Commit d1e78426 by Mustafa Tekpinar

Added custom frequency file input option.

parent 05a0fb8c
S2A 2.5607342137e-06
S2L 6.1954797779e-06
S2W 6.840647125218045e-07
F3L 1.5903965494e-06
F3S 1.2003274493e-06
F3L 1.67277954004e-05
V4L 1.5903965494e-06
V4M 1.5903965494e-06
A5P 1.2003245677e-06
A5V 2.0521632536e-06
G6W 6.5666780489e-06
G6V 1.5903965494e-06
V7F 5.01813964553e-05
V7G 6.3620921103e-06
I8L 1.5903965494e-06
I8N 1.2003216862e-06
I8M 1.3680957338e-06
R9W 1.2003245677e-06
R9P 6.840516103258959e-07
R9Q 6.1954644244e-06
R10W 1.3680976055e-06
R10G 1.3680976055e-06
R10Q 2.0521520234e-06
R10L 1.3681013489e-06
L11V 1.5904066669e-06
D12N 2.560721099e-06
D12E 2.0521464083e-06
E13Q 2.0521492158e-06
E13K 3.42024869312e-05
E13D 1.5903914907e-06
T14R 1.3680938621e-06
T14I 3.4202346554e-06
V15L 2.0521436008e-06
V15M 2.0521436008e-06
V15A 3.044813566e-06
V16M 2.0521464083e-06
V16L 8.8926344361e-06
V16G 2.0521520234e-06
N17D 1.2003216862e-06
R18G 1.2390007706e-06
R18C 6.8769569899e-05
R18L 1.5904066669e-06
I19V 6.567281802e-06
A20V 1.590386432e-06
A21T 1.2003216862e-06
G22R 1.2003245677e-06
G22A 0.0003172014898557
E23K 2.4006433724e-06
E23G 7.9542598243e-06
I25V 1.2003216862e-06
I25T 2.7362101847e-06
I25N 1.3681050923e-06
R27W 6.4025077342e-06
R27Q 3.96506775309e-05
P28T 6.840553537592262e-07
P28S 6.840553537592262e-07
P28L 1.5904218434e-06
N30K 1.5904521973e-06
A31T 1.3681163227e-06
A31S 5.51349194844e-05
A31G 5.51361491178e-05
I32F 6.5693526559e-06
I32V 1.17713824063e-05
I32M 6.840731356270762e-07
K33T 2.5608916e-06
K33N 4.801298271e-06
E34D 1.5905483256e-06
E34D 6.5676268537e-06
M35I 6.841012141428348e-07
M35I 6.841012141428348e-07
I36V 1.5906900095e-06
I36T 3.7174536929e-06
I36M 2.0522137914e-06
E37K 1.5905280871e-06
E37D 6.840890465030052e-07
E37D 1.2391205218e-06
C39R 1.5906647069e-06
A42T 6.84875215735693e-07
A42G 6.5728933876e-06
A42V 6.2019119254e-06
K43Q 1.5905129086e-06
S44F 1.5905685646e-06
T45A 3.1810764126e-06
T45R 1.3687848612e-06
S46G 1.3686106412e-06
Q48K 1.5905635048e-06
Q48H 6.1963473771e-06
V49M 4.7715842614e-06
V49A 1.200552254e-06
I50T 1.5905078491e-06
I50M 8.0548523049e-06
V51I 1.5905230275e-06
K52N 1.5905078491e-06
E53K 5.5763671083e-06
E53D 1.5905027897e-06
G54R 6.5735847072e-06
G55D 1.3682379967e-06
K57Q 1.5905027897e-06
K57T 1.590517968e-06
Q60E 6.5725477824e-06
Q60H 1.2007021706e-06
Q62E 6.843296717133699e-07
N64S 2.6040601017e-05
T66I 1.5905736244e-06
G67R 2.4073414284e-06
G67E 2.4069184463e-06
I68V 2.4074863194e-06
I68M 2.7422804804e-06
R69K 1.3713809257e-06
R69T 1.3713809257e-06
E71K 7.016549233021003e-07
L73M 6.2587448573e-06
L73V 2.7816605122e-06
D74N 6.574535509e-06
D74V 5.1239220548e-06
I75V 2.45024772e-06
V76I 1.44986971884e-05
V76A 6.895144163674174e-07
C77G 2.4286876586e-06
C77S 6.5732390292e-06
E78Q 2.4188067058e-06
R79K 6.868745148948738e-07
R79S 7.5466313209e-06
F80V 1.2058391555e-06
T81A 1.5910139531e-06
T81I 4.60211434281e-05
T81S 2.0363115067e-06
T82A 2.7415662568e-06
T82I 1.5909785154e-06
K84E 2.4064029569e-06
L85V 3.181946906e-06
Q86E 1.2023710757e-06
S87A 1.2024520402e-06
S87F 6.847664124813743e-07
F88V 6.847645368663531e-07
F88L 5.12272775e-06
E89G 4.7934567945e-06
E89D 6.848470736484543e-07
D90G 1.5909987653e-06
A92T 1.3703416947e-06
A92V 6.5772165219e-06
S93G 6.45551344298e-05
I94V 6.5698705735e-06
S95A 1.30419084567e-05
T96A 5.4918425543e-06
R100Q 1.7549247576e-05
E102D 6.2919287138e-06
A103S 1.5904774931e-06
A105S 3.1809347494e-06
S106N 3.7177162812e-06
I107V 5.1209045565e-06
I107L 6.5684033525e-06
I107R 1.5904673747e-06
H109Y 1.2003850835e-06
H109P 1.3681556304e-06
H109R 6.840778152196368e-07
H109L 1.31281835845e-05
V110G 1.5904572564e-06
H112Y 6.840918543814715e-07
H112D 6.840918543814715e-07
H112R 3.1809043947e-06
I115V 6.1957254451e-06
I115T 4.7713414149e-06
T116A 4.1044725068e-06
T116K 1.36308493382e-05
T117M 8.2092482654e-06
T117R 6.841030861258421e-07
K118E 6.840843667567834e-07
K118Q 2.736337467e-06
A120G 3.8414456128e-06
D121H 1.2005147807e-06
D121G 6.4020486555e-06
D121V 1.5904420792e-06
G122R 1.5904471383e-06
K123Q 6.5694389699e-06
K123N 1.3684046317e-06
C124R 4.3375452963e-06
C124G 1.3684065043e-06
C124Y 1.98434420845e-05
A125T 1.2009646147e-06
Y126N 5.20548658285e-05
R127G 6.844636337626746e-07
R127K 1.369011601e-06
R127T 6.845058005021535e-07
A128T 1.5906292847e-06
A128G 3.1812383288e-06
S129G 6.5701295629e-06
S129N 7.9528681223e-06
Y130C 4.7910880287e-06
D132H 0.0001140305973839
D132G 4.8032469949e-06
K134E 3.1810662934e-06
L135R 6.841395918423195e-07
L135P 6.841395918423195e-07
K136R 1.5905129086e-06
A137T 2.06768651327e-05
