servalcat 0.4.72__cp312-cp312-macosx_11_0_arm64.whl → 0.4.88__cp312-cp312-macosx_11_0_arm64.whl

servalcat/xtal/twin.py

@@ -0,0 +1,115 @@
+"""
+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().to_numpy(), 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)
+            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) / sum(ratios))
+    alphas = numpy.maximum(0, numpy.mean(alphas, axis=0))
+    alphas /= numpy.sum(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)
+        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().to_numpy(), 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-0.4.88.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: servalcat
-Version: 0.4.72
+Version: 0.4.88
 Summary: Structure refinement and validation for crystallography and single particle analysis
 Author: Keitaro Yamashita, Garib N. Murshudov
 License: MPL-2.0
@@ -10,7 +10,7 @@ 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==0.6.7
 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 [v0.6.7](https://github.com/project-gemmi/gemmi/releases/tag/v0.6.7). 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-0.4.88.dist-info/RECORD

@@ -0,0 +1,45 @@
+servalcat-0.4.88.dist-info/RECORD,,
+servalcat-0.4.88.dist-info/WHEEL,sha256=1MNIlynTwkwwhETLr2_rT6EoaGjOw8ZJmXs1JD1RAw4,114
+servalcat-0.4.88.dist-info/entry_points.txt,sha256=G1mDxhOCdF3umYz4k0kfwJbSdYSKqhvQdGCmrP8FRAY,111
+servalcat-0.4.88.dist-info/METADATA,sha256=B0VVGu-KUJy9euhZEeDrZ_mIlwvMBeKh3e8Pz8zm_ww,2741
+servalcat-0.4.88.dist-info/licenses/LICENSE,sha256=HyVuytGSiAUQ6ErWBHTqt1iSGHhLmlC8fO7jTCuR8dU,16725
+servalcat/__init__.py,sha256=6hLXc7c2AoM0dJqaoKHAGlmleut4b6M7aAbDE0byRG4,231
+servalcat/ext.cpython-312-darwin.so,sha256=pWiZmt-i8GMjurYxZcEsq_FTyPsXBPJOYgakCHkgjgo,2131640
+servalcat/__main__.py,sha256=bNEZKrG5765uOp32UiBAJmeJi3O0sk4I5QjrXUbngIE,4070
+servalcat/refmac/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/refmac/refmac_keywords.py,sha256=yzYSJELMjdTnf4pT0_8EdIOjCDncqkjpPJ3VNcsFDrU,26649
+servalcat/refmac/exte.py,sha256=HtmlTHRzCeCN-vSJZdKCD1GIhQO6zTe1OKLUObC3gZ8,9019
+servalcat/refmac/refmac_wrapper.py,sha256=iZvHZRpFKrdxx0ggT9AFUmjnuBXyfZBdJ69ZnN0_zkQ,18130
+servalcat/xtal/twin.py,sha256=Q1lbYm17w75KohvOS5blyp8TEGviWJ9zJlmmy8zSnU8,4741
+servalcat/xtal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/xtal/sigmaa.py,sha256=LvRu76y0AqrT_n7LpDQnqcKm4NDkslroCkWowmIs5lk,74185
+servalcat/xtal/french_wilson.py,sha256=pL97K22WIkHHy_IexGPFhCan2WRHHemdWO0x7glTT7s,11656
