Summary: ELASPIC is a novel ensemble machine-learning approach that predicts the effects of mutations on protein folding and protein–protein interactions. Here, we present the ELASPIC webserver, which makes the ELASPIC pipeline available through a fast and intuitive interface. The webserver can be used to evaluate the effect of mutations on any protein in the Uniprot database, and allows all predicted results, including modeled wild-type and mutated structures, to be managed and viewed online and downloaded if needed. It is backed by a database which contains improved structural domain definitions, and a list of curated domain–domain interactions for all known proteins, as well as homology models of domains and domain–domain interactions for the human proteome. Homology models for proteins of other organisms are calculated on the fly, and mutations are evaluated within minutes once the homology model is available. Availability and implementation: The ELASPIC webserver is available online at http://elaspic.kimlab.org. Contact:pm.kim@utoronto.ca or pi@kimlab.org Supplementary data: Supplementary data are available at Bioinformatics online.

One stepping stone for reducing the maternal mortality is to identify severe maternal morbidity (SMM) using Electronic Health Records (EHRs). We aim to develop a pipeline to represent and classify the unstructured text of maternal progress notes in eight classes according to the silver labels defined by the ICD-10 codes associated with SMM. We preprocessed the text, removing protected health information (PHI) and reducing stop words. We built different pipelines to classify the SMM by the combination of six word-embeddings schemes, three different approaches for the representation of the documents (average, clustering, and principal component analysis), and five well-known machine learning classifiers. Additionally, we implemented an algorithm for typos and misspelling adjustment based on the Levenshtein distance to the Spanish Billion Word Corpus dictionary. We analyzed 43,529 documents constructed by an average of 4.15 progress notes from 22,937 patients. The pipeline with the best performance was the one that included Word2Vec, typos and spelling adjustment, document representation by PCA, and an SVM classifier. We found that it is possible to identify conditions such as miscarriage complication or hypertensive disorders from clinical notes written in Spanish, with a true positive rate higher than 0.85. This is the first approach to classify SMM from the unstructured text contained in the maternal EHRs, which can contribute to the solution of one of the most important public health problems in the world. Future works must test other representation and classification approaches to detect the risk of SMM.

El lenguaje escrito no ha sido ajeno a los cambios culturales y tecnológicos. Por ejemplo, la invención de la imprenta en el siglo XV, o el desarrollo de los computadores personales y los teléfonos inteligentes en las últimas décadas, fueron hitos que marcaron drásticamente su evolución. De manera paralela al desarrollo del lenguaje, la evolución de la computación y el surgimiento de algoritmos inteligentes, capaces de tomar decisiones han tenido avances impresionantes en los últimos años formando una nueva área de estudio conocida como inteligencia artificial IA, considerada por muchos como la siguiente gran revolución. La integración de las técnicas de IA con el fin de interpretar, manipular y comprender el lenguaje humano da como resultado la rama del procesamiento natural del lenguaje PNL, la cual, teniendo en cuenta los últimos avances en modelos de generación de lenguaje, se puede convertir en el próximo gran hito en cuanto al lenguaje escrito. Los primeros algoritmos de PNL estaban basados en reglas, posteriormente se empezó a utilizar esquemas de clasificación supervisada basados en modelos como la regresión logística, las máquinas de soporte vectorial, los modelos ocultos de Markov, o los árboles aleatorios condicionales, entre otros. El problema de los modelos de clasificación tradicionales es que los mismos están orientados a evaluar cada palabra, o las relaciones entre cada palabra y la palabra anterior, pero no capturan el contexto de las mismas en una frase completa.