P138L 3.1810460551e-06
P138R 3.1810460551e-06
P139S 6.841115101761587e-07
P139A 8.2093381221e-06
P141S 1.2005118982e-06
P141L 2.0523963095e-06
P141R 2.7365284126e-06
C142R 1.368243613e-06
C142S 3.1811472489e-06
C142W 1.5905382063e-06
A143V 6.841564419486418e-07
G144V 6.5734982843e-06
N145H 1.2006445059e-06
N145S 6.842023158879988e-07
N145I 6.842023158879988e-07
Q146P 1.2008204004e-06
G147R 1.2009848075e-06
T148N 6.84532040206674e-07
T148I 6.84532040206674e-07
Q149H 1.3691596782e-06
I150T 6.846763945488804e-07
T151M 8.0679394979e-06
V152M 1.09589491463e-05
E153K 1.2019461912e-06
L155I 6.842734794759012e-07
N158S 1.2004283128e-06
I159V 1.368161246e-06
I159K 1.2004023748e-06
A160V 4.21320293883e-05
T161A 1.2003706744e-06
T161R 6.840955982552826e-07
T161M 3.4204779912e-06
R163G 2.5608719256e-06
K164N 3.1808639226e-06
A165S 1.5904572564e-06
L166I 1.5904521973e-06
N168S 1.2003476206e-06
N168K 1.200344739e-06
P169L 5.1227539925e-06
S170G 1.200353384e-06
E171A 2.4007298218e-06
G174W 1.5904420792e-06
G174R 2.5610949192e-06
I176V 1.2005118982e-06
I176N 6.5749677826e-06
L177S 1.97083169097e-05
E178Q 6.843193691122873e-07
E178K 6.843193691122873e-07
V179F 1.5904521973e-06
V180G 5.08658357753e-05
G181S 1.31414679019e-05
Y183C 4.1069898228e-06
V185I 3.1810662934e-06
V185G 1.3687005556e-06
H186N 4.8051049434e-06
A188T 6.843053206107288e-07
A188V 1.02457179302e-05
I190V 1.8592521344e-06
I190S 3.6030928949e-06
V194I 2.053531458e-06
K196T 3.1810258172e-06
G198R 2.4044241404e-06
G198E 1.2020964562e-06
E199Q 4.02953338003e-05
E199K 6.84502989224554e-07
T200P 1.2014927345e-06
T200A 1.2014927345e-06
T200I 6.844608228314228e-07
V201L 1.17773510382e-05
V201A 1.3685357215e-06
V201E 6.842678607597016e-07
D203H 4.3375883009e-06
D203V 1.42516342906e-05
V204F 1.5904572564e-06
R205S 1.5904572564e-06
T206A 1.5904673747e-06
P208S 1.11531626651e-05
P208L 6.841133822155149e-07
P208H 1.3682267644e-06
N209S 4.0270418961e-05
A210P 4.1046353647e-06
A210D 1.2005436061e-06
T212A 4.059446535e-06
V213L 6.841536335399477e-07
V213M 0.0014672568740488
N215S 1.8471288776e-05
I216T 1.2006099098e-06
R217C 0.0001332262566024
R217S 6.84220105397265e-07
R217H 1.54926732049e-05
R217P 2.7368055184e-06
S218P 4.1054891758e-06
S218C 6.0050105808e-06
I219F 1.3691165638e-06
I219V 0.284034317711987
G221R 1.2025156627e-06
N222K 3.1809549863e-06
A223V 1.43966172062e-05
V224I 6.858832873562903e-07
R226Q 1.2145326114e-06
R226L 1.2145326114e-06
E227K 1.346072564e-06
L228M 5.42321756915e-05
I229T 1.411781315e-06
E230Q 1.268272638e-06
I231V 3.4820687388e-06
G232R 6.948845379851684e-07
G232R 6.948845379851684e-07
G232V 1.2550232304e-06
E234D 6.88721361243996e-07
D235G 6.874628770046417e-07
D235V 6.8457430058e-06
T237I 8.2391778399e-06
L238R 6.861929739329014e-07
K241E 1.2412152987e-06
K241Q 6.853624402192612e-07
N243I 6.851680306078263e-07
N243S 2.0555040918e-06
Y245C 1.5905078491e-06
I246L 6.850112684353657e-07
I246V 2.4813187713e-06
I246T 2.4067446612e-06
S247T 6.850572570855472e-07
S247P 6.850572570855472e-07
S247A 1.73709339606e-05
N248S 5.5849281405e-06
N250H 1.2045116187e-06
S252L 6.862767973932462e-07
V253L 2.4171637966e-06
V253G 6.866613290192691e-07
C256R 6.922590211734345e-07
C256Y 4.8486124656e-06
I257V 1.3894292224e-06
I257F 6.947146112377035e-07
I257S 1.244394005e-06
F258I 1.2311450141e-06
F258L 2.0740863649e-06
L259S 6.2593455506e-06
L259F 7.00942768022991e-07
L259F 7.00942768022991e-07
L260F 8.869291977e-06
L260V 1.4022157813e-06
L260H 2.80305982e-06
F261I 1.2515832528e-06
F261Y 6.5714248163e-06
I262F 1.2657234495e-06
I262T 1.4088654265e-06
I262M 1.9159021152e-06
N263S 2.1279100943e-06
N263K 1.2813448996e-06
H264N 1.4224791535e-06
H264D 4.2674192497e-06
H264Y 1.41196887507e-05
R265C 1.2009386536e-06
R265H 7.25099344807e-05
R265L 2.0525648165e-06
L266R 6.841161902937595e-07
L266P 1.239246439e-06
V267L 6.841021501330579e-07
V267I 3.0982159233e-06
E268G 0.000114003608462
S269T 6.4029996772e-06
T270A 4.37800817045e-05
T270N 1.2003994929e-06
L272W 1.44096025591e-05
K274R 6.4027372982e-06
A275P 1.5903965494e-06
A275V 2.4007182949e-06
I276V 3.4202440138e-06
I276L 6.840488027777854e-07
I276T 2.0521520234e-06
I276M 6.5701295629e-06
E277K 1.2003274493e-06
A281G 6.5734982843e-06
A282T 2.7362289019e-06
A282D 6.840665843050499e-07
A282G 4.9567891902e-06
Y283C 9.2930930015e-06
Y283F 6.840609689860438e-07
P285A 2.736322492e-06
P285S 1.368161246e-06
K286Q 1.2008204004e-06
K286R 4.1044331982e-06
N287K 1.64188334966e-05
T288I 1.858855837e-06
T288R 6.841339753246558e-07
P290S 1.5904117257e-06
P290Q 6.842744159375723e-07
P290L 6.842744159375723e-07
L292Q 1.2012964391e-06
