Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 12
Encontrada(s) 1 página(s)

IRTA Pubpro. Open Digital Archive
Publicación Artículo científico (JournalArticle)

Analysis of the causal structure of traits involved in sow lactation feed efficiency

  • Mora, Mónica
  • David, Ingrid
  • Gilbert, Hélène
  • Rosa, Guilherme J. M.
  • Sánchez, Juan Pablo
  • Piles, Miriam
Background Feed efficiency during lactation involves a set of phenotypic traits that form a complex system, with some traits exerting causal effects on the others. Information regarding such interrelationships can be used to predict the effect of external interventions on the system, and ultimately to optimize management practices and multi-trait selection strategies. Structural equation models can be used to infer the magnitude of the different causes of such interrelationships. The causal network necessary to fit structural equation models can be inferred using the inductive causation (IC) algorithm. By implementing these statistical tools, we inferred the causal association between the main energy sources and sinks involved in sow lactation feed efficiency for the first time, i.e., daily lactation feed intake (dLFI) in kg/day, daily sow weight balance (dSWB) in kg/day, daily litter weight gain (dLWG) in kg/day, daily back fat thickness balance (dBFTB) in mm/day, and sow metabolic body weight (SMBW) in kg0.75. Then, we tested several selection strategies based on selection indices, with or without dLFI records, to improve sow efficiency during lactation. Results The IC algorithm using 95% highest posterior density (HPD95%) intervals resulted in a fully directed acyclic graph, in which dLFI and dLWG affected dSWB, the posterior mean of the corresponding structural coefficients (PMλ) being 0.12 and − 0.03, respectively. In turn, dSWB influenced dBFTB and SMBW, with PMλ equal to 0.70 and − 1.22, respectively. Multiple indirect effects contributed to the variances and covariances among the analyzed traits, with the most relevant indirect effects being those involved in the association between dSWB and dBFTB and between dSWB and SMBW. Selection strategies with or without phenotypic information on dLFI, or that hold this trait constant, led to the same pattern and similar responses in dLFI, dSWB, and dLWG. Conclusions Selection based on an index including only dBFTB and dLWG records can reduce dLFI, keep dSWB constant or increase it, and increase dLWG. However, a favorable response for all three traits is probably not achievable. Holding the amount of feed provided to the sows constant did not offer an advantage in terms of response over the other strategies., info:eu-repo/semantics/publishedVersion
IRTA Pubpro. Open Digital Archive
Publicación Artículo científico (JournalArticle)

Novel phenotypes of feeding and social behaviour and their relationship with individual rabbit growth and feed efficiency

  • Piles, M.
  • Mora, M.
  • Kyriazakis, I.
  • Tusell Palomero, L.
  • Pascual, M.
  • Sanchez, J.P.
Due to the lack of a recording system for individual consumption of group-housed rabbits, published studies about feeding behaviour are based on information recorded at the group- and not at the individual level and periods covering only a few days or, in some cases, only part of a day. Such information could be used to inform rabbit management systems but cannot be used for genetic selection. We aimed to generate and use information from a novel automated feeder for group-housed rabbits to identify new phenotypes for individual animals that could be incorporated into breeding programs to improve feed efficiency and social behaviour under different feeding regimens. At 39 d of age, rabbits from 15 batches were placed in cages and fed ad libitum to become used to the electronic feeder. From 42 to 58–59 d, one group of 1 086 rabbits was fed ad libitum (AL), while another group of 1 134 rabbits was fed on a restricted feeding schedule (R) by limiting the feeding time to the period between 1800 and 0600 h of the following day. We implemented a reliable multivariate method to remove anomalous feeding behaviour records. We then defined novel traits for feeding behaviour that apply to both types of feeding regimes, and for social behaviour that indicates an animal’s rank within the cage hierarchy. We based these traits on feeder records and a biologically sound definition of a meal. Finally, we estimated the phenotypic correlations of those traits with growth and feed efficiency traits. Our findings demonstrate that variables about resource distribution among cage mates and an animal's priority for feed access were found to be good indicators of an animal's dominant or subordinate status within the cage. Based on results obtained in R animals (results were similar in AL animals), the most efficient animals were those that ate less frequently (phenotypic correlation with feed conversion ratio, rho = 0.6), and consumed smaller amounts per meal (rho = 0.7), spent less time at the feeder (rho = 0.4), and appeared to be subordinate, as they did not have priority access to the feeder (rho = −0.3), and had the smallest share of resources (range of rho = 0.2–0.6). We conclude that quantifying feeding and social behaviour traits can enhance the understanding of the mechanisms through which individuals exert their effects on the performance of their cage mates., This work has been funded by the Feed-a-Gene (grant agreement no. 633531), Genef (RTA2014-00015-C02), Genef2 (RTI2018-097610-R-I00) and Genef3 (PID2021-128173OR-C21) projects., info:eu-repo/semantics/publishedVersion
IRTA Pubpro. Open Digital Archive
Publicación Artículo científico (JournalArticle)

