The widening gap between known proteins and their functions has encouraged the development of methods to automatically infer annotations. Automatic functional annotation of proteins is expected to meet the conflicting requirements of maximizing annotation coverage, while minimizing erroneous functional assignments. This trade-off imposes a great challenge in designing intelligent systems to tackle the problem of automatic protein annotation. In this work, we present a system that utilizes rule mining techniques to predict metabolic pathways in prokaryotes. The resulting knowledge represents predictive models that assign pathway involvement to UniProtKB entries. We carried out an evaluation study of our system performance using cross-validation technique. We found that it achieved very promising results in pathway identification with an F1-measure of 0.982 and an AUC of 0.987. Our prediction models were then successfully applied to 6.2 million UniProtKB/TrEMBL reference proteome entries of prokaryotes. As a result, 663,724 entries were covered, where 436,510 of them lacked any previous pathway annotations.