_pct, confident).
    confident=False if the curve never monotonically crosses the midpoint.
    """
    means = responses.groupby(concs).mean()
    c = np.array(means.index, dtype=float)
    v = np.array(means.values, dtype=float)
    order = np.argsort(c)
    c, v = c[order], v[order]

    untreated = v[0]
    max_dose  = v[-1]
    target    = (untreated + max_dose) / 2.0
    spread    = abs(untreated - max_dose)

    if spread < 5.0:
        return np.nan, target, False

    for i in range(len(v) - 1):
        if (v[i] >= target >= v[i+1]) or (v[i] <= target <= v[i+1]):
            log_c1, log_c2 = np.log10(max(c[i], 1e-6)), np.log10(max(c[i+1], 1e-6))
            frac = (target - v[i]) / (v[i+1] - v[i])
            ic50 = 10 ** (log_c1 + frac * (log_c2 - log_c1))
            confident = (spread >= 20.0) and (CONC_MIN <= ic50 <= CONC_MAX)
            return ic50, target, confident

    return np.nan, target, False


METRICS_FOR_TI = {
    'FoldD0':        'PctViable_FoldD0',
    'TotalCellArea': 'PctViable_TotalCellArea',
}

all_summary_rows = []

for metric_label, pv_col in METRICS_FOR_TI.items():
    if pv_col not in df.columns:
        print(f'\n  {metric_label}: column {pv_col} not found, skipping.')
        continue

    all_drugs_in_df = sorted(df.Drug.dropna().unique())
    drug_ab = {d: parse_drug(d, TEST_AB, ISO_AB)[0] for d in all_drugs_in_df}
    drug_lp = {d: parse_drug(d, TEST_AB, ISO_AB)[1] for d in all_drugs_in_df}
    test_lps = {drug_lp[d] for d in all_drugs_in_df if drug_ab[d] == TEST_AB}
    iso_lps  = {drug_lp[d] for d in all_drugs_in_df if drug_ab[d] == ISO_AB}
    matched_lps = sorted(test_lps & iso_lps)

    if not matched_lps:
        print(f'\n  {metric_label}: no matched LPs between {TEST_AB} and {ISO_AB}.')
        continue

    days = sorted(df[df.Day.isin(fit_days)].Day.unique())

    print(f'\n{"="*60}')
    print(f'  {metric_label} (%Viable)')
    print(f'  Matched LPs: {matched_lps}')
    print(f'{"="*60}')

    for day in days:
        day_df = df[(df.Day == day)].copy()
        rows = []
        for lp in matched_lps:
            test_drug = f'{TEST_AB}-{lp}'
            iso_drug  = f'{ISO_AB}-{lp}'
            test_sub = day_df[(day_df.Drug == test_drug)].dropna(subset=['Conc', pv_col])
            iso_sub  = day_df[(day_df.Drug == iso_drug)].dropna(subset=['Conc', pv_col])
            if test_sub.empty or iso_sub.empty:
                continue

            t_ic50, t_target, t_conf = relative_ic50(test_sub.Conc, test_sub[pv_col])
            i_ic50, i_target, i_conf = relative_ic50(iso_sub.Conc, iso_sub[pv_col])

            t_untx = test_sub.groupby('Conc')[pv_col].mean().sort_index().iloc[0]
            t_maxd = test_sub.groupby('Conc')[pv_col].mean().sort_index().iloc[-1]
            i_untx = iso_sub.groupby('Conc')[pv_col].mean().sort_index().iloc[0]
            i_maxd = iso_sub.groupby('Conc')[pv_col].mean().sort_index().iloc[-1]

            ti = i_ic50 / t_ic50 if (not np.isnan(t_ic50) and t_ic50 > 0
                                      and not np.isnan(i_ic50)) else np.nan
            ti_conf = t_conf and i_conf and not np.isnan(ti)

            def fmt(val, conf):
                if np.isnan(val):
                    return 'NA'
                return f'{val:.2f}' if conf else f'{val:.2f}*'

            rows.append({
                'LP': lp,
                f'{TEST_AB} untx→max': f'{t_untx:.0f}→{t_maxd:.0f}%',
                f'{TEST_AB} IC50 (nM)': fmt(t_ic50, t_conf),
                f'{ISO_AB} untx→max': f'{i_untx:.0f}→{i_maxd:.0f}%',
                f'{ISO_AB} IC50 (nM)': fmt(i_ic50, i_conf),
                f'TI ({ISO_AB}/{TEST_AB})': fmt(ti, ti_conf),
            })
            all_summary_rows.append({
                'Method': metric_label, 'Day': day, 'LP': lp,
                f'{TEST_AB}_IC50_nM': t_ic50, f'{TEST_AB}_confident': t_conf,
                f'{TEST_AB}_untreated_%': t_untx, f'{TEST_AB}_maxdose_%': t_maxd,
                f'{ISO_AB}_IC50_nM': i_ic50, f'{ISO_AB}_confident': i_conf,
                f'{ISO_AB}_untreated_%': i_untx, f'{ISO_AB}_maxdose_%': i_maxd,
                'TI': ti, 'TI_confident': ti_conf,
            })

        if not rows:
            print(f'\n  Day {day}: no matched LP pairs with data.')
            continue

        tbl = pd.DataFrame(rows)
        print(f'\n--- {metric_label} — Day {day} ---')
        print(f'    IC50 = conc at midpoint of (untreated, max-dose)')
        print(f'    TI = IC50({ISO_AB}) / IC50({TEST_AB})  ;  * = low confidence')
        print(tbl.to_string(index=False))

