very promising

ipqa-research · Sep 6, 2024 · 678160e · 678160e
1 parent 203447c
commit 678160e
Show file tree

Hide file tree

Showing 6 changed files with 359 additions and 130 deletions.
diff --git a/ugropy/groupscsv/unifac/unifac_info.csv b/ugropy/groupscsv/unifac/unifac_info.csv
@@ -111,4 +111,4 @@ NCO|109|51|1.0567|0.732
 (CH2)2SU|118|55|2.6869|2.12
 CH2CHSU|119|55|2.4595|1.808
 IMIDAZOL|178|84|2.026|0.868
-BTI|179|85|5.774|4.932
+BTI|179|85|5.774|4.932
diff --git a/ugropy/groupscsv/unifac/unifac_subgroups.csv b/ugropy/groupscsv/unifac/unifac_subgroups.csv
@@ -1,114 +1,114 @@
-group|detection_smarts|smarts|contribute|composed|molecular_weight
-CH3|[CX4H3]||"{""CH3"": 1}"|n|15.035
-CH2|[CX4H2]||"{""CH2"": 1}"|n|14.027
-CH|[CX4H]||"{""CH"": 1}"|n|13.019
-C|[CX4H0]||"{""C"": 1}"|n|12.011
-CH2=CH|[CH2]=[CH]||"{""CH2=CH"": 1}"|n|27.046
-CH=CH|[CH]=[CH]||"{""CH=CH"": 1}"|n|26.038
-CH2=C|[CH2]=[CH0]||"{""CH2=C"": 1}"|n|26.038
-CH=C|[CH]=[CH0]||"{""CH=C"": 1}"|n|25.03
-ACH|[cH]||"{""ACH"": 1}"|n|13.019
-AC|[cH0]||"{""AC"": 1}"|n|12.011
-ACCH3|[c][CX4H3]||"{""ACCH3"": 1, ""CH3"": -1, ""AC"": -1}"|y|27.046
-ACCH2|[c][CX4H2]||"{""ACCH2"": 1, ""CH2"": -1, ""AC"": -1}"|y|26.038
-ACCH|[c][CX4H]||"{""ACCH"": 1, ""CH"": -1, ""AC"": -1}"|y|25.03
-OH|[OH]||"{""OH"": 1}"|n|17.007
-CH3OH|[CH3][OH]||"{""CH3OH"": 1, ""CH3"": -1, ""OH"": -1}"|n|32.042
-H2O|[OH2]||"{""H2O"": 1}"|n|18.015
-ACOH|[cH0][OH]||"{""ACOH"": 1, ""OH"": -1, ""AC"": -1}"|y|29.018
-CH3CO|[CH3]C(=O)([#6,Si])|[CH3]C(=O)|"{""CH3CO"": 1, ""CH3"" : -1}"|n|43.045
-CH2CO|[CH2]C(=O)[$([#6,Si]);!$([CH3])]|[CH2]C(=O)|"{""CH2CO"": 1, ""CH2"": -1}"|n|42.037
-HCO|[CH](=O)([#6,Si])|[CH](=O)|"{""HCO"": 1}"|n|29.018
-CH3COO|[CH3][C](=O)[OH0]||"{""CH3COO"": 1, ""CH3"": -1, ""COO"": -1}"|y|59.044
-CH2COO|[CH2][C](=O)[OH0]||"{""CH2COO"": 1, ""CH2"": -1, ""COO"": -1}"|y|58.036
-HCOO|[CH](=O)[OH0]||"{""HCOO"": 1, ""COO"": -1}"|n|45.017
-CH3O|[CH3]O[$([Si,#6]);!$([CH](=O));!$(C(=O)[!O])]|[CH3][OH0]|"{""CH3O"": 1, ""CH3"": -1}"|n|31.034
-CH2O|[CH2]O[$([Si,#6]);!$([CH](=O));!$(C(=O)[!O]);!$([CH3])]|[CH2][OH0]|"{""CH2O"": 1, ""CH2"": -1}"|n|30.026
