Methods and systems for use in implementing resources in plant breeding

Patent metadata

Field	Value
Publication number	US-12137651-B2
Application number	US-202318109146-A
Country	US
Kind code	B2
Filing date	Feb 13, 2023
Priority date	Mar 28, 2019
Publication date	Nov 12, 2024
Grant date	Nov 12, 2024

Abstract

Exemplary systems and methods are disclosed for allocating resources in a breeding pipeline to multiple origins. One exemplary method includes accessing a data structure including data representative of multiple origins, in which the data includes, for each of the multiple origins, a trait performance expression or genotypic component information. The exemplary method further includes determining a resource allocation, which allocates n resources among the multiple origins based on a probability associated with the trait performance expressions and/or the genotypic components for the origins, and then allocating the n resources in the breeding pipeline for the multiple origins, based on the determined resource allocation.

First claim

What is claimed is:

1. A computer-implemented method for allocating resources in a breeding pipeline to multiple origins, the method comprising:
for multiple origins, accessing a data structure including data representative of the multiple origins, the data including, for each of the multiple origins, a trait performance expression and/or genotypic components;
determining, by at least one computing device, a resource allocation, which allocates n resources among the multiple origins, based on: (i) a probability associated with the trait performance expressions and/or genotypic components for the origins, and (ii) a predefined target portfolio, wherein n is an integer, and whereby a relative value for each potential resource allocation is diminished based on a deviation of the resource allocation from the predefined target portfolio; and
allocating the n resources in a breeding pipeline for the multiple origins, based on the determined resource allocation.

2. The c method of claim 1 , wherein determining the resource allocation includes determining the resource allocation based on a comparison of:

value
⁢

∑

i
=
1

N

-

λ
1

⁢

ℙ
⁡
(

θ
i

>
η

)

⁢

x
i

+

λ
2

[

ℙ
⁡
(

θ
i

>
η

)

⁢

(

1
-

ℙ
⁡
(

θ
i

>
η

)

)

⁢

U
i

⁢

x
i

]

+

λ
3

⁢



TI
H

⁢
x

-
ξ



1

for multiple potential resource allocations;
wherein N is a number of the potential allocations; λ 1 , λ 2 , and λ 3 are weighting variables, η is a target threshold for breeding value; θ i is a variable for a breeding value, or a vector thereof, for the specific origin; is the probability of finding a breeding value, or a vector thereof, larger than some threshold for the specific origin; U i is a confidence level of genetic learning for a specific origin; T is a transition probability matrix; I H is an incidence matrix for mapping heterotic pools; x is a selected one of the multiple origins; ξ is a target portfolio of breeding objectives; and x i is an integer decision variable for resources allocated to the specific origin.

3. The method of claim 2 , wherein at least one of the n resources is allocated in the resource allocation to each of the multiple origins;
wherein each of the n resources is allocated in the resource allocation to one of the multiple origins;
wherein determining the resource allocation for a hybrid crop in which male and female heterotic pools are kept separate includes determining the resource allocation, subject to:
M T y≥mα M ,
F T y≥Mα F ,
and
α M +α F ≤1;

wherein M is the male incidence vector; α M is the minimum fraction of m origins that are designated to be devoted to male crosses; F is the female incidence vector; T is a transition probability matrix; y is the binary selection variable that indicates which of the multiple origins have been selected; and α F is the minimum fraction of m origins that are designated to be devoted to female crosses; and
whereby the n resources are able to be properly allocated to each heterotic pool without exceeding the maximum m origins.

4. The method of claim 1 , wherein at least one of the n resources is allocated in the resource allocation to each of the multiple origins; and wherein each of the n resources is allocated in the resource allocation to one of the multiple origins.

5. The method of claim 4 , wherein determining the resource allocation for a hybrid crop in which male and female heterotic pools are kept separate includes determining the resource allocation, subject to:
M T y≥mα M ,
F T y≥Mα F ,
and
α M +α F ≤1;

wherein M is the male incidence vector; α M is the minimum fraction of m origins that are designated to be devoted to male crosses; F is the female incidence vector; T is a transition probability matrix; y is the binary selection variable that indicates which of the multiple origins have been selected; and α F is the minimum fraction of m origins that are designated to be devoted to female crosses; and
whereby the n resources are able to be properly allocated to each heterotic pool without exceeding the maximum m origins.

6. The method of claim 1 , wherein determining the resource allocation includes determining the resource allocation based on a confidence in the trait performance expression and/or the genotypic components for each of the multiple origins.

7. The method of claim 1 , further comprising planting a plant product based on at least one of the multiple origins and at least one progeny from the multiple origins.

8. A system for allocating resources in a breeding pipeline, the system comprising:
a data structure including data representative of multiple selected origins, the data including a trait performance expression and/or genotypic components for each of the multiple selected origins; and
a computing device coupled in communication with the data structure and configured to:
access data in the data structure for each of the multiple selected origins; and
determine a resource allocation, which a

Assignees

• Monsanto Technology Llc

Inventors

• Chavali Srinivas Phani Kumar
• Dasgupta Sambarta
• Dong Qianni
• Gutierrez Gaitan Humberto Ignacio
• Kovacs Anthony Paul
• Moran Jorge Luis
• Ocheya Silvano Assanga
• Stewart-Brown Benjamin Bruce
• Wang Zi
• Yu Chong

Classifications

• G06N3/126

  Evolutionary algorithms, e.g. genetic algorithms or genetic programming · CPC title

• G06Q10/0631

  Resource planning, allocation, distributing or scheduling for enterprises or organisations · CPC title

• G16B20/00

  ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations · CPC title

• G06Q50/02

  Agriculture; Fishing; Forestry; Mining · CPC title

• A01H1/04 Primary

  Processes of selection {involving genotypic or phenotypic markers; Methods of using phenotypic markers for selection} · CPC title