Drug-induced liver injury (DILI) is a key safety issue in the drug discovery pipeline and a regulatory concern. Thus, many in silico tools have been proposed to improve the hepatotoxicity prediction of organic-type chemicals. Here, classifiers for the prediction of DILI were developed by using QuBiLS-MAS 0−2.5D molecular descriptors and shallow machine learning techniques, on a training set composed of 1075 molecules. The best ensemble model build, E13, was obtained with good statistical parameters for the learning series, namely, the following: accuracy = 0.840, sensibility = 0.890, specificity = 0.761, Matthew's correlation coefficient = 0.660, and area under the ROC curve = 0.904. The model was also satisfactorily evaluated with Y-scrambling test, and repeated k-fold cross-validation and repeated k-holdout validation. In addition, an exhaustive external validation was also carried out by using two test sets and five external test sets, with an average accuracy value equal to 0.854 (±0.062) and a coverage equal to 98.4% according to its applicability domain. A statistical comparison of the performance of the E13 model, with regard to results and tools (e.g., Padel DDPredictor Software, Deep Learning DILIserver, and Vslead) reported in the literature, was also performed. In general, E13 presented the best global performance in all experiments. The sum of the ranking differences procedure provided a very similar grouping pattern to that of the M-ANOVA statistical analysis, where E13 was identified as the best model for DILI predictions. A noncommercial and fully cross-platform software for the DILI prediction was also developed, which is freely available at http://tomocomd.com/apps/ptoxra. This software was used for the screening of seven data sets, containing natural products, leads, toxic materials, and FDA approved drugs, to assess the usefulness of the QSAR models in the DILI labeling of organic substances; it was found that 50−92% of the evaluated molecules are positive-DILI compounds. All in all, it can be stated that the E13 model is a relevant method for the prediction of DILI risk in humans, as it shows the best results among all of the methods analyzed.

No abstract

Introduction Colorectal cancer is the most common malignant neoplasm of the gastrointestinal tract. Its incidence and mortality vary markedly at a global level. Assessing the epidemiological behavior of this condition allows reevaluating diagnostic, therapeutic and prognostic options, based on new findings. In Colombia, few studies have correlated variables associated with surgical and oncological outcomes in this type of cancer. Then, the aim of this study was to evaluate the surgical outcomes and factors associated with postoperative complications of colorectal cancer in a Colombian Caribbean Population. Methods Retrospective cross‐sectional study, including patients with a histopathological diagnosis of colorectal cancer who underwent open or laparoscopic surgery, during a period of two years (2018–2020), from a regional referral hospital. Clinical history variables were collected. Frequencies and prevalence ratios were calculated. Results A total of 84 patients were finally included. Adenocarcinoma of non‐special type with advanced clinical stages was the most prevalent (72.6%). Rectal neoplasia (45.2%) was the most frequent anatomical subsite, followed by proximal colon (p = 0.026). The anatomical subsite of the neoplasm, intraoperative complication (PR 1.38; 95% CI, 1.21–1.59, p = 0.001) and intensive care stay (PR 1.062; 95% CI, 1.01–1.12, p = 0.048) were associated with postoperative outcome. Conclusions The anatomical subsite of the neoplasm location, the presence of intraoperative complications and the stay in intensive care may be associated with the surgical and oncological outcome of individuals with colon cancer from the Colombian Caribbean region.

Introducción: El daño hepático inducido por fármacos es la causa más común de muerte por insuficiencia hepática aguda y representa aproximadamente el 10% de los casos en todo el mundo. Los AINEs son el grupo farmacológico con mayor número de casos de daño hepático reportados; su consumo ha aumentado debido al tratamiento de enfermedades emergentes como el virus Chikun-gunya y Zika, siendo el departamento de Bolívar uno de los principales focos de estas enfermedades.Objetivo: Determinar el riesgo de daño hepático relacionado con los medicamentos AINES en pacientes afectados con Chikun-gunya y Zika.Métodos: Estudio analítico observacional retrospectivo realizado en el Hospital Universitario del Caribe en el departamento de Bolívar – Colombia. Se revisaron 432 historias clínicas de pacientes hombres y mujeres con edades entre los 18-62 años que ingresaron al servicio de urgencias entre los años 2014 al 2016 y fueron diagnosticados con Chikun-gunya y Zika.  Resultados: Fueron incluidas 112 historias clínicas de las cuales el 74,1% de los pacientes tenían diagnóstico de Chikun-gunya y tratamiento con AINES. La mediana de edad fue de 50 años (RIC: 38 - 58) y el promedio de edad fue de 48 años (DE: 14,2). Se encontraron diferencias estadísticas en el sexo, siendo más frecuente el femenino en el grupo con daño hepático encontrado en 54,3% comparado con un 7,8% en aquellos sin hepatotoxicidad, (p<0,0001).Conclusiones: La variable más asociada a la hepatotoxicidad en pacientes con Chikun-gunya y tratamiento con AINES fue el sexo femenino, lo que indica un mayor riesgo de desarrollo de dicha entidad.

No abstract