PreAcrs: a machine learning framework for identifying anti-CRISPR proteins

Zhu, Lin; Wang, Xiaoyu; Li, Fuyi; Song, Jiangning

doi:10.1186/s12859-022-04986-3

BMC Bioinformatics

Table 1 Performance comparison of different features and classifiers based on the fivefold cross-validation

From: PreAcrs: a machine learning framework for identifying anti-CRISPR proteins

Feature	Model	PRE	SN	SP	F-score	ACC	MCC
AAC	SVM	0.874 ± 0.077	0.638 ± 0.175	0.886 ± 0.116	0.716 ± 0.096	0.762 ± 0.050	0.562 ± 0.080
	KNN	0.762 ± 0.035	0.808 ± 0.063	0.742 ± 0.071	0.782 ± 0.017	0.775 ± 0.015	0.557 ± 0.032
	RF	0.669 ± 0.041	0.621 ± 0.091	0.689 ± 0.082	0.640 ± 0.054	0.655 ± 0.040	0.314 ± 0.078
	MLP	0.790 ± 0.071	0.704 ± 0.128	0.794 ± 0.116	0.732 ± 0.054	0.749 ± 0.033	0.514 ± 0.059
	LR	0.743 ± 0.051	0.738 ± 0.124	0.733 ± 0.118	0.732 ± 0.055	0.735 ± 0.040	0.483 ± 0.075
	XGB	0.793 ± 0.071	0.718 ± 0.077	0.801 ± 0.094	0.749 ± 0.034	0.760 ± 0.033	0.528 ± 0.072
	Light	0.800 ± 0.069	0.670 ± 0.076	0.820 ± 0.086	0.723 ± 0.023	0.745 ± 0.016	0.503 ± 0.043
	CAT	0.785 ± 0.052	0.745 ± 0.063	0.791 ± 0.069	0.762 ± 0.039	0.768 ± 0.038	0.540 ± 0.077
	Ens_vote	0.826 ± 0.058	0.745 ± 0.085	0.835 ± 0.083	0.779 ± 0.043	0.790 ± 0.036	0.589 ± 0.072
	Sta_LR	0.837 ± 0.048	0.745 ± 0.080	0.849 ± 0.066	0.785 ± 0.038	0.797 ± 0.030	0.603 ± 0.060
	Sta_GBC	0.818 ± 0.064	0.701 ± 0.096	0.837 ± 0.078	0.750 ± 0.058	0.769 ± 0.046	0.550 ± 0.092
PAAC	SVM	0.869 ± 0.054	0.658 ± 0.140	0.900 ± 0.047	0.741 ± 0.103	0.779 ± 0.069	0.580 ± 0.124
	KNN	0.711 ± 0.030	0.934 ± 0.031	0.616 ± 0.063	0.807 ± 0.017	0.775 ± 0.025	0.583 ± 0.046
	RF	0.808 ± 0.058	0.758 ± 0.122	0.811 ± 0.093	0.774 ± 0.068	0.784 ± 0.050	0.578 ± 0.090
	MLP	0.893 ± 0.067	0.614 ± 0.143	0.917 ± 0.061	0.714 ± 0.098	0.766 ± 0.058	0.566 ± 0.094
	LR	0.748 ± 0.032	0.760 ± 0.153	0.735 ± 0.088	0.743 ± 0.069	0.748 ± 0.040	0.509 ± 0.080
	XGB	0.841 ± 0.048	0.748 ± 0.120	0.854 ± 0.053	0.785 ± 0.069	0.801 ± 0.049	0.612 ± 0.091
	Light	0.848 ± 0.048	0.760 ± 0.105	0.859 ± 0.055	0.796 ± 0.059	0.810 ± 0.044	0.628 ± 0.083
	CAT	0.856 ± 0.047	0.801 ± 0.112	0.861 ± 0.055	0.823 ± 0.064	0.831 ± 0.051	0.670 ± 0.097
	Ens_vote	0.871 ± 0.043	0.770 ± 0.122	0.881 ± 0.053	0.810 ± 0.065	0.825 ± 0.046	0.662 ± 0.082