+servalcat/xtal/run_refmac_small.py,sha256=Yg-bEPuOdQxCwdwY8StCvXabcWHrRl6A22gJgLsypeU,10394
+servalcat/utils/symmetry.py,sha256=H-5RBiQOp0MlWJE8LGJWvqe-YzmtzzrXfLO_2E_OpZU,11937
+servalcat/utils/generate_operators.py,sha256=fCrcTcciRn-6fpFtHYvf1oPXAObjuqR3WQejz5d0RrA,10980
+servalcat/utils/maps.py,sha256=ZoB3wwZZTLHYuwC4HBGFAYX4zmkZ8CdxD9wSLftL48c,13217
+servalcat/utils/__init__.py,sha256=j-fMAqHvzyMMQXb2Sf7Urnk4oQ31pT-g_NXf3K-NM4c,1137
+servalcat/utils/logger.py,sha256=oQcoKcM81fSsoQt_dKgwfUekJN5CcLMbti_kLb2loXM,3828
+servalcat/utils/model.py,sha256=_XpYd1WKtI1ErCXzNCxIukYClhJWl8BcFUfTgu-NB4E,30272
+servalcat/utils/restraints.py,sha256=IookRqipmUQlEgYRbt9lhzSuRHPuIq0QputfN87cEms,36911
+servalcat/utils/refmac.py,sha256=SFIReNexBpBBMgBUX67V_63NY8Yy8mOmAn9rYBPiDIo,30921
+servalcat/utils/commands.py,sha256=zkSFmdXIthC4ogvxgiHsVUyhBLZaiwflJAwP0CCBnZ8,64037
+servalcat/utils/hkl.py,sha256=3sw5NVJTKAp-7KzZmKsgGCpeRLKih4Wdf1kPK1JR4fM,28170
+servalcat/utils/fileio.py,sha256=NROzr_mpgc5qbvhaoEsIOHEFnN0uthabqKUiINE8Xnw,29085
+servalcat/spa/shiftback.py,sha256=A9OfaZ8r2BC6A2uGXxNNhmyBNORUB_MeqJC29ZRebnw,4664
+servalcat/spa/localcc.py,sha256=0otKfGKH33cFsD6Qvh8iL1mINlWqb3gqAbVKqy8fQPY,7985
+servalcat/spa/translate.py,sha256=InePz9d38KaUK4wr8uk06_6v4y80T3HYcURWp8c21zM,5091
+servalcat/spa/run_refmac.py,sha256=KWl7Cc6MLlsJdEsJ6MXBP8_2FiWeDZ66xmk04Ka-cVY,49196
+servalcat/spa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/spa/fsc.py,sha256=lRkNRRBSIcVlnoF5mvCKNXTxasp73a7SCLth4hTnWzE,17419
+servalcat/spa/realspcc_from_var.py,sha256=VpdvNEY4zRza08Vz727JI6Seq-ix-oujx4Gvzy_VkYI,5275
+servalcat/spa/shift_maps.py,sha256=iP1w4LNXETvZblElJ64AFMcE-lPrhx1s4SfacGktg4o,13268
+servalcat/spa/fofc.py,sha256=7ZG7wXtbcaeHG9dVZvYofNb75cbqthhE7O_XTVx-y70,22762
+servalcat/refine/xtal.py,sha256=YRZusmJXcMp1HtrKZiUd6JF-igS6MbHvOIuyFSPOVv0,14384
+servalcat/refine/refine.py,sha256=4ly66LSUNHbT6hqRnp-J-0G0CXOwLu_UKHW0LzT9CUw,38290
+servalcat/refine/refine_spa.py,sha256=J6LS8efSQ6sHEp5VH4It8TT734CQ5SVknP5AiQW9p0U,17896
+servalcat/refine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+servalcat/refine/spa.py,sha256=P_IkA291ocl92SpZ8Uagcab_Usqj2JzW8cAw_aCPmpg,6238
+servalcat/refine/cgsolve.py,sha256=tHuWXr76x4sRAMUQ4dGVJzyHF_n1LiwKHTjAwh8iFMg,3072
+servalcat/refine/refine_geom.py,sha256=GNVyll5LVoEmAzzenikg-nKjJXCtJ8B8Gd13q5nMtCk,10757
+servalcat/refine/refine_xtal.py,sha256=tW4AC1O8esxls6MS6YMiya-R41-daIROGxZscLf2b4c,13843