L294F 2.0334419869e-06
L296S 2.5610424467e-06
I298V 1.2003274493e-06
I298M 6.5707339509e-06
S299R 1.2003303309e-06
S299N 1.2003332124e-06
P300T 1.5904117257e-06
P300H 3.1807829815e-06
P300L 1.5903914907e-06
N302D 1.2003332124e-06
D304H 1.5903813734e-06
D304N 1.5903813734e-06
D304G 1.2003332124e-06
N306D 6.5715111847e-06
N306I 6.3615457283e-06
N306S 1.590386432e-06
V307A 6.0016516545e-06
H308Y 3.1807526296e-06
P309S 1.43650052056e-05
T310A 1.59037631484e-05
T310R 1.3680919905e-06
K311E 1.5903813734e-06
K311N 1.2003303309e-06
H312R 1.31395684965e-05
H312P 8.8926101041e-06
H312Q 1.2004427232e-06
E313A 1.2003245677e-06
V314F 4.7711441203e-06
H315Y 1.16294501459e-05
H315Q 1.67275259493e-05
H318Q 2.4782041941e-06
E319K 6.44336284063e-05
E320K 1.2003216862e-06
E324G 1.2003332124e-06
R325W 4.7883743742e-06
R325Q 6.87659059877e-05
V326M 4.3368734611e-06
V326L 6.840525461803874e-07
V326A 0.0005786377356059
Q327E 6.8150193112e-06
Q327R 1.2003303309e-06
Q328P 1.3681032206e-06
Q328H 1.5904016082e-06
H329Y 1.5904117257e-06
H329L 1.2003216862e-06
I330V 3.1808032164e-06
I330M 1.368106964e-06
E331K 1.30098465953e-05
S332G 1.2003216862e-06
S332N 3.1808234515e-06
L334P 1.5903965494e-06
G336D 7.4344744012e-06
G336A 1.3680994772e-06
S337C 2.0521464083e-06
N338H 1.2003245677e-06
N338S 0.0001263785483565
S339F 1.2003245677e-06
S340F 1.31278388951e-05
R341G 6.5690937278e-06
R341K 1.2003216862e-06
R341S 1.5904370202e-06
M342V 1.2003216862e-06
M342T 1.2003274493e-06
T345A 1.2003216862e-06
T345I 3.0977897889e-06
T347S 3.5576806768e-06
L348W 7.91031600130362e-07
L348S 1.5820632002e-06
P350S 7.892385741931614e-07
P350R 1.5652538685e-06
P350Q 7.826355094252795e-07
G351E 7.605291457584529e-07
L352V 7.4626865671e-06
L352I 2.413663265e-06
L352F 8.045039348287453e-07
L352P 1.4650275937e-06
A353P 7.418650784819067e-07
A353V 7.506391692526186e-07
G354S 1.45454160782e-05
P355S 1.9670196374e-06
P355A 7.24366830953064e-07
P355L 4.3778565513e-06
S356P 6.958119081249957e-07
S356F 5.6638611674e-06
G357R 1.6038801067e-06
G357E 6.861440079043789e-07
M359T 1.6032732426e-06
V360I 1.6038595275e-06
V360A 1.2004600162e-06
K361E 3.1905050569e-06
S362Y 1.6071279338e-06
T363A 1.2428165205e-06
T364A 3.1032077237e-06
T364P 6.84178910048262e-07
S365G 1.5906394052e-06
S365R 1.5958635217e-06
L366V 1.2003591474e-06
L366P 1.5920676819e-06
T367A 1.5907557998e-06
T367N 1.3685862914e-06
T367I 4.9668277988e-06
S368T 1.5932954129e-06
S368L 7.4489745245e-06
T371A 1.864968799e-06
S372P 1.5906444655e-06
G373R 1.16302775805e-05
G373E 7.9535765643e-06
S374R 1.2003274493e-06
S374N 1.2003389757e-06
S374R 7.9526151379e-06
S375G 1.29977452332e-05
D376A 6.840656484121468e-07
D376V 6.840656484121468e-07
K377E 3.1809448678e-06
V378F 1.2003360941e-06
Y379H 2.5629131095e-06
Y379C 4.02935353051e-05
Y379F 6.1990054315e-06
Y379S 4.7883940273e-06
A380V 6.6019673862e-06
H381Y 3.8447046882e-06
Q382H 6.5998759223e-06
M383V 1.3680957338e-06
M383T 6.8169113937e-06
V384I 5.1260626968e-06
V384F 1.5903965494e-06
V384D 0.0010107169459616
R385C 4.83422332624e-05
R385H 3.28473169939e-05
R385L 1.3681013489e-06
T386I 6.5822384876e-06
D387N 1.590386432e-06
R389W 1.67314442086e-05
R389Q 9.10882254526e-05
Q391K 6.840459952527208e-07
Q391R 3.1807627469e-06
K392R 6.5805059092e-06
L393V 1.2003216862e-06
A395G 1.5903965494e-06
Q398E 6.8405161032e-06
P399A 1.2003216862e-06
S401N 3.0986268125e-06
K402I 1.5903914907e-06
P403T 1.3680994772e-06
P403A 6.840497386245948e-07
P403S 1.8590770054e-06
P403R 3.0985730451e-06
L404P 1.5903965494e-06
S406G 3.7178637155e-06
S406T 6.840459952527208e-07
S406N 0.0010354288943527
P408H 1.5903813734e-06
Q409E 9.5766439335e-06
Q409P 4.7711592962e-06
Q409R 6.581025587e-06
Q409H 2.78853947456e-05
A410V 1.5903813734e-06
I411F 1.3680919905e-06
I411V 3.7176241407e-06
T413I 5.1234626409e-06
D415N 2.04925906476e-05
D415E 2.0302837118e-06
D418N 4.7711441203e-06
I419V 2.29266273567e-05
I419T 9.9141066584e-06
S421G 4.7883285176e-06
S421N 1.5903813734e-06
G422S 2.5612589099e-06
R423G 1.3680901188e-06
R423K 2.41652456676e-05
R423T 1.11531903081e-05
A424T 5.51445530812e-05
A424G 1.5903813734e-06
R425G 1.3680901188e-06
R425T 1.5903763148e-06
Q426L 3.1807526296e-06
Q426H 6.5747948664e-06
D428N 2.5611933111e-06
D428E 2.0521351782e-06
E429K 1.5903914907e-06
E429A 3.6011379595e-06
M431I 3.1807425125e-06
L432H 1.5903763148e-06
E433K 6.840459952527208e-07
E433Q 2.4783823102e-06
P435T 1.5903712562e-06
A436S 1.5903763148e-06
A436V 1.2003216862e-06
P437S 4.3373034117e-06
P437A 1.36315250082e-05
V440M 2.560721099e-06
A441T 0.0003401503848841
A442T 4.7711441203e-06
A442G 1.3681032206e-06
