Score

Scoring functions to calculate kinase score based on substrate sequence

Setup

from katlas.score import *

Algorithms

Multiply

source

multiply_func

 multiply_func (values, factor=17)

Multiply the possibilities of the amino acids at each position in a phosphorylation site

	Type	Default	Details
values			list of values, possibilities of amino acids at certain positions
factor	int	17	scale factor

The function implement formula from Johnson et al. Nature: An atlas of substrate specificities for the human serine/threonine kinome, Supplementary Note2 (page 160)

Multiply class, consider the dynamics of scale factor

source

multiply

 multiply (values, kinase, num_dict={'SYK': 18, 'PTK2': 18, 'ZAP70': 18,
           'ERBB2': 18, 'CSK': 18, 'FGFR4': 18, 'EGFR': 18, 'ERBB4': 18,
           'EPHA8': 18, 'EPHA7': 18, 'EPHA5': 18, 'EPHA2': 18, 'EPHB2':
           18, 'EPHB1': 18, 'EPHB3': 18, 'EPHB4': 18, 'EPHA4': 18,
           'EPHA3': 18, 'EPHA6': 18, 'FRK': 18, 'EPHA1': 18, 'TEC': 18,
           'BTK': 18, 'ITK': 18, 'BMX': 18, 'TXK': 16, 'ABL2': 18, 'ABL1':
           18, 'SRMS': 18, 'PTK2B': 18, 'FER': 18, 'MERTK': 18, 'AXL': 18,
           'FES': 18, 'PTK6': 18, 'YES1': 18, 'FGR': 18, 'SRC': 18, 'FYN':
           18, 'LCK': 18, 'BLK': 18, 'LYN': 18, 'HCK': 18, 'PDGFRB': 18,
           'PDGFRA': 18, 'FLT3': 18, 'TYRO3': 18, 'ROS1': 18, 'TEK': 18,
           'LTK': 18, 'ALK': 18, 'MUSK': 18, 'KIT': 18, 'CSF1R': 18,
           'MET': 18, 'KDR': 18, 'RET': 18, 'MST1R': 16, 'JAK3': 16,
           'FLT1': 16, 'MATK': 18, 'FGFR3': 18, 'FGFR2': 18, 'FGFR1': 18,
           'FLT4': 18, 'INSR': 18, 'IGF1R': 18, 'INSRR': 16, 'NTRK3': 18,
           'NTRK1': 18, 'NTRK2': 18, 'TNK1': 18, 'TNK2': 18, 'DDR2': 18,
           'DDR1': 18, 'TYK2': 18, 'JAK2': 18, 'JAK1': 18, 'TNNI3K_TYR':
           18, 'NEK10_TYR': 16, 'PINK1_TYR': 16, 'MAP2K7_TYR': 16,
           'PKMYT1_TYR': 16, 'TESK1_TYR': 16, 'LIMK1_TYR': 16,
           'LIMK2_TYR': 16, 'WEE1_TYR': 18, 'MAP2K6_TYR': 16,
           'MAP2K4_TYR': 16, 'PDHK1_TYR': 16, 'BMPR2_TYR': 16,
           'PDHK4_TYR': 16, 'PDHK3_TYR': 16, 'AAK1': 17, 'ACVR2A': 17,
           'ACVR2B': 17, 'AKT1': 17, 'AKT2': 17, 'AKT3': 17, 'ALK2': 17,
           'ALK4': 17, 'ALPHAK3': 17, 'AMPKA1': 17, 'AMPKA2': 17,
           'ANKRD3': 17, 'ATM': 17, 'ATR': 17, 'AURA': 17, 'AURB': 17,
           'AURC': 17, 'GRK2': 17, 'GRK3': 17, 'BCKDK': 17, 'BIKE': 17,
           'BMPR1A': 17, 'BMPR1B': 17, 'BMPR2': 17, 'BRAF': 17, 'BRSK1':
           17, 'BRSK2': 17, 'BUB1': 17, 'CAMK1A': 17, 'CAMK1B': 17,
           'CAMK1D': 17, 'CAMK1G': 17, 'CAMK2A': 17, 'CAMK2B': 17,
           'CAMK2D': 17, 'CAMK2G': 17, 'CAMK4': 17, 'CAMKK1': 17,
           'CAMKK2': 17, 'CAMLCK': 17, 'CDK1': 17, 'CDC7': 17, 'CDK10':
           17, 'CDK19': 17, 'CDK2': 17, 'CDK3': 17, 'CDK4': 17, 'CDK5':
           17, 'CDK6': 17, 'CDK7': 17, 'CDK8': 17, 'CDK9': 17, 'CDKL1':
           17, 'CDKL5': 17, 'CHAK1': 17, 'CHAK2': 17, 'CDK13': 17, 'CHK1':
           17, 'CHK2': 17, 'CK1A': 17, 'CK1A2': 17, 'CK1D': 17, 'CK1E':
           17, 'CK1G1': 17, 'CK1G2': 17, 'CK1G3': 17, 'CK2A1': 17,
           'CK2A2': 17, 'CLK1': 17, 'CLK2': 17, 'CLK3': 17, 'CLK4': 17,
           'COT': 17, 'CRIK': 17, 'CDK12': 17, 'DAPK1': 17, 'DAPK2': 17,
