redicTF: prediction of bacterial transcription factors in complex microbial communities using deep learnin

Autor(es)

Monteiro, Lummy Maria Oliveira ^{[1, 2, 3]} ; Saraiva, Joao Pedro ^[1] ; Toscan, Rodolfo Brizola ^[1] ; Stadler, Peter F. ^[3] ; Silva-Rocha, Rafael ^[2] ; da Rocha, Ulisses Nunes ^[1]

Afiliação do(s) autor(es)

^[1] UFZ Helmholtz Ctr Environm Res, Leipzig - Germany

^[2] Univ Sao Paulo, Ribeirao Preto Med Sch FMRP, Ribeirao Preto - Brazil

^[3] Univ Leipzig, Bioinformat Grp, Inst Comp Sci, Leipzig - Germany

• Tipo de documento: Artigo Científico
• Fonte: ENVIRONMENTAL MICROBIOME; v. 17, n. 1 FEB 8 2022.
• Citações Web of Science: 0

Resumo

Background: Transcription factors (TFs) are proteins controlling the flow of genetic information by regulating cellular gene expression. A better understanding ofTFs in a bacterial community context may open novel revenues for exploring gene regulation in ecosystems where bacteria play a key role. Here we describe PredicTF, a platform supporting the prediction and classification of novel bacterial TF in single species and complex microbial communities. PredicTF is based on a deep learning algorithm. Results: To train PredicTF, we created a TF database (BacTFDB) by manually curating a total of 11,961 TF distributed in 99 TF families. Five model organisms were used to test the performance and the accuracy of PredicTF. PredicTF was able to identify 24-62% of the known TFs with an average precision of 88% in our five model organisms. We demonstrated PredicTF using pure cultures and a complex microbial community. In these demonstrations, we used (meta) genomes for TF prediction and (meta)transcriptomes for determining the expression of putative TFs. Conclusion: PredicTF demonstrated high accuracy in predicting transcription factors in model organisms. We prepared the pipeline to be easily implemented in studies profiling TFs using (meta)genomes and (meta)transcriptomes. PredicTF is an open-source software available at https://github.com/mdsufz/PredicTF. (AU)

• Processo FAPESP: 19/15675-0 - Desvendando a complexidade das redes de regulação gênica microbianas
• Beneficiário: Rafael Silva Rocha
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 18/21133-2 - Reconstrução de redes regulatórias bacterianas em amostras ambientais terrestres
• Beneficiário: Lummy Maria Oliveira Monteiro
• Modalidade de apoio: Bolsas no Exterior - Estágio de Pesquisa - Doutorado
• Processo FAPESP: 16/19179-9 - Desvendando as relações arquitetura/função de promotores bacterianos complexos utilizando abordagens de biologia sintética
• Beneficiário: Lummy Maria Oliveira Monteiro
• Modalidade de apoio: Bolsas no Brasil - Doutorado