Skip to main content

Table 6 Performance of random forest using different feature set at genus level

From: Prediction of microbial communities for urban metagenomics using neural network approach

Evaluation metric
Features Precision Recall F1 score Ranking loss
Fs+Fm+Fc 0.7288 0.5026 0.5941 0.1365
Fs+Fc 0.7285 0.4654 0.5679 0.1422
Fs+Fm 0.6751 0.5283 0.5927 0.1649
Fc+Fm 0.6930 0.5113 0.5861 0.1440
F c 0.7063 0.4611 0.5576 0.1376
F s 0.6498 0.5227 0.5791 0.1855
F m 0.6328 0.5258 0.5725 0.2552
  1. Higher precision, recall, F1 score, and lower ranking loss indicate better performance. Bold entries indicate best performance among different methods