Feeding Behaviour in Group-Housed Growing-Finishing Pigs and Its Relationship with Growth and Feed Efficiency

  • Piles, Miriam
  • Tusell Palomero, Llibertat
  • Mora Fenoll, Mónica
  • Garcia-Baccino, Carolina
  • Cudrey, Denis
  • Hassenfratz, Claire
  • Mercat, Marie-José
  • David, Ingrid
Feed consumption and feeding patterns influence the individual feed efficiency in group-housed livestock species. Using the meal as the unit of feeding behaviour, the main objectives of this research were to identify feeding behaviour (FB) traits that may indicate an individual’s rank within the social hierarchy or its level of dominance among pen mates and to assess the relationship between growth and feed efficiency with the identified traits, as well as those describing individual feed consumption patterns. Data from 5516 pigs during the fattening period were used. Pens were equipped with an automatic concentrate feeder that recorded individual feed intake, time spent at the feeder, and body weight at each visit. A meal criterion was established. Then, different FB traits were computed: number of meals, number of visits to complete a meal, occupation time to complete a meal, time between first and last visit within a meal, feeding rate, feeding rate to complete a meal, and interval between meals. Social ranking (SR) traits were also calculated: position/order in which each animal accessed the feeder, ratio of visits to the feeder during preferred times, distribution among the cage mates of the total daily feed, number of visits, number of meals, and occupation time. Pigs that eat more and faster tend to have a poorer feed efficiency and higher final weight. Animals that eat more, more times, and occupy the feeder longer, eat mainly in the preferred period. They could be considered dominant, while others have to adapt their feeding schedules to off-peak times., This study was part of the project PID2021-128173OR-C21 (GENEF3), and M.M. is a recipient of a “Formacion de Personal Investigador (FPI)” associated with the research project RTI2018-097610R-I00., info:eu-repo/semantics/publishedVersion
IRTA Pubpro. Open Digital Archive
Publicación Artículo científico (JournalArticle)

Impact of multi-output and stacking methods on feed efficiency prediction from genotype using machine learning algorithms

  • Mora, Mónica
  • González, Pablo
  • Quevedo, José Ramón
  • Montañés, Elena
  • Tusell Palomero, Llibertat
  • Bergsma, Rob
  • Piles, Miriam
Feeding represents the largest economic cost in meat production; therefore, selection to improve traits related to feed efficiency is a goal in most livestock breeding programs. Residual feed intake (RFI), that is, the difference between the actual and the expected feed intake based on animal's requirements, has been used as the selection criteria to improve feed efficiency since it was proposed by Kotch in 1963. In growing pigs, it is computed as the residual of the multiple regression model of daily feed intake (DFI), on average daily gain (ADG), backfat thickness (BFT), and metabolic body weight (MW). Recently, prediction using single-output machine learning algorithms and information from SNPs as predictor variables have been proposed for genomic selection in growing pigs, but like in other species, the prediction quality achieved for RFI has been generally poor. However, it has been suggested that it could be improved through multi-output or stacking methods. For this purpose, four strategies were implemented to predict RFI. Two of them correspond to the computation of RFI in an indirect way using the predicted values of its components obtained from (i) individual (multiple single-output strategy) or (ii) simultaneous predictions (multi-output strategy). The other two correspond to the direct prediction of RFI using (iii) the individual predictions of its components as predictor variables jointly with the genotype (stacking strategy), or (iv) using only the genotypes as predictors of RFI (single-output strategy). The single-output strategy was considered the benchmark. This research aimed to test the former three hypotheses using data recorded from 5828 growing pigs and 45,610 SNPs. For all the strategies two different learning methods were fitted: random forest (RF) and support vector regression (SVR). A nested cross-validation (CV) with an outer 10-folds CV and an inner threefold CV for hyperparameter tuning was implemented to test all strategies. This scheme was repeated using as predictor variables different subsets with an increasing number (from 200 to 3000) of the most informative SNPs identified with RF. Results showed that the highest prediction performance was achieved with 1000 SNPs, although the stability of feature selection was poor (0.13 points out of 1). For all SNP subsets, the benchmark showed the best prediction performance. Using the RF as a learner and the 1000 most informative SNPs as predictors, the mean (SD) of the 10 values obtained in the test sets were: 0.23 (0.04) for the Spearman correlation, 0.83 (0.04) for the zero–one loss, and 0.33 (0.03) for the rank distance loss. We conclude that the information on predicted components of RFI (DFI, ADG, MW, and BFT) does not contribute to improve the quality of the prediction of this trait in relation to the one obtained with the single-output strategy., info:eu-repo/semantics/publishedVersion
IRTA Pubpro. Open Digital Archive
Publicación Artículo científico (JournalArticle)

