Rosado Galindo, Heizel M.

Profile Picture

Filters

2017 - 201912020 - 20221
Reset filters

Settings

Citations

Publication Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    Publication
    A decision tree-based approach for missing value imputation of mixed-type data
    (2017-05) Rosado Galindo, Heizel M.; Dávila, Saylisse; College of Engineering; Torres, Wandaliz; Artiles, Noel; Department of Industrial Engineering; De Hoyos, Moraima
    Researchers and practitioners of many areas of knowledge frequently struggle with missing data. Missing data is a problem because almost all standard statistical methods assume that the information is complete. Missing value imputation offers a solution to this problem. The main contribution of this work lies on the development of a random forest-based imputation method that can handle any type of data, including high-dimensional data with non-linear complex interactions. The premise behind the proposed scheme is that a variable can be imputed taking into account only those variables that are related to it using feature selection. This work compares the performance of the proposed scheme with other two imputation methods commonly used in literature: KNN and missForest. The results suggest that the proposed method can be useful in complex categorical scenarios with high volume of missing values. The proposed method is an approximation of missForest that signi cantly reduces the amount of variables used in the imputation.
  • Thumbnail Image
    Publication
    Effect of physical cues in the expansion and secretory functions of cells
    (2022-11-28) Rosado Galindo, Heizel M.; Domenech, Maribella; College of Engineering; Torres Lugo, Madeline; Resto Irizarry, Pedro J.; Torres García, Wandaliz; Other; Latorre Estevez, Magda
    It is well established that cells have the ability to perceive different biochemical and physical cues of their microenvironment such as soluble factors, nutrients and matrix-mediated signals, including surface chemistry, stiffness and topography. The mechanisms underlying the interactions in cell topography are not fully understood, but they can greatly influence cell proliferation, cytoskeletal organization, differentiation, and receptor signaling. Hence, the development of in vitro culture models that can recapitulate these cell-substrate interactions still is a key research topic. Scientists have employed many microfabrication techniques and materials to generate culture substrates containing topographies for cell-based assays. However, the fabrication techniques and types of material used are often costly, require highly trained staff and could produce toxic byproducts that can undermine the biological interpretation of the results. Thus, in this work we developed an array of culture surfaces on polystyrene using razor printing, sanding methods and plasma treatment to examine the impact of microscale topographies on cell behavior. The proposed technology consists of culture substrates of defined roughness, geometries, and levels of wettability on polystyrene films bound to the bottom of a culture well using double-sided medical-grade tape. Results showed that substrates with grooved micropatterns and high level of surface wettability supported enhanced secretory and immunosuppressive capacity in human bone marrow-derived mesenchymal stem cells (hBM- MSCs). Also, we demonstrated that surface roughness can modulate the oncogenic activity of triple-negative breast cancer (TNBC) cells by enhancing the proportion of cancer stem cells (CSC) and fundamental oncogenic signaling pathways. Overall, we validated the potential and versatility of the proposed polystyrene topographical array as an effective culture strategy to modulate cell function.