servalcat 0.4.72__cp38-cp38-win_amd64.whl → 0.4.99__cp38-cp38-win_amd64.whl

servalcat/xtal/twin.py

@@ -0,0 +1,121 @@
+"""
+Author: "Keitaro Yamashita, Garib N. Murshudov"
+MRC Laboratory of Molecular Biology
+    
+This software is released under the
+Mozilla Public License, version 2.0; see LICENSE.
+"""
+from __future__ import absolute_import, division, print_function, generators
+import argparse
+import gemmi
+import numpy
+import pandas
+from servalcat.utils import logger
+from servalcat import utils
+from servalcat import ext
+
+def find_twin_domains_from_data(hkldata, max_oblique=5, min_alpha=0.05):
+    logger.writeln("Finding possible twin operators from data")
+    ops = gemmi.find_twin_laws(hkldata.cell, hkldata.sg, max_oblique, False)
+    logger.writeln(f" {len(ops)} possible twin operator(s) found")
+    #for op in ops:
+    #    logger.writeln(f"  {op.triplet()}")
+    if not ops:
+        return
+    twin_data = ext.TwinData()
+    twin_data.setup(hkldata.miller_array(), hkldata.df.bin, hkldata.sg, hkldata.cell, ops)
+    if "I" in hkldata.df:
+        Io = hkldata.df.I.to_numpy()
+    else:
+        Io = hkldata.df.FP.to_numpy()**2
+    alphas = []
+    ccs, nums = [], []
+    for i_bin, bin_idxes in hkldata.binned():
+        ratios = [1.]
+        ccs.append([])
+        nums.append([])
+        for i_op, op in enumerate(ops):
+            ii = numpy.array(twin_data.pairs(i_op, i_bin))
+            val = numpy.all(numpy.isfinite(Io[ii]), axis=1)
+            if numpy.sum(val) == 0:
+                cc = numpy.nan
+            else:
+                cc = numpy.corrcoef(Io[ii][val].T)[0,1]
+            rr = (1 - numpy.sqrt(1 - cc**2)) / cc
+            ratios.append(rr)
+            ccs[-1].append(cc)
+            nums[-1].append(len(val))
+        alphas.append(numpy.array(ratios) / numpy.nansum(ratios))
+    alphas = numpy.maximum(0, numpy.mean(alphas, axis=0))
+    alphas /= numpy.nansum(alphas)
+    ccs = numpy.array(ccs)
+    nums = numpy.array(nums)
+    tmp = [{"Operator": gemmi.Op().triplet(),
+            "R_twin_obs": 0,
+            "CC_mean": 1,
+            "Alpha_from_CC": alphas[0]}]
+    for i_op, op in enumerate(ops):
+        ii = numpy.array(twin_data.pairs(i_op))
+        val = numpy.all(numpy.isfinite(Io[ii]), axis=1)
+        if numpy.sum(val) == 0:
+            r_obs = numpy.nan
+        else:
+            r_obs = numpy.sum(numpy.abs(Io[ii][val, 0] - Io[ii][val, 1])) / numpy.sum(Io[ii][val])
+        tmp.append({"Operator": op.triplet(),
+                    "CC_mean": numpy.sum(nums[:,i_op] * ccs[:,i_op]) / numpy.sum(nums[:,i_op]),
+                    "R_twin_obs": r_obs,
+                    "Alpha_from_CC": alphas[i_op+1],
+                    })
+    df = pandas.DataFrame(tmp)
+    logger.writeln(df.to_string(float_format="%.2f"))
+
+    sel_idxes = [i for i, a in enumerate(alphas) if i > 0 and a > min_alpha]
+    if not sel_idxes:
+        logger.writeln(" No twinning detected")
+        return
+    
+    if len(sel_idxes) + 1 != len(alphas):
+        ops = [ops[i-1] for i in sel_idxes]
+        logger.writeln(" Twin operators after filtering small fractions")
+        alphas = numpy.array([alphas[0]] + [alphas[i] for i in sel_idxes])
+        alphas /= numpy.sum(alphas)
