DSpace Coleção: Artigo em periódico indexado (SAPC)Artigo em periódico indexado (SAPC)https://www.alice.cnptia.embrapa.br/alice/handle/item/9022026-06-03T22:28:45Z2026-06-03T22:28:45ZComparison of machine learning methods for marker identification in GWAS.COSTA, W. G. daPEREIRA, H. D.SILVA, G. N.BORÉM, A.CAIXETA, E. T.OLIVEIRA, A. C. B. deCRUZ, C. DNASCIMENTO, M.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11865472026-05-09T15:13:13Z2026-01-01T00:00:00ZTítulo: Comparison of machine learning methods for marker identification in GWAS.
Autoria: COSTA, W. G. da; PEREIRA, H. D.; SILVA, G. N.; BORÉM, A.; CAIXETA, E. T.; OLIVEIRA, A. C. B. de; CRUZ, C. D; NASCIMENTO, M.
Conteúdo: Genome-wide association studies (GWAS) are essential for identifying genomic regions associated with agronomic traits, but Linear Mixed Model (LMM)-based GWAS face challenges in capturing complex gene interactions. This study explores the potential of machine learning (ML) methodologies to enhance marker identification and association modeling in plant breeding. Unlike LMM-based GWAS, ML approaches do not require prior assumptions about marker–phenotype relationships, enabling the detection of epistatic effects and non-linear interactions. The research sought to assess and contrast approaches utilizing ML (Decision Tree—DT; Bagging—BA; Random Forest—RF; Boosting—BO; and Multivariate Adaptive Regression Splines—MARS) and LMM-based GWAS. A simulated F2 population comprising 1000 individuals was analyzed using 4010 SNP markers and ten traits modeled with epistatic interactions. The simulation included quantitative trait loci (QTL) counts varying between 8 and 240, with heritability levels set at 0.5 and 0.8. These characteristics simulate traits of candidate crops that represent a diverse range of agronomic species, including major cereal crops (e.g., maize and wheat) as well as leguminous crops (e.g., soybean), such as yield, with moderate heritability and a high number of QTLs, and plant height, with high heritability and an average number of QTLs, among others. To validate the simulation findings, the methodologies were further applied to a real Coffea arabica population (n = 195) to identify genomic regions associated with yield, a complex polygenic trait. Results demonstrated a fundamental trade-off between sensitivity and precision. Specifically, for the most complex trait evaluated (240 QTLs under epistatic control), Ensemble methods (Bagging and Random Forest) maintained a Detection Power (DP) exceeding 90%, significantly outperforming state-of-the-art GWAS methods (FarmCPU), which dropped to approximately 30%, and traditional Linear Mixed Models, which failed to detect signals (0%). However, this sensitivity resulted in lower precision for ensembles. In contrast, MARS (Degree 1) and BLINK achieved exceptional Specificity (>99%) and Precision (>90%), effectively minimizing false positives. The real data analysis corroborated these trends: while standard GWAS models failed to detect significant associations, the ML framework successfully prioritized consensus genomic regions harboring functional candidates, such as SWEET sugar transporters and NAC transcription factors. In conclusion, ML Ensembles are recommended for broad exploratory screening to recover missing heritability, while MARS and BLINK are the most effective methods for precise candidate gene validation.2026-01-01T00:00:00ZLow-density marker panels for genomic prediction in Coffea arabica L.ARCANJO, E. S.NASCIMENTO, M.AZEVEDO, C. F.CAIXETA, E. T.OLIVEIRA, A. C. B. dePEREIRA, A. A.NASCIMENTO, A. C. C.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11865482026-05-09T15:13:26Z2025-01-01T00:00:00ZTítulo: Low-density marker panels for genomic prediction in Coffea arabica L.
Autoria: ARCANJO, E. S.; NASCIMENTO, M.; AZEVEDO, C. F.; CAIXETA, E. T.; OLIVEIRA, A. C. B. de; PEREIRA, A. A.; NASCIMENTO, A. C. C.
Conteúdo: Developing new cultivars, particularly in perennial species like Coffea arabica, can be a time-consuming process. Employing molecular markers in genome-wide selection (GWS) for predicting genetic values offers an alternative to accelerate this process. However, implementing GWS typically involves genotyping many markers for both training and candidate individuals, which can increase the total genotyping cost for the breeding program. Therefore, this study aimed to assess the feasibility of using low-density marker panels to predict the genetic merit of C. arabica for a range of desirable agronomic traits. For this purpose, GWS analyses were performed using the G-BLUP method with panels of varying marker densities, selected based on marker effect magnitude. The results indicate that employing lower-density panels might be advantageous for this species' improvement. Models based on these panels yielded accurate predictions for various traits and demonstrated high agreement in terms of selected individuals compared to more complex models.2025-01-01T00:00:00ZAgronomic performance of irrigated and rainfed arabica coffee cultivars in the cerrado mineiro region.VOLTOLINI, G. B.CARVALHO, G. R.ANDRADE, V. T.FERREIRA, A. D.RAPOSO, F. V.CARVALHO, J. P. F.VILELA, D. J. M.SILVA, C. A. daCOSTA, J. de O.ABREU, G. B.ABRAHÃO, J. C. de R.BOTELHO, C. E.NADALETI, D. H. S.MALTA, M. R.SILVA, V. A.SALGADO, S. M. de L.FARIA, R. S. deOLIVEIRA, A. C. B. dePEREIRA, A. A.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11865322026-05-09T15:12:47Z2025-01-01T00:00:00ZTítulo: Agronomic performance of irrigated and rainfed arabica coffee cultivars in the cerrado mineiro region.
