Impact of Translation on Biomedical Information Extraction: Experiment on Real-Life Clinical Notes.

Background: Biomedical natural language processing tasks are best performed with English models, and translation tools have undergone major improvements. On the other hand, building annotated biomedical data sets remains a challenge. Objective: The aim of our study is to determine whether the use of English tools to extract and normalize French medical concepts based on translations provides comparable performance to that of French models trained on a set of annotated French clinical notes. Methods: We compared 2 methods: 1 involving French-language models and 1 involving English-language models. For the native French method, the named entity recognition and normalization steps were performed separately. For the translated English method, after the first translation step, we compared a 2-step method and a terminology-oriented method that performs extraction and normalization at the same time. We used French, English, and bilingual annotated data sets to evaluate all stages (named entity recognition, normalization, and translation) of our algorithms. Results: The native French method outperformed the translated English method, with an overall F1-score of 0.51 (95% CI 0.47-0.55), compared with 0.39 (95% CI 0.34-0.44) and 0.38 (95% CI 0.36-0.40) for the 2 English methods tested. Conclusions: Despite recent improvements in translation models, there is a significant difference in performance between the 2 approaches in favor of the native French method, which is more effective on French medical texts, even with few annotated documents.

Impact of translation on biomedical information extraction: an experiment on real-life clinical notes.

BACKGROUND: Biomedical natural language processing tasks are best performed with English models, and translation tools have undergone major improvements. On the other hand, building annotated biomedical datasets remains a challenge. OBJECTIVE: The aim of our study is to determine whether the use of English tools to extract and normalize French medical concepts on translations provides comparable performance to that of French models trained on a set of annotated French clinical notes. METHODS: We compare two methods: one involving French-language models and one involving English-language models. For the native French method, the Named Entity Recognition (NER) and normalization steps are performed separately. For the translated English method, after the first translation step, we compare a two-step method and a terminology-oriented method that performs extraction and normalization at the same time. We used French, English and bilingual annotated datasets to evaluate all stages (NER, normalization and translation) of our algorithms. RESULTS: The native French method outperformed the translated English method, with an overall f1 score of 0.51 [0.47;0.55], compared with 0.39 [0.34;0.44] and 0.38 [0.36;0.40] for the two English methods tested. CONCLUSIONS: Despite recent improvements in translation models, there is a significant difference in performance between the two approaches in favor of the native French method, which is more effective on French medical texts, even with few annotated documents.

Structural design of thiadiazole-based donor-acceptor COF/Fe-doped N vacancy g-C3Nx nanosheets for photocatalytic nitrogen fixation under visible light.

The rational design of efficient photocatalysts to achieve artificial nitrogen fixation is an urgent challenge. Herein, we combined donor-acceptor covalent organic framework with iron-doped nitrogen vacancy graphitized carbon nitride (D-A COF/Fe-g-C3Nx) for photocatalytic nitrogen fixation. The photocatalyst exhibited good crystallinity, high porosity, and a large specific surface area. Without a sacrificial agent, the optimal 40 % D-A COF/Fe-g-C3Nx exhibited an excellent rate of ammonia production (646 µmol h-1 g-1) at 420 nm, and durable stability after successive cycling. Exhaustive experimental research and theory calculations verified that the D-A unit and Fe doping redistributed the distribution of the charge, which enhanced the visible light utilization and provided chemisorption sites for further polarization. Besides N-vacancies can serve as electron-trapping active sites to promote the directional migration of carriers. The reaction mechanism demonstrated that superoxide radical and hydrogen peroxide were formed by electron and hole, respectively, which promote the reduction of nitrogen to ammonia. This work provides a new idea for the rationalizing design of efficient catalysts for photocatalytic nitrogen fixation under mild conditions.

Discrete-Time Control Barrier Function: High-Order Case and Adaptive Case.

This article proposes the novel concepts of the high-order discrete-time control barrier function (CBF) and adaptive discrete-time CBF. The high-order discrete-time CBF is used to guarantee forward invariance of a safe set for discrete-time systems of high relative degree. An optimization problem is then established unifying high-order discrete-time CBFs with discrete-time control Lyapunov functions to yield a safe controller. To improve the feasibility of such optimization problems, the adaptive discrete-time CBF is designed, which can relax constraints on system control input through time-varying penalty functions. The effectiveness of the proposed methods in dealing with high relative degree constraints and improving feasibility is verified on the discrete-time system of a three-link manipulator.

