initial port commit

data/chembl_population_mean_std.csv

@@ -0,0 +1,211 @@
+descriptor,mean,std
+MaxEStateIndex,11.757876634688678,2.516468283339003
+MinEStateIndex,-1.0882420870403298,1.579724651088519
+MaxAbsEStateIndex,11.757876634688678,2.516468283339003
+MinAbsEStateIndex,0.16455809015449166,0.18592289221451222
+qed,0.5887637977488095,0.1889526493905691
+MolWt,387.70384361941046,92.9520445214072
+HeavyAtomMolWt,365.4751374380403,88.32292876266523
+ExactMolWt,387.2632998324875,92.82887295290816
+NumValenceElectrons,143.03638400220203,34.830609535789414
+NumRadicalElectrons,0.0001359873995932393,0.011800245246466057
+MaxPartialCharge,0.2717038932739987,0.08398088556066878
+MinPartialCharge,-0.42263511312046054,0.07320721219691713
+MaxAbsPartialCharge,0.42686135260037206,0.0714689799871696
+MinAbsPartialCharge,0.2674818221004431,0.07739879975759226
+FpDensityMorgan1,1.1142676060218886,0.18503353402936784
+FpDensityMorgan2,1.841313074202009,0.2409088200165603
+FpDensityMorgan3,2.5185740421134946,0.29229935912220123
+BCUT2D_MWHI,27.06362950640183,15.320342950103614
+BCUT2D_MWLOW,10.023117006912916,0.2284018169088508
+BCUT2D_CHGHI,2.270908569903605,0.14582892436638903
+BCUT2D_CHGLO,-2.227662668465513,0.1376358712154033
+BCUT2D_LOGPHI,2.3109234696103895,0.11548253618217962
+BCUT2D_LOGPLOW,-2.3186909890541068,0.17458200557668133
+BCUT2D_MRHI,6.662519156820602,1.1151755160650167
+BCUT2D_MRLOW,0.03389066563536082,0.28145942644410565
+BalabanJ,1.7714270246627704,0.39376258706397754
+BertzCT,943.3954387711781,327.31466716926866
+Chi0,19.440618097205263,4.67122503457481
+Chi0n,15.432499979700077,3.8447753961816344
+Chi0v,15.995615756636038,3.855404543368619
+Chi1,13.158712304086757,3.1932928204249986
+Chi1n,9.015942581997239,2.380033532376943
+Chi1v,9.568575955171879,2.4532188458456248
+Chi2n,6.839402179898282,2.065115755548227
+Chi2v,7.475957556889567,2.1998451534984333
+Chi3n,4.828821865402848,1.6759363689938012
+Chi3v,5.365507516526876,1.797198269999827
+Chi4n,3.3879595704703083,1.375297565005399
+Chi4v,3.8221001079012624,1.4752295349404965
+HallKierAlpha,-2.6820753151740093,0.9388576662624227
+Ipc,80046401722.77925,42765760538543.875
+Kappa1,18.812680990123432,4.811572084937507
+Kappa2,7.949468380149388,2.308481118660745
+Kappa3,4.177950109740563,7.230646116692463
+LabuteASA,161.83136311553312,38.27334636128311
+PEOE_VSA1,13.025752401100918,7.261493645063624
+PEOE_VSA10,8.926138213282139,7.91916921235045
+PEOE_VSA11,4.262679227779316,5.911619841338072
+PEOE_VSA12,4.157980244135961,5.2045911289564
+PEOE_VSA13,3.1309571413459776,4.2624381925763535
+PEOE_VSA14,2.6927820222016288,4.222231213593859
+PEOE_VSA2,7.50686671015611,5.803910502108028
+PEOE_VSA3,6.279614415942617,5.99079013631374
+PEOE_VSA4,2.990605422684538,5.234845058389229
+PEOE_VSA5,2.271363815493391,4.819650568842531
+PEOE_VSA6,26.643369165986293,19.55670059383572
+PEOE_VSA7,41.068856839261926,18.725930210177275
+PEOE_VSA8,23.93492388724091,14.439924058869712
+PEOE_VSA9,14.925761825198052,10.302213802505305
+SMR_VSA1,14.351687499000315,9.16069193681072
+SMR_VSA10,22.726767259303344,13.252685865208836
+SMR_VSA2,0.34016476248791433,1.3872222015399889
+SMR_VSA3,11.419014867560842,7.784683229308473
+SMR_VSA4,3.3337289541112956,6.066985428367323
+SMR_VSA5,27.733203051152625,21.332122874216736
+SMR_VSA6,17.38698899776703,14.352274546561102
+SMR_VSA7,56.995376506540595,24.451230156426
+SMR_VSA8,0.0,0.0
+SMR_VSA9,7.530719433885769,8.630237721849342
+SlogP_VSA1,8.78160884840049,6.319020222727868
+SlogP_VSA10,6.293338198829007,7.307537361044556