Use of Bayes factors to evaluate the effects of host genetics, litter and cage on the rabbit cecal microbiota

  • Velasco-Galilea, María
  • Piles, Miriam
  • Ramayo-Caldas, Yuliaxis
  • Varona, Luis
  • Sánchez, Juan Pablo
Background The rabbit cecum hosts and interacts with a complex microbial ecosystem that contributes to the variation of traits of economic interest. Although the influence of host genetics on microbial diversity and specific microbial taxa has been studied in several species (e.g., humans, pigs, or cattle), it has not been investigated in rabbits. Using a Bayes factor approach, the aim of this study was to dissect the effects of host genetics, litter and cage on 984 microbial traits that are representative of the rabbit microbiota. Results Analysis of 16S rDNA sequences of cecal microbiota from 425 rabbits resulted in the relative abundances of 29 genera, 951 operational taxonomic units (OTU), and four microbial alpha-diversity indices. Each of these microbial traits was adjusted with mixed linear and zero-inflated Poisson (ZIP) models, which all included additive genetic, litter and cage effects, and body weight at weaning and batch as systematic factors. The marginal posterior distributions of the model parameters were estimated using MCMC Bayesian procedures. The deviance information criterion (DIC) was used for model comparison regarding the statistical distribution of the data (normal or ZIP), and the Bayes factor was computed as a measure of the strength of evidence in favor of the host genetics, litter, and cage effects on microbial traits. According to DIC, all microbial traits were better adjusted with the linear model except for the OTU present in less than 10% of the animals, and for 25 of the 43 OTU with a frequency between 10 and 25%. On a global scale, the Bayes factor revealed substantial evidence in favor of the genetic control of the number of observed OTU and Shannon indices. At the taxon-specific level, significant proportions of the OTU and relative abundances of genera were influenced by additive genetic, litter, and cage effects. Several members of the genera Bacteroides and Parabacteroides were strongly influenced by the host genetics and nursing environment, whereas the family S24-7 and the genus Ruminococcus were strongly influenced by cage effects. Conclusions This study demonstrates that host genetics shapes the overall rabbit cecal microbial diversity and that a significant proportion of the taxa is influenced either by host genetics or environmental factors, such as litter and/or cage., info:eu-repo/semantics/publishedVersion
IRTA Pubpro. Open Digital Archive
Publicación Artículo científico (JournalArticle)

Longitudinal modelling of performance and feed efficiency traits in growing Duroc pigs

  • Herrera-Cáceres, William
  • Ramayo-Caldas, Yuliaxis
  • Sánchez, Juan Pablo
In this study we used the phenotypic information of 1,499 Duroc pigs, recorded longitudinally in the age period from 110 to 200 days of age for individual daily feed intake (DFI), backfat thickness (BF) and live body weight (BW). Our aim was to estimate the genetic parameters for production and feed efficiency traits during the fattening period, with the objective to define, based on these parameters, the optimal moment for recording the phenotypes in order to maximize the expected response in a selection program to improve feed efficiency. Additionally to the aforementioned traits, two other traits were derived: average daily gain (ADG) and residual feed intake (RFI). The variance components for these traits were estimated through Bayesian procedures and using a multi-trait random regression animal model fitting Legendre polynomials of degree one. The estimated heritability patterns along the fattening were fairly flat, around 0.15(0.04), 0.37(0.05) and 0.34(0.09) for DFI, BF and DWG, respectively. RFI was the trait with the lowest heritability estimate, below 0.05 from 140d onwards. The only trait that showed relevant variation in the heritability estimate along the fattening period was BW, from 0.18(0.05) to 0.32(0.10). The correlations between performance at different moments of the fattening period and those at 120 days, was not always high. For the case of DFI and RFI these correlations reached values as low as 0.27(0.18) and -0.26(0.23). This points to a certain degree of genetic determinism variation along the studied period. Nonetheless, in particular for the feed efficiency trait (RFI), this variation seems irrelevant given the low estimated heritabilities and the low level of genetic heterogeneity along the fattening period., info:eu-repo/semantics/acceptedVersion
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Use of Bayes factors to evaluate the effects of host genetics, litter and cage on the rabbit cecal microbiota