A442D 3.4202580516e-06
K443Q 3.8416620566e-06
N444S 1.2003216862e-06
N444K 2.4006433724e-06
Q445E 1.5903813734e-06
S446R 6.5739304215e-06
E448V 1.2003245677e-06
E448D 1.92065346826e-05
D450Y 5.121415969e-06
D450N 1.590386432e-06
T452A 2.4782287603e-06
K453T 1.31430223694e-05
K453N 8.0543133326e-06
G454R 9.04525477261e-05
E457K 1.2003216862e-06
E457V 2.56082602e-06
M458V 3.1807829815e-06
M458T 1.5903914907e-06
E460K 1.5904016082e-06
E460A 0.0001493090275583
T465S 6.840544178970525e-07
T465A 6.840544178970525e-07
S466C 2.4006491355e-06
S467G 1.2003216862e-06
S467N 6.5722022135e-06
S467T 1.5904572564e-06
N468S 1.5904724339e-06
N468K 6.840665843050499e-07
P469L 1.5905280871e-06
R472K 3.7173799905e-06
H473D 6.840619048661428e-07
H473Y 1.3681238097e-06
H473R 1.5903965494e-06
R474G 4.02701195712e-05
R474W 9.9133695419e-06
R474Q 9.5767618505e-06
D476N 1.5903965494e-06
D476Y 6.5696979252e-06
D478Y 3.1807728641e-06
D478V 1.5903813734e-06
V479L 6.5696116045e-06
V479L 2.4006664249e-06
E480Q 1.2003389757e-06
M481V 1.8584919452e-06
M481T 6.5715975553e-06
M481I 1.5903965494e-06
V482M 1.5904016082e-06
V482L 3.1808032164e-06
E483K 6.5704749139e-06
D484Y 6.5695252861e-06
D484H 1.2003360941e-06
D484G 9.9126079699e-06
D485Y 1.2003389757e-06
D485G 1.2003418573e-06
S486F 5.1212979417e-06
R487L 6.840562896239606e-07
R487Q 2.23040312058e-05
E489K 1.2003389757e-06
M490V 2.5607866736e-06
M490T 1.3681107075e-06
M490K 6.840553537592262e-07
A492T 3.71729707894e-05
C494G 1.590386432e-06
C494Y 1.5903914907e-06
T495I 1.3683484581e-06
P496S 1.2004254307e-06
P496R 2.78812481877e-05
P496L 1.67287489126e-05
P496H 2.0522053682e-06
R497W 9.292931796e-06
R497G 4.1044051212e-06
R497Q 2.1684770352e-05
I500M 3.8415439933e-06
I501L 1.3680938621e-06
I501S 6.8404786693e-06
I501T 1.3680957338e-06
L503F 6.567281802e-06
T504A 1.5903965494e-06
S505N 1.73474723493e-05
S505I 6.5708203012e-06
V506I 1.5904016082e-06
V506A 6.5758325003e-06
L507M 1.5904016082e-06
L507F 9.5424703547e-06
S508G 1.2003332124e-06
S508R 3.1808032164e-06
L509F 6.840553537592262e-07
L509I 1.3681107075e-06
E511V 1.5904167846e-06
E512D 2.0521548309e-06
I513T 5.5767126394e-06
N514S 6.3616873739e-06
G517E 1.2003216862e-06
H518Y 1.5904572564e-06
H518R 6.5715975553e-06
E519K 1.5904420792e-06
V520A 1.5911861019e-06
L521V 2.4024601191e-06
L521H 5.0772452086e-06
R522W 1.92191804941e-05
R522Q 4.21565819443e-05
E523K 6.5695252861e-06
M524L 1.2006791041e-06
M524I 7.6852136489e-06
M524I 5.5077364484e-05
H526R 7.6849970925e-06
N527K 6.841573780899967e-07
H528Y 1.5908317186e-06
H528R 1.5908266571e-06
F530L 3.4206651962e-06
V531M 5.124814866e-06
G532S 1.3682342526e-06
G532D 3.4206605158e-06
Q537K 1.5907102521e-06
L540F 6.841189983950568e-07
A541T 1.5907861665e-06
A541S 1.5907811053e-06
A541P 1.5907811053e-06
A541V 4.7889312747e-06
Q542R 6.0016804705e-06
H543Y 6.5735847072e-06
H543R 5.63864816198e-05
Q544E 1.2003562657e-06
T545A 6.01066552319e-05
K546R 7.6845640162e-06
L547S 6.5724613867e-06
Y548H 4.9574772389e-06
L549F 3.1818456613e-06
L550V 6.843671383324984e-07
N551H 7.2107237884e-06
N551S 6.818770712e-06
T552I 3.1820177811e-06
T553I 6.84822685710216e-07
L555F 6.853972013861473e-07
S556T 3.1085827971e-06
E557K 6.254565833e-06
L559M 1.8709470609e-06
L559Q 1.8712761604e-06
F560L 6.879973360743147e-07
Y561C 3.1093560523e-06
Q562P 6.866179534115986e-07
Q562H 6.866141818786039e-07
I563V 3.0600878857e-06
L564F 4.8096214415e-06
I565F 6.1711972396e-06
Y566H 1.3710424858e-06
D567Y 6.873135661951696e-07
F568S 6.855381611672796e-07
A569S 2.0680185073e-06
A569V 6.859491547e-06
N570D 1.2054554089e-06
N570S 1.86281717567e-05
G572D 1.865878188e-06
V573I 2.4192397297e-06
L574V 6.882312456985547e-07
R575G 1.3777843299e-06
R575M 1.2153267284e-06
R575T 1.3147687979e-05
L576F 6.902950044731116e-07
S577L 1.93925259953e-05
E578K 5.1226490242e-06
E578G 5.45240729978e-05
P579R 4.8013213236e-06
A580T 1.3681575022e-06
P581A 3.1810764126e-06
P581L 6.31921711095e-05
R319H 2.54014985645e-05
R319P 6.840787511458319e-07
L582V 5.24935727381e-05
D584E 1.02609566495e-05
L585F 1.3681312968e-06
L585I 6.840656484121468e-07
L323S 1.5904673747e-06
A586V 1.2003274493e-06
P324L 2.4006433724e-06
M587L 3.1808942766e-06
M587T 6.5705612573e-06
M587I 6.840600331085056e-07
M587I 3.0978281746e-06
A589T 1.5904623155e-06
A589V 6.3618290258e-06
D591G 1.2003216862e-06
S592N 4.3369755667e-06
S592T 6.8152473191e-06
S595C 2.4782717524e-06
G596R 6.840778152196368e-07
G596S 1.3681556304e-06
T598A 0.0001608095887095
T598R 6.840628407488026e-07
T598I 6.840628407488026e-07
E599D 1.5904420792e-06
D601E 6.840553537592262e-07
G602S 1.5904319613e-06
