masster 0.3.18__py3-none-any.whl → 0.3.20__py3-none-any.whl

masster/data/libs/central_carbon_metabolites.csv

@@ -0,0 +1,120 @@
+Name,Formula,SMILES,InChIKey
+Glucose,C6H11O,OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O,WQZGKKKJIJFFOK-GASJEMHNSA-N
+Glucose-6-phosphate,C6H13O9P,O=C[C@H](O)[C@@H](O)[C@H](O)[C@H](O)COP(=O)(O)O,VFRROHXSMXFLSN-SLPGGIOYSA-N
+Fructose-6-phosphate,C6H13O9P,O=C(CO)[C@@H](O)[C@H](O)[C@H](O)COP(=O)(O)O,GSXOAOHZAIYLCY-HSUXUTPPSA-N
+"Fructose-1,6-bisphosphate",C6H13O12P,O=P(O)(O)OC[C@H]1O[C@](O)(COP(=O)(O)O)[C@@H](O)[C@@H]1O,RNBGYGVWRKECFJ-ARQDHWQXSA-N
+Glyceraldehyde-3-phosphate,C3H7O6P,O=C[C@H](O)COP(=O)(O)O,LXJXRIRHZLFYRP-VKHMYHEASA-N
+Dihydroxyacetone phosphate,C3H7O6P,O=C(CO)COP(=O)(O)O,GNGACRATGGDKBX-UHFFFAOYSA-N
+3-Phosphoglycerate,C3H7O7P,O=C(O)C(O)COP(=O)(O)O,OSJPPGNTCRNQQC-UHFFFAOYSA-N
+2-Phosphoglycerate,C3H7O7P,O=C(O)C(CO)OP(=O)(O)O,GXIURPTVHJPJLF-UHFFFAOYSA-N
+Phosphoenolpyruvate,C3H5O6P,C=C(OP(=O)(O)O)C(=O)O,DTBNBXWJWCWCIK-UHFFFAOYSA-N
+Pyruvate,C3H6O,CC(=O)C(=O)O,LCTONWCANYUPML-UHFFFAOYSA-M
+Lactate,C3H8O,CC(O)C(=O)O,JVTAAEKCZFNVCJ-UHFFFAOYSA-M
+Acetyl-CoA,C23H38N7O17P3S,CC(=O)SCCN=C(O)CCN=C(O)[C@H](O)C(C)(C)COP(=O)(O)OP(=O)(O)OC[C@H]1O[C@@H](n2cnc3c(N)ncnc32)[C@H](O)[C@@H]1OP(=O)(O)O,ZSLZBFCDCINBPY-ZSJPKINUSA-N
+Citric acid,C6H7O,O=C(O)CC(O)(CC(=O)O)C(=O)O,KRKNYBCHXYNGOX-UHFFFAOYSA-N
+Isocitrate,C6H7O,O=C(O)CC(C(=O)O)C(O)C(=O)O,ODBLHEXUDAPZAU-UHFFFAOYSA-N
+Alpha-ketoglutaric acid,C5H5O,O=C(O)CCC(=O)C(=O)O,KPGXRSRHYNQIFN-UHFFFAOYSA-N
+Succinyl-CoA,C25H40N7O19P3S,CC(C)(COP(=O)(O)OP(=O)(O)OC[C@H]1O[C@@H](n2cnc3c(N)ncnc32)[C@H](O)[C@@H]1OP(=O)(O)O)[C@@H](O)C(O)=NCCC(O)=NCCSC(=O)CCC(=O)O,VNOYUJKHFWYWIR-ITIYDSSPSA-N
+Succinic acid,C4H5O,O=C(O)CCC(=O)O,KDYFGRWQOYBRFD-UHFFFAOYSA-N
+Fumaric acid,C4H3O,O=C(O)/C=C/C(=O)O,VZCYOOQTPOCHFL-OWOJBTEDSA-N
+Malic acid,C4H5O,O=C(O)CC(O)C(=O)O,BJEPYKJPYRNKOW-UHFFFAOYSA-N
+Oxaloacetic acid,C4H3O,O=C(O)CC(=O)C(=O)O,KHPXUQMNIQBQEV-UHFFFAOYSA-N
+Ribose-5-phosphate,C5H11O8P,O=C[C@H](O)[C@H](O)[C@H](O)COP(=O)(O)O,PPQRONHOSHZGFQ-LMVFSUKVSA-N
+Ribulose-5-phosphate,C5H11O8P,O=C(CO)[C@H](O)[C@H](O)COP(=O)(O)O,FNZLKVNUWIIPSJ-UHNVWZDZSA-N
+Sedoheptulose-7-phosphate,C7H15O10P,O=C(CO)[C@@H](O)[C@H](O)[C@H](O)[C@H](O)COP(=O)(O)O,JDTUMPKOJBQPKX-GBNDHIKLSA-N
+Erythrose-4-phosphate,C4H9O7P,O=C[C@H](O)[C@H](O)COP(=O)(O)O,NGHMDNPXVRFFGS-IUYQGCFVSA-N
+"Sedoheptulose-1,7-bisphosphate",C7H15O13P,O=C(COP(=O)(O)O)[C@@H](O)[C@H](O)[C@H](O)[C@H](O)COP(=O)(O)O,OKHXOUGRECCASI-SHUUEZRQSA-N
+Glycerol-3-phosphate,C3H9O6P,O=P(O)(O)OCC(O)CO,AWUCVROLDVIAJX-UHFFFAOYSA-N
+Glycerate,C3H9O,O=C(O)C(O)CO,RBNPOMFGQQGHHO-UHFFFAOYSA-M
+Pentose,C5H9O,OC1COC(O)C(O)C1O,SRBFZHDQGSBBOR-UHFFFAOYSA-N
+Acetaldehyde,C2H4O,CC=O,IKHGUXGNUITLKF-UHFFFAOYSA-N