-CHO|[CH]O[$([Si,#6]);!$([CH](=O));!$(C(=O)[!O]);!$([CH3]);!$([CH2])]|[CH][OH0]|"{""CHO"": 1, ""CH"": -1}"|n|29.018
-THF|[C]1[CH2]O[CH2][C]1|[CH2;R][O;R]|"{""THF"": 1, ""CH2O"": -1}"|n|30.026
-CH3NH2|[CH3][NH2]||"{""CH3NH2"": 1, ""CH3"": -1}"|n|31.058
-CH2NH2|[CH2][NH2]||"{""CH2NH2"": 1, ""CH2"": -1}"|n|30.05
-CHNH2|[CH][NH2]||"{""CHNH2"": 1, ""CH"": -1}"|n|29.042
-CH3NH|[CH3][NH][#6,Si;!$([CH](=O));!$(C(=O)[!N])]|[CH3][NH]|"{""CH3NH"": 1, ""CH3"": -1}"|n|30.05
-CH2NH|[CH2][NH][$([#6,Si;!$([CH](=O));!$(C(=O)[!N])])&!$([CH3])]|[CH2][NH]|"{""CH2NH"": 1, ""CH2"": -1}"|n|29.042
-CHNH|[CH][NH][$([#6,Si;!$([CH](=O));!$(C(=O)[!N])])&!$([CH3])&!$([CH2])]|[CH][NH]|"{""CHNH"": 1, ""CH"": -1}"|n|28.034
-CH3N|[CH3][NH0]([#6,Si;!$([CH](=O));!$(C(=O)[!N])])[#6,Si;!$([CH](=O));!$(C(=O)[!N])]|[CH3][NH0]|"{""CH3N"": 1, ""CH3"": -1}"|n|29.042
-CH2N|[CH2][NH0]([$([#6,Si;!$([CH](=O));!$(C(=O)[!N])])&!$([CH3])])[$([#6,Si;!$([CH](=O));!$(C(=O)[!N])])&!$([CH3])]|[CH2][NH0]|"{""CH2N"": 1, ""CH2"": -1}"|n|28.034
-ACNH2|[cH0][NH2]||"{""ACNH2"": 1, ""AC"": -1}"|n|28.034
-C5H5N|[n](:[cH]:[cH]1):[cH]:[cH]:[cH]:1||"{""C5H5N"": 1, ""ACH"": -5}"|n|79.102
-C5H4N|[n](:[cH0]:[cH]1):[cH]:[cH]:[cH]:1,[n](:[cH]:[cH0]1):[cH]:[cH]:[cH]:1,[n](:[cH]:[cH]1):[cH0]:[cH]:[cH]:1,[n](:[cH]:[cH]1):[cH]:[cH]:[cH0]:1||"{""C5H4N"": 1, ""ACH"": -4, ""AC"":-1}"|n|78.094
-C5H3N|[n](:[cH]:[cH]1):[cH0]:[cH0]:[cH]:1,[n](:[cH]:[cH]1):[cH0]:[cH]:[cH0]:1,[n](:[cH]:[cH0]1):[cH0]:[cH]:[cH]:1,[n](:[cH0]:[cH]1):[cH0]:[cH]:[cH]:1,[n](:[cH]:[cH]1):[cH]:[cH0]:[cH0]:1||"{""C5H3N"": 1, ""ACH"": -3, ""AC"": -2}"|n|77.086
-CH3CN|[CH3][C]#[N]||"{""CH3CN"": 1, ""CH3"": -1}"|n|41.053
-CH2CN|[CH2][C]#[N]||"{""CH2CN"": 1, ""CH2"": -1}"|n|40.045
-COOH|[CH0](*)(=O)(-[OH])|[CH0](=O)(-[OH])|"{""COOH"": 1, ""OH"": -1}"|n|45.017
-HCOOH|[CH](=O)(-[OH])||"{""HCOOH"": 1, ""OH"": -1}"|n|46.025
-CH2CL|[CH2](Cl)([!Cl])|[CH2][Cl]|"{""CH2CL"": 1, ""CH2"": -1}"|n|49.48
-CHCL|[CH](Cl)([!Cl])([!Cl])|[CH][Cl]|"{""CHCL"": 1, ""CH"": -1}"|n|48.472
-CCL|[CH0](Cl)([!Cl])([!Cl])([!Cl])|[CH0][Cl]|"{""CCL"": 1, ""C"": -1}"|n|47.464
-CH2CL2|[CH2](Cl)(Cl)||"{""CH2CL2"": 1, ""CH2"": -1}"|n|84.933
-CHCL2|[CH](Cl)(Cl)([!Cl])|[CH](Cl)(Cl)|"{""CHCL2"": 1, ""CH"": -1}"|n|83.925