        # Grouped bar chart: IC50 by LP
        plot_rows = [r for r in rows
                     if r[f'{TEST_AB} IC50 (nM)'] != 'NA' or r[f'{ISO_AB} IC50 (nM)'] != 'NA']
        if not plot_rows:
            continue
        lps_plot = [r['LP'] for r in plot_rows]

        fig, ax = plt.subplots(figsize=(max(6, len(lps_plot) * 2.5), 5))
        x = np.arange(len(lps_plot))
        width = 0.35
        colors = {TEST_AB: '#2196F3', ISO_AB: '#FF9800'}

        for j, ab in enumerate([TEST_AB, ISO_AB]):
            col_name = f'{ab} IC50 (nM)'
            vals, labels, hatches = [], [], []
            for r in plot_rows:
                raw = r[col_name]
                if raw == 'NA':
                    vals.append(0); labels.append('NA'); hatches.append('//')
                else:
                    v = float(raw.rstrip('*'))
                    vals.append(v)
                    labels.append(raw)
                    hatches.append('//' if raw.endswith('*') else '')
            bars = ax.bar(x + (j - 0.5) * width, vals, width, label=ab,
                          color=colors[ab], alpha=0.85)
            for bar, lbl, hatch in zip(bars, labels, hatches):
                bar.set_hatch(hatch)
                if lbl != 'NA' and bar.get_height() > 0:
                    ax.text(bar.get_x() + bar.get_width() / 2, bar.get_height(),
                            lbl, ha='center', va='bottom', fontsize=9)

        ax.set_xticks(x)
        ax.set_xticklabels(lps_plot, fontsize=11)
        ax.set_ylabel('Relative IC50 (nM)')
        ax.set_title(f'{metric_label} — Day {day}\nRelative IC50 by Linker-Payload  (* = low confidence)',
                     fontsize=13)
        ax.legend()
        ax.set_yscale('log')
        plt.tight_layout()
        save_fig()

        # TI bar chart
        ti_rows = [r for r in plot_rows if r[f'TI ({ISO_AB}/{TEST_AB})'] != 'NA']
        if ti_rows:
            ti_vals = [float(r[f'TI ({ISO_AB}/{TEST_AB})'].rstrip('*')) for r in ti_rows]
            ti_lps  = [r['LP'] for r in ti_rows]
            ti_conf = [not r[f'TI ({ISO_AB}/{TEST_AB})'].endswith('*') for r in ti_rows]

            fig, ax = plt.subplots(figsize=(max(5, len(ti_vals) * 2), 4.5))
            bar_colors = ['#4CAF50' if c else '#FFC107' for c in ti_conf]
            bar_hatches = ['' if c else '//' for c in ti_conf]
            bars = ax.bar(range(len(ti_vals)), ti_vals, color=bar_colors, alpha=0.85)
            for bar, hatch, v, c in zip(bars, bar_hatches, ti_vals, ti_conf):
                bar.set_hatch(hatch)
                lbl = f'{v:.1f}' + ('' if c else '*')
                ax.text(bar.get_x() + bar.get_width() / 2, bar.get_height(),
                        lbl, ha='center', va='bottom', fontsize=10, fontweight='bold')
            ax.axhline(1.0, color='red', linestyle='--', linewidth=1, label='TI = 1')
            ax.set_xticks(range(len(ti_vals)))
            ax.set_xticklabels(ti_lps, fontsize=11)
            ax.set_ylabel(f'Therapeutic Index\nIC50({ISO_AB}) / IC50({TEST_AB})')
            ax.set_title(f'{metric_label} — Day {day}\nTherapeutic Index  (* = low confidence)',
                         fontsize=13)
            ax.legend()
            plt.tight_layout()
            save_fig()

# Export combined summary
if all_summary_rows:
    df_ti_summary = pd.DataFrame(all_summary_rows)
    out = os.path.join(DATA_DIR, f'{ZIP_STEM}_therapeutic_index_{TEST_AB}_vs_{ISO_AB}.csv')
    df_ti_summary.to_csv(out, index=False)
    print(f'\nSaved combined summary: {out}')
    print('\n' + '='*60)
    print('  Combined Therapeutic Index Summary')
    print('='*60)
    print(df_ti_summary.round(2).to_string(index=False))