G602V 1.2003389757e-06
P603S 2.0521913299e-06
P603R 0.0001053255053765
P603L 8.8927195988e-06
K604Q 6.840544178970525e-07
E605D 1.5904066669e-06
G606A 3.0977744349e-06
L607I 1.5904066669e-06
L607H 0.000190808719215
L607P 6.840525461803874e-07
A608P 1.5904016082e-06
A608T 6.5653846658e-06
A608V 6.1565318751e-06
E609K 1.2003360941e-06
I611V 1.5904269023e-06
I611L 1.5904269023e-06
I611T 2.7362326454e-06
V612F 2.4006548986e-06
V612I 1.31428496326e-05
E613Q 1.5904370202e-06
E613D 1.3681144509e-06
E613D 1.3681144509e-06
F614L 7.9521851014e-06
K616Q 1.2003360941e-06
K616N 1.5904471383e-06
K617Q 1.2003216862e-06
K617T 6.3617278452e-06
K618E 0.0047796290537015
K618R 3.22172533304e-05
K618M 1.43653393093e-05
K618T 0.0047746551121706
A619P 1.2003389757e-06
A619D 4.9566847709e-06
E620D 1.5904724339e-06
M621L 1.5904471383e-06
M621V 3.1808942766e-06
M621T 1.2003245677e-06
M621K 6.5716839282e-06
L622F 1.2003476206e-06
D624Y 6.840656484121468e-07
D624N 6.840656484121468e-07
Y625D 1.590492671e-06
Y625S 6.5779952901e-06
Y625C 2.05219975291e-05
F626L 4.89472014592e-05
F626L 4.7715690827e-06
E629D 6.840965342301383e-07
I630M 1.97350244056e-05
D631V 3.1812484491e-06
E633K 1.5906039841e-06
G634V 1.860061382e-06
N635H 2.4031587118e-06
N635S 2.0535680059e-06
I637T 1.2009069249e-06
G638R 1.3685207385e-06
G638V 1.5905635048e-06
L639F 1.2007223545e-06
L641P 1.2004830743e-06
I643T 2.5614622875e-06
D644H 1.3682230203e-06
N645S 1.5904977303e-06
N645K 3.1810156983e-06
Y646C 5.94878836813e-05
V647L 6.84094662282988e-07
V647M 5.01915955722e-05
P648S 2.4010353264e-06
P649S 6.8161763976e-06
P654T 6.842041884243599e-07
P654L 1.2006675711e-06
I655F 6.841901446514803e-07
I655V 0.0007269324442406
I655T 5.51584970115e-05
I657V 4.7717815923e-06
R659Q 2.79076690274e-05
R659P 6.5864871629e-06
R659L 6.846351442389322e-07
V664G 3.1812585695e-06
D667E 6.5759189846e-06
E668K 6.843015744410625e-07
E669Q 1.5905382063e-06
K670R 1.0262023671e-05
E671G 3.1810865319e-06
C672W 3.8416325401e-06
F673L 6.5703022339e-06
E674K 2.0522811789e-06
E674Q 6.840937263132548e-07
S675T 2.72614622057e-05
S675I 2.7363000298e-06
S677G 1.31387053119e-05
S677C 3.0977936274e-06
E679A 1.590492671e-06
C680G 3.4887586723e-05
C680Y 1.5905331467e-06
C680W 6.840834308152222e-07
A681T 2.0522137914e-06
M682T 3.1809752233e-06
Y684H 2.5609703004e-06
Y684S 3.7173707779e-06
Y684C 2.60215954459e-05
S685A 1.3681500149e-06
I686M 2.0522362534e-06
R687W 7.4352390677e-06
R687Q 8.6745208256e-06
Q689K 1.3681799649e-06
Q689R 0.0003060627688891
Q689P 6.840806230059049e-07
Y690N 6.840918543814715e-07
Y690D 4.1045511262e-06
I691V 1.92053685819e-05
I691K 4.7886560841e-06
I691T 6.5709930084e-06
S692P 9.5774432057e-06
E694A 6.81599900858e-05
S695W 7.4372021245e-06
S695L 1.3685844183e-06
T696I 1.5905938641e-06
L697I 6.844074195239536e-07
G699D 6.850347312608749e-07
Q700R 1.5906798883e-06
Q701K 9.50563255325e-05
S702T 6.5693526559e-06
E703K 7.4347599811e-06
V704L 6.840750074564176e-07
V704L 5.4726000596e-06
V704M 6.840750074564176e-07
V704E 1.5905432659e-06
V704G 3.1810865319e-06
P705A 3.1811067706e-06
L101P 1.5905432659e-06
A102V 2.4006548986e-06
S707C 1.590558445e-06
P103L 5.472644984e-06
Q105P 1.5905331467e-06
Q105R 6.5698705735e-06
N710H 1.2003274493e-06
N710K 1.5905382063e-06
T106I 6.5694389699e-06
S711P 1.5905280871e-06
S711C 1.5905280871e-06
W712C 6.5696979252e-06
K713T 3.4203797168e-06
W714R 1.2003274493e-06
W714C 6.840740715404664e-07
V716L 6.1566329511e-06
V716M 0.0016088584477148
V716A 6.5689211203e-06
E717D 6.5689211203e-06
H718Y 0.0040380586094655
I719V 3.4203656781e-06
I719T 4.7885119493e-06
Y721H 3.8412488668e-06
Y721C 1.11519326918e-05
Y721S 5.4725626232e-06
K722E 1.5905078491e-06
A723T 6.5690937278e-06
R725C 1.4250221498e-05
R725G 6.1957484773e-06
R725S 1.368178093e-06
R725H 9.47864949688e-05
S726L 1.5904977303e-06
H727Y 1.200353384e-06
H727L 9.542956026e-06
H727Q 3.4203843964e-06
P730R 6.840768792960028e-07
P730L 6.840768792960028e-07
H733R 2.73625885e-06
T735I 2.0522081759e-06
D737V 9.5426828298e-06
G738E 1.23901612207e-05
N739K 6.5694389699e-06
I740T 9.9126816653e-06
I740M 6.840675202005138e-07
L741M 1.02609566495e-05
L743F 2.0522474846e-06
L743R 1.31361164385e-05
A744V 1.5904774931e-06
L746P 1.5904825524e-06
P747S 6.3619504467e-06
P747R 6.5709066537e-06
D748H 1.05327724115e-05
Y750H 1.3681518867e-06
Y750C 3.6010687972e-06
K751Q 1.5905432659e-06
K751R 0.0001369301135962
V752L 2.5610949192e-06
V752A 1.200344739e-06
F753L 2.4010699167e-06
R755S 1.200457134e-06
C756G 1.2005320758e-06
C756Y 1.2006012611e-06
......@@ -5,3 +5,6 @@
#If you are using GnomAD v4.0.0 data.
