Combining word embeddings to extract chemical and drug entities in biomedical literature

Background Natural language processing (NLP) and text mining technologies for the extraction and indexing of chemical and drug entities are key to improving the access and integration of information from unstructured data such as biomedical literature. Methods In this paper we evaluate two important tasks in NLP: the named entity recognition (NER) and Entity indexing using the SNOMED-CT terminology. For this purpose, we propose a combination of word embeddings in order to improve the results obtained in the PharmaCoNER challenge. Results For the NER task we present a neural network composed of BiLSTM with a CRF sequential layer where different word embeddings are combined as an input to the architecture. A hybrid method combining supervised and unsupervised models is used for the concept indexing task. In the supervised model, we use the training set to find previously trained concepts, and the unsupervised model is based on a 6-step architecture. This architecture uses a dictionary of synonyms and the Levenshtein distance to assign the correct SNOMED-CT code. Conclusion On the one hand, the combination of word embeddings helps to improve the recognition of chemicals and drugs in the biomedical literature. We achieved results of 91.41% for precision, 90.14% for recall, and 90.77% for F1-score using micro-averaging. On the other hand, our indexing system achieves a 92.67% F1-score, 92.44% for recall, and 92.91% for precision. With these results in a final ranking, we would be in the first position.

INTELLIGENT DATA MODEL FOR ARABIC MORPHOLOGY: MORPHOSCRIPT LANGUAGE

This paper aims to propose a specific formalism for Arabic morphology modeling that is too complex to model exhaustively with classical approaches. Therefore, it was necessary to find out an adequate representation of formalism. We designed, thus, a declarative, object-oriented language, referenced to us: MorphoScript, which allowed us to represent the complete morphological knowledge that we could identify optimally. The study that we are presenting here aims to propose an adequate data model of natural language morphological components and composition rules. We will thus present the basic elements and the theoretical and technical foundations of a language reproducing and assisting a morphological analysis process and the principles that guided the conception of this data model fully based on class concepts. Therefore, it is an object-oriented language using inheritance as basic support to define the morphological links between the different morphological classes. We have also used aggregation concepts and an annotation indexing system allowing the morphological designer a better representation of morphological knowledge.

Agree – Disagree: Comparing Traffic Limitations in the Kara Sea

This study investigates variability of ships’ operational limitations for ice conditions in view of national rules and international recommendations (the Rules for Navigation in the Water Area of the Northern Sea Route and the International Maritime Organization Recommendations). As an example, the Kara Sea region is considered for the period of 2017–2019. The ship data from two datasets were considered: (1) the Northern Sea Route Administration data and (2) the Automatic Identification System data. For each ship’s ice class, the ice information (concentration and type) was used to derive operational limitations based on the Polar Operational Limit Assessment Risk Indexing System (POLARIS), and the results were compared with the newly updated Northern Sea Route access criteria. Preliminary results indicate that national rules are generally stricter than international recommendations, however on some occasions, the national rules impose lesser restrictions on operations as ships with ice class PC7/Arc4 are allowed to operate when the international recommendations suggest an elevated probability of an accidental event.

Evaluation of the Surface Water Quality in Bangladesh with an Introduction of Water Quality Index (WQI) and its Prediction from Limited Parameters

Healthy aquatic environment is crucial for preserving aquatic lives in surface waters. Increasing industrial or agricultural discharge or run-off can pollute water leading to unhealthy aquatic environment causing distress in fishes and other aquatic lives. In places with lack of infrastructure and regulatory enforcement, pollution can be particularly challenging to handle. Assignment of an indexing system can be helpful for analyzing pollution pattern in the polluted rivers which can be helpful for remediation purposes and prevention of future pollution. Bangladesh currently does not have any indexing system in place. Assignment of indices in the rivers of Bangladesh can be helpful for remediation of the rivers on a preferential basis as remediation of all the rivers at once will pose challenges with funding and infrastructural allocation. Parameters monitored in the water monitoring stations of ten rivers were extracted from the reports published by the Department of Environment (DOE) of Bangladesh. A water quality index (WQI) was assigned on the rivers across seven years of time period to identify the most polluted rivers. The degree of pollution in the river was in the order of Mayuri > Buriganga > Korotoa > Turag > Shitalakhya > Surma > Halda > Dhaleshwari > Mathavanga > Brahmaputra based on the WQI analysis. Among the ten rivers, only Mathavanga and Brahmaputra were in good condition. The most polluted rivers were located in areas with manufacturing, textile etc. industries. Hence, monitoring of industrial discharge intro the rivers and regulatory enforcement is crucial for the prevention of pollution in rivers. In addition to regulatory enforcement, adoption of remediation plans and implementation of them is also essential for remediation of the polluted rivers.