	Sta_LR	0.866 ± 0.046	0.745 ± 0.131	0.881 ± 0.051	0.794 ± 0.076	0.813 ± 0.056	0.640 ± 0.102
	Sta_GBC	0.875 ± 0.035	0.719 ± 0.081	0.896 ± 0.035	0.786 ± 0.050	0.807 ± 0.037	0.627 ± 0.068
PSSM-AC	SVM	0.776 ± 0.389	0.226 ± 0.186	0.990 ± 0.014	0.327 ± 0.240	0.608 ± 0.087	0.298 ± 0.190
	KNN	0.821 ± 0.042	0.828 ± 0.046	0.818 ± 0.048	0.824 ± 0.033	0.823 ± 0.033	0.647 ± 0.068
	RF	0.881 ± 0.058	0.359 ± 0.092	0.954 ± 0.019	0.505 ± 0.102	0.657 ± 0.049	0.387 ± 0.094
	MLP	1.000 ± 0.000	0.231 ± 0.087	1.000 ± 0.000	0.367 ± 0.110	0.615 ± 0.045	0.357 ± 0.076
	LR	0.952 ± 0.035	0.507 ± 0.184	0.971 ± 0.025	0.640 ± 0.157	0.739 ± 0.083	0.543 ± 0.130
	XGB	0.936 ± 0.042	0.352 ± 0.108	0.976 ± 0.020	0.502 ± 0.117	0.664 ± 0.051	0.418 ± 0.088
	Light	1.000 ± 0.000	0.272 ± 0.064	1.000 ± 0.000	0.424 ± 0.083	0.636 ± 0.033	0.395 ± 0.057
	CAT	0.957 ± 0.032	0.424 ± 0.140	0.976 ± 0.026	0.572 ± 0.121	0.700 ± 0.057	0.483 ± 0.080
	Ens_vote	0.988 ± 0.014	0.328 ± 0.090	0.995 ± 0.006	0.485 ± 0.106	0.661 ± 0.043	0.432 ± 0.069
	Sta_LR	0.981 ± 0.016	0.338 ± 0.081	0.993 ± 0.006	0.496 ± 0.097	0.665 ± 0.040	0.436 ± 0.064
	Sta_GBC	0.977 ± 0.023	0.347 ± 0.141	0.990 ± 0.009	0.496 ± 0.147	0.669 ± 0.068	0.438 ± 0.107
RPSSM	SVM	0.914 ± 0.062	0.713 ± 0.229	0.915 ± 0.068	0.767 ± 0.172	0.814 ± 0.090	0.659 ± 0.133
	KNN	0.738 ± 0.020	0.925 ± 0.024	0.670 ± 0.035	0.820 ± 0.014	0.797 ± 0.016	0.616 ± 0.031
	RF	0.922 ± 0.015	0.694 ± 0.102	0.939 ± 0.020	0.787 ± 0.063	0.817 ± 0.042	0.657 ± 0.064
	MLP	0.870 ± 0.034	0.898 ± 0.016	0.864 ± 0.040	0.883 ± 0.017	0.881 ± 0.019	0.763 ± 0.038
	LR	0.815 ± 0.066	0.876 ± 0.069	0.789 ± 0.105	0.840 ± 0.027	0.833 ± 0.033	0.676 ± 0.057
	XGB	0.892 ± 0.017	0.777 ± 0.078	0.905 ± 0.021	0.828 ± 0.045	0.841 ± 0.034	0.690 ± 0.058
	Light	0.907 ± 0.013	0.767 ± 0.092	0.920 ± 0.020	0.828 ± 0.053	0.843 ± 0.039	0.698 ± 0.066
	CAT	0.926 ± 0.014	0.765 ± 0.066	0.939 ± 0.011	0.836 ± 0.042	0.852 ± 0.034	0.716 ± 0.061
	Ens_vote	0.913 ± 0.026	0.849 ± 0.047	0.917 ± 0.032	0.879 ± 0.021	0.883 ± 0.017	0.771 ± 0.032
	Sta_LR	0.921 ± 0.020	0.844 ± 0.052	0.927 ± 0.019	0.880 ± 0.031	0.886 ± 0.026	0.775 ± 0.049
	Sta_GBC	0.892 ± 0.035	0.820 ± 0.025	0.898 ± 0.039	0.854 ± 0.010	0.859 ± 0.012	0.722 ± 0.026
