Matches in SemOpenAlex for { <https://semopenalex.org/work/W4283778430> ?p ?o ?g. }
- W4283778430 abstract "The identification of chemicals in articles has attracted a large interest in the biomedical scientific community, given its importance in drug development research. Most of previous research have focused on PubMed abstracts, and further investigation using full-text documents is required because these contain additional valuable information that must be explored. The manual expert task of indexing Medical Subject Headings (MeSH) terms to these articles later helps researchers find the most relevant publications for their ongoing work. The BioCreative VII NLM-Chem track fostered the development of systems for chemical identification and indexing in PubMed full-text articles. Chemical identification consisted in identifying the chemical mentions and linking these to unique MeSH identifiers. This manuscript describes our participation system and the post-challenge improvements we made. We propose a three-stage pipeline that individually performs chemical mention detection, entity normalization and indexing. Regarding chemical identification, we adopted a deep-learning solution that utilizes the PubMedBERT contextualized embeddings followed by a multilayer perceptron and a conditional random field tagging layer. For the normalization approach, we use a sieve-based dictionary filtering followed by a deep-learning similarity search strategy. Finally, for the indexing we developed rules for identifying the more relevant MeSH codes for each article. During the challenge, our system obtained the best official results in the normalization and indexing tasks despite the lower performance in the chemical mention recognition task. In a post-contest phase we boosted our results by improving our named entity recognition model with additional techniques. The final system achieved 0.8731, 0.8275 and 0.4849 in the chemical identification, normalization and indexing tasks, respectively. The code to reproduce our experiments and run the pipeline is publicly available. Database URL https://github.com/bioinformatics-ua/biocreativeVII_track2." @default.
- W4283778430 created "2022-07-03" @default.
- W4283778430 creator A5017535544 @default.
- W4283778430 creator A5039688642 @default.
- W4283778430 creator A5053662030 @default.
- W4283778430 creator A5073280030 @default.
- W4283778430 creator A5090944649 @default.
- W4283778430 date "2022-01-01" @default.
- W4283778430 modified "2023-09-26" @default.
- W4283778430 title "Chemical identification and indexing in PubMed full-text articles using deep learning and heuristics" @default.
- W4283778430 cites W1550258693 @default.
- W4283778430 cites W1552716293 @default.
- W4283778430 cites W1850865022 @default.
- W4283778430 cites W2028102159 @default.
- W4283778430 cites W2029017735 @default.
- W4283778430 cites W2044420612 @default.
- W4283778430 cites W2053713852 @default.
- W4283778430 cites W2061167720 @default.
- W4283778430 cites W2091940856 @default.
- W4283778430 cites W2096951189 @default.
- W4283778430 cites W2096953947 @default.
- W4283778430 cites W2097106271 @default.
- W4283778430 cites W2107580398 @default.
- W4283778430 cites W2121844933 @default.
- W4283778430 cites W2122402213 @default.
- W4283778430 cites W2125117006 @default.
- W4283778430 cites W2140611297 @default.
- W4283778430 cites W2142016317 @default.
- W4283778430 cites W2142955026 @default.
- W4283778430 cites W2146089916 @default.
- W4283778430 cites W2149369282 @default.
- W4283778430 cites W2156235098 @default.
- W4283778430 cites W2163303745 @default.
- W4283778430 cites W2168041406 @default.
- W4283778430 cites W2168905447 @default.
- W4283778430 cites W2169099542 @default.
- W4283778430 cites W2169491861 @default.
- W4283778430 cites W2335791510 @default.
- W4283778430 cites W2346452181 @default.
- W4283778430 cites W2346750198 @default.
- W4283778430 cites W2414378847 @default.
- W4283778430 cites W2428528690 @default.
- W4283778430 cites W2479527281 @default.
- W4283778430 cites W2606900069 @default.
- W4283778430 cites W2734608416 @default.
- W4283778430 cites W2743028754 @default.
- W4283778430 cites W2769387903 @default.
- W4283778430 cites W2799125718 @default.
- W4283778430 cites W2911489562 @default.
- W4283778430 cites W2913389685 @default.
- W4283778430 cites W2917968119 @default.
- W4283778430 cites W2944400536 @default.
- W4283778430 cites W2948909602 @default.
- W4283778430 cites W2979250794 @default.
- W4283778430 cites W2979576300 @default.
- W4283778430 cites W3036263923 @default.
- W4283778430 cites W3036529033 @default.
- W4283778430 cites W3045942044 @default.
- W4283778430 cites W3088349482 @default.
- W4283778430 cites W3088624469 @default.
- W4283778430 cites W3092486910 @default.
- W4283778430 cites W3093194543 @default.
- W4283778430 cites W3102749286 @default.
- W4283778430 cites W3104015140 @default.
- W4283778430 cites W3113300158 @default.
- W4283778430 cites W3131198033 @default.
- W4283778430 cites W3131882755 @default.
- W4283778430 cites W3137481621 @default.
- W4283778430 cites W3139150463 @default.
- W4283778430 cites W3164045210 @default.
- W4283778430 cites W3173561451 @default.
- W4283778430 cites W3212714602 @default.
- W4283778430 cites W4213060373 @default.
- W4283778430 cites W4229909500 @default.
- W4283778430 cites W74342042 @default.
- W4283778430 cites W2977393556 @default.
- W4283778430 doi "https://doi.org/10.1093/database/baac047" @default.
- W4283778430 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/35776534" @default.
- W4283778430 hasPublicationYear "2022" @default.
- W4283778430 type Work @default.
- W4283778430 citedByCount "3" @default.
- W4283778430 countsByYear W42837784302023 @default.
- W4283778430 crossrefType "journal-article" @default.
- W4283778430 hasAuthorship W4283778430A5017535544 @default.
- W4283778430 hasAuthorship W4283778430A5039688642 @default.
- W4283778430 hasAuthorship W4283778430A5053662030 @default.
- W4283778430 hasAuthorship W4283778430A5073280030 @default.
- W4283778430 hasAuthorship W4283778430A5090944649 @default.
- W4283778430 hasBestOaLocation W42837784301 @default.
- W4283778430 hasConcept C110615152 @default.
- W4283778430 hasConcept C111919701 @default.
- W4283778430 hasConcept C116834253 @default.
- W4283778430 hasConcept C119857082 @default.
- W4283778430 hasConcept C127705205 @default.
- W4283778430 hasConcept C136886441 @default.
- W4283778430 hasConcept C144024400 @default.
- W4283778430 hasConcept C152565575 @default.
- W4283778430 hasConcept C154945302 @default.
- W4283778430 hasConcept C158154518 @default.
- W4283778430 hasConcept C162324750 @default.