File size: 15,065 Bytes
ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 90b47cf ef53368 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 | {
"cells": [
{
"cell_type": "markdown",
"id": "3a2b8d51",
"metadata": {},
"source": [
"# SI Figure S3: inter-method correlation and PCA of NS372 and delta-22 shieldings\n",
"\n",
"Inter-method correlation matrices and PC1/PC2 loadings for NS372 (44 functionals x 8 nuclei) and\n",
"delta22 (18 functionals, ¹H/¹³C), plus a combined summary table."
]
},
{
"cell_type": "markdown",
"id": "0fb6f798",
"metadata": {},
"source": [
"Two independent NMR shielding datasets, analyzed separately (never pooled):\n",
"\n",
"| Dataset | Source | Methods | Nuclei | Reference |\n",
"|---|---|---|---|---|\n",
"| **NS372** | Schattenberg & Kaupp, *JCTC* **17**, 7602 (2021) | 44 DFT/WFT functionals | ¹H ¹¹B ¹³C ¹⁵N ¹⁷O ¹⁹F ³¹P ³³S | CCSD(T)/pcSseg-3 |\n",
"| **delta22** | in-house delta-22 set | 18 gas-phase functionals, largest basis (pcSseg-3; mp2 → pcSseg-2), PBE0/cc-pVTZ geometry | ¹H ¹³C | DSD-PBEP86 (highest-rung in-set method, stands in for CCSD(T)) |"
]
},
{
"cell_type": "markdown",
"id": "3ff927f7",
"metadata": {},
"source": [
"## 1. Configuration"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9e5a25b8",
"metadata": {},
"outputs": [],
"source": [
"import os, sys\n",
"\n",
"REPO = os.path.abspath(\"../..\")\n",
"for _p in (\"analysis/code\", \"analysis/code/shared\"):\n",
" sys.path.insert(0, os.path.join(REPO, _p))"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "06e0333d",
"metadata": {},
"outputs": [],
"source": [
"import glob\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"\n",
"import paths\n",
"import leveling\n",
"import leveling_plots"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "fbd3d68f",
"metadata": {},
"outputs": [],
"source": [
"# inputs:\n",
"# - the Kaupp NS372 spreadsheet is small and ships in the repo's data/ns372/ folder\n",
"# - delta22.hdf5 is large: it resolves from the repo's data/delta22/ folder, carried by the\n",
"# Hugging Face checkout via Git LFS (see analysis/code/paths.py)\n",
"# the delta22 file is encoded as whole numbers (real value x 10,000); the loader\n",
"# in leveling.py decodes it on read (a plain-decimal copy also works, since the\n",
"# decode step is a no-op on floating-point data).\n",
"KAUPP_XLSX = os.path.join(REPO, \"data\", \"ns372\", \"ct1c00919_si_002.xlsx\")\n",
"DELTA22_H5 = paths.dataset_file(\"delta22\", root=REPO)\n",
"SAVE_DPI = 200 # SI-quality raster output\n",
"\n",
"def figure_path(name):\n",
" os.makedirs(\"figures\", exist_ok=True)\n",
" return os.path.join(\"figures\", name)\n",
"\n",
"# self-clean: this notebook builds PNG names dynamically (one per nucleus), so drop any\n",
"# previously written figures before regenerating. Scope the delete to THIS figure's own prefix:\n",
"# the figures/ folder is shared with the other notebooks in this directory, and a full reproduce\n",
"# run executes them in name order, so a broad \"figures/*.png\" wipe would destroy the panels written\n",
"# by notebooks that sort before this one. (glob on a missing folder returns [])\n",
"for _stale in glob.glob(os.path.join(\"figures\", \"si_figure_s03_*.png\")):\n",