-CCL2|[CH0](Cl)(Cl)([!Cl])([!Cl])|[CH0](Cl)(Cl)|"{""CCL2"": 1, ""C"": -1}"|n|82.917
-CHCL3|[CH](Cl)(Cl)(Cl)||"{""CHCL3"": 1, ""CH"": -1}"|n|119.378
-CCL3|[CH0](Cl)(Cl)(Cl)([!Cl])|[CH0](Cl)(Cl)(Cl)|"{""CCL3"": 1, ""C"": -1}"|n|118.37
-CCL4|[CH0](Cl)(Cl)(Cl)(Cl)||"{""CCL4"": 1, ""C"": -1}"|n|153.823
-ACCL|[cH0](Cl)||"{""ACCL"": 1, ""AC"": -1}"|n|47.464
-CH3NO2|[CH3]N(=O)(O)||"{""CH3NO2"": 1, ""CH3"": -1}"|n|61.04
-CH2NO2|[CH2]N(=O)(O)||"{""CH2NO2"": 1, ""CH2"": -1}"|n|60.032
-CHNO2|[CH]N(=O)(O)||"{""CHNO2"": 1, ""CH"": -1}"|n|59.024
-ACNO2|[cH0]N(=O)(O)||"{""ACNO2"": 1, ""AC"": -1}"|n|58.016
-CS2|C(=S)(=S)||"{""CS2"": 1}"|n|76.141
-CH3SH|[CH3][SH]||"{""CH3SH"": 1, ""CH3"": -1}"|n|48.1072
-CH2SH|[CH2][SH]||"{""CH2SH"": 1, ""CH2"": -1}"|n|47.0994
-FURFURAL|c1coc(c1)[CH]=O||"{""FURFURAL"": 1, ""ACH"": -3, ""HCO"": -1, ""CH"": 1, ""AC"": -1}"|n|96.0842
-DOH|[CH2]([OH])[CH2][OH]||"{""DOH"": 1, ""CH2"": -2, ""OH"": -2}"|n|62.0668
-I|[I][#6,Si]|[I]|"{""I"": 1}"|n|126.9
-BR|[Br][#6,Si]|[Br]|"{""BR"": 1}"|n|79.904
-CH=-C|[CH]#[C][*]|[CH]#[C]|"{""CH=-C"": 1}"|n|25.0298
-C=-C|[*][CH0]#[CH0][*]|[CH0]#[CH0]|"{""C=-C"": 1}"|n|24.022
-DMSO|[CH3][S](=O)[CH3]||"{""DMSO"": 1, ""CH3"": -1, ""CH3S"": -1}"|n|78.1328
-ACRY|[CH2]=[CH]-C#N||"{""ACRY"": 1, ""CH2=CH"": -1}"|n|53.0634
-CL-(C=C)|Cl[C]=[C]||"{""CL-(C=C)"": 1}"|n|35.453
-C=C|[CH0]=[CH0]||"{""C=C"": 1}"|n|24.022
-ACF|[cH0]F||"{""ACF"": 1, ""AC"": -1}"|n|31.009
-DMF|[CH3]N([CH3])[CH]=O||"{""DMF"": 1, ""CH3"": -2}"|n|73.0936
-HCON(CH2)2|[*][CH2]N([CH2][*])[CH]=O|[CH2]N([CH2])[CH]=O|"{""HCON(CH2)2"": 1, ""CH2"": -2}"|n|71.078
-CF3|[CH0](F)(F)(F)[!F]|[CH0](F)(F)(F)|"{""CF3"": 1, ""C"": -1}"|n|69.005
-CF2|[CH0](F)(F)([!F])[!F]|[CH0](F)(F)|"{""CF2"": 1, ""C"": -1}"|n|50.007
-CF|[CH0](F)([!F])([!F])[!F]|[CH0](F)|"{""CF"": 1, ""C"": -1}"|n|31.009
-COO|[C](*)(=O)[OH0][#6,Si]|[C](=O)[OH0]|"{""COO"": 1}"|n|44.009
-SIH3|[SiX4H3]||"{""SIH3"": 1}"|n|31.1094
-SIH2|[SiX4H2]||"{""SIH2"": 1}"|n|30.1016
-SIH|[SiX4H]||"{""SIH"": 1}"|n|29.0938
-SI|[SiX4H0]||"{""SI"": 1}"|n|28.086
-SIH2O|[SiX4H2]O[Si,CH0;!$([CH](=O));!$(C(=O)[!O])]|[SiX4H2]O|"{""SIH2O"": 1, ""SIH2"": -1}"|n|46.1006
