Table 2. Predictive performance of mlLGPR on T1 golden datasets.

mlLGPR-L1: the mlLGPR with L1 regularizer, mlLGPR-L2: the mlLGPR with L2 regularizer, mlLGPR-EN: the mlLGPR with elastic net penalty, L2: AB: abundance features, RE: reaction evidence features, and PE: pathway evidence features. For each performance metric, ‘↓’ indicates the lower score is better while ‘↑’ indicates the higher score is better.

Methods	Hamming Loss ↓
	EcoCyc	HumanCyc	AraCyc	YeastCyc	LeishCyc	TrypanoCyc	SixDB
mlLGPR-L1 (+AB+RE+PE)	0.0776	0.0645	0.1069	0.0487	0.0412	0.0602	0.1365
mlLGPR-L2 (+AB+RE+PE)	0.0606	0.0515	0.1112	0.0412	0.0234	0.0344	0.1426
mlLGPR-EN (+AB+RE+PE)	0.0804	0.0633	0.1069	0.0550	0.0380	0.0590	0.1281
Methods	Average Precision Score ↑
	EcoCyc	HumanCyc	AraCyc	YeastCyc	LeishCyc	TrypanoCyc	SixDB
mlLGPR-L1 (+AB+RE+PE)	0.6253	0.6686	0.7390	0.6815	0.4525	0.5395	0.7391
mlLGPR-L2 (+AB+RE+PE)	0.7437	0.7945	0.8418	0.7934	0.6186	0.7268	0.8488
mlLGPR-EN (+AB+RE+PE)	0.6187	0.6686	0.7372	0.6480	0.4731	0.5455	0.7561
Methods	Average Recall Score ↑
	EcoCyc	HumanCyc	AraCyc	YeastCyc	LeishCyc	TrypanoCyc	SixDB
mlLGPR-L1 (+AB+RE+PE)	0.9023	0.8244	0.7275	0.8690	0.9310	0.8971	0.6738
mlLGPR-L2 (+AB+RE+PE)	0.7655	0.7204	0.5529	0.7380	0.8391	0.8057	0.5211
mlLGPR-EN (+AB+RE+PE)	0.8827	0.8459	0.7314	0.8603	0.9080	0.8914	0.6904
Methods	Average F1 Score ↑
	EcoCyc	HumanCyc	AraCyc	YeastCyc	LeishCyc	TrypanoCyc	SixDB
mlLGPR-L1 (+AB+RE+PE)	0.7387	0.7384	0.7332	0.7639	0.6090	0.6738	0.6919
mlLGPR-L2 (+AB+RE+PE)	0.7544	0.7556	0.6675	0.7647	0.7122	0.7642	0.6306
mlLGPR-EN (+AB+RE+PE)	0.7275	0.7468	0.7343	0.7392	0.6220	0.6768	0.7098