An MVMD-CCA Recognition Algorithm in SSVEP-Based BCI and Its Application in Robot Control.

This article proposes a novel recognition algorithm for the steady-state visual evoked potentials (SSVEP)-based brain-computer interface (BCI) system. By combining the advantages of multivariate variational mode decomposition (MVMD) and canonical correlation analysis (CCA), an MVMD-CCA algorithm is investigated to improve the detection ability of SSVEP electroencephalogram (EEG) signals. In comparison with the classical filter bank canonical correlation analysis (FBCCA), the nonlinear and non-stationary EEG signals are decomposed into a fixed number of sub-bands by MVMD, which can enhance the effect of SSVEP-related sub-bands. The experimental results show that MVMD-CCA can effectively reduce the influence of noise and EEG artifacts and improve the performance of SSVEP-based BCI. The offline experiments show that the average accuracies of MVMD-CCA in the training dataset and testing dataset are improved by 3.08% and 1.67%, respectively. In the SSVEP-based online robotic manipulator grasping experiment, the recognition accuracies of the four subjects are 92.5%, 93.33%, 90.83%, and 91.67%, respectively.

Correction: Overexpression of a maize plasma membrane intrinsic protein ZmPIP1;1 confers drought and salt tolerance in Arabidopsis.

[This corrects the article DOI: 10.1371/journal.pone.0198639.].

Overexpression of a maize plasma membrane intrinsic protein ZmPIP1;1 confers drought and salt tolerance in Arabidopsis.

Drought and salt stress are major abiotic stress that inhibit plants growth and development, here we report a plasma membrane intrinsic protein ZmPIP1;1 from maize and identified its function in drought and salt tolerance in Arabidopsis. ZmPIP1;1 was localized to the plasma membrane and endoplasmic reticulum in maize protoplasts. Treatment with PEG or NaCl resulted in induced expression of ZmPIP1;1 in root and leaves. Constitutive overexpression of ZmPIP1;1 in transgenic Arabidopsis plants resulted in enhanced drought and salt stress tolerance compared to wild type. A number of stress responsive genes involved in cellular osmoprotection in ZmPIP1;1 overexpression plants were up-regulated under drought or salt condition. ZmPIP1;1 overexpression plants showed higher activities of reactive oxygen species (ROS) scavenging enzymes such as catalase and superoxide dismutase, lower contents of stress-induced ROS such as superoxide, hydrogen peroxide and malondialdehyde, and higher levels of proline under drought and salt stress than did wild type. ZmPIP1;1 may play a role in drought and salt stress tolerance by inducing of stress responsive genes and increasing of ROS scavenging enzymes activities, and could provide a valuable gene for further plant breeding.

Graphene oxide and carbon nanodots co-modified BiOBr nanocomposites with enhanced photocatalytic 4-chlorophenol degradation and mechanism insight.

Non-metallic graphene oxide (GO) and carbon nanodots (CDots) co-doped BiOBr ternary system (GO/CDots/BiOBr) were successfully synthesized via a simple one-step solvothermal process. The compositional characterization, optical and electrical properties of photocatalysts were investigated in detail. The prepared ternary photocatalysts possessed the excellent visible-light driven photocatalytic 4-chlorophenol (4-CP) degradation. Additionally, the 4-CP removal efficiencies decreased in the order of GO/CDots/BiOBr (88.9%) > CDots/BiOBr (62.9%) > GO/BiOBr (60.5%) > pristine BiOBr (46.9%) in 6 h under visible light irradiation. The dissolved organic carbon (DOC) removal and the dechlorination efficiency by the GO/CDots/BiOBr were 58.4% and 78.2%, respectively, much higher than pristine BiOBr. The co-existence of GO and CDots on the BiOBr greatly promoted visible light harvesting and utilizing ability and inhibited the recombination of photogenerated electron/hole pairs. The synergistic effect between GO, CDots and BiOBr was expounded, and the photocatalytic reaction mechanism was proposed in detail via the band structure analysis and free radical trapping experiments.