+SlogP_VSA11,3.513047589162341,5.486942914769042
+SlogP_VSA12,6.167392056466631,9.173119044076243
+SlogP_VSA2,36.844047268688314,18.70817480763132
+SlogP_VSA3,11.037534948536745,8.462561112537216
+SlogP_VSA4,6.301108206548251,7.733393365667694
+SlogP_VSA5,28.23624070173914,18.965031437120057
+SlogP_VSA6,45.45843075098563,21.340395294212648
+SlogP_VSA7,1.1049891394211389,2.667242754185263
+SlogP_VSA8,8.079913623032056,9.378082438106741
+SlogP_VSA9,0.0,0.0
+TPSA,75.66528019957927,30.904987170511045
+EState_VSA1,9.261203010797361,12.403452280814758
+EState_VSA10,10.397478485576682,7.588433566000087
+EState_VSA11,0.047255090666268824,0.5053328737369644
+EState_VSA2,14.43241906673185,11.06277545688234
+EState_VSA3,19.210615805357484,13.178938356233145
+EState_VSA4,24.27628967599556,17.5245675106803
+EState_VSA5,14.043137042441318,13.807177302798996
+EState_VSA6,17.00020639221226,14.63638682478035
+EState_VSA7,23.496283738727637,20.222170673451355
+EState_VSA8,20.5613238692743,17.351135541665702
+EState_VSA9,9.09143915402905,8.309757097086326
+VSA_EState1,15.169368705180721,17.295871249171938
+VSA_EState10,1.9514258307827814,3.503968473957925
+VSA_EState2,19.274761273216875,11.99677511390377
+VSA_EState3,8.37100085751774,7.5670085104039355
+VSA_EState4,2.8686743660922964,2.9115023433209397
+VSA_EState5,0.23200888893102628,1.5102398246136246
+VSA_EState6,11.086529772094854,6.639413984373607
+VSA_EState7,2.5107446349814,3.542957048804867
+VSA_EState8,3.2611961954850885,3.1380869271295206
+VSA_EState9,0.34967562997091567,2.0732177368317783
+FractionCSP3,0.32932356264045093,0.19543747277780718
+HeavyAtomCount,27.34683558959549,6.63096938088552
+NHOHCount,1.497019746025782,1.2783355071248135
+NOCount,5.964194899980995,2.165527599749088
+NumAliphaticCarbocycles,0.2692009839152575,0.6809046158719172
+NumAliphaticHeterocycles,0.7079209110391185,0.809025824099174
+NumAliphaticRings,0.977121894954376,1.0617738930541925
+NumAromaticCarbocycles,1.476964608323521,0.892972356887753
+NumAromaticHeterocycles,1.0370906997725897,0.9289829218353998
+NumAromaticRings,2.5140553080961108,1.1256875189799262
+NumHAcceptors,5.010462837756656,1.9510298391888645
+NumHDonors,1.366591445791818,1.0989530374841023
+NumHeteroatoms,7.046296882884811,2.4998460476792594
+NumRotatableBonds,5.2525444389345575,2.5925159181994184
+NumSaturatedCarbocycles,0.19225996858636457,0.5795146924773747
+NumSaturatedHeterocycles,0.473572023077444,0.6892130950176582
+NumSaturatedRings,0.6658319916638086,0.9171185008019471
+RingCount,3.4911772030504866,1.2472574237537182
+MolLogP,3.4509174459927965,1.6013698045407503
+MolMR,104.86188053108269,25.142634855216052
+fr_Al_COO,0.05612402050842903,0.2437636449731326
+fr_Al_OH,0.1566148858688885,0.5013955009166311
+fr_Al_OH_noTert,0.12974344802878346,0.4594653363181852
+fr_ArN,0.05829490369470665,0.2545524756969779
+fr_Ar_COO,0.028545338963612176,0.17171109903266563
+fr_Ar_N,1.4499522678766086,1.524084125038301
+fr_Ar_NH,0.12768069940121854,0.3594574918851356
+fr_Ar_OH,0.08456777852294746,0.3166314160559749
+fr_COO,0.08466935947204121,0.29592803998571904
+fr_COO2,0.08498229433134613,0.2964680838171961
+fr_C_O,1.0163725552305451,0.9317542432418391
+fr_C_O_noCOO,0.9313918993016037,0.9023019852657759
+fr_C_S,0.014708484521466348,0.12244350558521289
+fr_HOCCN,0.011757175656398616,0.11064644750363647
+fr_Imine,0.03464019590923688,0.19830912213068522
+fr_NH0,2.1684594429868733,1.6048074266964687
+fr_NH1,0.8725830833859443,0.873711834637804
+fr_NH2,0.13866345685431108,0.3876857092698279