" os.remove(_stale)\n",
"\n",
"pd.set_option('display.width', 150)\n",
"pd.set_option('display.max_columns', 25)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "84ddcb3f",
"metadata": {},
"outputs": [],
"source": [
"# functional-family colours used for every figure (family ordering lives in leveling.py)\n",
"FAMILY_COLORS = {'LDA':'#777777','GGA':'#1f77b4','mGGA':'#17becf','GH':'#2ca02c',\n",
" 'RSH':'#9467bd','LH':'#8c564b','DH':'#ff7f0e','WFT':'#d62728',\n",
" 'ref':'#FF1493'}\n",
"\n",
"# proper Unicode-superscript labels for nuclei in figure titles\n",
"NUC_DISPLAY = {'1H':'¹H','11B':'¹¹B','13C':'¹³C',\n",
" '15N':'¹⁵N','17O':'¹⁷O','19F':'¹⁹F',\n",
" '31P':'³¹P','33S':'³³S'}\n",
"\n",
"# adjustText parameters tuned per nucleus -- 1H and 13C have very dense central\n",
"# clusters and need stronger expansion; the paramagnetic-shielding nuclei\n",
"# (15N/17O/19F) already spread methods along the parabola and need a gentler\n",
"# pass to avoid over-flinging labels.\n",
"PCA_ADJUST_DEFAULT = dict(\n",
" force_text=(0.35, 0.55), force_explode=(0.25, 0.40),\n",
" force_static=(0.10, 0.15), force_pull=(0.02, 0.02),\n",
" expand=(1.25, 1.35), time_lim=4,\n",
")\n",
"PCA_ADJUST = {\n",
" '1H': {**PCA_ADJUST_DEFAULT, 'force_text':(0.75, 1.05),\n",
" 'force_explode':(0.65, 0.90), 'expand':(1.7, 1.9), 'time_lim':7},\n",
" '11B': {**PCA_ADJUST_DEFAULT, 'force_text':(0.50, 0.75),\n",
" 'force_explode':(0.40, 0.60), 'expand':(1.4, 1.55), 'time_lim':5},\n",
" '13C': {**PCA_ADJUST_DEFAULT, 'force_text':(0.70, 1.00),\n",
" 'force_explode':(0.60, 0.85), 'expand':(1.6, 1.8), 'time_lim':6},\n",
" '15N': {**PCA_ADJUST_DEFAULT, 'force_text':(0.60, 0.85),\n",
" 'force_explode':(0.50, 0.70), 'expand':(1.5, 1.65), 'time_lim':6},\n",
" '17O': {**PCA_ADJUST_DEFAULT, 'force_text':(0.60, 0.85),\n",
" 'force_explode':(0.50, 0.70), 'expand':(1.5, 1.65), 'time_lim':6},\n",
" '31P': {**PCA_ADJUST_DEFAULT, 'force_text':(0.65, 0.90),\n",
" 'force_explode':(0.55, 0.75), 'expand':(1.55, 1.7), 'time_lim':6},\n",
" '33S': {**PCA_ADJUST_DEFAULT, 'force_text':(0.65, 0.90),\n",
" 'force_explode':(0.55, 0.75), 'expand':(1.55, 1.7), 'time_lim':6},\n",
"}"
]
},
{
"cell_type": "markdown",
"id": "4fbeeddb",
"metadata": {},
"source": [
"## 2. NS372 (Kaupp) - definitions\n",
"\n",
"Conventional GIAO shieldings for 44 functionals across 8 main-group nuclei, with a\n",
"CCSD(T)/pcSseg-3 reference. Kaupp Reduced-Set exclusions (F₃⁻, O₃, BH - multireference\n",
"outliers) are applied. Input: the Kaupp NS372 supporting-information spreadsheet."
]
},
{
"cell_type": "markdown",
"id": "34326933",
"metadata": {},
"source": [
"## 3. delta22 - definitions\n",
"\n",
"Gas-phase conventional GIAO shieldings from the delta-22 set: 18 functionals at their\n",
"largest available basis (pcSseg-3; plain MP2 only to pcSseg-2), at the PBE0/cc-pVTZ\n",
"geometry. Observations are pooled ¹H / ¹³C atom sites across all 22 solutes. There is no\n",
"CCSD(T) reference in the file; **DSD-PBEP86 is used as the reference** for delta22 - it\n",
"is the highest-rung double-hybrid available in this method set and stands in for CCSD(T)\n",
"in the same role. The stored whole-number shieldings are decoded on read."