  • Velasco-Galilea, María
  • Piles, Miriam
  • Ramayo-Caldas, Yuliaxis
  • Varona, Luis
  • Sánchez, Juan Pablo
Background The rabbit cecum hosts and interacts with a complex microbial ecosystem that contributes to the variation of traits of economic interest. Although the influence of host genetics on microbial diversity and specific microbial taxa has been studied in several species (e.g., humans, pigs, or cattle), it has not been investigated in rabbits. Using a Bayes factor approach, the aim of this study was to dissect the effects of host genetics, litter and cage on 984 microbial traits that are representative of the rabbit microbiota. Results Analysis of 16S rDNA sequences of cecal microbiota from 425 rabbits resulted in the relative abundances of 29 genera, 951 operational taxonomic units (OTU), and four microbial alpha-diversity indices. Each of these microbial traits was adjusted with mixed linear and zero-inflated Poisson (ZIP) models, which all included additive genetic, litter and cage effects, and body weight at weaning and batch as systematic factors. The marginal posterior distributions of the model parameters were estimated using MCMC Bayesian procedures. The deviance information criterion (DIC) was used for model comparison regarding the statistical distribution of the data (normal or ZIP), and the Bayes factor was computed as a measure of the strength of evidence in favor of the host genetics, litter, and cage effects on microbial traits. According to DIC, all microbial traits were better adjusted with the linear model except for the OTU present in less than 10% of the animals, and for 25 of the 43 OTU with a frequency between 10 and 25%. On a global scale, the Bayes factor revealed substantial evidence in favor of the genetic control of the number of observed OTU and Shannon indices. At the taxon-specific level, significant proportions of the OTU and relative abundances of genera were influenced by additive genetic, litter, and cage effects. Several members of the genera Bacteroides and Parabacteroides were strongly influenced by the host genetics and nursing environment, whereas the family S24-7 and the genus Ruminococcus were strongly influenced by cage effects. Conclusions This study demonstrates that host genetics shapes the overall rabbit cecal microbial diversity and that a significant proportion of the taxa is influenced either by host genetics or environmental factors, such as litter and/or cage., info:eu-repo/semantics/publishedVersion
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Novel phenotypes of feeding and social behaviour and their relationship with individual rabbit growth and feed efficiency

  • Piles, M.
  • Mora, M.
  • Kyriazakis, I.
  • Tusell Palomero, L.
  • Pascual, M.
  • Sanchez, J.P.
Due to the lack of a recording system for individual consumption of group-housed rabbits, published studies about feeding behaviour are based on information recorded at the group- and not at the individual level and periods covering only a few days or, in some cases, only part of a day. Such information could be used to inform rabbit management systems but cannot be used for genetic selection. We aimed to generate and use information from a novel automated feeder for group-housed rabbits to identify new phenotypes for individual animals that could be incorporated into breeding programs to improve feed efficiency and social behaviour under different feeding regimens. At 39 d of age, rabbits from 15 batches were placed in cages and fed ad libitum to become used to the electronic feeder. From 42 to 58–59 d, one group of 1 086 rabbits was fed ad libitum (AL), while another group of 1 134 rabbits was fed on a restricted feeding schedule (R) by limiting the feeding time to the period between 1800 and 0600 h of the following day. We implemented a reliable multivariate method to remove anomalous feeding behaviour records. We then defined novel traits for feeding behaviour that apply to both types of feeding regimes, and for social behaviour that indicates an animal’s rank within the cage hierarchy. We based these traits on feeder records and a biologically sound definition of a meal. Finally, we estimated the phenotypic correlations of those traits with growth and feed efficiency traits. Our findings demonstrate that variables about resource distribution among cage mates and an animal's priority for feed access were found to be good indicators of an animal's dominant or subordinate status within the cage. Based on results obtained in R animals (results were similar in AL animals), the most efficient animals were those that ate less frequently (phenotypic correlation with feed conversion ratio, rho = 0.6), and consumed smaller amounts per meal (rho = 0.7), spent less time at the feeder (rho = 0.4), and appeared to be subordinate, as they did not have priority access to the feeder (rho = −0.3), and had the smallest share of resources (range of rho = 0.2–0.6). We conclude that quantifying feeding and social behaviour traits can enhance the understanding of the mechanisms through which individuals exert their effects on the performance of their cage mates., This work has been funded by the Feed-a-Gene (grant agreement no. 633531), Genef (RTA2014-00015-C02), Genef2 (RTI2018-097610-R-I00) and Genef3 (PID2021-128173OR-C21) projects., info:eu-repo/semantics/publishedVersion
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Analysis of the causal structure of traits involved in sow lactation feed efficiency

