Evaluation of gut microbiota predictive potential associated with phenotypic characteristics to identify multifactorial diseases
Nenhuma Miniatura disponível
Citações na Scopus
0
Tipo de produção
article
Data de publicação
2024
Título da Revista
ISSN da Revista
Título do Volume
Editora
TAYLOR & FRANCIS INC
Autores
ALVES, Juliana Tepedin Martins o
FERNANDES, Gabriel da Rocha
Citação
GUT MICROBES, v.16, n.1, article ID 2297815, 18p, 2024
Resumo
Gut microbiota has been implicated in various clinical conditions, yet the substantial heterogeneity in gut microbiota research results necessitates a more sophisticated approach than merely identifying statistically different microbial taxa between healthy and unhealthy individuals. Our study seeks to not only select microbial taxa but also explore their synergy with phenotypic host variables to develop novel predictive models for specific clinical conditions. Design: We assessed 50 healthy and 152 unhealthy individuals for phenotypic variables (PV) and gut microbiota (GM) composition by 16S rRNA gene sequencing. The entire modeling process was conducted in the R environment using the Random Forest algorithm. Model performance was assessed through ROC curve construction. Results: We evaluated 52 bacterial taxa and pre-selected PV (p < 0.05) for their contribution to the final models. Across all diseases, the models achieved their best performance when GM and PV data were integrated. Notably, the integrated predictive models demonstrated exceptional performance for rheumatoid arthritis (AUC = 88.03%), type 2 diabetes (AUC = 96.96%), systemic lupus erythematosus (AUC = 98.4%), and type 1 diabetes (AUC = 86.19%). Conclusion: Our findings underscore that the selection of bacterial taxa based solely on differences in relative abundance between groups is insufficient to serve as clinical markers. Machine learning techniques are essential for mitigating the considerable variability observed within gut microbiota. In our study, the use of microbial taxa alone exhibited limited predictive power for health outcomes, while the integration of phenotypic variables into predictive models substantially enhanced their predictive capabilities.
Palavras-chave
Gut microbiota, phenotypic variables, 16S rRNA, random forest, prediction models
Referências
- Ahmad A, 2019, PLOS ONE, V14, DOI 10.1371/journal.pone.0226372
- Ananthakrishnan AN, 2017, CELL HOST MICROBE, V21, P603, DOI 10.1016/j.chom.2017.04.010
- Aronson Jeffrey K, 2017, Curr Protoc Pharmacol, V76, DOI 10.1002/cpph.19
- Balmant BD, 2023, NUTRIENTS, V15, DOI 10.3390/nu15081999
- Bielka W, 2022, INT J MOL SCI, V23, DOI 10.3390/ijms23010480
- Callahan BJ, 2016, NAT METHODS, V13, P581, DOI [10.1038/nmeth.3869, 10.1038/NMETH.3869]
- Castellarin M, 2012, GENOME RES, V22, P299, DOI 10.1101/gr.126516.111
- Chávez-Carbajal A, 2020, MICROORGANISMS, V8, DOI 10.3390/microorganisms8010094