{servalcat-0.4.72.dist-info → servalcat-0.4.88.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: scikit-build-core 0.9.5
+Generator: scikit-build-core 0.10.6
 Root-Is-Purelib: false
 Tag: cp312-cp312-macosx_11_0_arm64
 

servalcat-0.4.72.dist-info/RECORD

@@ -1,44 +0,0 @@
-servalcat-0.4.72.dist-info/RECORD,,
-servalcat-0.4.72.dist-info/WHEEL,sha256=mgQAlqZn1gpBQ0zqn0f5_muqckw_PxmecVM-Qtn7Mi0,113
-servalcat-0.4.72.dist-info/entry_points.txt,sha256=G1mDxhOCdF3umYz4k0kfwJbSdYSKqhvQdGCmrP8FRAY,111
-servalcat-0.4.72.dist-info/METADATA,sha256=TZYkYT2ZTIau48irzZGbtp_ceVKiJm0iTG0N8x5MPn8,2741
-servalcat-0.4.72.dist-info/licenses/LICENSE,sha256=HyVuytGSiAUQ6ErWBHTqt1iSGHhLmlC8fO7jTCuR8dU,16725
-servalcat/__init__.py,sha256=FjeqVIsFlkCS8CNh8kLmauTGhRN3GKyJk1EzJT-OPa8,231
-servalcat/ext.cpython-312-darwin.so,sha256=wditWvvIiuQzxDlR8kWMDlBAJLHIGF2fOFfcfIe2qH8,1996232
-servalcat/__main__.py,sha256=bNEZKrG5765uOp32UiBAJmeJi3O0sk4I5QjrXUbngIE,4070
-servalcat/refmac/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/refmac/refmac_keywords.py,sha256=0l04qPfsjTu8Ipr2e1JwnBsmnQws3iVB_E0cnnaMHdo,26512
-servalcat/refmac/exte.py,sha256=jlRBlNslSKPC0Gt6DZ4JFw1l9SqPDalsOv5E-5M5WN8,8847
-servalcat/refmac/refmac_wrapper.py,sha256=e404-q0cd8_NeIkLKC9lzfjKxS9GFqxPVSUwtNUyM3s,16658
-servalcat/xtal/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/xtal/sigmaa.py,sha256=y2bfLbesfdvi8KS3nuUkAa6CPdWNIPY73nrL2svZJTw,64792
-servalcat/xtal/french_wilson.py,sha256=Y90X8AwgnwOZ3sTyOD1IIAWaOV4g69zDym3CcIPJEw8,11073
-servalcat/xtal/run_refmac_small.py,sha256=Yg-bEPuOdQxCwdwY8StCvXabcWHrRl6A22gJgLsypeU,10394
-servalcat/utils/symmetry.py,sha256=H-5RBiQOp0MlWJE8LGJWvqe-YzmtzzrXfLO_2E_OpZU,11937
-servalcat/utils/generate_operators.py,sha256=fCrcTcciRn-6fpFtHYvf1oPXAObjuqR3WQejz5d0RrA,10980
-servalcat/utils/maps.py,sha256=ZoB3wwZZTLHYuwC4HBGFAYX4zmkZ8CdxD9wSLftL48c,13217
-servalcat/utils/__init__.py,sha256=j-fMAqHvzyMMQXb2Sf7Urnk4oQ31pT-g_NXf3K-NM4c,1137
-servalcat/utils/logger.py,sha256=oQcoKcM81fSsoQt_dKgwfUekJN5CcLMbti_kLb2loXM,3828
-servalcat/utils/model.py,sha256=cijlnPeMFIBHEQYw_CtJd2nPZXUXdsHN83h4vvelMRw,29841
-servalcat/utils/restraints.py,sha256=mpW-v08cGyX21FseO6AIB0babQznQpeRYwDqJWkfe8k,36032
-servalcat/utils/refmac.py,sha256=y18HZkpxG8pJPipCZJB3E25NiqrCpEqt_DFGuHHc3aw,30073
-servalcat/utils/commands.py,sha256=zkSFmdXIthC4ogvxgiHsVUyhBLZaiwflJAwP0CCBnZ8,64037
-servalcat/utils/hkl.py,sha256=H0QnnvXFqhmnzXAcCeCcPmpiKy7W5AOqVUmB-np4n3E,27765
-servalcat/utils/fileio.py,sha256=6znifeyHQ0warGJrLR6L0nCgryActgkSPzkmXEMRra8,28975
-servalcat/spa/shiftback.py,sha256=A9OfaZ8r2BC6A2uGXxNNhmyBNORUB_MeqJC29ZRebnw,4664
-servalcat/spa/localcc.py,sha256=0otKfGKH33cFsD6Qvh8iL1mINlWqb3gqAbVKqy8fQPY,7985
-servalcat/spa/translate.py,sha256=InePz9d38KaUK4wr8uk06_6v4y80T3HYcURWp8c21zM,5091
-servalcat/spa/run_refmac.py,sha256=gQE4I-x_hzcU6DlDq5xW47fVMaDoCR5GlpOfjiv5s2A,48591
-servalcat/spa/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/spa/fsc.py,sha256=qTz8nS_KJpno0s0Hw7Isp2n_6PDzaYkBye5zSnO3Ufg,17278
-servalcat/spa/realspcc_from_var.py,sha256=VpdvNEY4zRza08Vz727JI6Seq-ix-oujx4Gvzy_VkYI,5275
-servalcat/spa/shift_maps.py,sha256=iP1w4LNXETvZblElJ64AFMcE-lPrhx1s4SfacGktg4o,13268
-servalcat/spa/fofc.py,sha256=OvF1_wUcUzG4JLkRsCj-1ea2ukbQrc6ki01vI9aTISo,22188
-servalcat/refine/xtal.py,sha256=VnrGjWgRfj9ALGfHXgLIYswMwqsqe4vO7nsqrAFm8XA,11848
-servalcat/refine/refine.py,sha256=KAzc8NSmhGunFqJD6SWcliEwtXSPULHNNxJF4W2LMuA,38227
-servalcat/refine/refine_spa.py,sha256=HTzhmUkoxzxeY5qFlW6-Ryla7a0-TwiBWR6P3AaxjRs,17340
-servalcat/refine/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-servalcat/refine/spa.py,sha256=-7O6a0-1YCfyRtlKbAT5sFseg7XkDTybt9uFC4vDVAQ,6194
-servalcat/refine/cgsolve.py,sha256=tHuWXr76x4sRAMUQ4dGVJzyHF_n1LiwKHTjAwh8iFMg,3072
-servalcat/refine/refine_geom.py,sha256=nWeHjWG3ieKP9JDUi-4XAxNpELIPuxawA59_PM-4W9o,10366
-servalcat/refine/refine_xtal.py,sha256=UEx1fYHk9p23AaWTFYg8P1_TUetLmouqPGfCLcjOufc,12595