]
},
{
"cell_type": "markdown",
"id": "eedf9b3d",
"metadata": {},
"source": [
"## 4. Load datasets + global colour scale\n",
"\n",
"Run the loaders, analyse every nucleus, and compute the figure-wide\n",
"-log10(1-|r|) maximum used as the colour scale on every correlation matrix\n",
"below, for NS372 and delta22 alike."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4bec0cf4",
"metadata": {},
"outputs": [],
"source": [
"ns372 = leveling.load_ns372(KAUPP_XLSX)\n",
"delta22 = leveling.load_delta22(DELTA22_H5)\n",
"\n",
"res_ns372 = {nuc: leveling.analyze_nucleus(d['M'], d['methods'], d['ref'])\n",
" for nuc, d in ns372.items()}\n",
"res_delta22 = {nuc: leveling.analyze_nucleus(d['M'], d['methods'], d['ref'])\n",
" for nuc, d in delta22.items()}\n",
"\n",
"GLOBAL_VMAX = max(leveling.dataset_logr_max(res_ns372), leveling.dataset_logr_max(res_delta22))\n",
"print(f'NS372 : {len(ns372)} nuclei')\n",
"print(f'delta22: {len(delta22)} nuclei (reference = {leveling.DELTA22_REF})')\n",
"print(f'global colour scale: 0 -> {GLOBAL_VMAX} on the -log10(1-|r|) axis')\n",
"for nuc, d in ns372.items():\n",
" print(f' NS372 {nuc:4s}: {d[\"M\"].shape[0]:4d} mols x {d[\"M\"].shape[1]-1} methods + CCSD(T)')\n",
"for nuc, d in delta22.items():\n",
" print(f' delta22 {nuc:4s}: {d[\"M\"].shape[0]:4d} sites x {d[\"M\"].shape[1]} methods')"
]
},
{
"cell_type": "markdown",
"id": "667fef3c",
"metadata": {},
"source": [
"## 5. NS372 results"
]
},
{
"cell_type": "markdown",
"id": "c5f2cbda",
"metadata": {},
"source": [
"### 5.1 Leveling diagnostics - NS372"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "8b9b9449",
"metadata": {},
"outputs": [],
"source": [
"sum_ns372 = leveling.summarize(ns372, res_ns372)\n",
"print('NS372 - leveling diagnostics (CCSD(T) included as a method column):')\n",
"sum_ns372.round(5)"
]
},
{
"cell_type": "markdown",
"id": "2b666d04",
"metadata": {},
"source": [
"### 5.2 Per-method scaled RMSE vs CCSD(T)\n",
"\n",
"Scaled RMSE = RMSE of residuals after a per-method linear fit of each method's shieldings\n",
"against the CCSD(T) reference (slope and intercept) - the error that survives empirical\n",
"linear scaling."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4020359a",
"metadata": {},
"outputs": [],
"source": [
"rmse_ns372 = pd.DataFrame({nuc: res_ns372[nuc]['scaled_rmse'] for nuc in res_ns372})\n",
"rmse_ns372 = rmse_ns372.drop(index='CCSD(T)', errors='ignore')\n",
"rmse_ns372 = rmse_ns372.reindex(ns372['1H']['methods'][:-1]) # family order\n",
"print('NS372 - per-method scaled RMSE vs CCSD(T) (ppm):')\n",
"rmse_ns372.round(3)"
]
},
{
"cell_type": "markdown",
"id": "ba763232",
"metadata": {},
"source": [
"### 5.3 Inter-method correlation matrices - NS372 (one nucleus per file)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "133a5053",
"metadata": {},
"outputs": [],
"source": [
"NS372_NUCS = ['1H', '11B', '13C', '15N', '17O', '19F', '31P', '33S']\n",
"for nuc in NS372_NUCS:\n",
" fams = {nuc: ns372[nuc]['families']}\n",
" fig = leveling_plots.plot_corr_matrix('NS372', [nuc], res_ns372, fams,\n",
" GLOBAL_VMAX, ref_name='CCSD(T)',\n",
" nuc_display=NUC_DISPLAY)\n",
" fig.savefig(figure_path(f'si_figure_s03_corr_{nuc}.png'),\n",
" dpi=SAVE_DPI, bbox_inches='tight')\n",
" plt.show()"
]
},
{
"cell_type": "markdown",
"id": "0fa55480",
