DeepPeptide predicts cleaved peptides in proteins using conditional random fields.

MOTIVATION: Peptides are ubiquitous throughout life and involved in a wide range of biological processes, ranging from neural signaling in higher organisms to antimicrobial peptides in bacteria. Many peptides are generated post-translationally by cleavage of precursor proteins and can thus not be detected directly from genomics data, as the specificities of the responsible proteases are often not completely understood. RESULTS: We present DeepPeptide, a deep learning model that predicts cleaved peptides directly from the amino acid sequence. DeepPeptide shows both improved precision and recall for peptide detection compared to previous methodology. We show that the model is capable of identifying peptides in underannotated proteomes. AVAILABILITY AND IMPLEMENTATION: DeepPeptide is available online at ku.biolib.com/DeepPeptide.

Impact of microRNA-130a on the neutrophil proteome.

BACKGROUND: MicroRNAs (miRNAs) are important for the development and function of neutrophils. miR-130a is highly expressed during early neutrophil development and regulates target proteins important for this process. miRNA targets are often identified by validating putative targets found by in silico prediction algorithms one at a time. However, one miRNA can have many different targets, which may vary depending on the context. Here, we investigated the effect of miR-130a on the proteome of a murine and a human myeloid cell line. RESULTS: Using pulsed stable isotope labelling of amino acids in cell culture and mass spectrometry for protein identification and quantitation, we found 44 and 34 proteins that were significantly regulated following inhibition of miR-130a in a miR-130a-overexpressing 32Dcl3 clone and Kasumi-1 cells, respectively. The level of miR-130a inhibition correlated with the impact on protein levels. We used RAIN, a novel database for miRNA-protein and protein-protein interactions, to identify putative miR-130a targets. In the 32Dcl3 clone, putative targets were more up-regulated than the remaining quantified proteins following miR-130a inhibition, and three significantly derepressed proteins (NFYC, ISOC1, and CAT) are putative miR-130a targets with good RAIN scores. We also created a network including inferred, putative neutrophil miR-130a targets and identified the transcription factors Myb and CBF-ß as putative miR-130a targets, which may regulate the primary granule proteins MPO and PRTN3 and other proteins differentially expressed following miR-130a inhibition in the 32Dcl3 clone. CONCLUSION: We have experimentally identified miR-130a-regulated proteins within the neutrophil proteome. Linking these to putative miR-130a targets, we provide an association network of potential direct and indirect miR-130a targets that expands our knowledge on the role of miR-130a in neutrophil development and is a valuable platform for further experimental studies.