Preliminary construction of evaluation index system and method of regional suitability of straw storage and transportation mode

The industrial utilization of straw from the field is an important way to achieve its comprehensive utilization. Construction of an efficient collection system is the premise and foundation for the efficient utilization of straw resources. It has become an urgent problem to reduce the cost of storage and transportation of straw from the field. In order to construct an indexing system and method of regional suitability evaluation of straw storage and transportation technology model, a model based on regional suitability criteria for straw storage and transportation technology has been constructed by using literature analysis. The evaluation method of the straw storage and transportation technology model is briefly discussed. This method provides a quantifiable basis for screening, evaluation, integration, and popularization of the straw storage and transportation technology model.

THE QUEST FOR INDEXING A JOURNAL

Hearing about the selection of one’s journal by a reputable indexing system pleases every editor. Journals with an international editorial members selected from prolific researchers have a higher chance of being selected by a prestigious indexing system. Geographic distribution of authors’ affiliations is another important factor. Considering a minimum of internationally acceptable editorial standards would also influence the decision of the indexing systems to select a journal—publishing few quality articles is much better than publishing a bunch of poorly designed badly reported ones. The key to success is having a group of dedicated staff with good communication skills.

Liberating host-virus knowledge from COVID-19 lockdown

Connecting basic data about bats and other potential mammal hosts of SARS-CoV-2 with their ecological context is now critical for understanding the emergence and spread of COVID-19. However, when global lockdown started in March 2020, the world’s bat experts were locked out of their research laboratories, which, in turn, locked up large volumes of offline ecological and taxonomic data. Global lockdown has put a magnifying glass on the long-standing problem of biological ‘dark data’ that is published but disconnected from digital knowledge resources, and thus unavailable for high-throughput analysis. Host-to-virus knowledge will be biased until this challenge is addressed. Here we outline two viable solutions: (i) how to interconnect published data about mammal hosts and viruses in the short term; and (ii) how to shift the publishing paradigm beyond unstructured text (e.g., PDFs) to labeled networks of digital knowledge. Biological taxonomy is foundational to both solutions as the indexing system for biodiversity data. Building digitally connected ‘knowledge graphs’ of host-virus interactions will establish the needed agility for quickly identifying reservoir hosts of novel zoonoses, allow for AI-based predictions of emergence, and thereby improve planetary health security.

Automatic protray conveying and dibbling system towards development of automatic protray seeder for vegetable nursery

Quality and healthy seedling production is very important for successful vegetable cultivation. Recent days hybrid vegetable seedlings are raised in protrays under protected cultivation to ensure quality seedling production. Vegetable nursery raising is an upcoming successful entrepreneurship area. Growing media filled protrays are dibbled and seeded manually. This process is very tedious, labour intensive, time consuming and drudgery. Keeping this in view, an automatic protray conveying, dibbling and seeding system was designed and developed. The design and construction of automatic protray conveying and dibbling system is presented is this paper. The machine was designed suitable for 98 protray cell (Protray dimension : 530 x 275 mm and protray cavity matrix: 14 x 7 (lengthwise x widthwise) which is widely used for vegetable nursery raising. This system consisted of protray conveyor and indexing system, dibbling unit, penumatic systems, electronic controls and programmable logic controller (PLC). The main conveyor shaft was driven by a stepper motor and the stepper motor was driven by a micro-stepping drive with 3200 pulse/rev configuration. Each protray was detected by a sensor and indexed by determined distance pre-programed of PLC. The function of dibbling unit was to make 10 mm dia. x 10 mm deep depressions at the center of the each cell of the growing media filled protray. The dibbling unit was a set of conically shaped tubular pegs arranged in a common bar. The stroke of the operation was 30 mm and indenting was 10 mm deep. Proximity sensor of PNP type was used for the dead end limits of all motions and conveyor index. The sensors used were dibbling station home sensor, dibbling station lower sensor, main conveyor indexing sensor and tray detection sensor. The entire cycle was controlled by a logic programme and this synchronized the conveyor motion (position/inching) with the dibbling system. This machine was able to index the growing media protrays at the predetermined distance of 38.3 mm and to make uniform depth cavities. The dibbling capacity was found to be 300 protrays/h.