Table 4. Performance and robustness scores for mlLGPR-EN with AB, RE and PE feature sets trained on both Synset-1 and Synset-2 training sets at 0 and ρ noise.

The best performance scores are highlighted in bold. The ‘↓’ indicates the lower score is better while ‘↑’ indicates the higher score is better.

Dataset	Average F1 Score ↑		Robustness Score ↓
	mlLGPR-EN0	mlLGPR-ENρ	RLAρ	s(M0)	ELAρ
EcoCyc	0.7280	0.7275	0.0007	0.3736	0.3743
HumanCyc	0.7111	0.7468	−0.0502	0.4063	0.3561
AraCyc	0.7662	0.7343	0.0416	0.3051	0.3468
YeastCyc	0.7176	0.7392	−0.0301	0.3935	0.3634
LeishCyc	0.5559	0.6220	−0.1189	0.7989	0.6800
TrypanoCyc	0.6667	0.6768	−0.0151	0.4999	0.4848
SixDB	0.7448	0.7098	0.0470	0.3426	0.3896