Logo Locus

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 6 of 6

Recent Submissions

  • Thumbnail Image
    Item type:Item,
    Integrating autoencoder deep neural networks with principal component-based methods for subpopulation identification
    (Crop Breeding and Applied Biotechnology, 2026) Azevedo, Camila Ferreira; Costa, Jaquicele Aparecida da; Nascimento, Ana Carolina Campana; Nascimento, Moyses; Cruz, Cosme Damião
    This study evaluated statistical dimensionality reduction techniques—Principal Component Analysis (PCA), Sparse PCA (SPCA), Independent PCA (IPCA), deep learning based on autoencoders (AE), and their hybrid combinations—for subpopulation identification in genomic data. High-dimensional single nucleotide polymorphism (SNP) datasets pose computational challenges and may hinder clustering performance. We compared methods based on clustering agreement with known subpopulation labels using Oryza sativa data (413 genotypes; 44,100 SNPs). PCA and SPCA exhibited strong performance (Adjusted Rand Index [ARI] = 0.715), with PCA achieving the lowest computational time (4.89 s). The standalone autoencoder performed poorly, likely due to the high?dimensional (p >> n) setting. Among the hybrid approaches, IPCA-AE achieved the highest agreement (ARI = 0.758), demonstrating that combining dimensionality reduction with nonlinear representation learning improves population structure identification.
  • Thumbnail Image
    Item type:Item,
    Artificial neural networks classify cotton genotypes for fiber length
    (Crop Breeding and Applied Biotechnology, 2018) Carvalho, Luiz Paulo de; Teodoro, Paulo Eduardo; Barroso, Lais Mayara Azevedo; Farias, Francisco José Correia; Morello, Camilo de Lellis; Nascimento, Moysés
    Fiber length is the main trait that needs to be improved in cotton. However, the presence of genotypes x environments interaction for this trait can hinder the recommendation of genotypes with greater length fibers. The aim of this study was to evaluate the adaptability and stability of the fibers length of cotton genotypes for recommendation to the Midwest and Northeast, using artificial neural networks (ANNs) and Eberhart and Russell method. Seven trials were carried out in the states of Ceará, Rio Grande do Norte, Goiás and Mato Grosso do Sul. Experimental design was a randomized block with four replications. Data were submitted to analysis of adaptability and stability through the Eberhart & Russell and ANNs methodologies. Based on these methods, the genotypes BRS Aroeira, CNPA CNPA 2009 42 and CNPA 2009 27 has better performance in unfavorable, general and favorable environment, respectively, for having fiber length above the overall mean of environments and high phenotypic stability.
  • Thumbnail Image
    Item type:Item,
    Diversity between Jatropha curcas L. accessions based on oil traits and X-ray digital images analysis from it seeds
    (Crop Breeding and Applied Biotechnology, 2018) Pinto, Milena Silva; Damasceno Junior, Pedro Corrêa; Oliveira, Lucas Couto de; Machado, Adelia Ferreira de Faria; Souza, Marco Andre Alves de; Muniz, Dandara Rêgo; Dias, Luiz Antônio dos Santos
    Jatropha curcas L. is a species with high potential for the biodiesel production. Therefore, the oil yield and quality from it seeds should be known. This study aimed to estimate the correlation between morphological traits, yield and oil quality evaluated in the seeds, to know the genetic diversity between J. curcas accessions and it behavior regarding to three harvest seasons. For this purpose, X-ray digital images from seeds of 18 accessions were obtained, and the seeds analyzed for external and internal morphological aspects. The same seeds were analyzed for oil yield and quality. In general, the results concerning diversity indicated a narrow genetic base. More rounded and very long seeds had lower oil yield. Larger seeds presented higher oil yield only when their internal cavity was filled by their endosperm. Most of the accessions showed variation regarding the size of the endosperm, yield and oil quality between harvest seasons.
  • Thumbnail Image
    Item type:Item,
    Estimation of genetic parameters and selection for rooting capacity in peach
    (Crop Breeding and Applied Biotechnology, 2018) Oliveira, João Alison Alves; Bruckner, Cláudio Horst; Silva, Danielle Fabíola Pereira da; Santos, Carlos Eduardo Magalhães dos; Penso, Gener Augusto; Aquino, César Fernandes
    One of the most important criteria in the improvement of rootstocks is easiness of propagation. The objective of the present study was to verify the existence of genetic variability and the possibility of gains with selection in the rooting capacity among peach genotypes. Seventy-seven genotypes of peach belonging to five F3 families were evaluated. Rooting percentage (RP), number of roots per cutting (NR) and mean root length (RL) were evaluated. Genetic values were estimated. The nineteen genotypes with the lowest rank summation index were selected to estimate the genetic gains. The variables RP, NR and RL had progeny mean heritabilities of 0.53, 0.60 and 0.83, respectively. Of the individuals selected, 89.5% belonged to the 713 (Talismã x Adafuel) family. The estimation of the genetic and phenotypic parameters show the possibility of success by selecting superior genotypes, with gains of 9.09, 17.47 and 24% for RP, NR and RL, respectively.
  • Thumbnail Image
    Item type:Item,
    Selection for hypocotyl diameter results in genetic gain in common bean plant architecture
    (Crop Breeding and Applied Biotechnology, 2018) Anjos, Rafael Silva Ramos dos; Poersch, Nerison Luís; Batista, Lorena Guimarães; Moura, Lisandra Magna; Carneiro, José Eustáquio de Souza; Dias, Luiz Antônio dos Santos; Carneiro, Pedro Crescêncio Souza
    Studies highlight the hypocotyl diameter (HD) as an effective indicator of plant architecture (PA). Here, we estimated the genetic gain based on HD to improve PA. Twenty populations of cycles zero (C0) and one (C1), both in the F4 generation, were evaluated for PA, grain yield (GY) and HD. Plants with thickest HD in C0 were intercrossed in a circulant diallel mating design. In cycle C1, an estimated genetic gain of 4.93% was achieved for PA and 4.95% for HD. The populations with the highest probability of breeding lines with a thicker HD belong to cycle C1, and this selection strategy did not alter the GY of the populations of this cycle. Thus, indirect selection based on HD is promising for breeding for common bean PA by recurrent mass selection.