We invite you to read our new article https://www.mdpi.com/2073-4425/14/8/1650. We present the artificial intelligence free software application called SAMBA (Structure-Learning of Aquaculture Microbiomes Using a Bayesian-Network Approach). The application has been developed in collaboration with Professor Jaume Pérez and his team from the Torre de la Sal Aquaculture Institute (IATS) and with Professor Vicente Arnau from the i2sysbio center of the University of Valencia.
SAMBA uses Bayesian networks to model and infer the interrelationships between microbiomes and other biotic and abiotic variables that intervene in the dynamics of a given system. Although it has been tested with data from sea bream, SAMBA is not restricted to fish farming and aquaculture, but is capable of adapting to data from other systems and/or vertebrate organisms, including humans. This is because it accepts input data on the microbial abundance of 16s rRNA amplicons, as well as continuous and categorical information from different experimental or environmental conditions. From this, SAMBA can create and train a network model scenario that can be used to infer information about how specific environmental or experimental conditions influence gut microbiome or pan-microbiome diversity, and predict how diversity and functional profile of that microbiome would change under other conditions.
Accessing to GitHub you can test all the features of SAMBA with two example datasets and an user manual: https://github.com/biotechvana/SAMBA/
Please, report us your opinion
SAMBA uses Bayesian networks to model and infer the interrelationships between microbiomes and other biotic and abiotic variables that intervene in the dynamics of a given system. Although it has been tested with data from sea bream, SAMBA is not restricted to fish farming and aquaculture, but is capable of adapting to data from other systems and/or vertebrate organisms, including humans. This is because it accepts input data on the microbial abundance of 16s rRNA amplicons, as well as continuous and categorical information from different experimental or environmental conditions. From this, SAMBA can create and train a network model scenario that can be used to infer information about how specific environmental or experimental conditions influence gut microbiome or pan-microbiome diversity, and predict how diversity and functional profile of that microbiome would change under other conditions.
Accessing to GitHub you can test all the features of SAMBA with two example datasets and an user manual: https://github.com/biotechvana/SAMBA/
Please, report us your opinion