+        df = pandas.DataFrame({"Operator": [x.triplet() for x in [gemmi.Op()]+ops],
+                               "Alpha": alphas})
+        logger.writeln(df.to_string(float_format="%.2f"))
+        twin_data = ext.TwinData()
+        twin_data.setup(hkldata.miller_array(), hkldata.df.bin, hkldata.sg, hkldata.cell, ops)
+    twin_data.alphas = alphas
+    if "I" not in hkldata.df:
+        logger.writeln('Generating "observed" intensities for twin refinement: Io = Fo**2, SigIo = 2*F*SigFo')
+        hkldata.df["I"] = hkldata.df.FP**2
+        hkldata.df["SIGI"] = 2 * hkldata.df.FP * hkldata.df.SIGFP
+    return twin_data
+
+# find_twin_domains_from_data()
+
+def estimate_twin_fractions_from_model(twin_data, hkldata):
+    logger.writeln("Estimating twin fractions")
+    Ic = numpy.abs(twin_data.f_calc.sum(axis=1))**2
+    Ic_all = Ic[twin_data.twin_related(hkldata.sg)]
+    rr = twin_data.obs_related_asu()
+    tmp = []
+    for i_bin, bin_idxes in hkldata.binned():
+        cc_o_c = []
+        i_tmp = Ic_all[numpy.asarray(twin_data.bin)==i_bin,:]
+        P = numpy.corrcoef(i_tmp.T)
+        iobs = hkldata.df.I.to_numpy()[bin_idxes]
+        ic_bin = Ic[rr[bin_idxes,:]]
+        val = numpy.isfinite(iobs) & numpy.isfinite(ic_bin).all(axis=1)
+        iobs, ic_bin = iobs[val], ic_bin[val,:]
+        cc_o_c = [numpy.corrcoef(iobs, ic_bin[:,i])[0,1] for i in range(len(twin_data.ops)+1)]
+        frac_est = numpy.dot(numpy.linalg.pinv(P), cc_o_c)
+        tmp.append(frac_est.tolist())
+
+    df = pandas.DataFrame(tmp)
+    df.iloc[:,:] /= df.sum(axis=1).to_numpy()[:,None]
+    mean_alphas = numpy.maximum(0, df.mean())
+    mean_alphas /= numpy.sum(mean_alphas)
+    logger.write(" Estimated fractions from data-model correlations: ")
+    logger.writeln(" ".join("%.2f"%x for x in mean_alphas))
+    twin_data.alphas = mean_alphas
+

{servalcat-0.4.72.dist-info → servalcat-0.4.99.dist-info}/METADATA

@@ -1,16 +1,16 @@
 Metadata-Version: 2.1
 Name: servalcat
-Version: 0.4.72
+Version: 0.4.99
 Summary: Structure refinement and validation for crystallography and single particle analysis
 Author: Keitaro Yamashita, Garib N. Murshudov
 License: MPL-2.0
 Project-URL: Repository, https://github.com/keitaroyam/servalcat
-Requires-Python: >=3.7
+Requires-Python: >=3.8
 Requires-Dist: packaging
 Requires-Dist: numpy>=1.15
 Requires-Dist: scipy
 Requires-Dist: pandas>=1.1.0
-Requires-Dist: gemmi==0.6.6
+Requires-Dist: gemmi==0.7.0
 Description-Content-Type: text/markdown
 
 # Servalcat
@@ -40,7 +40,7 @@ pip install servalcat
 ```
 will install the stable version.
 
-The required GEMMI version is now [v0.6.6](https://github.com/project-gemmi/gemmi/releases/tag/v0.6.6). It may not work with the latest gemmi code from the github. The policy is in the main branch I only push the code that works with the latest package of GEMMI.
+The required GEMMI version is now [v0.7.0](https://github.com/project-gemmi/gemmi/releases/tag/v0.7.0). It may not work with the latest gemmi code from the github. The policy is in the main branch I only push the code that works with the latest package of GEMMI.
 
 To use the Refmac5 related commands, you also need to install [CCP4](https://www.ccp4.ac.uk/). For "No Refmac5" commands, you may just need [the monomer library](https://github.com/MonomerLibrary/monomers) if CCP4 is not installed.