+fr_N_O,0.016161201320333884,0.15487091310020373
+fr_Ndealkylation1,0.07335619086732655,0.27478010580833173
+fr_Ndealkylation2,0.14404123968079552,0.38303815266173985
+fr_Nhpyrrole,0.12768069940121854,0.3594574918851356
+fr_SH,0.008236248888617036,0.09128718504112371
+fr_aldehyde,0.0038813752968239025,0.0644567398715665
+fr_alkyl_carbamate,0.009099686955913868,0.09900620633351406
+fr_alkyl_halide,0.2598888507808626,0.9181820474797185
+fr_allylic_oxid,0.1019135447819068,0.47157988502482356
+fr_amide,0.7852840880542988,0.9066208410785727
+fr_amidine,0.027571035666928083,0.175533099895616
+fr_aniline,0.6475135605105699,0.8542775173815877
+fr_aryl_methyl,0.4487775333524116,0.7392207082462369
+fr_azide,0.0006908596806644487,0.027652433048820757
+fr_azo,0.0013975572512413628,0.03833900272659876
+fr_barbitur,0.0017405294879664804,0.04187941053754055
+fr_benzene,1.4757084998132222,0.8929935018524333
+fr_benzodiazepine,0.0010261860395007897,0.0320347594097395
+fr_bicyclic,0.8660305660352627,1.1729812498450534
+fr_diazo,0.0,0.0
+fr_dihydropyridine,0.0011796497314112324,0.03434168123834526
+fr_epoxide,0.0031588398363345226,0.06355361840997185
+fr_ester,0.11190561491426787,0.3792499169672557
+fr_ether,0.7913248777205671,1.0307916631330358
+fr_furan,0.04551864174256111,0.21513563389202153
+fr_guanido,0.013077181860482389,0.12840879294348725
+fr_halogen,0.7047713554830775,1.1711246086284846
+fr_hdrzine,0.011233433021017427,0.10682181338318988
+fr_hdrzone,0.026035852613688744,0.16309813858883795
+fr_imidazole,0.09449158188844446,0.3020442893302488
+fr_imide,0.02984459207056927,0.1851805231585741
+fr_isocyan,0.0,0.0
+fr_isothiocyan,0.0,0.0
+fr_ketone,0.08472124221485791,0.3062515351793875
+fr_ketone_Topliss,0.061198698890036984,0.26455719905053593
+fr_lactam,0.002793476100077988,0.05297572294144425
+fr_lactone,0.016205984319396717,0.1324190123702844
+fr_methoxy,0.30608524498485024,0.6850004665227354
+fr_morpholine,0.04155807699617488,0.2067913794695565
+fr_nitrile,0.05143054375299008,0.23255981130956072
+fr_nitro,0.03423878732007611,0.19178455943098008
+fr_nitro_arom,0.028007396840723255,0.17431640217515046
+fr_nitro_arom_nonortho,0.01893556272568993,0.14134496202915198
+fr_nitroso,3.822938944388253e-06,0.001955230527931856
+fr_oxazole,0.015920902300972338,0.12816189106229653
+fr_oxime,0.011007879623298519,0.1078298216936682
+fr_para_hydroxylation,0.25588186463300877,0.5648214616344769
+fr_phenol,0.061809822987004194,0.27395571248026945
+fr_phenol_noOrthoHbond,0.060393151041040885,0.2708814041204626
+fr_phos_acid,0.0013041683141713069,0.036089723890630546
+fr_phos_ester,0.0013019837776316566,0.036059524761244785
+fr_piperdine,0.14092663670938893,0.3939055198353871
+fr_piperzine,0.07965366357700382,0.2760577458859027
+fr_priamide,0.02570598759620153,0.1606304634878668
+fr_prisulfonamd,0.0,0.0
+fr_pyridine,0.2513986495195112,0.5053445348173503
+fr_quatN,0.0038688142117209124,0.06654608941729591
+fr_sulfide,0.06695003746480166,0.24993551981269405
+fr_sulfonamd,0.1038195529127518,0.31620177904811836
+fr_sulfone,0.028000843231104307,0.16918526287280575
+fr_term_acetylene,0.003606123692827948,0.06263375068367018
+fr_tetrazole,0.011501584881259517,0.1076261554337455
+fr_thiazole,0.05210119647066277,0.2288155759915653
+fr_thiocyan,0.0,0.0
+fr_thiophene,0.059991742451880124,0.24605121670473437
+fr_unbrch_alkane,0.19092521676063814,0.865393113351381
+fr_urea,0.05973232873779663,0.24236557216398927
+sascore,2.8405588800894073,0.7445938054054921
+num_fused_rings,1.2614376871874748,1.2404985101625285