           'DAPK3': 17, 'DCAMKL1': 17, 'DCAMKL2': 17, 'DLK': 17, 'DMPK1':
           17, 'DNAPK': 17, 'DRAK1': 17, 'DYRK1A': 17, 'DYRK1B': 17,
           'DYRK2': 17, 'DYRK3': 17, 'DYRK4': 17, 'ERK1': 17, 'ERK2': 17,
           'ERK5': 17, 'ERK7': 17, 'MTOR': 17, 'GAK': 17, 'GCK': 17,
           'GCN2': 17, 'GRK4': 17, 'GRK5': 17, 'GRK6': 17, 'GRK7': 17,
           'GSK3A': 17, 'GSK3B': 17, 'HASPIN': 17, 'HGK': 17, 'HIPK1': 17,
           'HIPK2': 17, 'HIPK3': 17, 'HIPK4': 17, 'HPK1': 17, 'HRI': 17,
           'HUNK': 17, 'ICK': 17, 'IKKA': 17, 'IKKB': 17, 'IKKE': 17,
           'IRAK1': 17, 'IRAK4': 17, 'IRE1': 17, 'IRE2': 17, 'JNK1': 17,
           'JNK2': 17, 'JNK3': 17, 'KHS1': 17, 'KHS2': 17, 'KIS': 17,
           'LATS1': 17, 'LATS2': 17, 'LKB1': 17, 'LOK': 17, 'LRRK2': 17,
           'MAK': 17, 'MEK1': 17, 'MEK2': 17, 'MEK5': 17, 'MEKK1': 17,
           'YSK4': 17, 'MEKK2': 17, 'MEKK3': 17, 'ASK1': 17, 'MEKK6': 17,
           'MAP3K15': 17, 'MAPKAPK2': 17, 'MAPKAPK3': 17, 'MAPKAPK5': 17,
           'MARK1': 17, 'MARK2': 17, 'MARK3': 17, 'MARK4': 17, 'MASTL':
           17, 'MELK': 17, 'MINK': 17, 'MLK1': 17, 'MLK2': 17, 'MLK3': 17,
           'MLK4': 17, 'MNK1': 17, 'MNK2': 17, 'MOK': 17, 'MOS': 17,
           'MPSK1': 17, 'MRCKA': 17, 'MRCKB': 17, 'MSK1': 17, 'MSK2': 17,
           'SRPK3': 17, 'MST1': 17, 'MST2': 17, 'MST3': 17, 'MST4': 17,
           'MYO3A': 17, 'MYO3B': 17, 'NDR1': 17, 'NDR2': 17, 'NEK1': 17,
           'NEK11': 17, 'NEK2': 17, 'NEK3': 17, 'NEK4': 17, 'NEK5': 17,
           'NEK6': 17, 'NEK7': 17, 'NEK8': 17, 'NEK9': 17, 'NIK': 17,
           'NIM1': 17, 'NLK': 17, 'NUAK1': 17, 'NUAK2': 17, 'OSR1': 17,
           'P38A': 17, 'P38B': 17, 'P38D': 17, 'P38G': 17, 'P70S6K': 17,
           'P70S6KB': 17, 'PAK1': 17, 'PAK2': 17, 'PAK3': 17, 'PAK4': 17,
           'PAK5': 17, 'PAK6': 17, 'PASK': 17, 'PBK': 17, 'CDK16': 17,
           'CDK17': 17, 'CDK18': 17, 'PDHK1': 16, 'PDHK4': 16, 'PDK1': 17,
           'PERK': 17, 'CDK14': 17, 'PHKG1': 17, 'PHKG2': 17, 'PIM1': 17,
           'PIM2': 17, 'PIM3': 17, 'PINK1': 17, 'PKACA': 17, 'PKACB': 17,
           'PKACG': 17, 'PKCA': 17, 'PKCB': 17, 'PKCD': 17, 'PKCE': 17,
           'PKCG': 17, 'PKCH': 17, 'PKCI': 17, 'PKCT': 17, 'PKCZ': 17,
           'PRKD1': 17, 'PRKD2': 17, 'PRKD3': 17, 'PKG1': 17, 'PKG2': 17,
           'PKN1': 17, 'PKN2': 17, 'PKN3': 17, 'PKR': 17, 'PLK1': 17,
           'PLK2': 17, 'PLK3': 17, 'PLK4': 17, 'PRKX': 17, 'PRP4': 17,
           'PRPK': 17, 'QIK': 17, 'QSK': 17, 'RAF1': 17, 'GRK1': 17,
           'RIPK1': 17, 'RIPK2': 17, 'RIPK3': 17, 'ROCK1': 17, 'ROCK2':
           17, 'P90RSK': 17, 'RSK2': 17, 'RSK3': 17, 'RSK4': 17, 'SBK':
           17, 'MYLK4': 17, 'SGK1': 17, 'SGK3': 17, 'DSTYK': 17, 'SIK':
           17, 'SKMLCK': 17, 'SLK': 17, 'SMG1': 17, 'SMMLCK': 17, 'SNRK':
           17, 'SRPK1': 17, 'SRPK2': 17, 'SSTK': 17, 'STK33': 17, 'STLK3':
           17, 'TAK1': 17, 'TAO1': 17, 'TAO2': 17, 'TAO3': 17, 'TBK1': 17,
           'TGFBR1': 17, 'TGFBR2': 17, 'TLK1': 17, 'TLK2': 17, 'TNIK': 17,
           'TSSK1': 17, 'TSSK2': 17, 'TTBK1': 17, 'TTBK2': 17, 'TTK': 17,
           'ULK1': 17, 'ULK2': 17, 'VRK1': 17, 'VRK2': 17, 'WNK1': 17,
           'WNK3': 17, 'WNK4': 17, 'YANK2': 17, 'YANK3': 17, 'YSK1': 17,
           'ZAK': 17, 'EEF2K': 17, 'FAM20C': 17})

Multiply values, consider the dynamics of scale factor, which is PSPA random aa number.

multiply(values=[1,2,3,4,5],kinase='PDHK1')

22.906890595608516

Sum

source

sumup

 sumup (values, kinase=None)

Sum up the possibilities of the amino acids at each position in a phosphorylation site sequence

	Type	Default	Details
values			list of values, possibilities of amino acids at certain positions
kinase	NoneType	None

Utils

source

STY2sty

 STY2sty (input_string:str)

Replace all ‘STY’ with ‘sty’ in a sequence

STY2sty('AAkUuPSFSTtH') # convert all capital STY to sty in a string

'AAkUuPsFsttH'

source

get_dict

 get_dict (input_string:str)

Get a dictionary of input string; no need for the star in the middle; make sure it is 15 or 10 length

	Type	Details
input_string	str	phosphorylation site sequence

cols = get_dict("PSVEPPLsQETFSDL")
cols

['-7P',
 '-6S',
 '-5V',
 '-4E',
 '-3P',
 '-2P',
 '-1L',
 '0s',
 '1Q',
 '2E',
 '3T',
 '4F',
 '5S',
 '6D',
 '7L']

Scoring func

source

predict_kinase

 predict_kinase (input_string:str, ref:pandas.core.frame.DataFrame,
                 func:Callable, to_lower:bool=False, to_upper:bool=False,
                 verbose=True)

Predict kinase given a phosphorylation site sequence

	Type	Default	Details
input_string	str		site sequence
ref	DataFrame		reference dataframe for scoring
func	Callable		function to calculate score
to_lower	bool	False	convert capital STY to lower case
to_upper	bool	False	convert all letter to uppercase
verbose	bool	True

ref = Data.get_pspa_st_norm().astype('float32')

predict_kinase("PSVEPPLsQETFSDL",ref,multiply)

considering string: ['-5V', '-4E', '-3P', '-2P', '-1L', '0s', '1Q', '2E', '3T', '4F']

kinase
ATM       5.037
SMG1      4.385
DNAPK     3.818
ATR       3.507
FAM20C    3.170
          ...  
PKN1     -7.275
P70S6K   -7.295
AKT3     -7.375
PKCI     -7.742
NEK3     -8.254
Length: 303, dtype: float64

Params

Here we provide different PSSM settings from either PSPA data or kinase-substrate dataset for kinase prediction:

source

Params

 Params (name=None)

Params()

Available parameter sets:

['PSPA_st', 'PSPA_y', 'PSPA', 'CDDM', 'CDDM_upper']

for p in ['PSPA', 'CDDM','CDDM_upper']:
    print(predict_kinase("PSVEPPLsQETFSDL",**Params(p)).head())

considering string: ['-5V', '-4E', '-3P', '-2P', '-1L', '0s', '1Q', '2E', '3T', '4F', '5S']
kinase
ATM       5.037
SMG1      4.385
DNAPK     3.818
ATR       3.507
FAM20C    3.170
dtype: float64
considering string: ['-7P', '-6S', '-5V', '-4E', '-3P', '-2P', '-1L', '0s', '1Q', '2E', '3T', '4F', '5S', '6D', '7L']
kinase
ATR      3.064
ATM      2.909
DNAPK    2.270
CK2A1    1.873
TSSK1    1.856
dtype: float64
considering string: ['-7P', '-6S', '-5V', '-4E', '-3P', '-2P', '-1L', '0S', '1Q', '2E', '3T', '4F', '5S', '6D', '7L']
kinase
ATR      3.229
ATM      3.038
DNAPK    2.479
CK2A1    2.006
CDK8     1.999
dtype: float64

Score sequences in df

source

cut_seq

 cut_seq (input_string:str, min_position:int, max_position:int)

Extract sequence based on a range relative to its center position

	Type	Details
input_string	str	site sequence
min_position	int	minimum position relative to its center
max_position	int	maximum position relative to its center

cut_seq('AAkUuPSFSTtH',-5,4)

'AkUuPSFSTt'

source

predict_kinase_df

 predict_kinase_df (df, seq_col, ref, func, to_lower=False,
                    to_upper=False)

df = Data.get_psp_human_site()
df_sty = df[df['site_seq'].str[7].isin(list('sty'))]

out_cddm = predict_kinase_df(df_sty.head(500),'site_seq', **Params('CDDM'))

input dataframe has a length 500
Preprocessing
Finish preprocessing
Merging reference
Finish merging
CPU times: user 28 ms, sys: 12 ms, total: 40 ms
Wall time: 39.9 ms

Percentile scoring

source

get_pct

 get_pct (site, ref, func, pct_ref)

Replicate the precentile results from The Kinase Library.

st_pct = Data.get_pspa_st_pct()
y_pct = Data.get_pspa_tyr_pct()

out = get_pct('PSVEPPLyQETFSDL',**Params('PSPA_y'), pct_ref=y_pct)
out.sort_values('percentile',ascending=False)

considering string: ['-5V', '-4E', '-3P', '-2P', '-1L', '0Y', '1Q', '2E', '3T', '4F', '5S']

	log2(score)	percentile
ABL2	3.137	96.568694
BMX	2.816	96.117567
BTK	1.956	95.693780
CSK	2.303	95.174299
MERTK	2.509	93.588517
...	...	...
FLT1	-1.919	25.358852
PINK1_TYR	-1.227	21.927546
MUSK	-3.031	21.298701
TNNI3K_TYR	-3.549	11.004785
PKMYT1_TYR	-1.739	4.798360

93 rows × 2 columns

get_pct('PSVEPPLsQETFSDL',**Params('PSPA_st'), pct_ref=st_pct)

considering string: ['-5V', '-4E', '-3P', '-2P', '-1L', '0S', '1Q', '2E', '3T', '4F']

	log2(score)	percentile
ATM	5.037	99.822351
SMG1	4.385	99.831819
DNAPK	3.818	99.205315
ATR	3.507	99.680344
FAM20C	3.170	95.370556
...	...	...
PKN1	-7.275	14.070436
P70S6K	-7.295	4.089816
AKT3	-7.375	11.432995
PKCI	-7.742	8.129511
NEK3	-8.254	4.637240

303 rows × 2 columns

source

get_pct_df

 get_pct_df (score_df, pct_ref)

Replicate the precentile results from The Kinase Library.

	Details
score_df	output from predict_kinase_df
pct_ref	a reference df for percentile calculation

# substrate score first
# score_df = predict_kinase_df(df_sty,'site_seq', **Params('PSPA_st'))

# get percentile reference
# pct_ref = Data.get_pspa_st_pct()

# pct = get_pct_df(score_df,pct_ref)

Setup

Algorithms

Multiply

multiply_func

multiply

Sum

sumup

Utils

STY2sty

get_dict

Scoring func

predict_kinase

Params

Params

Score sequences in df

cut_seq

predict_kinase_df

Percentile scoring

get_pct

get_pct_df

End