 

servalcat-0.4.99.dist-info/RECORD

@@ -0,0 +1,45 @@
+servalcat/__init__.py,sha256=HJt3p1jXzt-hnlShh1LfxHF3WRNM7hyk1FY-B4EqExc,241
+servalcat/__main__.py,sha256=XUM193aDwZAEQY02VzvZasAzD6AYEM-_A4wqy93KDWE,4190
+servalcat/ext.cp38-win_amd64.pyd,sha256=b3XA-uj4P_eMgKwSrIG3jDYCQU49xOMqosymXrWmaFs,1334784
+servalcat/refine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/refine/cgsolve.py,sha256=Xz7EwGI-mr4nnbfARyfFjAqbJbPWGH9qNWQ0GpltDuc,3172
+servalcat/refine/refine.py,sha256=P6epHQZLpz3Tl2fuGrdCp6WOxuzvik7YJJTBsd4zuHg,44941
+servalcat/refine/refine_geom.py,sha256=RMfhmBb-jlSFZoMhV3QONev9U2ZuHuPyjSslhECMYXo,11585
+servalcat/refine/refine_spa.py,sha256=BFoJPNhyLVUWl2U2aDufkRJheYmzhnP4iEdE9DZ5JWc,19528
+servalcat/refine/refine_xtal.py,sha256=kI6oqE2u8E82KUqk6zg4Y9JVLC2PIE9LG227rXWlYM8,15017
+servalcat/refine/spa.py,sha256=7aYSnSty0fSe46P_RQ79Bd_8RwD88k3uAaLHVsz6yHc,6616
+servalcat/refine/xtal.py,sha256=qusNpwRdBie9pnHol_NTDgou08reuiERWBujyhREFbc,14893
+servalcat/refmac/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/refmac/exte.py,sha256=LRPej2yCZ4RoWJnEQldILEiUED6S_w1lgutWAdhu9_o,9201
+servalcat/refmac/refmac_keywords.py,sha256=WPLDQdk91i5yKZ0QcfaTQ6qL-_qBv7_91eUv4Is9j54,27288
+servalcat/refmac/refmac_wrapper.py,sha256=7FuYyWqN1UvSilFECWOSmWmYObXFLvO49PWkRbwBPHQ,18233
+servalcat/spa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/spa/fofc.py,sha256=DONPNvHPP9odKGNekpo781D_skjReUEytQ1wHBJxGwc,23592
+servalcat/spa/fsc.py,sha256=Rszx-zzJiX5iSY-Qp6q5uCrEhE3a5eyW-m_szT5itLA,17839
+servalcat/spa/localcc.py,sha256=FJMXiC0Po5eb1Le404mgNDj9VcxH5CRR9F5B7uDZn5w,8173
+servalcat/spa/realspcc_from_var.py,sha256=x3NaqGKpGmQyh3qp-SJ9kTA_hP2EvxBOIszYbV2EPKk,5403
+servalcat/spa/run_refmac.py,sha256=bHSj-8_RLdrfHTCyNWoMtXsrNT37AfpONZ8D3jR01ZE,50527
+servalcat/spa/shift_maps.py,sha256=G_EddBcdyncl2bhW7I-4YF0ZFtX9Q95a2SIJ9rpPeR4,13561
+servalcat/spa/shiftback.py,sha256=EtITj8Nllz-MWE6oJrxruDWeT0q7tS3RXCKtpWMuHNg,4801
+servalcat/spa/translate.py,sha256=PGf1vHh_b_mxDta_CAghY7QBRVPzHSaGLDhrnafqCdA,5228
+servalcat/utils/__init__.py,sha256=4umrD2fhG1QAQppDBQM95-6y8QYbtxr7Mi_-Nkc3XOA,1172
+servalcat/utils/commands.py,sha256=fEWF6HesIAuxnzbaKAPws_QaIPxJUQc6DVthHeex_Vk,72503
+servalcat/utils/fileio.py,sha256=3fyHTQ62sibP3cUYtX8D9G7cC6qelkfPKnbA47MqPOo,30246
+servalcat/utils/generate_operators.py,sha256=fCrcTcciRn-6fpFtHYvf1oPXAObjuqR3WQejz5d0RrA,10980
+servalcat/utils/hkl.py,sha256=sMaXJprnceVLDHWfwPSTWmbVbAJEPfj86tF3C0S2g_o,28776
+servalcat/utils/logger.py,sha256=VXSkn54Rp2dxnCQ-Smb5T0NZqysvw8GGb4bKyA8Vuig,4729
