@article{CaliskanCaliskanRasbachetal.2023,
  author    = {Caliskan, Aylin and Caliskan, Deniz and Rasbach, Lauritz and Yu, Weimeng and Dandekar, Thomas and Breitenbach, Tim},
  title     = {Optimized cell type signatures revealed from single-cell data by combining principal feature analysis, mutual information, and machine learning},
  series = {Computational and Structural Biotechnology Journal},
  volume    = {21},
  journal   = {Computational and Structural Biotechnology Journal},
  issn      = {2001-0370},
  doi       = {10.1016/j.csbj.2023.06.002},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349989},
  pages     = {3293-3314},
  year      = {2023},
  abstract  = {Machine learning techniques are excellent to analyze expression data from single cells. These techniques impact all fields ranging from cell annotation and clustering to signature identification. The presented framework evaluates gene selection sets how far they optimally separate defined phenotypes or cell groups. This innovation overcomes the present limitation to objectively and correctly identify a small gene set of high information content regarding separating phenotypes for which corresponding code scripts are provided. The small but meaningful subset of the original genes (or feature space) facilitates human interpretability of the differences of the phenotypes including those found by machine learning results and may even turn correlations between genes and phenotypes into a causal explanation. For the feature selection task, the principal feature analysis is utilized which reduces redundant information while selecting genes that carry the information for separating the phenotypes. In this context, the presented framework shows explainability of unsupervised learning as it reveals cell-type specific signatures. Apart from a Seurat preprocessing tool and the PFA script, the pipeline uses mutual information to balance accuracy and size of the gene set if desired. A validation part to evaluate the gene selection for their information content regarding the separation of the phenotypes is provided as well, binary and multiclass classification of 3 or 4 groups are studied. Results from different single-cell data are presented. In each, only about ten out of more than 30000 genes are identified as carrying the relevant information. The code is provided in a GitHub repository at https://github.com/AC-PHD/Seurat_PFA_pipeline.},
  language  = {en}
}
@article{CaliskanDangwalDandekar2023,
  author    = {Caliskan, Aylin and Dangwal, Seema and Dandekar, Thomas},
  title     = {Metadata integrity in bioinformatics: bridging the gap between data and knowledge},
  series = {Computational and Structural Biotechnology Journal},
  volume    = {21},
  journal   = {Computational and Structural Biotechnology Journal},
  issn      = {2001-0370},
  doi       = {10.1016/j.csbj.2023.10.006},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-349990},
  pages     = {4895-4913},
  year      = {2023},
  abstract  = {In the fast-evolving landscape of biomedical research, the emergence of big data has presented researchers with extraordinary opportunities to explore biological complexities. In biomedical research, big data imply also a big responsibility. This is not only due to genomics data being sensitive information but also due to genomics data being shared and re-analysed among the scientific community. This saves valuable resources and can even help to find new insights in silico. To fully use these opportunities, detailed and correct metadata are imperative. This includes not only the availability of metadata but also their correctness. Metadata integrity serves as a fundamental determinant of research credibility, supporting the reliability and reproducibility of data-driven findings. Ensuring metadata availability, curation, and accuracy are therefore essential for bioinformatic research. Not only must metadata be readily available, but they must also be meticulously curated and ideally error-free. Motivated by an accidental discovery of a critical metadata error in patient data published in two high-impact journals, we aim to raise awareness for the need of correct, complete, and curated metadata. We describe how the metadata error was found, addressed, and present examples for metadata-related challenges in omics research, along with supporting measures, including tools for checking metadata and software to facilitate various steps from data analysis to published research. Highlights • Data awareness and data integrity underpins the trustworthiness of results and subsequent further analysis. • Big data and bioinformatics enable efficient resource use by repurposing publicly available RNA-Sequencing data. • Manual checks of data quality and integrity are insufficient due to the overwhelming volume and rapidly growing data. • Automation and artificial intelligence provide cost-effective and efficient solutions for data integrity and quality checks. • FAIR data management, various software solutions and analysis tools assist metadata maintenance.},
  language  = {en}
}