-SIHO|[SiX4H]O[Si,CH0;!$([SiH2]);!$([CH](=O));!$(C(=O)[!O])]|[SiX4H]O|"{""SIHO"": 1, ""SIH"": -1}"|n|45.0928
-SIO|[SiX4H0]O[Si,CH0;!$([SiH]);!$([SiH2]);!$([CH](=O));!$(C(=O)[!O])]|[SiX4H0]O|"{""SIO"": 1, ""SI"": -1}"|n|44.085
-NMP|[CH2]1N([CH3])[C](=O)[CH2][CH2]1||"{""NMP"": 1, ""CH2"": -2, ""AMCH3CH2"": -1}"|n|99.1312
-CCL3F|[CH0](Cl)(Cl)(Cl)(F)||"{""CCL3F"": 1, ""CCL3"": -1, ""CF"": -1, ""C"": 1}"|n|137.368
-CCL2F|[CH0](Cl)(Cl)(F)([!Cl&!F])|[CH0](Cl)(Cl)(F)|"{""CCL2F"": 1, ""CCL2"": -1, ""CF"": -1, ""C"": 1}"|n|101.915
-HCCL2F|[CH](Cl)(Cl)(F)||"{""HCCL2F"": 1, ""CHCL2"": -1}"|n|102.9228
-HCCLF|[CH](Cl)(F)([!Cl&!F])|[CH](Cl)(F)|"{""HCCLF"": 1, ""CHCL"": -1}"|n|67.4698
-CCLF2|[CH0](Cl)(F)(F)([!Cl&!F])|[CH0](Cl)(F)(F)|"{""CCLF2"": 1, ""CCL"": -1, ""CF2"": -1, ""C"": 1}"|n|85.46
-HCCLF2|[CH](Cl)(F)(F)||"{""HCCLF2"": 1, ""CHCL"": -1}"|n|86.4678
-CCLF3|[CH0](Cl)(F)(F)(F)||"{""CCLF3"": 1, ""CCL"": -1, ""CF3"": -1, ""C"": 1}"|n|104.458
-CCL2F2|[CH0](Cl)(Cl)(F)(F)||"{""CCL2F2"": 1, ""CCL2"": -1, ""CF2"": -1, ""C"": 1}"|n|120.913
-AMH2|[CH0](=O)([NH2])([!O])|[CH0](=O)([NH2])|"{""AMH2"": 1}"|n|44.0326
-AMHCH3|[CH0](=O)([NH][CH3])([!O])|[CH0](=O)([NH][CH3])|"{""AMHCH3"": 1, ""CH3"": -1}"|n|58.0592
-AMHCH2|[CH0](=O)([NH][CH2])([!O])|[CH0](=O)([NH][CH2])|"{""AMHCH2"": 1, ""CH2"": -1}"|n|57.0514
-AM(CH3)2|[CH0](=O)([N]([CH3])[CH3])([!O])|[CH0](=O)([N]([CH3])[CH3])|"{""AM(CH3)2"": 1, ""CH3"": -2}"|n|72.0858
-AMCH3CH2|[CH0](=O)([N]([CH3])[CH2])([!O])|[CH0](=O)([N]([CH3])[CH2])|"{""AMCH3CH2"": 1, ""CH3"": -1, ""CH2"": -1}"|n|71.078
-AM(CH2)2|[CH0](=O)([N]([CH2])[CH2])([!O])|[CH0](=O)([N]([CH2])[CH2])|"{""AM(CH2)2"": 1, ""CH2"": -2}"|n|70.0702
-C2H5O2|[OH][CH2][CH2]O[#6,Si]|[OH][CH2][CH2]O|"{""C2H5O2"": 1, ""OH"": -1, ""CH2"": -1, ""CH2O"": -1}"|y|61.059
-C2H4O2|[OH][CH2][CH]O[#6,Si]|[OH][CH2][CH]O|"{""C2H4O2"": 1, ""OH"": -1, ""CHO"": -1, ""CH2"": -1}"|y|60.0512
-CH3S|[CH3][S][#6,Si]|[CH3][S]|"{""CH3S"": 1, ""CH3"": -1}"|n|47.0994
-CH2S|[CH2][S][$([#6,Si])&!$([CH3])]|[CH2][S]|"{""CH2S"": 1, ""CH2"": -1}"|n|46.0916
-CHS|[CH][S][$([#6,Si])&!$([CH3])&!$([CH2])]|[CH][S]|"{""CHS"": 1, ""CH"": -1}"|n|45.0838
