Skip to main content

Table 4 Evaluation of all the methods by cross validation on New York dataset at genus level

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

Evaluation metric
Methods Precision Recall F1 score Ranking loss
IDW 0.5669 0.6686 0.6129 0.1790
kNN 0.7203 0.5109 0.5977 0.1273
SVM 0.7510 0.4787 0.5845 0.0725
Random Forest (RF) 0.7288 0.5026 0.5941 0.1365
Neural Network 0.7419 0.5110 0.6050 0.0718
MetaMLAnn 0.7456 0.5325 0.6212 0.0682
MetaMLAnn+ IDW 0.6578 0.6170 0.6363 0.0688
  1. Higher precision, recall, F1 score, and lower ranking loss indicate better performance. Bold entries indicate best performance among different methods