KNN

import pandas as pd

df = pd.read_excel('out/uniprot_kd_active_D1_D2.xlsx')

pspa=pd.read_csv('out/pspa_uniprot_unique_no_TYR_category_remove2kd.csv')

pspa

	uniprot	kd_ID	kinase	group	pspa_category	pspa_category_detail	-5P	-5G	-5A	-5C	...	4E	4s	4t	4y	0s	0t	0y	0S	0T	0Y
0	Q2M2I8	Q2M2I8_AAK1_HUMAN_KD1	AAK1	Other	NAK	NAK	0.0720	0.0245	0.0284	0.0456	...	0.0457	0.0251	0.0251	0.0270	0.1013	1.0000	0.0	0.1013	1.0000	0.0
1	P27037	P27037_AVR2A_HUMAN_KD1	ACVR2A	TKL	acidophilic	TGFBR	0.0415	0.0481	0.0584	0.0489	...	0.0640	0.0703	0.0703	0.0589	0.9833	1.0000	0.0	0.9833	1.0000	0.0
2	Q13705	Q13705_AVR2B_HUMAN_KD1	ACVR2B	TKL	acidophilic	TGFBR	0.0533	0.0517	0.0566	0.0772	...	0.0697	0.0761	0.0761	0.0637	0.9593	1.0000	0.0	0.9593	1.0000	0.0
3	P31749	P31749_AKT1_HUMAN_KD1	AKT1	AGC	basophilic	AKT/ROCK	0.0603	0.0594	0.0552	0.0605	...	0.0312	0.0393	0.0393	0.0263	1.0000	0.6440	0.0	1.0000	0.6440	0.0
4	P31751	P31751_AKT2_HUMAN_KD1	AKT2	AGC	basophilic	AKT/ROCK	0.0602	0.0617	0.0643	0.0582	...	0.0350	0.0548	0.0548	0.0417	1.0000	0.6077	0.0	1.0000	0.6077	0.0
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
357	P17948	P17948_VGFR1_HUMAN_KD1	FLT1	TK	FGF and VEGF receptors	FGF and VEGF receptors	0.0642	0.0688	0.0597	0.0618	...	0.0510	0.0677	0.0677	0.0380	0.0000	0.0000	1.0	0.0000	0.0000	1.0
358	P35968	P35968_VGFR2_HUMAN_KD1	KDR	TK	FGF and VEGF receptors	FGF and VEGF receptors	0.0634	0.0672	0.0556	0.0517	...	0.0338	0.0300	0.0300	0.0292	0.0000	0.0000	1.0	0.0000	0.0000	1.0
359	P35916	P35916_VGFR3_HUMAN_KD1	FLT4	TK	FGF and VEGF receptors	FGF and VEGF receptors	0.0457	0.0531	0.0488	0.0553	...	0.0497	0.0445	0.0445	0.0500	0.0000	0.0000	1.0	0.0000	0.0000	1.0
360	P07947	P07947_YES_HUMAN_KD1	YES1	TK	SRC	SRC	0.0677	0.0571	0.0537	0.0530	...	0.0492	0.0371	0.0371	0.0467	0.0000	0.0000	1.0	0.0000	0.0000	1.0
361	P43403	P43403_ZAP70_HUMAN_KD1	ZAP70	TK	SYK and FAK	SYK and FAK	0.0602	0.0880	0.0623	0.0496	...	0.0558	0.0440	0.0440	0.0318	0.0000	0.0000	1.0	0.0000	0.0000	1.0

362 rows × 219 columns