environment.yml

@@ -0,0 +1,31 @@
+name: molskill
+channels:
+  - conda-forge
+  - pytorch
+  - defaults
+dependencies:
+  - python=3.9
+  - pip=22.1.2
+  - numpy=1.23.1
+  - pandas=1.4.2
+  - statsmodels=0.13.2
+  - scipy=1.8.1
+  - matplotlib=3.5.2
+  - rdkit=2022.03.3
+  - tqdm=4.64.0
+  - scikit-learn=1.0.1
+  - pytorch=1.11
+  - cudatoolkit=11.3
+  - black=22.6.0
+  - httplib2=0.20.4
+  - pre-commit=2.20.0
+  - pyright=1.1.269
+  - pip:
+    - protobuf==3.20.1
+    - pytorch-lightning==1.6.3
+    - PubChemPy==1.0.4
+    - psycopg2==2.9.3
+    - tensorboard==2.9.0
+    - guacamol==0.5.4
+    - pytest-lazy-fixture==0.6.3
+    - pytest==7.2.0

models/default/default/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}

models/default/default/version_1/hparams.yaml

@@ -0,0 +1 @@
+{}

models/default/default/version_2/hparams.yaml

@@ -0,0 +1 @@
+{}

models/test/default/version_0/hparams.yaml

@@ -0,0 +1 @@
+{}