Transcriptional regulation is a fundamental process in biological systems, where transcription factors (TFs) play crucial roles. Except for TFs, an increasing number of small non-coding RNAs (ncRNAs) have been shown to mediate post-transcriptional processes in both prokaryotes and eukaryotes. In this work, we propose a novel approach to infer the activities of regulators including TFs and ncRNAs by exploring target gene expression profiles and (post) transcriptional regulatory relationships. The inference process is efficiently achieved by an iteration algorithm, in which two linear programming models are iteratively solved. In contrast to the existing works, for the first time, the effects of ncRNAs on transcription process are considered and thus more reasonable inference can be expected. Experiments on a model system of E. coli carbon source transition from glucose to acetate illustrate the effectiveness of our method.