prescott -e ../data/MLH1_normPred_evolCombi.txt -g ../data/gnomAD_v4.0.0_MLH1_HUMAN_ENSG00000076242.csv -s ../data/MLH1.fasta
#If you have a custom frequency file
#prescott -e ../data/MLH1_normPred_evolCombi.txt -g ../data/custom-frequency-file.txt -s ../data/MLH1.fasta
......@@ -558,6 +558,134 @@ def rankSortData(dataArray):
return (normalizedRankedDataArray)
def plotLabeledPositions(myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList, useFrequencies):
clinvarLabeledDF = myBigMergedDF.loc[(myBigMergedDF['labels']==0) | (myBigMergedDF['labels']==1)]
clinvarLabeledDF['labels'] = clinvarLabeledDF['labels'].astype('int64')
if(len(clinvarLabeledDF)>0):
print("\nMutations with ClinVar labels according to the gnomAD file:\n")
print(clinvarLabeledDF)
fprESCOTT, tprESCOTT, AUC_ESCOTT = plotROCandAUCV2(clinvarLabeledDF['labels'], \
clinvarLabeledDF['ESCOTT'])
fprPRESCOTT, tprPRESCOTT, AUC_PRESCOTT = plotROCandAUCV2(clinvarLabeledDF['labels'], \
clinvarLabeledDF['PRESCOTT'])
fig = plt.figure(figsize=(12,6))
# plt.rcParams.update({'font.size': 18})
plt.grid(linestyle='--')
# plt.title(protName + " - "+method+" AUC={:.2f}".format(AUC_ESCOTT))
plt.title("AUC={:.2f} -> AUC={:.2f}".format(AUC_ESCOTT, AUC_PRESCOTT))
plt.ylim([0.0, 1.0])
#plt.xlim([1000, 1863])
plt.scatter(myBigMergedDF.loc[myBigMergedDF['labels'] == 1, 'position'], myBigMergedDF.loc[myBigMergedDF['labels'] == 1, 'ESCOTT'], marker='o', color='red', label='pathogenic')
plt.scatter(myBigMergedDF.loc[myBigMergedDF['labels'] == 0, 'position'], myBigMergedDF.loc[myBigMergedDF['labels'] == 0, 'ESCOTT'], marker='o', color='blue', label='benign')
if (useFrequencies.lower() == 'true'):
#print(selectedPositionsList)
#print(selectedValuesList)
plt.scatter(selectedPositionsList, selectedValuesList, marker='o', color='olive', label='PRESCOTT')
# Add vertical lines connecting old and new values
for i in range(len(selectedPositionsList)):
plt.annotate("", xy=(selectedPositionsList[i], selectedValuesList[i]), xycoords='data', \
xytext=(selectedPositionsList[i], myBigMergedDF.loc[myBigMergedDF['mutant'] == selectedMutantsList[i], 'ESCOTT'].values[0]), textcoords='data',
arrowprops=dict(arrowstyle="->", connectionstyle="arc3"))
plt.xticks(rotation = 90)
plt.ylabel("PR/ESCOTT Score")
plt.xlabel("Position")
plt.legend(loc='upper right')
plt.tight_layout()
plt.savefig("clinvar-vs-position.png")
plt.close()
print("@> AUC= {:.3f} {:.3f}".format( AUC_ESCOTT, AUC_PRESCOTT))
def runPrescottModel(myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList, \
version=2, scalingCoeff=1.0, freqCutoff=-4.0):
# # print(myBigMergedDF)
# scalingCoeff = args.coefficient
# freqCutoff = args.frequencycutoff
for index, row in myBigMergedDF.iterrows():
if(row['log10frequency'] != 999.0):
# print(row['log10frequency'])
# freq = np.log10(row['log10frequency'])
freq = row['log10frequency']
# print(freq)
temp1 = row['PRESCOTT']
label = row['labels']
if(version==1):
if(freq>freqCutoff):
temp2 = temp1 - freq*scalingCoeff/freqCutoff
if(temp2<0.0):
myBigMergedDF.at[index,'PRESCOTT'] = 0.0
selectedValuesList.append(0.0)
else:
myBigMergedDF.at[index,'PRESCOTT'] = temp2
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==2):
if(freq>freqCutoff):
temp2 = temp1 - scalingCoeff*(freqCutoff - freq)/freqCutoff
if(temp2<0.0):
temp2 = 0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==3):
temp2 = temp1 - scalingCoeff*(freqCutoff - freq)/freqCutoff
if(freq>freqCutoff):
if(temp2<0.0):
temp2 = 0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
else:
if(temp2>1.0):
temp2 = 1.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==4):
temp2 = temp1 - scalingCoeff*(freqCutoff - freq)/freqCutoff
if(freq>freqCutoff):
if(temp2<0.0):
temp2 = 0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
else:
print(myBigMergedDF.loc[index, 'Selected Population'])
sys.exit(-1)
if (myBigMergedDF.iloc[index,'Selected Population'].values==None):
if(temp2>1.0):
temp2 = 1.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==5):
if(freq>freqCutoff):
temp2 = temp1*0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
return myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList
def main():
# Adding the main parser
main_parser = argparse.ArgumentParser(description=\
......@@ -634,13 +762,13 @@ def main():
args = main_parser.parse_args()
print("\n\n@> Running PRESCOTT with the following parameters:\n\n")
print("@> ESCOTT file : {}".format(args.escottfile))
print("@> GNOMAD frequency file : {}".format(args.gnomadfile))
print("@> Frequency file : {}".format(args.gnomadfile))
print("@> Use population max. freq : {}".format(str(args.usepopmax).lower()))
print("@> Which equation to use (Default=2): {}".format(str(args.equation)))
print("@> Scaling coefficient (Default=1.0): {}".format(args.coefficient))
print("@> Frequency cutoff (Default=-4.0) : {}".format(args.frequencycutoff))
print("@> Name of the output file : {}".format(args.outputfile))
print("@> GnomAD data version (Default=4) : {}".format(str(args.gnomadversion)))
# End of argument parsing!
protein = os.path.splitext(os.path.basename(args.escottfile))[0]
......@@ -649,6 +777,9 @@ def main():
# Check if file exists
usePopMaxOrNot = args.usepopmax.lower()
version = args.equation
useFrequencies = args.usefrequencies
if (os.path.exists(args.escottfile)):
#Convert the matrix format to singleline format
localResidueList = None
......@@ -703,197 +834,141 @@ def main():
print("ERROR: ESCOTT input file does not exist!")
sys.exit(-1)
#Create a dataframe to merge ESCOTT data with frequency data
myBigMergedDF = pd.DataFrame()
myBigMergedDF = pd.concat([myBigMergedDF, dfESCOTT], ignore_index=True)
if (args.gnomadversion==2 or args.gnomadversion==3):
gnomadDF = getGnomADOverallFrequency(args.gnomadfile, usePopMax=usePopMaxOrNot)
elif (args.gnomadversion==4):
gnomadDF = getGnomADV4OverallFrequency(args.gnomadfile, usePopMax=usePopMaxOrNot)
else:
print("ERROR: Unknown GnomAD version!")
sys.exit(-1)
# Assign labels to pathogenic/benign mutations for performance evaluation
gnomadDF['labels'] = ""
for index, row in gnomadDF.iterrows():
if ((row['ClinVar Clinical Significance']=='Benign/Likely benign') or \
(row['ClinVar Clinical Significance']=='Benign') or \
(row['ClinVar Clinical Significance']=='Likely benign')):
gnomadDF.at[index,'labels'] = 0
if((row['ClinVar Clinical Significance']=='Pathogenic/Likely pathogenic') or \
(row['ClinVar Clinical Significance']=='Pathogenic') or \
(row['ClinVar Clinical Significance']=='Likely pathogenic')):
gnomadDF.at[index,'labels'] = 1
if (len(gnomadDF.loc[(gnomadDF['labels']==0) | (gnomadDF['labels']==1)]) > 0):
print(gnomadDF.loc[(gnomadDF['labels']==0) | (gnomadDF['labels']==1)])
# print(gnomadDF['ClinVar Clinical Significance'])
# Add frequency column and a dummy frequency to each row in myBigMergedDF
myBigMergedDF['frequency'] = 999.0
myBigMergedDF['log10frequency'] = 999.0
myBigMergedDF['labels'] = np.nan
myBigMergedDF['position'] = ""
useFrequencies = args.usefrequencies
selectedPositionsList = []
selectedValuesList = []
selectedMutantsList = []