+servalcat/utils/maps.py,sha256=1Gm54nEvPj4peCuo0Rx-8_gvRD1pr2qECq7U9N6mrVw,13570
+servalcat/utils/model.py,sha256=YPqYNCPZrbtUPbtMROQUA1RowEC7zrBlUvAEFNfoW5k,30959
+servalcat/utils/refmac.py,sha256=dY92UZo2orgZJOEmPacCek8PMj-ydCp6-pR0rdsAVG8,31682
+servalcat/utils/restraints.py,sha256=hclAJ3CKzIqeyC-I0rH8TSwikwQN1k8dUtYWKC0OAnU,37741
+servalcat/utils/symmetry.py,sha256=PSSD-S_j_t1m4E9F8Fd9RJqTWyKf92zLCjSED7iXFkU,12164
+servalcat/xtal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/xtal/french_wilson.py,sha256=u4wzHuotO8-avPkhuEylg9WmMZYdGHYz1IvG07uqW3M,12045
+servalcat/xtal/run_refmac_small.py,sha256=_Rw7wz7_yAlQgDqjJ_njeK6ZqN_r7KAakoor9WeNhxI,10634
+servalcat/xtal/sigmaa.py,sha256=uF552XnFyaBKfN36c8ajMOxFGrW_r3p9FFQ4T5nB1wg,76970
+servalcat/xtal/twin.py,sha256=gsDyyeC5jxsY8wepcB9lnNNPgVCvqlGVj9_kQZkkdWg,5021
+servalcat-0.4.99.dist-info/METADATA,sha256=OxT6LeODHswv4-Yg1Xtv6pjkvHjriRcZNFfq5asJObs,2741
+servalcat-0.4.99.dist-info/WHEEL,sha256=kwS-TzWMc793MQ545g1AsDhyMUJrOZEAGChkok6pUJs,104
+servalcat-0.4.99.dist-info/entry_points.txt,sha256=G1mDxhOCdF3umYz4k0kfwJbSdYSKqhvQdGCmrP8FRAY,111
+servalcat-0.4.99.dist-info/licenses/LICENSE,sha256=JoTeFzAOCkNGhvHsf4r2BFIHpLRXo_4EsrnOZV58XVA,17098
+servalcat-0.4.99.dist-info/RECORD,,

{servalcat-0.4.72.dist-info → servalcat-0.4.99.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: scikit-build-core 0.9.5
+Generator: scikit-build-core 0.10.7
 Root-Is-Purelib: false
 Tag: cp38-cp38-win_amd64
 

servalcat-0.4.72.dist-info/RECORD

@@ -1,44 +0,0 @@
-servalcat/__init__.py,sha256=38MjgJlCYiBGXs6xPMoSqHeHNYgnEGdawRSdJ63BoBI,241
-servalcat/__main__.py,sha256=XUM193aDwZAEQY02VzvZasAzD6AYEM-_A4wqy93KDWE,4190
-servalcat/ext.cp38-win_amd64.pyd,sha256=DOpCEuK7oph-WerCALRXzVDXMyo-I5_KPJQIityugX8,1861120
-servalcat/refine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/refine/cgsolve.py,sha256=Xz7EwGI-mr4nnbfARyfFjAqbJbPWGH9qNWQ0GpltDuc,3172
-servalcat/refine/refine.py,sha256=mC7iSnY5TwEoGeYSc_Wx-tXSY7rxp91HzF--SuSUzqc,39048
-servalcat/refine/refine_geom.py,sha256=K5rXXZGiNobcWo2rVUCWeTZW24iJhRDMY7ggYuZp7AU,10580
-servalcat/refine/refine_spa.py,sha256=ZU8arWp_3TJ7v2BFBf1Vp07gl16yeV3Rv6LrvzGEqPk,17676
-servalcat/refine/refine_xtal.py,sha256=IrOOni5156efry4DBJ83sGTnAZ072n4sUJjxn0tDyiA,12844
-servalcat/refine/spa.py,sha256=4_USXJEzbRXmIEf9nmS1spi-hWdqTEAfuMPCyIT59uA,6327
-servalcat/refine/xtal.py,sha256=X7a_U9j7DTl1-OekvC0WmHcjt_ARF7Bp5ee-Rs3_thU,12075
-servalcat/refmac/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/refmac/exte.py,sha256=nTXTy9dXENnsXHq_1CgnCt6eJelBXBVhDq8vq1Ji_Ok,9027