SSA	SVM	0.903 ± 0.038	0.740 ± 0.099	0.915 ± 0.043	0.807 ± 0.054	0.828 ± 0.033	0.671 ± 0.047
	KNN	0.699 ± 0.036	0.937 ± 0.043	0.592 ± 0.070	0.799 ± 0.028	0.765 ± 0.037	0.566 ± 0.071
	RF	0.840 ± 0.016	0.663 ± 0.068	0.874 ± 0.018	0.739 ± 0.043	0.768 ± 0.029	0.550 ± 0.052
	MLP	0.881 ± 0.046	0.772 ± 0.146	0.886 ± 0.070	0.811 ± 0.073	0.829 ± 0.046	0.675 ± 0.075
	LR	0.817 ± 0.036	0.811 ± 0.113	0.813 ± 0.062	0.808 ± 0.053	0.812 ± 0.037	0.633 ± 0.072
	XGB	0.858 ± 0.018	0.731 ± 0.112	0.879 ± 0.028	0.784 ± 0.064	0.805 ± 0.046	0.620 ± 0.083
	Light	0.908 ± 0.038	0.624 ± 0.123	0.934 ± 0.034	0.732 ± 0.083	0.779 ± 0.054	0.591 ± 0.089
	CAT	0.882 ± 0.021	0.745 ± 0.119	0.898 ± 0.033	0.802 ± 0.063	0.822 ± 0.045	0.657 ± 0.080
	Ens_vote	0.887 ± 0.026	0.787 ± 0.119	0.898 ± 0.034	0.828 ± 0.069	0.842 ± 0.051	0.695 ± 0.092
	Sta_LR	0.903 ± 0.033	0.738 ± 0.118	0.917 ± 0.045	0.806 ± 0.069	0.828 ± 0.048	0.672 ± 0.083
	Sta_GBC	0.882 ± 0.080	0.597 ± 0.112	0.915 ± 0.060	0.705 ± 0.083	0.756 ± 0.060	0.545 ± 0.115
RPSSM&PSSM_AC&SSA	SVM	0.974 ± 0.020	0.713 ± 0.155	0.978 ± 0.018	0.811 ± 0.115	0.846 ± 0.071	0.722 ± 0.110
	KNN	0.826 ± 0.015	0.917 ± 0.033	0.806 ± 0.022	0.869 ± 0.017	0.862 ± 0.015	0.729 ± 0.033
	RF	0.966 ± 0.014	0.665 ± 0.093	0.976 ± 0.013	0.784 ± 0.062	0.820 ± 0.042	0.676 ± 0.066
	MLP	0.969 ± 0.021	0.740 ± 0.110	0.973 ± 0.019	0.833 ± 0.067	0.857 ± 0.046	0.738 ± 0.069
	LR	0.927 ± 0.029	0.796 ± 0.078	0.934 ± 0.031	0.853 ± 0.041	0.865 ± 0.028	0.741 ± 0.045
	XGB	0.961 ± 0.013	0.699 ± 0.084	0.971 ± 0.012	0.806 ± 0.051	0.835 ± 0.037	0.698 ± 0.060
	Light	0.972 ± 0.008	0.595 ± 0.091	0.983 ± 0.006	0.734 ± 0.066	0.789 ± 0.044	0.628 ± 0.070
	CAT	0.965 ± 0.009	0.730 ± 0.106	0.973 ± 0.009	0.827 ± 0.070	0.852 ± 0.049	0.728 ± 0.082
	Ens_vote	0.970 ± 0.002	0.774 ± 0.045	0.976 ± 0.000	0.860 ± 0.028	0.875 ± 0.022	0.766 ± 0.039
	Sta_LR	0.978 ± 0.015	0.750 ± 0.047	0.983 ± 0.012	0.848 ± 0.031	0.866 ± 0.025	0.754 ± 0.043
	Sta_GBC	0.982 ± 0.012	0.662 ± 0.058	0.988 ± 0.008	0.790 ± 0.044	0.825 ± 0.030	0.688 ± 0.051

The bold values indicate the best performance

Back to article page

ISSN: 1471-2105

Contact us

General enquiries: journalsubmissions@springernature.com