-MORPH|[CH2]1O[CH2][CH2][NH][CH2]1||"{""MORPH"": 1, ""CH2"": -2, ""CH2O"": -1, ""CH2NH"": -1}"|n|87.1202
-C4H4S|[s](:[cH]:[cH]1):[cH]:[cH]:1||"{""C4H4S"": 1, ""ACH"": -4}"|n|84.1402
-C4H3S|[s](:[cH0]:[cH]1):[cH]:[cH]:1,[s](:[cH]:[cH0]1):[cH]:[cH]:1||"{""C4H3S"": 1, ""ACH"": -3, ""AC"": -1}"|n|83.1324
-C4H2S|[s](:[cH]:[cH]1):[cH0]:[cH0]:1,[s](:[cH]:[cH0]1):[cH0]:[cH]:1,[s](:[cH0]:[cH]1):[cH0]:[cH]:1,[s](:[cH]:[cH0]1):[cH]:[cH0]:1||"{""C4H2S"": 1, ""ACH"": -2, ""AC"": -2}"|n|82.1246
-NCO|[NX2H0]=[CX2H0]=[OX1H0]||"{""NCO"": 1}"|n|42.017
-(CH2)2SU|[CH2]S(=O)(=O)[CH2]||"{""(CH2)2SU"": 1, ""CH2"": -1, ""CH2S"": -1}"|n|92.1162
-CH2CHSU|[CH2]S(=O)(=O)[CH]||"{""CH2CHSU"": 1, ""CH"": -1, ""CH2S"": -1}"|n|91.1084
-IMIDAZOL|[c]1:[c]:[n]:[c]:[n]:1||"{""IMIDAZOL"": 1, ""ACH"": -3}"|n|68.0782
-BTI|C(F)(F)(F)S(=O)(=O)[N-]S(=O)(=O)C(F)(F)F||"{""BTI"": 1, ""CF3"": -2}"|n|279.91784
+group|smarts|molecular_weight
+CH3|[CX4H3]|15.035
+CH2|[CX4H2]|14.027
+CH|[CX4H]|13.019
+C|[CX4H0]|12.011
+CH2=CH|[CH2]=[CH]|27.046
+CH=CH|[CH]=[CH]|26.038
+CH2=C|[CH2]=[CH0]|26.038
+CH=C|[CH]=[CH0]|25.03
+ACH|[cH]|13.019
+AC|[cH0]|12.011
+ACCH3|[c][CX4H3]|27.046
+ACCH2|[c][CX4H2]|26.038
+ACCH|[c][CX4H]|25.03
+OH|[OH]|17.007
+CH3OH|[CH3][OH]|32.042
+H2O|[OH2]|18.015
+ACOH|[cH0][OH]|29.018
+CH3CO|[CH3]C(=O)|43.045
+CH2CO|[CH2]C(=O)|42.037
+HCO|[CH](=O)|29.018
+CH3COO|[CH3][C](=O)[OH0]|59.044
+CH2COO|[CH2][C](=O)[OH0]|58.036
+HCOO|[CH](=O)[OH0]|45.017
+CH3O|[CH3][OH0]|31.034
+CH2O|[CH2][OH0]|30.026
+CHO|[CH][OH0]|29.018
+THF|[CH2;R][O;R]|30.026
+CH3NH2|[CH3][NH2]|31.058
+CH2NH2|[CH2][NH2]|30.05
+CHNH2|[CH][NH2]|29.042
+CH3NH|[CH3][NH]|30.05
+CH2NH|[CH2][NH]|29.042
+CHNH|[CH][NH]|28.034
+CH3N|[CH3][NH0]|29.042
+CH2N|[CH2][NH0]|28.034
+ACNH2|[cH0][NH2]|28.034
+C5H5N|[n](:[cH]:[cH]1):[cH]:[cH]:[cH]:1|79.102
+C5H4N|[n](:[cH0]:[cH]1):[cH]:[cH]:[cH]:1,[n](:[cH]:[cH0]1):[cH]:[cH]:[cH]:1,[n](:[cH]:[cH]1):[cH0]:[cH]:[cH]:1,[n](:[cH]:[cH]1):[cH]:[cH]:[cH0]:1|78.094
+C5H3N|[n](:[cH]:[cH]1):[cH0]:[cH0]:[cH]:1,[n](:[cH]:[cH]1):[cH0]:[cH]:[cH0]:1,[n](:[cH]:[cH0]1):[cH0]:[cH]:[cH]:1,[n](:[cH0]:[cH]1):[cH0]:[cH]:[cH]:1,[n](:[cH]:[cH]1):[cH]:[cH0]:[cH0]:1|77.086
