Constituent vs Dependency Parsing-Based RDF Model Generation from Dengue Patients’ Case Sheets

Electronic Health Record (EHR) systems in healthcare organisations are primarily maintained in isolation from each other that makes interoperability of unstructured(text) data stored in these EHR systems challenging in the healthcare domain. Similar information may be described using different terminologies by different applications that can be evaded by transforming the content into the Resource Description Framework (RDF) model that is interoperable amongst organisations. RDF requires a document’s contents to be translated into a repository of triplets (subject, predicate, object) known as RDF statements. Natural Language Processing (NLP) techniques can help get actionable insights from these text data and create triplets for RDF model generation. This paper discusses two NLP-based approaches to generate the RDF models from unstructured patients’ documents, namely dependency structure-based and constituent(phrase) structure-based parser. Models generated by both approaches are evaluated in two aspects: exhaustiveness of the represented knowledge and the model generation time. The precision measure is used to compute the models’ exhaustiveness in terms of the number of facts that are transformed into RDF representations.

Introduction of loxP sites by electroporation in the mouse genome; a simple approach for conditional allele generation in complex targeting loci.

Background: The discovery of the CRISPR-Cas9 system and its applicability in mammalian embryos has revolutionized the way we generate genetically engineered animal models. To date, models harbouring conditional alleles (i.e.: two loxP sites flanking an exon or a critical DNA sequence of interest) remain the most challenging to generate as they require simultaneous cleavage of the genome using two guides in order to properly integrate the repair template. In the current manuscript, we describe a modification of the sequential electroporation procedure described by Horii et al (2017). We demonstrate production of conditional allele mouse models for eight different genes via one of two alternative strategies: either by consecutive sequential electroporation (strategy A) or non-consecutive sequential electroporation (strategy B). Results: By using strategy A, we demonstrated successful generation of conditional allele models for three different genes (Icam1, Lox, and Sar1b), with targeting efficiencies varying between 5 to 13%. By using strategy B, we generated five conditional allele models (Loxl1, Pard6a, Pard6g, Clcf1, and Mapkapk5), with targeting efficiencies varying between 3 to 25%. Conclusion: Our modified electroporation-based approach, involving one of the two alternative strategies, allowed the production of conditional allele models for eight different genes via two different possible paths. This reproducible method will serve as another reliable approach in addition to other well-established methodologies in the literature for conditional allele mouse model generation.

Structure of an ultrathin oxide film solved by machine learning enhanced global optimization

Determination of the atomic structure of solid surfaces is a challenge that has resisted solution despite advancements in experimental methods. Theory-based global optimization has the potential to revolutionize the field by providing reliable structure models as the basis for interpretation of experiments and for prediction of material properties. So far, however, the approach has been limited by the combinatorial complexity and computational expense of sufficiently accurate energy estimation for surfaces. We demonstrate how an evolutionary algorithm, utilizing machine learning for accelerated energy estimation and diverse population generation, can be used to solve an unknown surface structure—the (4 x 4) surface oxide on Pt3Sn(111)--based on limited experimental input. The algorithm is efficient and robust, and should be broadly applicable in surface studies, where it can replace manual, intuition based model generation.