Background: Peripheral artery disease (PAD) is a significant burden, particularly among patients with severe disease requiring invasive treatment. We applied a general Machine Learning (ML) workflow and investigated if a multi-dimensional marker set of standard clinical parameters can identify patients in need of vascular intervention without specialized intra–hospital diagnostics. Methods: This is a retrospective study involving patients with stable PAD (sPAD, Fontaine Class I and II, n = 38) and unstable PAD (unPAD, Fontaine Class III and IV, n = 18) in need of invasive therapeutic measures. ML algorithms such as Random Forest were utilized to evaluate a matrix consisting of multiple routinely clinically available parameters (age, complete blood count, inflammation, lipid, iron metabolism). Results: ML has enabled a generation of an Artificial Intelligence (AI) PAD score (AI-PAD) that successfully divided sPAD from unPAD patients (high AI-PAD in sPAD, low AI-PAD in unPAD, cutoff at 50 AI-PAD units). Furthermore, the probability score positively coincided with gold-standard intra-hospital mean ankle-brachial index (ABI). Conclusion: AI-based tools may be promising to enable the correct identification of patients with unstable PAD by using existing clinical information, thus supplementing clinical decision making. Additional studies in larger prospective cohorts are necessary to determine the usefulness of this approach in comparison to standard diagnostic measures.

Background: Deficient autophagy has been recently implicated as a driver of pulmonary fibrosis, yet bioinformatics approaches to study this cellular process are lacking. Autophagy-related 5 and 7 (ATG5/ATG7) are critical elements of macro-autophagy. However, an alternative ATG5/ATG7-independent macro-autophagy pathway was recently discovered, its regulation being unknown. Using a bioinformatics proteome profiling analysis of ATG7-deficient human fibroblasts, we aimed to identify key microRNA (miR) regulators in autophagy. Method: We have generated ATG7-knockout MRC-5 fibroblasts and performed mass spectrometry to generate a large-scale proteomics dataset. We further quantified the interactions between various proteins combining bioinformatics molecular network reconstruction and functional enrichment analysis. The predicted key regulatory miRs were validated via quantitative polymerase chain reaction. Results: The functional enrichment analysis of the 26 deregulated proteins showed decreased cellular trafficking, increased mitophagy and senescence as the major overarching processes in ATG7-deficient lung fibroblasts. The 26 proteins reconstitute a protein interactome of 46 nodes and miR-regulated interactome of 834 nodes. The miR network shows three functional cluster modules around miR-16-5p, miR-17-5p and let-7a-5p related to multiple deregulated proteins. Confirming these results in a biological setting, serially passaged wild-type and autophagy-deficient fibroblasts displayed senescence-dependent expression profiles of miR-16-5p and miR-17-5p. Conclusions: We have developed a bioinformatics proteome profiling approach that successfully identifies biologically relevant miR regulators from a proteomics dataset of the ATG-7-deficient milieu in lung fibroblasts, and thus may be used to elucidate key molecular players in complex fibrotic pathological processes. The approach is not limited to a specific cell-type and disease, thus highlighting its high relevance in proteome and non-coding RNA research.