+CH3CN|[CH3][C]#[N]|41.053
+CH2CN|[CH2][C]#[N]|40.045
+COOH|[CH0](=O)[OH]|45.017
+HCOOH|[CH](=O)[OH]|46.025
+CH2CL|[CH2][Cl]|49.48
+CHCL|[CH][Cl]|48.472
+CCL|[CH0][Cl]|47.464
+CH2CL2|[CH2](Cl)(Cl)|84.933
+CHCL2|[CH](Cl)(Cl)|83.925
+CCL2|[CH0](Cl)(Cl)|82.917
+CHCL3|[CH](Cl)(Cl)(Cl)|119.378
+CCL3|[CH0](Cl)(Cl)(Cl)|118.37
+CCL4|[CH0](Cl)(Cl)(Cl)(Cl)|153.823
+ACCL|[cH0](Cl)|47.464
+CH3NO2|[CH3]N(=O)(O)|61.04
+CH2NO2|[CH2]N(=O)(O)|60.032
+CHNO2|[CH]N(=O)(O)|59.024
+ACNO2|[cH0]N(=O)(O)|58.016
+CS2|C(=S)(=S)|76.141
+CH3SH|[CH3][SH]|48.1072
+CH2SH|[CH2][SH]|47.0994
+FURFURAL|c1coc(c1)[CH]=O|96.0842
+DOH|[CH2]([OH])[CH2][OH]|62.0668
+I|[I]|126.9
+BR|[Br]|79.904
+CH=-C|[CH]#[C]|25.0298
+C=-C|[CH0]#[CH0]|24.022
+DMSO|[CH3][S](=O)[CH3]|78.1328
+ACRY|[CH2]=[CH]-C#N|53.0634
+CL-(C=C)|Cl[C]=[C]|35.453
+C=C|[CH0]=[CH0]|24.022
+ACF|[cH0]F|31.009
+DMF|[CH3]N([CH3])[CH]=O|73.0936
+HCON(CH2)2|[CH2]N([CH2])[CH]=O|71.078
+CF3|[CH0](F)(F)(F)|69.005
+CF2|[CH0](F)(F)|50.007
+CF|[CH0](F)|31.009
+COO|[C](=O)[OH0]|44.009
+SIH3|[SiX4H3]|31.1094
+SIH2|[SiX4H2]|30.1016
+SIH|[SiX4H]|29.0938
+SI|[SiX4H0]|28.086
+SIH2O|[SiX4H2][OH0]|46.1006
+SIHO|[SiX4H][OH0]|45.0928
+SIO|[SiX4H0][OH0]|44.085
+NMP|[CH2]1N([CH3])[C](=O)[CH2][CH2]1|99.1312
+CCL3F|[CH0](Cl)(Cl)(Cl)(F)|137.368
+CCL2F|[CH0](Cl)(Cl)(F)|101.915
+HCCL2F|[CH](Cl)(Cl)(F)|102.9228
+HCCLF|[CH](Cl)(F)|67.4698
+CCLF2|[CH0](Cl)(F)(F)|85.46
+HCCLF2|[CH](Cl)(F)(F)|86.4678
+CCLF3|[CH0](Cl)(F)(F)(F)|104.458
+CCL2F2|[CH0](Cl)(Cl)(F)(F)|120.913
+AMH2|[CH0](=O)([NH2])|44.0326
+AMHCH3|[CH0](=O)([NH][CH3])|58.0592
+AMHCH2|[CH0](=O)([NH][CH2])|57.0514
+AM(CH3)2|[CH0](=O)([N]([CH3])[CH3])|72.0858
+AMCH3CH2|[CH0](=O)([N]([CH3])[CH2])|71.078
+AM(CH2)2|[CH0](=O)([N]([CH2])[CH2])|70.0702
+C2H5O2|[OH][CH2][CH2][OH0]|61.059
+C2H4O2|[OH][CH2][CH][OH0]|60.0512
+CH3S|[CH3][SH0]|47.0994
+CH2S|[CH2][SH0]|46.0916
+CHS|[CH][SH0]|45.0838
+MORPH|[CH2]1O[CH2][CH2][NH][CH2]1|87.1202
+C4H4S|[s](:[cH]:[cH]1):[cH]:[cH]:1|84.1402
+C4H3S|[s](:[cH0]:[cH]1):[cH]:[cH]:1,[s](:[cH]:[cH0]1):[cH]:[cH]:1|83.1324
+C4H2S|[s](:[cH]:[cH]1):[cH0]:[cH0]:1,[s](:[cH]:[cH0]1):[cH0]:[cH]:1,[s](:[cH0]:[cH]1):[cH0]:[cH]:1,[s](:[cH]:[cH0]1):[cH]:[cH0]:1|82.1246
