Chemical identification and indexing in PubMed full-text articles using deep learning and heuristics.

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.

Faecal Virome Analysis of Wild Animals from Brazil.

The Brazilian Cerrado fauna shows very wide diversity and can be a potential viral reservoir. Therefore, the animal's susceptibility to some virus can serve as early warning signs of potential human virus diseases. Moreover, the wild animal virome of this biome is unknown. Based on this scenario, high-throughput sequencing contributes a robust tool for the identification of known and unknown virus species in this environment. In the present study, faeces samples from cerrado birds (Psittacara leucophthalmus, Amazona aestiva, and Sicalis flaveola) and mammals (Didelphis albiventris, Sapajus libidinosus, and Galictis cuja) were collected at the Veterinary Hospital, University of Brasília. Viral nucleic acid was extracted, submitted to random amplification, and sequenced by Illumina HiSeq platform. The reads were de novo assembled, and the identities of the contigs were evaluated by Blastn and tblastx searches. Most viral contigs analyzed were closely related to bacteriophages. Novel archaeal viruses of the Smacoviridae family were detected. Moreover, sequences of members of Adenoviridae, Anelloviridae, Circoviridae, Caliciviridae, and Parvoviridae families were identified. Complete and nearly complete genomes of known anelloviruses, circoviruses, and parvoviruses were obtained, as well as putative novel species. We demonstrate that the metagenomics approach applied in this work was effective for identification of known and putative new viruses in faeces samples from Brazilian Cerrado fauna.