# Assign ESCOTT scores to PRESCOTT scores.
# Then, we will modify them according to different conditions.
myBigMergedDF['PRESCOTT'] = myBigMergedDF['ESCOTT']
labelsList = []
if (useFrequencies.lower() == 'true'):
# print(myBigMergedDF)
for index, row in myBigMergedDF.iterrows():
myBigMergedDF.at[index,'position'] = row['mutant'][1:-1]
# print(row['mutant'], row['ESCOTT'])
# print(row['mutant'][1:-1])
temp = (gnomadDF.loc[gnomadDF['mutant'] == row['mutant'], 'Allele Frequency Log'].values)
#print(temp)
if (len(temp) > 0):
myBigMergedDF.at[index,'frequency'] = temp[0]
myBigMergedDF.at[index,'labels'] = gnomadDF.loc[gnomadDF['mutant'] == row['mutant'], 'labels'].values[0]
# print(myBigMergedDF)
scalingCoeff = args.coefficient
freqCutoff = args.frequencycutoff
for index, row in myBigMergedDF.iterrows():
if(row['frequency'] != 999.0):
# print(row['frequency'])
# freq = np.log10(row['frequency'])
freq = row['frequency']
# print(freq)
temp1 = row['PRESCOTT']
label = row['labels']
if(version==1):
if(freq>freqCutoff):
temp2 = temp1 - freq*scalingCoeff/freqCutoff
if(temp2<0.0):
myBigMergedDF.at[index,'PRESCOTT'] = 0.0
selectedValuesList.append(0.0)
else:
myBigMergedDF.at[index,'PRESCOTT'] = temp2
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==2):
if(freq>freqCutoff):
temp2 = temp1 - scalingCoeff*(freqCutoff - freq)/freqCutoff
if(temp2<0.0):
temp2 = 0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==3):
temp2 = temp1 - scalingCoeff*(freqCutoff - freq)/freqCutoff
if(freq>freqCutoff):
if(temp2<0.0):
temp2 = 0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
else:
if(temp2>1.0):
temp2 = 1.0
file_name, file_extension = os.path.splitext(args.gnomadfile)
if(file_extension == ".csv"):
print("@> You frequency data is in gnomAD format!")
print("@> GnomAD data version (Default=4) : {}".format(str(args.gnomadversion)))
if (args.gnomadversion==2 or args.gnomadversion==3):
gnomadDF = getGnomADOverallFrequency(args.gnomadfile, usePopMax=usePopMaxOrNot)
elif (args.gnomadversion==4):
gnomadDF = getGnomADV4OverallFrequency(args.gnomadfile, usePopMax=usePopMaxOrNot)
else:
print("ERROR: Unknown GnomAD version!")
sys.exit(-1)
# Assign labels to pathogenic/benign mutations for performance evaluation
gnomadDF['labels'] = ""
for index, row in gnomadDF.iterrows():
if ((row['ClinVar Clinical Significance']=='Benign/Likely benign') or \
(row['ClinVar Clinical Significance']=='Benign') or \
(row['ClinVar Clinical Significance']=='Likely benign')):
gnomadDF.at[index,'labels'] = 0
if((row['ClinVar Clinical Significance']=='Pathogenic/Likely pathogenic') or \
(row['ClinVar Clinical Significance']=='Pathogenic') or \
(row['ClinVar Clinical Significance']=='Likely pathogenic')):
gnomadDF.at[index,'labels'] = 1
if (len(gnomadDF.loc[(gnomadDF['labels']==0) | (gnomadDF['labels']==1)]) > 0):
print(gnomadDF.loc[(gnomadDF['labels']==0) | (gnomadDF['labels']==1)])
# print(gnomadDF['ClinVar Clinical Significance'])
selectedPositionsList = []
selectedValuesList = []
selectedMutantsList = []
# # Assign ESCOTT scores to PRESCOTT scores.
# # Then, we will modify them according to different conditions.
# myBigMergedDF['PRESCOTT'] = myBigMergedDF['ESCOTT']
labelsList = []
if (useFrequencies.lower() == 'true'):
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==4):
temp2 = temp1 - scalingCoeff*(freqCutoff - freq)/freqCutoff
if(freq>freqCutoff):
if(temp2<0.0):
temp2 = 0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
else:
print(myBigMergedDF.loc[index, 'Selected Population'])
sys.exit(-1)
if (myBigMergedDF.iloc[index,'Selected Population'].values==None):
if(temp2>1.0):
temp2 = 1.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
if(version==5):
if(freq>freqCutoff):
temp2 = temp1*0.0
myBigMergedDF.at[index,'PRESCOTT'] = temp2
if(label==0 or label==1):
selectedValuesList.append(temp2)
selectedPositionsList.append(row['position'])
selectedMutantsList.append(row['mutant'])
# myBigMergedDF.dropna(subset = ['labels'], inplace=True)
# print(myBigMergedDF)
for index, row in myBigMergedDF.iterrows():
myBigMergedDF.at[index,'position'] = row['mutant'][1:-1]
# print(row['mutant'], row['ESCOTT'])
# print(row['mutant'][1:-1])
temp = (gnomadDF.loc[gnomadDF['mutant'] == row['mutant'], 'Allele Frequency Log'].values)
#print(temp)
if (len(temp) > 0):
myBigMergedDF.at[index,'log10frequency'] = temp[0]
myBigMergedDF.at[index,'labels'] = gnomadDF.loc[gnomadDF['mutant'] == row['mutant'], 'labels'].values[0]
# print(myBigMergedDF)
# scalingCoeff = args.coefficient
# freqCutoff = args.frequencycutoff
myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList = \
runPrescottModel(myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList, \
version=version, scalingCoeff= args.coefficient, freqCutoff=args.frequencycutoff)
# myBigMergedDF.dropna(subset = ['labels'], inplace=True)
clinvarLabeledDF = myBigMergedDF.loc[(myBigMergedDF['labels']==0) | (myBigMergedDF['labels']==1)]
clinvarLabeledDF['labels'] = clinvarLabeledDF['labels'].astype('int64')
if(len(clinvarLabeledDF)>0):
print("\nMutations with ClinVar labels according to the gnomAD file:\n")
print(clinvarLabeledDF)
#print(myBigMergedDF.loc[(myBigMergedDF['labels']=='0') | (myBigMergedDF['labels']=='1'), 'labels'])
# print(clinvarLabeledDF['labels'].values)
# print(clinvarLabeledDF['ESCOTT'].values)
numPathogenic = len(myBigMergedDF.loc[(myBigMergedDF['labels']==1)])
numBenign = len(myBigMergedDF.loc[(myBigMergedDF['labels']==0)])
if ((numPathogenic >=1) and (numBenign>=1)):
fprESCOTT, tprESCOTT, AUC_ESCOTT = plotROCandAUCV2(clinvarLabeledDF['labels'], \
clinvarLabeledDF['ESCOTT'])
fprPRESCOTT, tprPRESCOTT, AUC_PRESCOTT = plotROCandAUCV2(clinvarLabeledDF['labels'], \
clinvarLabeledDF['PRESCOTT'])
# fprPRESCOTT, tprPRESCOTT, AUC_PRESCOTT = plotROCandAUCV2(myBigMergedDF.loc[(myBigMergedDF['labels']==0) | (myBigMergedDF['labels']==1), 'labels'], \
# myBigMergedDF.loc[(myBigMergedDF['labels']==0) | (myBigMergedDF['labels']==1), 'PRESCOTT'])
fig = plt.figure(figsize=(12,6))
# plt.rcParams.update({'font.size': 18})
plt.grid(linestyle='--')
# plt.title(protName + " - "+method+" AUC={:.2f}".format(AUC_ESCOTT))
plt.title("AUC={:.2f} -> AUC={:.2f}".format(AUC_ESCOTT, AUC_PRESCOTT))
plt.ylim([0.0, 1.0])
#plt.xlim([1000, 1863])
plt.scatter(myBigMergedDF.loc[myBigMergedDF['labels'] == 1, 'position'], myBigMergedDF.loc[myBigMergedDF['labels'] == 1, 'ESCOTT'], marker='o', color='red', label='pathogenic')
plt.scatter(myBigMergedDF.loc[myBigMergedDF['labels'] == 0, 'position'], myBigMergedDF.loc[myBigMergedDF['labels'] == 0, 'ESCOTT'], marker='o', color='blue', label='benign')
numPathogenic = len(myBigMergedDF.loc[(myBigMergedDF['labels']==1)])
numBenign = len(myBigMergedDF.loc[(myBigMergedDF['labels']==0)])
if ((numPathogenic >=1) and (numBenign>=1)):
plotLabeledPositions(myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList, useFrequencies)
else:
print("@> You're using a custom frequency file!")