+NCO|[NX2H0]=[CX2H0]=[OX1H0]|42.017
+(CH2)2SU|[CH2]S(=O)(=O)[CH2]|92.1162
+CH2CHSU|[CH2]S(=O)(=O)[CH]|91.1084
+IMIDAZOL|[c]1:[c]:[n]:[c]:[n]:1|68.0782
+BTI|C(F)(F)(F)S(=O)(=O)[N-]S(=O)(=O)C(F)(F)F|279.91784
diff --git a/ugropy/refactor/__init__.py b/ugropy/refactor/__init__.py
@@ -1,6 +1,6 @@
 from .fragment import Fragment
 from .fragmentation_model import FragmentationModel
-from .fragmentation_unifac import unifac
+from .fragmentation_unifac import unifac2
 
 
 __all__ = ["Fragment", "FragmentationModel", "unifac"]
diff --git a/ugropy/refactor/fragmentation_model.py b/ugropy/refactor/fragmentation_model.py
@@ -1,21 +1,118 @@
 from typing import List
 
+import itertools
+
 from ugropy.refactor.fragment import Fragment
 
 from rdkit import Chem
 
+import numpy as np
+
+import pulp
+
 
 class FragmentationModel:
     def __init__(self, fragments: List[Fragment]):
         self.fragments = fragments
 
     def detect_fragments(self, molecule: Chem.rdchem.Mol):
-        detected = {}
+        batch = DetectionBatch(molecule)
 
         for fragment in self.fragments:
             match = molecule.GetSubstructMatches(fragment.mol_object)
 
             if match:
-                detected[fragment.name] = match
+                batch.add_fragment(fragment.name, match)
+        return batch
+
+class DetectionBatch:
+    def __init__(self, molecule: Chem.rdchem.Mol):     
+        self.n = molecule.GetNumAtoms()
+        self.fragments = {}
+        self.overlaped_fragments = {}
+        self.selected_fragments = []
+        self.overlaped_atoms = []
+        self.atoms_matrix = np.array([])
+        self.solution_atoms = {}
+        self.solution = {}
+
+        self.has_overlap = False
+
+
+    def get_groups(self):
+        self.build_overlap_matrix()
+        self.get_overlaped_fragments()
+        self.solve_overlap()
+
+        for frag in self.overlaped_fragments.keys():
+            if frag not in self.selected_fragments:
+                self.fragments.pop(frag)
+
+        for frag in self.fragments.keys():
+            name = frag.split("_")[0]
+
+            if name not in self.solution_atoms.keys():