+Acetic acid,C2H3O,CC(=O)O,QTBSBXVTEAMEQO-UHFFFAOYSA-N
+Alanine,C3H6NO,C[C@H](N)C(=O)O,QNAYBMKLOCPYGJ-REOHCLBHSA-N
+Arginine,C6H13N4O,N=C(N)NCCC[C@H](N)C(=O)O,ODKSFYDXXFIFQN-BYPYZUCNSA-N
+Asparagine,C4H7N2O,N=C(O)C[C@H](N)C(=O)O,DCXYFEDJOCDNAF-REOHCLBHSA-N
+Aspartic acid,C4H6NO,N[C@@H](CC(=O)O)C(=O)O,CKLJMWTZIZZHCS-REOHCLBHSA-N
+Cysteine,C3H7NO2S,N[C@@H](CS)C(=O)O,XUJNEKJLAYXESH-REOHCLBHSA-N
+Glutamic acid,C5H8NO,N[C@@H](CCC(=O)O)C(=O)O,WHUUTDBJXJRKMK-VKHMYHEASA-N
+Glutamine,C5H9N2O,N=C(O)CC[C@H](N)C(=O)O,ZDXPYRJPNDTMRX-VKHMYHEASA-N
+Glycine,C2H4NO,NCC(=O)O,DHMQDGOQFOQNFH-UHFFFAOYSA-N
+Histidine,C6H8N3O,N[C@@H](Cc1cnc[nH]1)C(=O)O,HNDVDQJCIGZPNO-YFKPBYRVSA-N
+Isoleucine,C6H12NO,CC[C@H](C)[C@H](N)C(=O)O,AGPKZVBTJJNPAG-WHFBIAKZSA-N
+Leucine,C6H12NO,CC(C)C[C@H](N)C(=O)O,ROHFNLRQFUQHCH-YFKPBYRVSA-N
+Lysine,C6H13N2O,NCCCC[C@H](N)C(=O)O,KDXKERNSBIXSRK-YFKPBYRVSA-N
+Methionine,C5H11NO2S,CSCC[C@H](N)C(=O)O,FFEARJCKVFRZRR-BYPYZUCNSA-N
+Phenylalanine,C9H10NO,N[C@@H](Cc1ccccc1)C(=O)O,COLNVLDHVKWLRT-QMMMGPOBSA-N
+Proline,C5H8NO,O=C(O)[C@@H]1CCCN1,ONIBWKKTOPOVIA-BYPYZUCNSA-N
+Serine,C3H6NO,N[C@@H](CO)C(=O)O,MTCFGRXMJLQNBG-REOHCLBHSA-N
+Threonine,C4H8NO,C[C@@H](O)[C@H](N)C(=O)O,AYFVYJQAPQTCCC-GBXIJSLDSA-N
+Tryptophan,C11H11N2O,N[C@@H](Cc1c[nH]c2ccccc12)C(=O)O,QIVBCDIJIAJPQS-VIFPVBQESA-N
+Tyrosine,C9H10NO,N[C@@H](Cc1ccc(O)cc1)C(=O)O,OUYCCCASQSFEME-QMMMGPOBSA-N
+Valine,C5H10NO,CC(C)[C@H](N)C(=O)O,KZSNJWFQEVHDMF-BYPYZUCNSA-N
+Ornithine,C5H11N2O,NCCC[C@H](N)C(=O)O,AHLPHDHHMVZTML-BYPYZUCNSA-N
+Citrulline,C6H12N3O,N=C(O)NCCC[C@H](N)C(=O)O,RHGKLRLOHDJJDR-BYPYZUCNSA-N
+Homocysteine,C4H9NO2S,N[C@@H](CCS)C(=O)O,FFFHZYDWPBMWHY-VKHMYHEASA-N
+S-adenosylmethionine,C15H22N6O5S,C[S](CC[C@H](N)C(=O)O)C[C@H]1O[C@@H](n2cnc3c(N)ncnc32)[C@H](O)[C@@H]1O,MEFKEPWMEQBLKI-AIRLBKTGSA-N
+S-adenosylhomocysteine,C14H20N6O5S,Nc1ncnc2c1ncn2[C@@H]1O[C@H](CSCC[C@H](N)C(=O)O)[C@@H](O)[C@H]1O,ZJUKTBDSGOFHSH-WFMPWKQPSA-N
+Formic acid,CHO,O=CO,BDAGIHXWWSANSR-UHFFFAOYSA-N
+Propionic acid,C3H5O,CCC(=O)O,XBDQKXXYIPTUBI-UHFFFAOYSA-N
+Butyric acid,C4H7O,CCCC(=O)O,FERIUCNNQQJTOY-UHFFFAOYSA-N
+Malonic acid,C3H3O,O=C(O)CC(=O)O,OFOBLEOULBTSOW-UHFFFAOYSA-N
+2-Hydroxyglutarate,C5H7O,O=C(O)CCC(O)C(=O)O,HWXBTNAVRSUOJR-UHFFFAOYSA-N
+3-Hydroxybutyrate,C4H10O,CC(O)CC(=O)O,WHBMMWSBFZVSSR-UHFFFAOYSA-M
+Acetoacetate,C4H8O,CC(=O)CC(=O)O,WDJHALXBUFZDSR-UHFFFAOYSA-M
+Beta-hydroxybutyrate,C4H7O,CC(O)CC(=O)O,WHBMMWSBFZVSSR-UHFFFAOYSA-N
+Pyruvic acid,C3H3O,CC(=O)C(=O)O,LCTONWCANYUPML-UHFFFAOYSA-N
+Lactic acid,C3H5O,CC(O)C(=O)O,JVTAAEKCZFNVCJ-UHFFFAOYSA-N
+Myristic acid,C14H27O,CCCCCCCCCCCCCC(=O)O,TUNFSRHWOTWDNC-UHFFFAOYSA-N
+Palmitic acid,C16H31O,CCCCCCCCCCCCCCCC(=O)O,IPCSVZSSVZVIGE-UHFFFAOYSA-N
+Stearic acid,C18H35O,CCCCCCCCCCCCCCCCCC(=O)O,QIQXTHQIDYTFRH-UHFFFAOYSA-N