Autoria: VOLTOLINI, G. B.; CARVALHO, G. R.; ANDRADE, V. T.; FERREIRA, A. D.; RAPOSO, F. V.; CARVALHO, J. P. F.; VILELA, D. J. M.; SILVA, C. A. da; COSTA, J. de O.; ABREU, G. B.; ABRAHÃO, J. C. de R.; BOTELHO, C. E.; NADALETI, D. H. S.; MALTA, M. R.; SILVA, V. A.; SALGADO, S. M. de L.; FARIA, R. S. de; OLIVEIRA, A. C. B. de; PEREIRA, A. A.
Conteúdo: Coffee genetic improvement programs have been evolving very quickly, with frequent launches of new cultivars. The adoption of these new genetic materials by rural producers requires knowledge of agronomic performance in different production systems. Thus, this research aimed to evaluate the agronomic performance of irrigated and rainfed Arabica coffee (Coffea arabica L.) cultivars in the Cerrado Mineiro region. Evaluations were conducted in experimental fields across 22 farms of Arabica coffee producers, and 11 used an irrigated production system and 11 used a rainfed system. Twelve cultivars were evaluated as follows: Catuaí Vermelho IAC 144, Bourbon Amarelo IAC J10, Topázio MG 1190, MGS Epamig 1194, Catiguá MG2, MGS Catiguá 3, MGS Ametista, Pau Brasil MG1, MGS Paraíso 2, MGS Aranãs, Sarchimor MG 8840, and IAC 125 RN. Based on grain yield, processing yield, seed density, grain size, and cup quality, agronomic performance evaluations were conducted annually for the 2019, 2020, 2021, and 2022 harvests. The results showed that the grain yield was higher in the irrigated system compared to the rainfed system. In irrigated fields, the average increases in grain yield were 38%. Irrigation improved the performance of the cultivars in terms of processing yield, although it reduced cup quality. MGS Paraíso 2 cultivar showed the best productive performance, with an average of over four harvests of 52 and 42 bags ha−1 (1 bag = 60 kg) in irrigated and rainfed systems, respectively. The cultivars least responsive to irrigation were IAC 125 RN, MGS Catiguá 3, MGS Ametista, and MGS Paraíso 2, with grain yield increases of 24%, 26%, 27%, and 28%, respectively. The most responsive cultivars were MGS EPAMIG 1194, Sarchimor MG 8840, and Pau Brasil MG1, with grain yield increases of 33%, 35%, and 39%, respectively. The agronomic performance results of coffee cultivars in irrigated and rainfed production systems will allow rural producers to adopt cultivars that are more suitable for the Cerrado Mineiro region.2025-01-01T00:00:00ZInitial vegetative vigor of Coffea canephora genotypes grown in the western amazon.KOLLN, A. M.ESPINDULA, M. C.ROCHA, R. B.ARAÚJO, L. F. B. deTEIXEIRA, A. L.LOPES JUNIOR, H.https://www.alice.cnptia.embrapa.br/alice/handle/doc/11865312026-05-09T15:13:20Z2025-01-01T00:00:00ZTítulo: Initial vegetative vigor of Coffea canephora genotypes grown in the western amazon.
Autoria: KOLLN, A. M.; ESPINDULA, M. C.; ROCHA, R. B.; ARAÚJO, L. F. B. de; TEIXEIRA, A. L.; LOPES JUNIOR, H.
Conteúdo: Understanding the vegetative vigor of clonal genotypes under nursery conditions is essential for efficient seedling production and the development of new cultivars. This study aimed to evaluate the initial vegetative vigor of Coffea canephora genotypes cultivated in the Western Amazon. Twenty-one genotypes from the Embrapa Germplasm Bank, four registered cultivars, and three publicly available clones were assessed in a completely randomized design with four replicates and six plants per plot. Vegetative traits were evaluated 128 days after planting the cuttings and included: shoot length (SL), shoot diameter (SD), number of roots (NR), root volume (RV), shoot dry mass (SDM), root dry mass (RDM), total dry mass (TDM), leaf area (LA), the SDM/RDM ratio, and the Dickson Quality Index (DQI). Genotype performance and experimental accuracy were analyzed using genetic parameter estimates and genotype divergence. All commercial genotypes, except GJ25 and AS2, exhibited superior vegetative vigor during the seedling stage. Genotype BAG15 was initially the most vigorous. Genotypes BAG30, BAG31, BAG21, BAG29, BAG19, BAG26, BAG24, BAG28, BAG39, BAG41, BAG33, BAG38, BAG43, BAG23, BAG34, and BAG32 were considered promising due to their high RDM/SDM ratio and/or proximity to ideotype III, which was characterized by greater root development a trait likely to enhance survival following transplanting in the field.2025-01-01T00:00:00Z