Skip to content

Commit

Permalink
Merge pull request #119 from jyaacoub/development
Browse files Browse the repository at this point in the history
development
  • Loading branch information
jyaacoub committed Jul 17, 2024
2 parents 2e2449f + 2663a19 commit 3bc02a9
Show file tree
Hide file tree
Showing 12 changed files with 25,241 additions and 144 deletions.
33 changes: 33 additions & 0 deletions playground.py
Original file line number Diff line number Diff line change
@@ -1,3 +1,36 @@
# %% oncokb proteins
import pandas as pd

kb_df = pd.read_csv('/cluster/home/t122995uhn/projects/downloads/oncoKB_DrugGenePairList.csv')
kb_prots = set(kb_df.gene)


davis_df = pd.read_csv('/cluster/home/t122995uhn/projects/MutDTA/splits/davis/test.csv')
davis_df['gene'] = davis_df.prot_id.str.split('(').str[0]
kiba_df = pd.read_csv('/cluster/home/t122995uhn/projects/MutDTA/splits/kiba/test.csv')
pdb_df = pd.read_csv('/cluster/home/t122995uhn/projects/MutDTA/splits/pdbbind/test.csv')

davis_df['db'] = 'davis'
kiba_df['db'] = 'kiba'
pdb_df['db'] = 'pdbbind'

#%%
all_df = pd.concat([davis_df, kiba_df, pdb_df], axis=0)
new_order = ['db'] + [x for x in all_df.columns if x != 'db']
all_df = all_df[new_order].drop(['seq_len',
'gene_matched_on_pdb_id',
'gene_matched_on_uniprot_id'], axis=1)

all_df.to_csv('/cluster/home/t122995uhn/projects/MutDTA/splits/all_tests.csv')

kb_overlap_test = all_df[all_df.gene.isin(kb_prots)]

kb_overlap_test.to_csv('/cluster/home/t122995uhn/projects/MutDTA/splits/all_tests_oncokb.csv')

['BRAF', 'ERBB2', 'FGFR2', 'FGFR3', 'KIT', 'PDGFRA', 'PIK3CA',
'RAF1', 'CHEK1', 'CHEK2', 'FGFR1', 'MAP2K1', 'MAP2K2', 'MTOR',
'EZH2', 'KDM6A', 'HRAS', 'KRAS', 'IDH1', 'PTEN', 'ESR1', 'BRIP1']