+Palmitoleic acid,C16H29O,CCCCCC/C=C\CCCCCCCC(=O)O,SECPZKHBENQXJG-FPLPWBNLSA-N
+Oleic acid,C18H33O,CCCCCCCC/C=C\CCCCCCCC(=O)O,ZQPPMHVWECSIRJ-KTKRTIGZSA-N
+Linoleic acid,C18H31O,CCCCC/C=C\C/C=C\CCCCCCCC(=O)O,OYHQOLUKZRVURQ-HZJYTTRNSA-N
+Alpha-linolenic acid,C18H29O,CC/C=C\C/C=C\C/C=C\CCCCCCCC(=O)O,DTOSIQBPPRVQHS-PDBXOOCHSA-N
+Arachidonic acid,C20H31O,CCCCC/C=C\C/C=C\C/C=C\C/C=C\CCCC(=O)O,YZXBAPSDXZZRGB-DOFZRALJSA-N
+Adenine,C5H4N,Nc1nc[nH]c2ncnc1-2,GFFGJBXGBJISGV-UHFFFAOYSA-N
+Guanine,C5H5N5O,N=c1nc(O)c2nc[nH]c2[nH]1,UYTPUPDQBNUYGX-UHFFFAOYSA-N
+Cytosine,C4H5N3O,N=c1ccnc(O)[nH]1,OPTASPLRGRRNAP-UHFFFAOYSA-N
+Thymine,C5H5N2O,Cc1cnc(O)nc1O,RWQNBRDOKXIBIV-UHFFFAOYSA-N
+Uracil,C4H3N2O,Oc1ccnc(O)n1,ISAKRJDGNUQOIC-UHFFFAOYSA-N
+Adenosine,C10H12N5O,Nc1ncnc2c1ncn2[C@@H]1O[C@H](CO)[C@@H](O)[C@H]1O,OIRDTQYFTABQOQ-KQYNXXCUSA-N
+Guanosine,C10H12N5O,N=c1nc(O)c2ncn([C@@H]3O[C@H](CO)[C@@H](O)[C@H]3O)c2[nH]1,NYHBQMYGNKIUIF-UUOKFMHZSA-N
+Cytidine,C9H12N3O,N=c1ccn([C@@H]2O[C@H](CO)[C@@H](O)[C@H]2O)c(O)n1,UHDGCWIWMRVCDJ-XVFCMESISA-N
+Uridine,C9H11N2O,O=c1nc(O)ccn1[C@@H]1O[C@H](CO)[C@@H](O)[C@H]1O,DRTQHJPVMGBUCF-XVFCMESISA-N
+AMP,C10H14N5O7P,Nc1ncnc2c1ncn2[C@@H]1O[C@H](COP(=O)(O)O)[C@@H](O)[C@H]1O,UDMBCSSLTHHNCD-KQYNXXCUSA-N
+ADP,C10H14N5O10P,Nc1ncnc2c1ncn2[C@@H]1O[C@H](COP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]1O,XTWYTFMLZFPYCI-KQYNXXCUSA-N
+ATP,C10H15N5O13P,Nc1ncnc2c1ncn2[C@@H]1O[C@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]1O,ZKHQWZAMYRWXGA-KQYNXXCUSA-N
+GMP,C10H14N5O8P,N=c1nc(O)c2ncn([C@@H]3O[C@H](COP(=O)(O)O)[C@@H](O)[C@H]3O)c2[nH]1,RQFCJASXJCIDSX-UUOKFMHZSA-N
+GDP,C10H14N5O11P,N=c1nc(O)c2ncn([C@@H]3O[C@H](COP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]3O)c2[nH]1,QGWNDRXFNXRZMB-UUOKFMHZSA-N
+GTP,C10H15N5O14P,N=c1nc(O)c2ncn([C@@H]3O[C@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]3O)c2[nH]1,XKMLYUALXHKNFT-UUOKFMHZSA-N
+CMP,C9H14N3O8P,N=c1ccn([C@@H]2O[C@H](COP(=O)(O)O)[C@@H](O)[C@H]2O)c(O)n1,IERHLVCPSMICTF-XVFCMESISA-N
+CDP,C9H14N3O11P,N=c1ccn([C@@H]2O[C@H](COP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]2O)c(O)n1,ZWIADYZPOWUWEW-XVFCMESISA-N
+CTP,C9H15N3O14P,N=c1ccn([C@@H]2O[C@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]2O)c(O)n1,PCDQPRRSZKQHHS-XVFCMESISA-N
+UMP,C9H13N2O9P,O=c1nc(O)ccn1[C@@H]1O[C@H](COP(=O)(O)O)[C@@H](O)[C@H]1O,DJJCXFVJDGTHFX-XVFCMESISA-N
+UDP,C9H13N2O12P,O=c1nc(O)ccn1[C@@H]1O[C@H](COP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]1O,XCCTYIAWTASOJW-XVFCMESISA-N
+UTP,C9H14N2O15P,O=c1nc(O)ccn1[C@@H]1O[C@H](COP(=O)(O)OP(=O)(O)OP(=O)(O)O)[C@@H](O)[C@H]1O,PGAVKCOVUIYSFO-XVFCMESISA-N
+NAD+,C21H26N7O14P,N=C(O)C1CCCN([C@@H]2O[C@H](COP(=O)(O)OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)[C@H](O)[C@@H]3O)[C@@H](O)[C@H]2O)C1,BAWFJGJZGIEFAR-NNYOXOHSSA-N
+NADH,C21H28N7O14P,N=C(O)C1=CN([C@@H]2O[C@H](COP(=O)(O)OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)[C@H](O)[C@@H]3O)[C@@H](O)[C@H]2O)C=CC1,BOPGDPNILDQYTO-NNYOXOHSSA-N
+NADP+,C21H27N7O17P,N=C(O)C1CCCN([C@@H]2O[C@H](COP(=O)(O)OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)[C@H](OP(=O)(O)O)[C@@H]3O)[C@@H](O)[C@H]2O)C1,XJLXINKUBYWONI-NNYOXOHSSA-N
+NADPH,C21H29N7O17P,N=C(O)C1=CN([C@@H]2O[C@H](COP(=O)(O)OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)[C@H](OP(=O)(O)O)[C@@H]3O)[C@@H](O)[C@H]2O)C=CC1,ACFIXJIJDZMPPO-NNYOXOHSSA-N
+FAD,C27H32N9O15P,Cc1cc2nc3c(O)nc(=O)nc-3n(C[C@H](O)[C@H](O)[C@H](O)COP(=O)(O)OP(=O)(O)OC[C@H]3O[C@@H](n4cnc5c(N)ncnc54)[C@H](O)[C@@H]3O)c2cc1C,VWWQXMAJTJZDQX-UYBVJOGSSA-N
+FMN,C17H21N4O9P,Cc1cc2nc3c(O)nc(=O)nc-3n(C[C@H](O)[C@H](O)[C@H](O)COP(=O)(O)O)c2cc1C,FVTCRASFADXXNN-SCRDCRAPSA-N
+Coenzyme A,C21H36N7O16P3S,CC(C)(COP(=O)(O)OP(=O)(O)OC[C@H]1O[C@@H](n2cnc3c(N)ncnc32)[C@H](O)[C@@H]1OP(=O)(O)O)[C@@H](O)C(O)=NCCC(O)=NCCS,RGJOEKWQDUBAIZ-IBOSZNHHSA-N
+Pantothenic acid,C9H16NO,CC(C)(CO)[C@@H](O)C(O)=NCCC(=O)O,GHOKWGTUZJEAQD-ZETCQYMHSA-N
+Riboflavin,C17H19N4O,Cc1cc2nc3c(O)nc(=O)nc-3n(C[C@H](O)[C@H](O)[C@H](O)CO)c2cc1C,AUNGANRZJHBGPY-SCRDCRAPSA-N
+Niacin,C6H4NO,O=C(O)c1cccnc1,PVNIIMVLHYAWGP-UHFFFAOYSA-N
+Fructose,C6H11O,OCC1(O)OC[C@@H](O)[C@@H](O)[C@@H]1O,LKDRXBCSQODPBY-VRPWFDPXSA-N
+Mannose,C6H11O,OC[C@H]1OC(O)[C@@H](O)[C@@H](O)[C@@H]1O,WQZGKKKJIJFFOK-QTVWNMPRSA-N
+Mannose-6-phosphate,C6H13O9P,O=C[C@@H](O)[C@@H](O)[C@H](O)[C@H](O)COP(=O)(O)O,VFRROHXSMXFLSN-KVTDHHQDSA-N
+Ribose,C5H9O,OC1OC[C@@H](O)[C@@H](O)[C@H]1O,SRBFZHDQGSBBOR-SOOFDHNKSA-N
+Glucosamine,C6H12NO,N[C@H]1C(O)O[C@H](CO)[C@@H](O)[C@@H]1O,MSWZFWKMSRAUBD-IVMDWMLBSA-N
+N-acetylglucosamine,C8H14NO,CC(O)=N[C@@H](C=O)[C@@H](O)[C@H](O)[C@H](O)CO,MBLBDJOUHNCFQT-LXGUWJNJSA-N
+Choline,C5H13NO,[H]OC([H])([H])C([H])([H])N(C([H])([H])[H])(C([H])([H])[H])C([H])([H])[H],OEYIOHPDSNJKLS-UHFFFAOYSA-N
+Betaine,C5H10NO,[H]OC(=O)C([H])([H])N(C([H])([H])[H])(C([H])([H])[H])C([H])([H])[H],KWIUHFFTVRNATP-UHFFFAOYSA-N
+Carnitine,C7H14NO,[H]OC(=O)C([H])([H])C([H])(O[H])C([H])([H])N(C([H])([H])[H])(C([H])([H])[H])C([H])([H])[H],PHIQHXFUZVPYII-UHFFFAOYSA-N
+Phosphocholine,C5H14NO4P,[H]OP(=O)(O[H])OC([H])([H])C([H])([H])N(C([H])([H])[H])(C([H])([H])[H])C([H])([H])[H],YHHSONZFOIEMCP-UHFFFAOYSA-O
+Glycerol,C3H7O,OCC(O)CO,PEDCQBHIVMGVHV-UHFFFAOYSA-N
+Sorbitol,C6H13O,OC[C@@H](O)[C@@H](O)[C@H](O)[C@@H](O)CO,FBPFZTCFMRRESA-JGWLITMVSA-N
+Inositol,C6H11O,OC1C(O)C(O)C(O)C(O)C1O,CDAISMWEOUEBRE-UHFFFAOYSA-N
+Cholesterol,C27H46O,CC(C)CCC[C@@H](C)[C@H]1CC[C@H]2[C@@H]3CC=C4C[C@@H](O)CC[C@]4(C)[C@H]3CC[C@]12C,HVYWMOMLDIMFJA-DPAQBDIFSA-N
+Pantothenate,C9H21NO,CC(C)(CO)C(O)C(O)=NCCC(=O)O,GHOKWGTUZJEAQD-UHFFFAOYSA-M

masster/data/libs/urine.py

@@ -0,0 +1,333 @@
+"""Generate a CSV of human urine metabolites.
+
+This improved script attempts to:
+- Download or scrape a urine metabolite list from the UrineMetabolome downloads page.
+- Fall back to HMDB scraping or a curated list if needed.
+- Resolve formula/SMILES/InChIKey using PubChem with bounded parallelism.
+- Use RDKit (if available) to convert InChI -> SMILES when PubChem does not provide SMILES.
+
+The goal is robust coverage and faster lookups by parallelizing per-name queries
+while avoiding aggressive parallelism that might overload PubChem.
+"""
+
+from __future__ import annotations
+
+import csv
+import sys
+import re
+import time
+import os
+from urllib.parse import quote, urljoin
+from concurrent.futures import ThreadPoolExecutor, as_completed
+from typing import Iterable
+
+try:
+    import requests
+    from bs4 import BeautifulSoup
+except Exception:
+    requests = None
+    BeautifulSoup = None
+
+
+URINEMETABOLOME_DOWNLOADS = "https://www.urinemetabolome.ca/downloads"
+HMDB_URINE_LIST_URL = "https://hmdb.ca/metabolites?utf8=%E2%9C%93&search=&biological_context=Urine"
+
+
+def normalize_name(name: str) -> str:
+    if not name:
+        return name
+    s = name
+    s = re.sub(r"\(.*?\)", "", s)
+    s = s.replace("➔", "->").replace("–", "-").replace("—", "-")
+    s = re.sub(r"\s+", " ", s).strip()
+    mapping = {
+        "AMP": "Adenosine monophosphate",
+        "ADP": "Adenosine diphosphate",
+        "ATP": "Adenosine triphosphate",
+        "GMP": "Guanosine monophosphate",
+        "GDP": "Guanosine diphosphate",
+        "GTP": "Guanosine triphosphate",
+        "NAD+": "Nicotinamide adenine dinucleotide",
+        "NADH": "Nicotinamide adenine dinucleotide (reduced)",
+    }
+    up = s.upper()
+    if up in mapping:
+        return mapping[up]
+    return s
+
+
+def fetch_urinemetabolome_names(limit: int = 2000) -> list[str]:
+    """Scrape the UrineMetabolome downloads page for any downloadable metabolite lists.
+
+    Best-effort: finds links on the downloads page that look like CSV/TSV/Excel and tries
+    to parse a simple name column. If anything fails, returns an empty list and the
+    caller should fall back to HMDB or a curated list.
+    """
+    if requests is None or BeautifulSoup is None:
+        return []
+    try:
+        r = requests.get(URINEMETABOLOME_DOWNLOADS, timeout=15)
+        r.raise_for_status()
+        soup = BeautifulSoup(r.text, "html.parser")
+        names = []
+        for a in soup.find_all("a", href=True):
+            href = a["href"]
+            if re.search(r"\.csv$|\.tsv$|\.xlsx?$", href, re.I):
+                url = urljoin(URINEMETABOLOME_DOWNLOADS, href)
+                # try to download and parse simple CSV/TSV
+                try:
+                    rr = requests.get(url, timeout=20)
+                    if rr.status_code != 200:
+                        continue
+                    text = rr.content.decode("utf-8", errors="ignore")
+                    # try CSV/TSV parse by splitting lines and looking for a header with 'name' or 'metabolite'
+                    lines = [l.strip() for l in text.splitlines() if l.strip()]
+                    if not lines:
+                        continue
+                    sep = "," if "," in lines[0] else "\t"
+                    header = [c.strip().lower() for c in lines[0].split(sep)]
+                    # find candidate column
+                    col_idx = None
+                    for i, c in enumerate(header):
+                        if any(k in c for k in ("name", "metabolite", "compound")):
+                            col_idx = i
+                            break
+                    if col_idx is None:
+                        # fallback: take first column
+                        col_idx = 0
+                    for l in lines[1:limit+1]:
+                        parts = [p.strip() for p in l.split(sep)]
+                        if len(parts) > col_idx:
+                            n = parts[col_idx]
+                            if n and n not in names:
+                                names.append(n)
+                        if len(names) >= limit:
+                            break
+                    if names:
+                        return names
+                except Exception:
+                    continue
+        return []
+    except Exception:
+        return []
+
+
+def fetch_hmdb_urine_names(limit: int = 500) -> list[str]:
+    """Fallback HMDB scrape (best-effort)."""
+    if requests is None or BeautifulSoup is None:
+        return []
+    try:
+        r = requests.get(HMDB_URINE_LIST_URL, timeout=20)
+        r.raise_for_status()
+        soup = BeautifulSoup(r.text, "html.parser")
+        names = []
+        for a in soup.find_all("a", href=True):
+            href = a["href"]
+            if re.search(r"/metabolites/HMDB", href):
+                text = a.get_text(strip=True)
+                if text and len(text) > 1:
+                    names.append(text)
+                    if len(names) >= limit:
+                        break
+        return list(dict.fromkeys(names))
+    except Exception:
+        return []
+
+
+def fetch_pubchem_name_once(name: str, timeout: int = 15):
+    """Fetch properties for a single name from PubChem and try inchI->SMILES if needed.
+
+    Returns (formula, smiles, inchikey) or (None, None, None) on failure.
+    """
+    if requests is None:
+        return (None, None, None)
+    q = normalize_name(name)
+    url_name = quote(q)
+    url = (
+        f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/{url_name}/property/"
+        + "MolecularFormula,CanonicalSMILES,InChI,InChIKey/JSON"
+    )
+    try:
+        r = requests.get(url, timeout=timeout)
+        if r.status_code != 200:
+            return (None, None, None)
+        j = r.json()
+        if "PropertyTable" in j and "Properties" in j["PropertyTable"]:
+            p = j["PropertyTable"]["Properties"][0]
+            formula = p.get("MolecularFormula")
+            smiles = p.get("CanonicalSMILES")
+            inchi = p.get("InChI")
+            inchikey = p.get("InChIKey")
+            if not smiles and inchi:
+                # try RDKit conversion
+                try:
+                    from rdkit import Chem
+                    m = Chem.MolFromInchi(inchi)
+                    if m is not None:
+                        try:
+                            Chem.SanitizeMol(m)
+                        except Exception:
+                            pass
+                        smiles = Chem.MolToSmiles(m, isomericSmiles=True)
+                except Exception:
+                    pass
+
+            # If still missing SMILES, and we have an InChIKey, try inchikey -> property
+            if not smiles and inchikey:
+                try:
+                    ik = quote(inchikey)
+                    url2 = (
+                        f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/inchikey/{ik}/property/"
+                        + "MolecularFormula,CanonicalSMILES,InChI,InChIKey/JSON"
+                    )
+                    r2 = requests.get(url2, timeout=timeout)
+                    if r2.status_code == 200:
+                        j2 = r2.json()
+                        if "PropertyTable" in j2 and "Properties" in j2["PropertyTable"]:
+                            p2 = j2["PropertyTable"]["Properties"][0]
+                            smiles = p2.get("CanonicalSMILES") or smiles
+                            formula = formula or p2.get("MolecularFormula")
+                except Exception:
+                    pass
+
+            # Final fallback: inchikey -> cids -> cid -> property
+            if not smiles and inchikey:
+                try:
+                    ik = quote(inchikey)
+                    urlc = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/inchikey/{ik}/cids/JSON"
+                    rc = requests.get(urlc, timeout=timeout)
+                    if rc.status_code == 200:
+                        jc = rc.json()
+                        if "IdentifierList" in jc and "CID" in jc["IdentifierList"] and jc["IdentifierList"]["CID"]:
+                            cid = jc["IdentifierList"]["CID"][0]
+                            try:
+                                url3 = (
+                                    f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cid}/property/"
+                                    + "MolecularFormula,CanonicalSMILES,InChI,InChIKey/JSON"
+                                )
+                                r3 = requests.get(url3, timeout=timeout)
+                                if r3.status_code == 200:
+                                    j3 = r3.json()
+                                    if "PropertyTable" in j3 and "Properties" in j3["PropertyTable"]:
+                                        p3 = j3["PropertyTable"]["Properties"][0]
+                                        smiles = p3.get("CanonicalSMILES") or smiles
+                                        formula = formula or p3.get("MolecularFormula")
+                            except Exception:
+                                pass
+                except Exception:
+                    pass
+
+            return (formula, smiles, inchikey)
+    except Exception:
+        return (None, None, None)
+    return (None, None, None)
+
+
+def fetch_pubchem_for_names(names: Iterable[str], workers: int = 8, delay: float = 0.05):
+    """Resolve a list of names via PubChem in parallel.
+
+    Returns dict name -> (formula, smiles, inchikey)
+    """
+    names = list(names)
+    results: dict[str, tuple | None] = {}
+    with ThreadPoolExecutor(max_workers=workers) as ex:
+        futures = {ex.submit(fetch_pubchem_name_once, n): n for n in names}
+        for fut in as_completed(futures):
+            n = futures[fut]
+            try:
+                res = fut.result()
+            except Exception:
+                res = (None, None, None)
+            results[n] = res
+            time.sleep(delay)  # polite small delay between completions
+    return results
+
+
+def generate_csv(out_path: str = "urine_metabolites.csv", workers: int = 8):
+    # Try UrineMetabolome downloads first
+    names = fetch_urinemetabolome_names()
+    if not names:
+        names = fetch_hmdb_urine_names()
+    if not names:
+        print("Falling back to curated urine list")
+        names = [
+            "Creatinine",
+            "Urea",
+            "Hippuric acid",
+            "Citrate",
+            "Creatine",
+            "Glycine",
+            "Taurine",
+            "Succinate",
+            "Fumaric acid",
+            "Malic acid",
+            "Lactic acid",
+            "Acetic acid",
+            "Formic acid",
+            "Alanine",
+            "Betaine",
+            "Choline",
+            "Trimethylamine N-oxide",
+            "Phenylacetylglutamine",
+            "p-Cresol sulfate",
+            "Indoxyl sulfate",
+            "Uric acid",
+            "Xanthine",
+            "3-Hydroxybutyrate",
+            "Acetoacetate",
+            "N-Acetylneuraminic acid",
+        ]
+
+    print(f"Resolving {len(names)} names via PubChem (workers={workers})...")
+    mapping = fetch_pubchem_for_names(names, workers=workers)
+
+    rows = []
+    for name in names:
+        formula, smiles, inchikey = mapping.get(name, (None, None, None))
+        rows.append({
+            "Name": name,
+            "Formula": formula or "",
+            "SMILES": smiles or "",
+            "InChIKey": inchikey or "",
+        })
+
+    # Ensure output directory exists
+    out_dir = os.path.join("masster", "data", "libs")
+    os.makedirs(out_dir, exist_ok=True)
+    out_path_full = os.path.join(out_dir, os.path.basename(out_path))
+
+    fieldnames = ["Name", "Formula", "SMILES", "InChIKey"]
+    with open(out_path_full, "w", newline="", encoding="utf-8") as f:
+        writer = csv.DictWriter(f, fieldnames=fieldnames)
+        writer.writeheader()
+        for r in rows:
+            writer.writerow(r)
+
+    print(f"Wrote {len(rows)} entries to {out_path_full}")
+    return out_path_full
+
+
+def test_load_with_lib(csv_path: str):
+    try:
+        from masster.lib import Lib
+    except Exception as e:
+        print(f"Cannot import masster.lib.Lib: {e}")
+        return False
+
+    try:
+        lib = Lib()
+        lib.import_csv(csv_path, polarity=None)
+        print(f"Lib loaded: {len(lib)} entries")
+        return True
+    except Exception as e:
+        print(f"Failed to load CSV with Lib.import_csv: {e}")
+        return False
+
+
+if __name__ == "__main__":
+    csv_file = generate_csv()
+    ok = test_load_with_lib(csv_file)
+    if not ok:
+        print("Test failed; please inspect messages above.")
+        sys.exit(2)
+    print("Done.")