- da Rocha IMG, 2023, NUTRIENTS, V15, DOI 10.3390/nu15194148
- Dekaboruah E, 2020, ARCH MICROBIOL, V202, P2147, DOI 10.1007/s00203-020-01931-x
- Dhaliwal J, 2021, J PEDIATR GASTR NUTR, V72, P262, DOI 10.1097/MPG.0000000000002956
- Douglas GM, 2018, MICROBIOME, V6, DOI 10.1186/s40168-018-0398-3
- Doumatey AP, 2020, FRONT CELL INFECT MI, V10, DOI 10.3389/fcimb.2020.00063
- Ghannam RB, 2021, COMPUT STRUCT BIOTEC, V19, P1092, DOI 10.1016/j.csbj.2021.01.028
- Gou WL, 2021, DIABETES CARE, V44, P358, DOI 10.2337/dc20-1536
- Gupta VK, 2020, NAT COMMUN, V11, DOI 10.1038/s41467-020-18476-8
- Han H, 2016, INT CONF SOFTW ENG, P219, DOI 10.1109/ICSESS.2016.7883053
- He ZX, 2016, GUT PATHOG, V8, DOI 10.1186/s13099-016-0146-9
- HOSMER DW, 1980, COMMUN STAT A-THEOR, V9, P1043, DOI 10.1080/03610928008827941
- Kohli A, 2020, WORLD J GASTROENTERO, V26, DOI 10.3748/wjg.v26.i44.6923
- Kuhn M, 2008, J STAT SOFTW, V28, P1, DOI 10.18637/jss.v028.i05
- Kurilshikov A, 2021, NAT GENET, V53, P156, DOI 10.1038/s41588-020-00763-1
- Ley RE, 2006, NATURE, V444, P1022, DOI 10.1038/4441022a
- Li PS, 2022, MICROB CELL FACT, V21, DOI 10.1186/s12934-022-01973-4
- Li Q, 2020, SCI REP-UK, V10, DOI 10.1038/s41598-020-62224-3
- Li Y, 2019, CLIN SCI, V133, P821, DOI 10.1042/CS20180841
- Love MI, 2014, GENOME BIOL, V15, DOI 10.1186/s13059-014-0550-8
- Marcos-Zambrano LJ, 2021, FRONT MICROBIOL, V12, DOI 10.3389/fmicb.2021.634511
- Metwaly A, 2022, NAT REV GASTRO HEPAT, V19, P383, DOI 10.1038/s41575-022-00581-2
- Olesen SW, 2016, NAT MICROBIOL, V1, DOI [10.1038/NMICROBIOL.2016.228, 10.1038/nmicrobiol.2016.228]
- Osman MA, 2021, SCI REP-UK, V11, DOI 10.1038/s41598-021-82465-0
- Pascal V, 2017, GUT, V66, P813, DOI 10.1136/gutjnl-2016-313235
- Pires DEV, 2018, bioRxiv, DOI [10.1101/263293, 10.1101/263293, DOI 10.1101/263293]
- Poussin C, 2018, DRUG DISCOV TODAY, V23, P1644, DOI 10.1016/j.drudis.2018.06.005
- Rinninella E, 2019, MICROORGANISMS, V7, DOI 10.3390/microorganisms7010014
- Salim F, 2023, CURR OPIN BIOTECH, V79, DOI 10.1016/j.copbio.2022.102884
- Sankarasubramanian J, 2020, FRONT MED-LAUSANNE, V7, DOI 10.3389/fmed.2020.606298
- Scher JU, 2015, ARTHRITIS RHEUMATOL, V67, P128, DOI 10.1002/art.38892
- Schloss PD, 2018, MBIO, V9, DOI 10.1128/mBio.00525-18
- Shariati A, 2021, INFECT AGENTS CANCER, V16, DOI 10.1186/s13027-021-00381-4
- Shilo S, 2022, DIABETES CARE, V45, P555, DOI 10.2337/dc21-1656
- Smart CEM, 2013, DIABETES CARE, V36, P3897, DOI 10.2337/dc13-1195
- Vila AV, 2018, SCI TRANSL MED, V10, DOI 10.1126/scitranslmed.aap8914
- Vujkovic-Cvijin I, 2020, NATURE, V587, P448, DOI 10.1038/s41586-020-2881-9
- Wei F, 2019, PLOS ONE, V14, DOI 10.1371/journal.pone.0213063
- Wilkinson JE, 2021, NAT MED, V27, P766, DOI 10.1038/s41591-021-01258-0
- Wu HL, 2018, BIOMED RES INT, V2018, DOI 10.1155/2018/2936257
- Yang L, 2022, MICROBIOME, V10, DOI 10.1186/s40168-022-01320-0
- Zuo WX, 2022, SCI REP-UK, V12, DOI 10.1038/s41598-022-07995-7