Cuproptosis-related gene CDKN2A as a molecular target for IPF diagnosis and therapeutics.

BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a progressive chronic interstitial lung disease with limited therapeutic options. Cuproptosis is a recently proposed novel form of programmed cell death, which has been strongly implicated in the development of various human diseases. However, the prognostic and therapeutic value of cuproptosis-related genes (CRGs) in IPF remains to be elucidated. METHODS: In the present study, weighted gene co-expression network analysis (WGCNA) was employed to identify the key CRGs associated with the development of IPF. The subsequent GSEA, immune cell correlation analysis, and single-cell RNA-Seq analysis were conducted to explore the potential role of the identified CRGs in IPF. In addition, ROC curves and survival analysis were used to assess the prognostic value of the key CRGs in IPF. Moreover, we explored the molecular mechanisms of participation of identified key CRGs in the development of pulmonary fibrogenesis through in vivo and in vitro experiments. RESULTS: The expression level of cyclin-dependent kinase inhibitor 2A (CDKN2A) is upregulated in the lung tissues of IPF patients and associated with disease severity. Notably, CDKN2A was constitutively expressed by fibrosis-promoting M2 macrophages. Decreased CDKN2A expression sensitizes M2 macrophages to elesclomol-induced cuproptosis in vitro. Inhibition of CDKN2A decreases the number of viable macrophages and attenuates bleomycin-induced pulmonary fibrosis in mice. CONCLUSION: These findings indicate that CDKN2A mediates the resistance of fibrosis-promoting M2 macrophages to cuproptosis and promotes pulmonary fibrosis in mice. Our work provides fresh insights into CRGs in IPF with potential value for research in the pathogenesis, diagnosis, and a new therapy strategy for IPF.

Testing and Validating Machine Learning Classifiers by Metamorphic Testing.

Machine Learning algorithms have provided core functionality to many application domains - such as bioinformatics, computational linguistics, etc. However, it is difficult to detect faults in such applications because often there is no "test oracle" to verify the correctness of the computed outputs. To help address the software quality, in this paper we present a technique for testing the implementations of machine learning classification algorithms which support such applications. Our approach is based on the technique "metamorphic testing", which has been shown to be effective to alleviate the oracle problem. Also presented include a case study on a real-world machine learning application framework, and a discussion of how programmers implementing machine learning algorithms can avoid the common pitfalls discovered in our study. We also conduct mutation analysis and cross-validation, which reveal that our method has high effectiveness in killing mutants, and that observing expected cross-validation result alone is not sufficiently effective to detect faults in a supervised classification program. The effectiveness of metamorphic testing is further confirmed by the detection of real faults in a popular open-source classification program.

Application of Metamorphic Testing to Supervised Classifiers.

Many applications in the field of scientific computing - such as computational biology, computational linguistics, and others - depend on Machine Learning algorithms to provide important core functionality to support solutions in the particular problem domains. However, it is difficult to test such applications because often there is no "test oracle" to indicate what the correct output should be for arbitrary input. To help address the quality of such software, in this paper we present a technique for testing the implementations of supervised machine learning classification algorithms on which such scientific computing software depends. Our technique is based on an approach called "metamorphic testing", which has been shown to be effective in such cases. More importantly, we demonstrate that our technique not only serves the purpose of verification, but also can be applied in validation. In addition to presenting our technique, we describe a case study we performed on a real-world machine learning application framework, and discuss how programmers implementing machine learning algorithms can avoid the common pitfalls discovered in our study. We also discuss how our findings can be of use to other areas outside scientific computing, as well.