masster/data/libs/urine_metabolites.csv

@@ -0,0 +1,51 @@
+Name,Formula,SMILES,InChIKey
+HMDB0000001,,,
+1-Methylhistidine,C7H11N3O2,Cn1cnc(C[C@H](N)C(=O)O)c1,BRMWTNUJHUMWMS-LURJTMIESA-N
+HMDB0000002,,,
+"1,3-Diaminopropane",C3H10N2,NCCCN,XFNJVJPLKCPIBV-UHFFFAOYSA-N
+HMDB0000005,,,
+2-Ketobutyric acid,C4H6O3,CCC(=O)C(=O)O,TYEYBOSBBBHJIV-UHFFFAOYSA-N
+HMDB0000008,,,
+2-Hydroxybutyric acid,C4H8O3,CCC(O)C(=O)O,AFENDNXGAFYKQO-UHFFFAOYSA-N
+HMDB0000010,,,
+2-Methoxyestrone,,,
+HMDB0000011,,,
+3-Hydroxybutyric acid,,,
+HMDB0000012,,,
+Deoxyuridine,,,
+HMDB0000014,,,
+Deoxycytidine,,,
+HMDB0000015,,,
+Cortexolone,,,
+HMDB0000016,,,
+Deoxycorticosterone,,,
+HMDB0000017,,,
+4-Pyridoxic acid,C8H9NO4,Cc1ncc(CO)c(C(=O)O)c1O,HXACOUQIXZGNBF-UHFFFAOYSA-N
+HMDB0000019,,,
+alpha-Ketoisovaleric acid,C5H8O3,CC(C)C(=O)C(=O)O,QHKABHOOEWYVLI-UHFFFAOYSA-N
+HMDB0000020,,,
+p-Hydroxyphenylacetic acid,C8H8O3,O=C(O)Cc1ccc(O)cc1,XQXPVVBIMDBYFF-UHFFFAOYSA-N
+HMDB0000021,,,
+Iodotyrosine,C9H10INO3,N[C@@H](Cc1ccc(O)c(I)c1)C(=O)O,UQTZMGFTRHFAAM-ZETCQYMHSA-N
+HMDB0000022,,,
+3-Methoxytyramine,C9H13NO2,COc1cc(CCN)ccc1O,DIVQKHQLANKJQO-UHFFFAOYSA-N
+HMDB0000023,,,
+(S)-3-Hydroxyisobutyric acid,,,
+HMDB0000024,,,
+3-O-Sulfogalactosylceramide (d18:1/24:0),,,
+HMDB0000026,,,
+Ureidopropionic acid,,,
+HMDB0000027,,,
+Tetrahydrobiopterin,,,
+HMDB0000030,,,
+Biotin,C10H16N2O3S,O=C(O)CCCC[C@@H]1SC[C@@H]2N=C(O)N[C@@H]21,YBJHBAHKTGYVGT-ZKWXMUAHSA-N
+HMDB0000031,,,
+Androsterone,C19H30O2,C[C@]12CC[C@@H](O)C[C@@H]1CC[C@@H]1[C@@H]2CC[C@]2(C)C(=O)CC[C@@H]12,QGXBDMJGAMFCBF-HLUDHZFRSA-N
+HMDB0000032,,,
+7-Dehydrocholesterol,C27H44O,CC(C)CCC[C@@H](C)[C@H]1CC[C@H]2C3=CC=C4C[C@@H](O)CC[C@]4(C)[C@H]3CC[C@]12C,UCTLRSWJYQTBFZ-DDPQNLDTSA-N
+HMDB0000033,,,
+Carnosine,C9H14N4O3,NCCC(O)=N[C@@H](Cc1cnc[nH]1)C(=O)O,CQOVPNPJLQNMDC-ZETCQYMHSA-N
+HMDB0000034,,,
+Adenine,C5H5N5,Nc1nc[nH]c2ncnc1-2,GFFGJBXGBJISGV-UHFFFAOYSA-N
+HMDB0000036,,,
+Taurocholic acid,,,

masster/sample/h5.py

@@ -900,7 +900,7 @@ def _load_sample5(self, filename: str, map: bool = True):
 def _load_sample5_study(self, filename: str, map: bool = True):
     """
     Optimized variant of _load_sample5 for study loading that skips reading ms1_df.
-    
+
     This is used when adding samples to studies where ms1_df data is not needed,
     improving loading throughput by skipping the potentially large ms1_df dataset.
 

masster/sample/helpers.py

@@ -176,7 +176,7 @@ def _get_feature_uids(self, features=None, verbose=True):
                 if not isinstance(features, pd.DataFrame):
                     if verbose:
                         self.logger.error(
-                            "Invalid input type. Expected None, list, polars DataFrame, or pandas DataFrame."
+                            "Invalid input type. Expected None, list, polars DataFrame, or pandas DataFrame.",
                         )
                     return []
 