  • Mora, Mónica
  • David, Ingrid
  • Gilbert, Hélène
  • Rosa, Guilherme J. M.
  • Sánchez, Juan Pablo
  • Piles, Miriam
Background Feed efficiency during lactation involves a set of phenotypic traits that form a complex system, with some traits exerting causal effects on the others. Information regarding such interrelationships can be used to predict the effect of external interventions on the system, and ultimately to optimize management practices and multi-trait selection strategies. Structural equation models can be used to infer the magnitude of the different causes of such interrelationships. The causal network necessary to fit structural equation models can be inferred using the inductive causation (IC) algorithm. By implementing these statistical tools, we inferred the causal association between the main energy sources and sinks involved in sow lactation feed efficiency for the first time, i.e., daily lactation feed intake (dLFI) in kg/day, daily sow weight balance (dSWB) in kg/day, daily litter weight gain (dLWG) in kg/day, daily back fat thickness balance (dBFTB) in mm/day, and sow metabolic body weight (SMBW) in kg0.75. Then, we tested several selection strategies based on selection indices, with or without dLFI records, to improve sow efficiency during lactation. Results The IC algorithm using 95% highest posterior density (HPD95%) intervals resulted in a fully directed acyclic graph, in which dLFI and dLWG affected dSWB, the posterior mean of the corresponding structural coefficients (PMλ) being 0.12 and − 0.03, respectively. In turn, dSWB influenced dBFTB and SMBW, with PMλ equal to 0.70 and − 1.22, respectively. Multiple indirect effects contributed to the variances and covariances among the analyzed traits, with the most relevant indirect effects being those involved in the association between dSWB and dBFTB and between dSWB and SMBW. Selection strategies with or without phenotypic information on dLFI, or that hold this trait constant, led to the same pattern and similar responses in dLFI, dSWB, and dLWG. Conclusions Selection based on an index including only dBFTB and dLWG records can reduce dLFI, keep dSWB constant or increase it, and increase dLWG. However, a favorable response for all three traits is probably not achievable. Holding the amount of feed provided to the sows constant did not offer an advantage in terms of response over the other strategies., info:eu-repo/semantics/publishedVersion
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Feeding Behaviour in Group-Housed Growing-Finishing Pigs and Its Relationship with Growth and Feed Efficiency

  • Piles, Miriam
  • Tusell Palomero, Llibertat
  • Mora Fenoll, Mónica
  • Garcia-Baccino, Carolina
  • Cudrey, Denis
  • Hassenfratz, Claire
  • Mercat, Marie-José
  • David, Ingrid
Feed consumption and feeding patterns influence the individual feed efficiency in group-housed livestock species. Using the meal as the unit of feeding behaviour, the main objectives of this research were to identify feeding behaviour (FB) traits that may indicate an individual’s rank within the social hierarchy or its level of dominance among pen mates and to assess the relationship between growth and feed efficiency with the identified traits, as well as those describing individual feed consumption patterns. Data from 5516 pigs during the fattening period were used. Pens were equipped with an automatic concentrate feeder that recorded individual feed intake, time spent at the feeder, and body weight at each visit. A meal criterion was established. Then, different FB traits were computed: number of meals, number of visits to complete a meal, occupation time to complete a meal, time between first and last visit within a meal, feeding rate, feeding rate to complete a meal, and interval between meals. Social ranking (SR) traits were also calculated: position/order in which each animal accessed the feeder, ratio of visits to the feeder during preferred times, distribution among the cage mates of the total daily feed, number of visits, number of meals, and occupation time. Pigs that eat more and faster tend to have a poorer feed efficiency and higher final weight. Animals that eat more, more times, and occupy the feeder longer, eat mainly in the preferred period. They could be considered dominant, while others have to adapt their feeding schedules to off-peak times., This study was part of the project PID2021-128173OR-C21 (GENEF3), and M.M. is a recipient of a “Formacion de Personal Investigador (FPI)” associated with the research project RTI2018-097610R-I00., info:eu-repo/semantics/publishedVersion
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Longitudinal modelling of performance and feed efficiency traits in growing Duroc pigs

  • Herrera-Cáceres, William
  • Ramayo-Caldas, Yuliaxis
  • Sánchez, Juan Pablo
In this study we used the phenotypic information of 1,499 Duroc pigs, recorded longitudinally in the age period from 110 to 200 days of age for individual daily feed intake (DFI), backfat thickness (BF) and live body weight (BW). Our aim was to estimate the genetic parameters for production and feed efficiency traits during the fattening period, with the objective to define, based on these parameters, the optimal moment for recording the phenotypes in order to maximize the expected response in a selection program to improve feed efficiency. Additionally to the aforementioned traits, two other traits were derived: average daily gain (ADG) and residual feed intake (RFI). The variance components for these traits were estimated through Bayesian procedures and using a multi-trait random regression animal model fitting Legendre polynomials of degree one. The estimated heritability patterns along the fattening were fairly flat, around 0.15(0.04), 0.37(0.05) and 0.34(0.09) for DFI, BF and DWG, respectively. RFI was the trait with the lowest heritability estimate, below 0.05 from 140d onwards. The only trait that showed relevant variation in the heritability estimate along the fattening period was BW, from 0.18(0.05) to 0.32(0.10). The correlations between performance at different moments of the fattening period and those at 120 days, was not always high. For the case of DFI and RFI these correlations reached values as low as 0.27(0.18) and -0.26(0.23). This points to a certain degree of genetic determinism variation along the studied period. Nonetheless, in particular for the feed efficiency trait (RFI), this variation seems irrelevant given the low estimated heritabilities and the low level of genetic heterogeneity along the fattening period., info:eu-repo/semantics/acceptedVersion
Recercat. Dipósit de la Recerca de Catalunya
Publicación Artículo científico (JournalArticle)

Impact of multi-output and stacking methods on feed efficiency prediction from genotype using machine learning algorithms

  • Mora, Mónica
  • González, Pablo
  • Quevedo, José Ramón
  • Montañés, Elena
  • Tusell Palomero, Llibertat
  • Bergsma, Rob
  • Piles, Miriam
Feeding represents the largest economic cost in meat production; therefore, selection to improve traits related to feed efficiency is a goal in most livestock breeding programs. Residual feed intake (RFI), that is, the difference between the actual and the expected feed intake based on animal's requirements, has been used as the selection criteria to improve feed efficiency since it was proposed by Kotch in 1963. In growing pigs, it is computed as the residual of the multiple regression model of daily feed intake (DFI), on average daily gain (ADG), backfat thickness (BFT), and metabolic body weight (MW). Recently, prediction using single-output machine learning algorithms and information from SNPs as predictor variables have been proposed for genomic selection in growing pigs, but like in other species, the prediction quality achieved for RFI has been generally poor. However, it has been suggested that it could be improved through multi-output or stacking methods. For this purpose, four strategies were implemented to predict RFI. Two of them correspond to the computation of RFI in an indirect way using the predicted values of its components obtained from (i) individual (multiple single-output strategy) or (ii) simultaneous predictions (multi-output strategy). The other two correspond to the direct prediction of RFI using (iii) the individual predictions of its components as predictor variables jointly with the genotype (stacking strategy), or (iv) using only the genotypes as predictors of RFI (single-output strategy). The single-output strategy was considered the benchmark. This research aimed to test the former three hypotheses using data recorded from 5828 growing pigs and 45,610 SNPs. For all the strategies two different learning methods were fitted: random forest (RF) and support vector regression (SVR). A nested cross-validation (CV) with an outer 10-folds CV and an inner threefold CV for hyperparameter tuning was implemented to test all strategies. This scheme was repeated using as predictor variables different subsets with an increasing number (from 200 to 3000) of the most informative SNPs identified with RF. Results showed that the highest prediction performance was achieved with 1000 SNPs, although the stability of feature selection was poor (0.13 points out of 1). For all SNP subsets, the benchmark showed the best prediction performance. Using the RF as a learner and the 1000 most informative SNPs as predictors, the mean (SD) of the 10 values obtained in the test sets were: 0.23 (0.04) for the Spearman correlation, 0.83 (0.04) for the zero–one loss, and 0.33 (0.03) for the rank distance loss. We conclude that the information on predicted components of RFI (DFI, ADG, MW, and BFT) does not contribute to improve the quality of the prediction of this trait in relation to the one obtained with the single-output strategy., info:eu-repo/semantics/publishedVersion