gnomadDF = pd.read_csv(args.gnomadfile, header=None, sep='\s+')
gnomadDF.columns = ['mutant', 'frequency']
print(gnomadDF)
# Assign labels to pathogenic/benign mutations for performance evaluation
# gnomadDF['labels'] = ""
# for index, row in gnomadDF.iterrows():
# if ((row['ClinVar Clinical Significance']=='Benign/Likely benign') or \
# (row['ClinVar Clinical Significance']=='Benign') or \
# (row['ClinVar Clinical Significance']=='Likely benign')):
# gnomadDF.at[index,'labels'] = 0
# if((row['ClinVar Clinical Significance']=='Pathogenic/Likely pathogenic') or \
# (row['ClinVar Clinical Significance']=='Pathogenic') or \
# (row['ClinVar Clinical Significance']=='Likely pathogenic')):
# gnomadDF.at[index,'labels'] = 1
# if (len(gnomadDF.loc[(gnomadDF['labels']==0) | (gnomadDF['labels']==1)]) > 0):
# print(gnomadDF.loc[(gnomadDF['labels']==0) | (gnomadDF['labels']==1)])
# # print(gnomadDF['ClinVar Clinical Significance'])
selectedPositionsList = []
selectedValuesList = []
selectedMutantsList = []
# # Assign ESCOTT scores to PRESCOTT scores.
# # Then, we will modify them according to different conditions.
# myBigMergedDF['PRESCOTT'] = myBigMergedDF['ESCOTT']
labelsList = []
if (useFrequencies.lower() == 'true'):
#print(selectedPositionsList)
#print(selectedValuesList)
plt.scatter(selectedPositionsList, selectedValuesList, marker='o', color='olive', label='PRESCOTT')
# Add vertical lines connecting old and new values
for i in range(len(selectedPositionsList)):
plt.annotate("", xy=(selectedPositionsList[i], selectedValuesList[i]), xycoords='data', \
xytext=(selectedPositionsList[i], myBigMergedDF.loc[myBigMergedDF['mutant'] == selectedMutantsList[i], 'ESCOTT'].values[0]), textcoords='data',
arrowprops=dict(arrowstyle="->", connectionstyle="arc3"))
plt.xticks(rotation = 90)
plt.ylabel("PR/ESCOTT Score")
plt.xlabel("Position")
plt.legend(loc='upper right')
plt.tight_layout()
plt.savefig("clinvar-vs-position.png")
plt.close()
print("@> AUC= {:.3f} {:.3f}".format( AUC_ESCOTT, AUC_PRESCOTT))
# Renaming the column just to make clear that the frequency column in the csv
# is actually log10 frequencies. Normally, one can deduce it from the values as well
# but it is always better to be clear.
myBigMergedDF = myBigMergedDF.rename(columns={'frequency': 'log10frequency'})
# print(myBigMergedDF)
for index, row in myBigMergedDF.iterrows():
myBigMergedDF.at[index,'position'] = row['mutant'][1:-1]
# print(row['mutant'], row['ESCOTT'])
# print(row['mutant'][1:-1])
temp = (gnomadDF.loc[gnomadDF['mutant'] == row['mutant'], 'frequency'].values)
#print(temp)
if (len(temp) > 0):
myBigMergedDF.at[index,'log10frequency'] = np.log10(temp[0])
# myBigMergedDF.at[index,'labels'] = gnomadDF.loc[gnomadDF['mutant'] == row['mutant'], 'labels'].values[0]
# print(myBigMergedDF)
# scalingCoeff = args.coefficient
# freqCutoff = args.frequencycutoff
myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList = \
runPrescottModel(myBigMergedDF, selectedPositionsList, selectedValuesList, selectedMutantsList, \
version=version, scalingCoeff= args.coefficient, freqCutoff=args.frequencycutoff)
# myBigMergedDF.dropna(subset = ['labels'], inplace=True)
# sys.exit(-1)
#Write the results to csv files.
myBigMergedDF['mutant'] = myBigMergedDF['mutant'].str.upper()
# myBigMergedDF = myBigMergedDF['mutant'].apply(lambda x: x.upper())
myBigMergedDF.to_csv(outfile+'-details.csv', index=None)
......@@ -918,14 +993,13 @@ def main():
variant = str(localResidueList[pos]).upper()+str(posList[pos])+item
# print(variant)
if(item=='Y'):
#print(myBigMergedDF.loc[myBigMergedDF['mutant']==variant, 'PRESCOTT'].values[0])
my_file.write("{:.2f}\n".format(float(myBigMergedDF.loc[myBigMergedDF['mutant']==variant, 'PRESCOTT'].values[0])))
else:
# print(myBigMergedDF.loc[myBigMergedDF['mutant']==variant, 'PRESCOTT'].values)
my_file.write("{:.2f},".format(float(myBigMergedDF.loc[myBigMergedDF['mutant']==variant, 'PRESCOTT'].values[0])))
if(os.path.exists(protein+'_singleline.txt')):
os.remove(protein+'_singleline.txt')
if(os.path.exists(protein+'_singleline_1-ranksort.txt')):
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment