SARS-CoV-2-induced phosphorylation and its pharmacotherapy backed by artificial intelligence and machine learning

Figures & data

Table 1. Predictions by all supervised-based methods.

Variant ID	Mutations	SNAP2 score	SNAP2	Mutpred-2 score	Mutpred-2	SNPs&GO score	SNPs&GO	PhD SNP	SIFT score	SIFT	PROVEAN score	PROVEAN
QNV71204.1	N74K	-58	N	0.42	N	0.684	D	N	0.71	N	-1.309	N
QQG33753.1	R102S	-18	N	0.707	D	0.538	D	N	0.34	N	-0.160	N
QQG33753.1	A222V	-90	N	0.196	N	0.075	N	N	1.00	N	-0.096	N
QQL13968.1	D614G	-52	N	0.460	N	0.245	N	N	0.62	N	0.598	N
QQD86527.1	V622F	-11	N	0.415	N	0.282	N	N	0.10	N	-0.593	N
QQL14099.1	Q677H	-53	N	0.406	N	0.054	N	N	0.12	N	0.002	N
QQL14015.1	D1153G	22	D	0.471	N	0.204	N	N	0.02	D	-2.483	N
QQL14122.1	P1162S	-52	N	0.487	N	0.413	N	N	0.65	N	-2.722	D

Table 2. Binding affinities (kcal/mol) of five model drugs against wild and mutated nucleocapsid protein of SARS-COV-2.

Mutation	Berberine	Disogen	Curcumin	Apigenin	Emodin
Normal	-8.19	-8.218	-7.674	-7.184	-7.529
R209I	-8.191	-8.22	-7.789	-7.531	-7.531
S194L	-8.191	-8.215	-7.927	-7.343	-7.876
S188P	-8.192	-8.22	-7.587	-7.538	-7.518
R195I	-8.19	-8.214	-7.584	-7.393	-7.539
S202N	-8.191	-8.215	-7.594	-7.537	-7.537
T205I	-8.191	-8.215	-7.703	-7.217	-7.524
S327L	-8.19	-8.216	-7.571	-7.152	-7.528
T379I	-8.192	-8.213	-7.594	-7.172	-7.537
S413I	-8.192	-8.213	-7.567	-7.328	-7.533
R14H	-8.191	-8.216	-7.572	-7.233	-7.538
P13L	-8.21	-8.132	-7.684	-7.342	-7.54
Q289H	-8.143	-8.243	-7.688	-7.986	-7.808
R203K	-8.176	-8.312	-7.599	-7.845	-7.519
G204R	-8.178	-8.218	-7.192	-7.134	-7.891
D348Y	-8.156	-8.21	-7.905	-7.685	-7.543
K374T	-8.176	-8.206	-7.13	-7.523	-7.578
D377Y	-8.139	-8.214	-7.562	-7.034	-7.599
D402Y	-8.172	-8.208	-7.192	-7.976	-7.521
D03Y	-8.141	-8.217	-7.987	-7.623	-7.532

Table 3. Mutations in the nucleocapsid protein in Pakistan.

Accession no.	Mutation	MU^pro	PROVEAN	POLYPHEN-2
QQL14284.1	R209I	-0.3569479	-2.455	0.998
QQL14165.1	S194L	-0.67079386	-4.272	0.994
QQH16682.1	G204R	-0.68136619	-1.656	1.000
QQH15938.1	R203K	-1.0587625	-1.604	0.969
QQH17450.1	S188P	-1.2061166	-2.918	0.994
QQH16058.1	R1951	-0.6286178	-3.993	0.101
QQ16646.1	S202N	-0.67746599	-0.404	0.994
QPB18048.1	T2051	-0.24030545	-1.562	0.000
QQH16970.1	Q289H	-0.39194072	-1.270	0.994
QQH17450.1	S327L	0.55558303	-3.022	0.000
QQL14308.1	T379I	-0.3859215	-0.648	0.000
QQH15866.1	D348Y	-0.99177863	-0.588	1.000
QQH16526.1	K374T	-1.1104731	-0.819	0.997
QQH17294.1	D377Y	-0.42988461	-1.779	1.000
QQH16634.1	S413I	-0.29679539	0.311	0.998
QQL14047.1	D402Y	-0.59573415	-1.449	1.000
QQH16058.1	R14H	-0.81985283	-0.609	0.998
QQH16034.1	P13L	-0.79830902	-1.230	1.000
QQH16778.1	D03Y	-0.63221612	-0.103	1.000

Figure 1. Therapeutic targets identified through interaction networks, artificial intelligence and machine learning.