SYSTEMS AND METHODS FOR SELECTING RECOMMENDED CROSSES WITH INCREASED AN PROBABILITY OF MEETING PLANT-BASED PRODUCT SPECIFICATIONS
A computer-based method for selecting recommended crosses from a population of plants with an increased probability of meeting a plant-based product specification, comprising: (a) collecting plant data for the plant population including at least labelled parentage information including genetic and phenotype information; (b) training a machine learning model mapping phenotypes to genotype based on the collected data; (c) extracting a target list including one or more phenotypes needed to meet the product specification; (d) simulating pairwise combinations of one or more available parents using rapid recombination simulation; (e) applying the phenotype-to-genotype mapping to predict phenotypes for each simulated combination; (f) selecting the simulated combinations that meets phonetic criteria on target list; (g) simulating selfed combinations of each selected simulated combination using rapid recombination simulation; (h) repeating (e) through (g) until F3 generation is simulated; and (i) creating a predictive crossing list of simulated F3 progeny that meets the product specification.
1 . A method for selecting recommended crosses from a population of plants in a germplasm with an increased probability of meeting a plant-based product specification, comprising:
(a) collecting into a database, with a processor, plant data for the population of plants in the germplasm, such plant data comprising at least labelled parentage information that includes genetic and phenotype information;
(b) training, with the processor, a machine learning model mapping phenotypes to genotype based on the data collected into the database;
(c) extracting, via the processor, a target selection list including one or more phenotypes needed to meet the plant-based product specification;
(d) simulating, via the processor, pairwise combinations of one or more available parents using rapid recombination simulation;
(e) applying, via the processor, the phenotype-to-genotype mapping to predict one or more phenotypes for each simulated pairwise combination;
(f) selecting, via the processor, the simulated pairwise combinations that at least meets phonetic criteria on the target selection list;
(g) simulating, via the processor, selfed combinations of each selected simulated pairwise combinations using rapid recombination simulation;
(h) repeating (e) through (g) until an F3 generation has been simulated; and
(i) creating a predictive crossing list of simulated F3 progeny that meets the product specification.
2 . The method according to claim 1 further comprising ranking potential crosses on the predictive crossing list to promote one or more goals selected from the group comprising: (a) maximizing one or more desired phenotypic results; (b) ensuring diversification across maturity subgroups; (c) ensuring genetic diversity; and (d) commercial feasibility of progeny.
3 . The method according to claim 2 wherein ensuring diversification further comprises limiting the number of crosses that involve a particular parent from the existing germplasm or contain any single pedigree.
4 . The method according to claim 2 wherein promoting commercial feasibility of progeny may comprise giving greater preference to selection of maturity groups supported by geographical considerations.
5 . A system for selecting recommended crosses from a population of plants in a germplasm with an increased probability of meeting a plant-based product specification, comprising:
(a) a database containing plant data for the population of plants in the germplasm, such plant data comprising at least labelled parentage information that includes genetic and phenotype information;
(b) a processor operably connected to the database that (1) trains a machine learning model mapping phenotypes to genotype based on the data collected into the database, (2) extracts a target selection list including one or more phenotypes needed to meet the plant-based product specification, (3) simulates pairwise combinations of one or more available parents using rapid recombination simulation, (4) applies the phenotype-to-genotype mapping to predict one or more phenotypes for each simulated pairwise combination, (5) selects the simulated pairwise combinations that at least meets phonetic criteria on the target selection list, (6) simulates selfed combinations of each selected simulated pairwise combinations using rapid recombination simulation, repeats (4) through (6) until an F3 generation has been simulated; and (7) creates a predictive crossing list of simulated F3 progeny that meets the product specification.
6 . The system according to claim 5 wherein the processor further ranks potential crosses on the predictive crossing list to promote one or more goals selected from the group comprising: (a) maximizing one or more desired phenotypic results; (b) ensuring diversification across maturity subgroups; (c) ensuring genetic diversity; and (d) commercial feasibility of progeny.
7 . The system according to claim 6 wherein ensuring diversification further comprises limiting the number of crosses that involve a particular parent from the existing germplasm or contain any single pedigree.
8 . The system according to claim 6 wherein promoting commercial feasibility of progeny may comprise giving greater preference to selection of maturity groups supported by geographical considerations.