"metadata": {},
"source": [
"### 5.4 PC1/PC2 structure - NS372 (one nucleus per file)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a37b38c6",
"metadata": {},
"outputs": [],
"source": [
"for nuc in NS372_NUCS:\n",
" fams = {nuc: ns372[nuc]['families']}\n",
" fig = leveling_plots.plot_pca_pair('NS372', [nuc], res_ns372, fams,\n",
" family_colors=FAMILY_COLORS, nuc_display=NUC_DISPLAY,\n",
" pca_adjust=PCA_ADJUST, pca_adjust_default=PCA_ADJUST_DEFAULT)\n",
" fig.savefig(figure_path(f'si_figure_s03_pca_{nuc}.png'),\n",
" dpi=SAVE_DPI, bbox_inches='tight')\n",
" plt.show()"
]
},
{
"cell_type": "markdown",
"id": "bc460701",
"metadata": {},
"source": [
"### 5.5 delta22 panels (lead the published figure: corr ¹H/¹³C + PCA)\n",
"\n",
"The same correlation + PCA layout on the delta22 gas-phase set. DSD-PBEP86 is the reference (delta22\n",
"has no CCSD(T)); it appears as an ordinary double-hybrid point in the PCA, with no CCSD(T) star."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "74e02974",
"metadata": {},
"outputs": [],
"source": [
"# delta22 correlation matrices (canonical S3 A = 1H, B = 13C)\n",
"for nuc in ['1H', '13C']:\n",
" fams = {nuc: delta22[nuc]['families']}\n",
" fig = leveling_plots.plot_corr_matrix('delta22', [nuc], res_delta22, fams,\n",
" GLOBAL_VMAX, ref_name=leveling.DELTA22_REF,\n",
" nuc_display=NUC_DISPLAY)\n",
" fig.savefig(figure_path(f'si_figure_s03_delta22_corr_{nuc}.png'),\n",
" dpi=SAVE_DPI, bbox_inches='tight')\n",
" plt.show()\n",
"\n",
"# delta22 PCA projection: 1H and 13C stacked in one figure (canonical S3 C)\n",
"fams = {nuc: delta22[nuc]['families'] for nuc in ['1H', '13C']}\n",
"fig = leveling_plots.plot_pca_pair('delta22', ['1H', '13C'], res_delta22, fams,\n",
" family_colors=FAMILY_COLORS, nuc_display=NUC_DISPLAY,\n",
" pca_adjust=PCA_ADJUST, pca_adjust_default=PCA_ADJUST_DEFAULT)\n",
"fig.savefig(figure_path('si_figure_s03_delta22_pca.png'),\n",
" dpi=SAVE_DPI, bbox_inches='tight')\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"id": "49825011",
"metadata": {},
"source": [
"## 6. Combined summary (both datasets)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "bffe5ff3",
"metadata": {},
"outputs": [],
"source": [
"# delta22's per-nucleus diagnostics (same summarize() used for NS372 above), computed here\n",
"# too so this combined table is self-contained -- it reuses res_delta22 from the shared load\n",
"# cell above, so this is cheap (no new correlation/PCA computation).\n",
"sum_delta22 = leveling.summarize(delta22, res_delta22)\n",
"\n",
"combined = pd.concat([sum_ns372.assign(dataset='NS372'),\n",
" sum_delta22.assign(dataset='delta22')], ignore_index=True)\n",
"combined = combined[['dataset','nucleus','n_obs','n_methods','r_min','r_median',\n",
" 'PC1_pct','PC2_pct','PC3plus_pct','parabola_R2']]\n",
"print('Leveling effect - both datasets (analyzed separately):')\n",
"print(f' PC1 range : {combined.PC1_pct.min():.2f}% - {combined.PC1_pct.max():.2f}%')\n",
"print(f' min pairwise r : {combined.r_min.min():.5f} (worst case, all nuclei)')\n",
"print(f' parabola R2 range : {combined.parabola_R2.min():.3f} - {combined.parabola_R2.max():.3f}')\n",
"print(f' global colour scale : 0 -> {GLOBAL_VMAX} on -log10(1-|r|)')\n",
"combined.round(5)"
]
}
],
"metadata": {
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|