Reclassification of massive datasets acquired through different approaches, such as web scraping, is a big challenge to demonstrate the effectiveness of a machine learning model. Notably, there is a strong influence of the quality of the dataset used for training those models. Thus, we propose a threshold algorithm as an efficient method to remove stopwords. This method employs an unsupervised classification technique, such as K-means, to accurately categorize user reviews from the IMDb dataset into their most suitable categories, generating a well-balanced dataset. Analysis of the performance of the algorithm revealed a notable influence of the text vectorization method used concerning the generation of clusters when assessing various preprocessing approaches. Moreover, the algorithm demonstrated that the word embedding technique and the removal of stopwords to retrieve the clustered text significantly impacted the categorization. The proposed method involves confirming the presence of a suggested stopword within each review across various genres. Upon satisfying this condition, the method assesses if the word’s frequency exceeds a predefined threshold. The threshold algorithm yielded a mapping genre success above 80% compared to precompiled lists and a Zipf’s law-based method. In addition, we employed the mini-batch K-means method for the clustering formation of each differently preprocessed dataset. This approach enabled us to reclassify reviews more coherently. Summing up, our methodology categorizes sparsely labeled data into meaningful clusters, in particular, by using a combination of the proposed stopword removal method and TF-IDF. The reclassified and balanced datasets showed a significant improvement, achieving 94% accuracy compared to the original dataset.
The process by which blood cells are generated has been widely studied in homeostasis and during pathogen-triggered inflammatory response. Recently, murine lungs have been shown to be a significant source of hematopoietic progenitors in a process known as extramedullary hematopoiesis. Using multiparametric flow cytometry, we have identified mesenchymal, endothelial, and hematopoietic progenitor cells that express the secreted small protein Isthmin 1 (ISM1). Further characterization of hematopoietic progenitor cells indicated that ISM1+ Lineage- Sca-1+ c-kit+ (ISM1+ LSK) cells are enriched in short-term hematopoietic stem cells (ST-HSCs). Moreover, most Sca-1+ ISM1+ cells express the residence marker CD49a, and this correlated with their localization in the extravascular region of the lung, indicating that ISM1+ cells are lung-resident cells. We also observed that ISM1+ cells express TLR4, TLR5, and TLR9, and, in a mouse model of sepsis induced by P. aeruginosa, we observed that all the LSK and ISM1+LSK cells were affected. We conclude that ISM1 is a novel biomarker associated with progenitor-like cells. ISM1+ cells are involved in the response to a bacterial challenge, suggesting an association between ISM1-producing cells and dangerous inflammatory responses like sepsis.
The large quantity of information retrieved from communities, public data repositories, web pages, or data mining can be sparsed and poorly classified. This work shows how to employ unsupervised classification algorithms such as K-means proper to classify user reviews into their closest category, forming a balanced data set. Moreover, we found that the text vectorization technique significantly impacts the clustering formation, comparing TF-IDF and Word2Vec. The value for mapping a cluster with movie genre was 81.34% ± 20.48 of the cases when the TF-IDF was applied, whereas Word2Vec only yielded a 53.51% ± 24.1. In addition, we highlight the impact of the removal of stop-words. Thus, we detected that pre-compiled lists are not the best method to remove stop-words before clustering because there is much ambiguity, centroids are poorly separated, and only 57% of clusters could match a movie genre. Thus, our proposed approach achieved a 94% of accuracy. After analyzing the classifiers’ results, we appreciated a similar effect when divided by the stop-words method removal. Statistically significant changes were observed, especially in precision metric and Jaccard scores in both classifiers, using custom-generated stop lists rather than pre-compiled ones. Reclassifying sparse data is strongly recommended as using custom-generated stop lists.
Isthmin1 (ISM1) is a constitutively secreted cytokine produced by barrier tissues and different immune cell types. Importantly, ISM1 is also expressed by cells with a hematopoietic stem cell phenotype in the lung and plays a role during hematopoiesis. Under inflammatory conditions, ISM1 levels are also altered. Given that the intestine is one of the tissues with the highest ISM1 gene expression, in this work, we characterized the immunophenotype of ISM1-producing cells in the small intestine of uninfected or Salmonella Typhimurium-infected mice. We found a variety of ISM1+-expressing cells, including CD45+ cells, EpCAM+ cells, and, importantly, we also found different subsets of cells carrying hematopoietic stem cell markers (LSKs) expressing ISM1, and their frequency was perturbed during infection. Finally, we also found that isthmin1 is secreted into the intestinal lumen, and its concentration was increased during S. Typhimurium infection. Our findings suggest that increased luminal ISM1 secretion during mucosal infection may serve as a potential novel biomarker of pathogen-mediated inflammation.