# %%
########################################################################
########################## VIOLIN PLOTTING #############################
Expand Down
13 changes: 11 additions & 2 deletions results/v113/model_media/model_stats.csv
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ DGM_davis1D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.7926
DGM_davis2D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.6802334756018732,0.4122965513634545,0.3365557862472744,0.9166151092410354,0.5022958078397446,0.9574001823903292
DGM_davis0D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.7482530045928646,0.5197366766877236,0.4542040532006625,0.8050527081134624,0.4461380075332078,0.897247294848785
DGM_davis4D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.7500256488232135,0.4202540848988467,0.463987592348891,0.915000329003,0.5261902546589091,0.9565564954580572
DGM_davis3D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8124008264671932,0.6416851004316045,0.5726087345262351,0.6139882867658651,0.41814691178938923,0.7835740467663954
DGM_davis3D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8124008264671932,0.6416851004316045,0.5726087345262351,0.6139882867658651,0.4181469117893892,0.7835740467663954
GVPLM_davis4D_nomsaF_binaryE_128B_0.00020535607176845963LR_0.08845592454543601D_2000E_gvpLF_binaryLE,0.7534531597279891,0.5219505901659167,0.4665234229987415,0.7990459549406203,0.4326813253593184,0.8938937044976993
GVPLM_davis2D_nomsaF_binaryE_128B_0.00020535607176845963LR_0.08845592454543601D_2000E_gvpLF_binaryLE,0.767553801569662,0.4679799645016079,0.4975432691118115,0.8307167291540061,0.4861246287088877,0.9114366292584504
GVPLM_davis3D_nomsaF_binaryE_128B_0.00020535607176845963LR_0.08845592454543601D_2000E_gvpLF_binaryLE,0.7881126560725141,0.5117816919373207,0.5344788271118109,0.7824263605065905,0.4710016337041163,0.8845486761657555
Expand All @@ -18,4 +18,13 @@ GVPLM_davis0D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277
GVPLM_davis2D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.6758544466241947,0.3482148623183911,0.3313455573966994,0.9952058429887072,0.5672084597638211,0.9976000415941788
GVPLM_davis1D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.7715096417472135,0.5070999916573449,0.505118493158149,0.8228862016569322,0.521357725135223,0.90713075223858
GVPLM_davis3D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.7784890152525039,0.5548561075227736,0.519896821064786,0.7201384467294399,0.534564816284727,0.8486097140201967
GVPLM_davis4D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.7591851271174638,0.4580465758811774,0.49007259211942494,0.8589132362281114,0.5267642440549613,0.9267757205646421
GVPLM_davis4D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.7591851271174638,0.4580465758811774,0.4900725921194249,0.8589132362281114,0.5267642440549613,0.926775720564642
EDIM_davis0D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8306312738976872,0.7361106276759142,0.5991969853638022,0.4799344828183976,0.3650483090313287,0.6927730384609361
EDIM_davis1D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8213008531051639,0.658980135244847,0.5928406093578696,0.598288902866782,0.4164140685964707,0.7734913721993169
EDIM_davis2D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8225446485053062,0.6603442335278025,0.5949532834745241,0.6383847882308629,0.4154985330988705,0.7989898548985856
EDIM_davis3D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8257508664241492,0.7310753856354779,0.5889781203307795,0.4852039936128347,0.3546071329782175,0.6965658573407361
EDIM_davis4D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8404380957025455,0.7536920423101249,0.6146193037809486,0.4475845677765498,0.344083449582884,0.6690176139508958
DGM_kiba0D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.5790729147254525,0.3237567466038684,0.220483622988913,0.5872366004827765,0.5416789341999021,0.7663136436752098
DGM_kiba1D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.6991041045925556,0.5827312646091369,0.5234334020017861,0.4359633916482334,0.4614902562500025,0.6602752393117838
DGM_kiba3D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.6703138545001528,0.5130147763454005,0.4537929112353873,0.4829267623645413,0.484057142425249,0.6949293218483023
DGM_kiba2D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.672607400192465,0.5094659678690476,0.4582769804170869,0.5474786138565632,0.5343923583458045,0.7399179777898109
13 changes: 11 additions & 2 deletions results/v113/model_media/model_stats_val.csv
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ DGM_davis1D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8163
DGM_davis2D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8343753726176008,0.7720660560854502,0.618611791650495,0.3283613673160558,0.3143092008198009,0.5730282430352416
DGM_davis0D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8345962630012087,0.7841559792978283,0.6289360094161347,0.3611685706886787,0.3225311759640188,0.6009730199340722
DGM_davis4D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8557152702768875,0.7904879365029139,0.6656571912339156,0.3427956306740941,0.3299113169392162,0.585487515387044
DGM_davis3D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8349019526166668,0.7875041565317034,0.6443896656067043,0.3662570748291923,0.32390817027678465,0.605191766987285
DGM_davis3D_nomsaF_binaryE_128B_0.00012LR_0.24D_2000E_originalLF_binaryLE,0.8349019526166668,0.7875041565317034,0.6443896656067043,0.3662570748291923,0.3239081702767846,0.605191766987285
GVPLM_davis4D_nomsaF_binaryE_128B_0.00020535607176845963LR_0.08845592454543601D_2000E_gvpLF_binaryLE,0.8317179299256213,0.7525555462006857,0.6231692649585702,0.4056508528712579,0.3161008745272529,0.6369072560987651
GVPLM_davis2D_nomsaF_binaryE_128B_0.00020535607176845963LR_0.08845592454543601D_2000E_gvpLF_binaryLE,0.8288787269604654,0.7293571227266307,0.6105211859324264,0.3761462606386942,0.3491652655728998,0.6133076394752427
GVPLM_davis3D_nomsaF_binaryE_128B_0.00020535607176845963LR_0.08845592454543601D_2000E_gvpLF_binaryLE,0.8164773292665711,0.7250154328888457,0.6154067444267105,0.4597009403992768,0.3855288712417378,0.6780124928047246
Expand All @@ -18,4 +18,13 @@ GVPLM_davis0D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277
GVPLM_davis2D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.8056817717122009,0.6600120446400118,0.5615058375759591,0.3972760533222704,0.3633167063701174,0.630298384356386
GVPLM_davis1D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.7796812905632664,0.6418365067480541,0.508433155533638,0.4350043675747687,0.3998515603735166,0.6595486089552223
GVPLM_davis3D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.7920895987899996,0.6645194989409928,0.5585099170472267,0.469367754560377,0.4311579323672002,0.6851041924848928
GVPLM_davis4D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.829644425075257,0.7189969797010738,0.591263254476021,0.35142261273003306,0.3509021611774669,0.5928090862411212
GVPLM_davis4D_nomsaF_aflowE_128B_0.00014968791626986144LR_0.00039427600918916277D_2000E_gvpLF_binaryLE,0.829644425075257,0.7189969797010738,0.591263254476021,0.351422612730033,0.3509021611774669,0.5928090862411212
EDIM_davis0D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8234292742670842,0.7808314559178251,0.6105927936621894,0.3630461745087596,0.3307242975196736,0.6025331314614655
EDIM_davis1D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8164513012688231,0.7316460353008426,0.5901484441437694,0.3885064322451407,0.3640839215268426,0.6233028415185837
EDIM_davis2D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.8216236400111289,0.7501182762791265,0.5974487525198227,0.350761726413648,0.3393165324142272,0.5922514047375895
EDIM_davis3D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.860215850035831,0.8257879154012255,0.6885140061655473,0.3049388665705435,0.3008343178958179,0.5522127004792116
EDIM_davis4D_nomsaF_binaryE_48B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.869855884432354,0.8198549396094414,0.6874469120379113,0.300964541267322,0.2915365434585408,0.5486023525900359
DGM_kiba0D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.588709694581878,0.3937358060010086,0.244256676114009,0.5859551462931225,0.5731926417196901,0.7654770710433608
DGM_kiba1D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.7435320925039093,0.6398140200524538,0.6268500070894489,0.4107691435515396,0.4127436749121904,0.6409127425410885
DGM_kiba3D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.6724758528185321,0.5028962013125743,0.4551672280896423,0.4654384967530096,0.4689483909867084,0.682230530504909
DGM_kiba2D_nomsaF_binaryE_128B_0.0001LR_0.4D_2000E_originalLF_binaryLE,0.730532492692012,0.6193619256451531,0.586863514576392,0.512769142470763,0.5601343077809119,0.7160790057464071
Loading

0 comments on commit 3bc02a9

Please sign in to comment.