-servalcat/refmac/refmac_keywords.py,sha256=U15TArxqL-2sVOmEu4lp6PMrYjZoZyyFQSCOYysa7IY,27149
-servalcat/refmac/refmac_wrapper.py,sha256=X3ZkqNoTxaxrVARVfK8cC-47rArlX15kmpZv2TxThM0,17026
-servalcat/spa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/spa/fofc.py,sha256=J1Zv8REWS931aP0W-D7HWuadMSdMdSLWAe6rg2xXNxw,22650
-servalcat/spa/fsc.py,sha256=rxynKDqMjoX8w7i4Ub4l7DQ8gRFXsthGn0AWykQvsBw,17663
-servalcat/spa/localcc.py,sha256=FJMXiC0Po5eb1Le404mgNDj9VcxH5CRR9F5B7uDZn5w,8173
-servalcat/spa/realspcc_from_var.py,sha256=x3NaqGKpGmQyh3qp-SJ9kTA_hP2EvxBOIszYbV2EPKk,5403
-servalcat/spa/run_refmac.py,sha256=NX3tC8cePXfCsJVqHvZ2IB_VhOOdYSgDVZ7lmCJov9w,49553
-servalcat/spa/shift_maps.py,sha256=G_EddBcdyncl2bhW7I-4YF0ZFtX9Q95a2SIJ9rpPeR4,13561
-servalcat/spa/shiftback.py,sha256=EtITj8Nllz-MWE6oJrxruDWeT0q7tS3RXCKtpWMuHNg,4801
-servalcat/spa/translate.py,sha256=8Cwxvxb_Ooi14ZcBaGu2xky0IFS92PHWzCzEDS6u2vY,5220
-servalcat/utils/__init__.py,sha256=4umrD2fhG1QAQppDBQM95-6y8QYbtxr7Mi_-Nkc3XOA,1172
-servalcat/utils/commands.py,sha256=7tE6fr8NZ7NR7-sIMU4YztU5aFb72ZApdLQ_q2x_IMk,65434
-servalcat/utils/fileio.py,sha256=OiycZdfHkNwIzvXRIJlIrOTM216J7INVhVn0OnuFOjE,29709
-servalcat/utils/generate_operators.py,sha256=fCrcTcciRn-6fpFtHYvf1oPXAObjuqR3WQejz5d0RrA,10980
-servalcat/utils/hkl.py,sha256=bgZXDs6V6Nnwta5zJykn75iupLAv38UTbdzwO26jM14,28465
-servalcat/utils/logger.py,sha256=2XKMrcc-COGBscVsLNqY9VEHN-AEJW_qFc8xJxs7W7U,3944
-servalcat/utils/maps.py,sha256=UXOGPr-uELKiHCbm6OHNBzTALpfDxm1TZFQjYFOQzcw,13562
-servalcat/utils/model.py,sha256=cqISbfdYm1Aixlvf7XMb9F3SAG1chq6E2I53ezjdOoc,30610
-servalcat/utils/refmac.py,sha256=LvynWy0D110Ikk9YzVMGfAZSj0vlBNEL-TAzmTnCF_Y,30814
-servalcat/utils/restraints.py,sha256=BeWa-PQEuaaInE_qU9oFC5W-pX9imIvnhMxWzkz1Wk4,36804
-servalcat/utils/symmetry.py,sha256=vDzGPza7PhmohTNf6OPTsMyUHvHJx7CEyl5Ob8OhukY,12232
-servalcat/xtal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/xtal/french_wilson.py,sha256=OixZuMkCanLn4L3g7CZSVkNzhYVMwUgqPBRcZnwWQ-0,11323
-servalcat/xtal/run_refmac_small.py,sha256=_Rw7wz7_yAlQgDqjJ_njeK6ZqN_r7KAakoor9WeNhxI,10634
-servalcat/xtal/sigmaa.py,sha256=Xd4lfOu9lwhSrSGxEe_bF3NhSEV6zBXkNG45v3XAC4U,66206
-servalcat-0.4.72.dist-info/METADATA,sha256=TZYkYT2ZTIau48irzZGbtp_ceVKiJm0iTG0N8x5MPn8,2741
-servalcat-0.4.72.dist-info/WHEEL,sha256=tcTF5BioUrOQaIPw5ryS5QMH_eju0kHydhlu3iIK_Go,103
-servalcat-0.4.72.dist-info/entry_points.txt,sha256=G1mDxhOCdF3umYz4k0kfwJbSdYSKqhvQdGCmrP8FRAY,111
-servalcat-0.4.72.dist-info/licenses/LICENSE,sha256=JoTeFzAOCkNGhvHsf4r2BFIHpLRXo_4EsrnOZV58XVA,17098
-servalcat-0.4.72.dist-info/RECORD,,