+                self.solution_atoms[name] = [self.fragments[frag]]
+            else:
+                self.solution_atoms[name].append(self.fragments[frag])
+
+        for frag in self.solution_atoms.keys():
+            self.solution[frag] = len(self.solution_atoms[frag])
+
+
+    def add_fragment(self, fragment_name: str, fragments: tuple):
+        for i, f in enumerate(fragments):
+            self.fragments[f"{fragment_name}_{i}"] = list(f)
+
+    def build_overlap_matrix(self):
+        self.atoms_matrix = np.zeros((len(self.fragments), self.n))
+
+        for i, fragment in enumerate(self.fragments.values()):
+            self.atoms_matrix[i, fragment] = 1
+
+    def get_overlaped_fragments(self):
+        overlap = np.sum(self.atoms_matrix, axis=0)
+        self.overlaped_atoms = np.argwhere(overlap > 1).flatten()
+
+        for name, frag in self.fragments.items():
+            if np.isin(frag, self.overlaped_atoms).any():
+                self.overlaped_fragments[name] = frag
+
+    def solve_overlap(self):
+        universe = set(self.overlaped_atoms)
+
+        all_elements = set(itertools.chain.from_iterable(self.overlaped_fragments.values()))
+
+        universe.update(all_elements)
+
+        problem = pulp.LpProblem("Set_Cover_Problem", pulp.LpMinimize)
+
+        n_frag = len(self.overlaped_fragments)
+
+        x = pulp.LpVariable.dicts("x", range(n_frag), cat="Binary")
+
+        problem += pulp.lpSum([x[i] for i in range(n_frag)])
+
+        for elem in universe:
+            sum_list = []
+            for i, subset in enumerate(self.overlaped_fragments.values()):
+                if elem in subset:
+                    sum_list.append(x[i])
+
+            # print(f"Restricción para el elemento {elem}: {sum_list} == 1")
+            problem += pulp.lpSum(sum_list) == 1
+
+        solver = pulp.getSolver('PULP_CBC_CMD', msg=False)
+
+        problem.solve(solver)
+
+        selected_subsets = [name for i, name in enumerate(self.overlaped_fragments.keys()) if pulp.value(x[i]) == 1]
+
+        self.selected_fragments = selected_subsets
+
+
+
+
 
-        return detected
+
+