@@ -298,7 +298,7 @@ def get_eic(self, mz, mz_tol=None):
     """
     # Use default mz_tol from sample parameters if not provided
     if mz_tol is None:
-        if hasattr(self, 'parameters') and hasattr(self.parameters, 'eic_mz_tol'):
+        if hasattr(self, "parameters") and hasattr(self.parameters, "eic_mz_tol"):
             mz_tol = self.parameters.eic_mz_tol
         else:
             mz_tol = 0.01  # fallback default
@@ -323,11 +323,7 @@ def get_eic(self, mz, mz_tol=None):
             return None
 
         # Aggregate intensities per retention time. Use sum in case multiple points per rt.
-        chrom = (
-            matches.group_by("rt")
-            .agg([pl.col("inty").sum().alias("inty")])
-            .sort("rt")
-        )
+        chrom = matches.group_by("rt").agg([pl.col("inty").sum().alias("inty")]).sort("rt")
 
         # Attach to Sample
         self.chrom_df = chrom

masster/sample/lib.py

@@ -1,28 +1,32 @@
 """
-_lib.py
+lib.py
 
-This module provides utility functions and algorithms for mass spectrometry data processing.
-It contains core functionality for compound library management, target identification,
-adduct handling, and various analytical operations used throughout the masster package.
+This module provides the Lib class and utility functions for mass spectrometry compound library 
+management and feature annotation. It contains core functionality for compound library management, 
+target identification, adduct handling, and various analytical operations.
 
 Key Features:
-- **Compound Libraries**: Load and manage compound databases with metadata.
-- **Adduct Calculations**: Handle various ionization adducts and charge states.
-- **Mass Calculations**: Precise mass calculations with adduct corrections.
-- **Target Matching**: Match detected features against compound libraries.
-- **Polarity Handling**: Support for positive and negative ionization modes.
-- **Database Integration**: Interface with various compound database formats.
+- **Lib Class**: Main class for managing compound libraries and annotations
+- **Compound Libraries**: Load and manage compound databases with metadata
+- **Adduct Calculations**: Handle various ionization adducts and charge states
+- **Mass Calculations**: Precise mass calculations with adduct corrections
+- **Target Matching**: Match detected features against compound libraries
+- **Polarity Handling**: Support for positive and negative ionization modes
+- **Database Integration**: Interface with various compound database formats
 
 Dependencies:
-- `pyopenms`: For mass spectrometry algorithms and data structures.
-- `polars` and `pandas`: For efficient data manipulation and analysis.
-- `numpy`: For numerical computations and array operations.
-- `tqdm`: For progress tracking during batch operations.
+- `pyopenms`: For mass spectrometry algorithms and data structures
+- `polars` and `pandas`: For efficient data manipulation and analysis
+- `numpy`: For numerical computations and array operations
+- `tqdm`: For progress tracking during batch operations
+
+Classes:
+- `Lib`: Main class for compound library management and annotation
 
 Functions:
-- `lib_load()`: Load compound libraries from CSV files.
-- `load_lib()`: Alias for lib_load function.
-- Various utility functions for mass calculations and library management.
+- `lib_load()`: Load compound libraries from CSV files (legacy)
+- `load_lib()`: Alias for lib_load function (legacy)
+- Various utility functions for mass calculations and library management
 
 Supported Adducts:
 - Positive mode: [M+H]+, [M+Na]+, [M+K]+, [M+NH4]+, [M-H2O+H]+
@@ -30,19 +34,22 @@ Supported Adducts:
 
 Example Usage:
 ```python
-from _lib import lib_load
+from masster.sample.lib import Lib
+
+# Create library instance
+lib = Lib()
 
-# Load compound library
-lib_load(self, csvfile="compounds.csv", polarity="positive")
+# Import compounds from CSV
+lib.import_csv("compounds.csv", polarity="positive")
 
-# Access loaded library data
-print(f"Loaded {len(self.lib_df)} compounds")
-print(self.lib_df.head())
+# Access library data
+print(f"Loaded {len(lib.lib_df)} compounds")
+print(lib.lib_df.head())
 ```
 
 See Also:
-- `parameters._lib_parameters`: For library-specific parameter configuration.
-- `single.py`: For applying library matching to detected features.
+- `parameters._lib_parameters`: For library-specific parameter configuration
+- `sample.py`: For applying library matching to detected features
 
 """
 

masster/sample/load.py

@@ -119,7 +119,7 @@ def load_study(
 ):
     """
     Optimized load method for study use that skips loading ms1_df for better performance.
-    
+
     This method is identical to load() but uses _load_sample5_study() for .sample5 files,
     which skips reading the potentially large ms1_df dataset to improve throughput when
     adding samples to studies.
@@ -250,7 +250,13 @@ def _load_mzML(
             precursorIsolationWindowLowerMZ = s.getPrecursors()[0].getIsolationWindowLowerOffset()
             precursorIsolationWindowUpperMZ = s.getPrecursors()[0].getIsolationWindowUpperOffset()
             prec_intyensity = s.getPrecursors()[0].getIntensity()
-            energy = s.getPrecursors()[0].getActivationEnergy()
+            # Try to get collision energy from meta values first, fallback to getActivationEnergy()
+            try:
+                energy = s.getPrecursors()[0].getMetaValue('collision energy')
+                if energy is None or energy == 0.0:
+                    energy = s.getPrecursors()[0].getActivationEnergy()
+            except Exception:
+                energy = s.getPrecursors()[0].getActivationEnergy()
 
         peaks = s.get_peaks()
         spect = Spectrum(mz=peaks[0], inty=peaks[1], ms_level=s.getMSLevel())
@@ -983,7 +989,7 @@ def index_file(self):
             self.set_source(self.file_source.replace(".sample5", ".mzml"))
         else:
             raise FileNotFoundError(
-                f"File {self.file_source} not found. Did the path change? Consider running source()."
+                f"File {self.file_source} not found. Did the path change? Consider running source().",
             )
         self.index_file()
     else: