WO2024099985A1 - Targeted crop protection product application based on genetic profiles - Google Patents

Abstract

Systems, methods, and computer programs disclosed herein relate to determining the efficacy of one or more crop protection products against harmful organisms based on a genetic profile.

Description

TARGETED CROP PROTECTION PRODUCT APPLICATION BASED ON GENETIC PROFILES

Field

Systems, methods, and computer programs disclosed herein relate to determining the efficacy of one or more crop protection products against harmful organisms based on a genetic profile.

Background

Ensuring global food security requires investments into a sustainable agricultural production of crops. Harmful organisms like phytopathogenic fungi, insects and bacteria are a significant risk for food production in every vegetation period. Strategies to control such harmful organisms include the use of crop protection products, however harmful organisms continue to evolve to become even more aggressive and more capable to adapt to their respective hosts. In particular phytopathogenic fungi and insects are capable through genetic mutation not only in the target gene for the crop protection product but also through mutation of other genes involved in metabolization or detoxification of pesticides to escape the action of the crop protection product. This mechanism is known as pesticide resistance. Different factors play a role in the development of such resistance such as agronomic methods, the harmful organism involved, rates and timing of the application of crop protection products and the affected crop. At the same time there is an overall effort to reduce the amount of chemical crop protection products used in agriculture and minimizing environmental impact. Therefore, there is the need to develop methods which allow a highly tailored, automated and precise application of crop protection products, in particular in a location-specific manner, in order to control harmful organisms and also minimise the development of pesticide resistance.

WO2021/228578A1 describes a method to identify variants in a location-specific manner in the field, determine their sequence information and compare that information to known resistance markers or predicted structures such as alphafolds to estimate the variants’ impact on inhibitor binding. Identifying resistance using DNA or RNA analysis allows a very early detection of resistant harmful organism in a field.

In WO2022/099169A1 a method is described to correlate frequency of certain genotypes with resistance using a pesticide resistance factor and geographic location in order to generate a map.

However, the information that a harmful organism with resistance is present in a field does not yet contain any information about how the resistance affects the efficacy of a crop protection product nor does it contain information about selecting alternative crop protection products providing better efficacy. In addition, the information that a harmful organism with resistance is present in a farmer' s field does not yet provide the farmer with information on how he/she can effectively control the harmful organism despite the presence of resistance.

Summary

These and further problems are addressed by the present disclosure.

The present disclosure goes one step further by not only analyzing sequence information from one specific variant but instead using a model in which genetic profiles comprising one or more variants are correlated to efficacy data of one or more crop protection products and optionally other agricultural data.

Therefore, in a first aspect, the present disclosure relates to a computer-implemented method comprising: receiving a genetic profile of one or more harmful organisms from an agricultural or horticultural area, the genetic profile comprising one or more variants; determining one or more biological targets based on the genetic profile; determining one or more active ingredients addressing the one or more biological targets; determining an expected efficacy of a crop protection product comprising the one or more active ingredients using a model in which, for a multitude of crop protection products, their efficacy is related to one or more genetic profiles of one or more harmful organisms; outputting the expected efficacy of the crop protection product.

In another aspect, the present disclosure provides a computer system comprising: a processor; and a memory storing an application program configured to perform, when executed by the processor, an operation, the operation comprising: receiving a genetic profile of one or more harmful organisms from an agricultural or horticultural area, the genetic profile comprising one or more variants; determining one or more biological targets based on the genetic profile; determining one or more active ingredients addressing the one or more biological targets; determining an expected efficacy of a crop protection product comprising the one or more active ingredients using a model in which, for a multitude of crop protection products, their efficacy is related to one or more genetic profiles of one or more harmful organisms; outputting the expected efficacy of the crop protection product. In another aspect, the present disclosure provides a non-transitory computer readable storage medium having stored thereon software instructions that, when executed by a processor of a computer system, cause the computer system to execute the following steps: receiving a genetic profile of one or more harmful organisms from an agricultural or horticultural area, the genetic profile comprising one or more variants; determining one or more biological targets based on the genetic profile; determining one or more active ingredients addressing the one or more biological targets; determining an expected efficacy of a crop protection product comprising the one or more active ingredients using a model in which, for a multitude of crop protection products, their efficacy is related to one or more genetic profiles of one or more harmful organisms; outputting the expected efficacy of the crop protection product.

Further aspects as well as preferred embodiments are defined in the dependent claims, the description and the drawings.

Detailed Description

The invention will be more particularly elucidated below without distinguishing between the aspects of the disclosure (method, computer system, computer-readable storage medium). On the contrary, the following elucidations are intended to apply analogously to all the aspects of the disclosure, irrespective of in which context (method, computer system, computer-readable storage medium) they occur.

If steps are stated in an order in the present description or in the claims, this does not necessarily mean that the invention is restricted to the stated order. On the contrary, it is conceivable that the steps can also be executed in a different order or else in parallel to one another, unless one step builds upon another step, this absolutely requiring that the building step be executed subsequently (this being, however, clear in the individual case). The stated orders are thus preferred embodiments of the present disclosure.

As used herein, the articles “a” and “an” are intended to include one or more items and may be used interchangeably with “one or more” and “at least one.” As used in the specification and the claims, the singular form of “a”, “an”, and “the” include plural referents, unless the context clearly dictates otherwise. Where only one item is intended, the term “one” or similar language is used. Also, as used herein, the terms “has”, “have”, “having”, or the like are intended to be open-ended terms.

Further, the phrase “based on” is intended to mean “based at least partially on” unless explicitly stated otherwise. Some implementations of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings, in which some, but not all implementations of the disclosure are shown. Indeed, various implementations of the disclosure may be embodied in many different forms and should not be construed as limited to the implementations set forth herein; rather, these example implementations are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

The present disclosure provides means for determining the efficacy of one or more crop protection products against one or more harmful organisms.

The term "crop protection product" refers to a composition which is used to protect plants or plant products from harmful organisms or to prevent such exposure, to destroy unwanted plants or plant parts and/or to inhibit unwanted growth of plants or to prevent such growth. Examples of crop protection products are herbicides, insecticides, nematicides, acaricides, or fungicides. A crop protection product typically comprises one or more active ingredients.

An "active ingredient" is a chemical or biological substance which in an organism has a specific effect or evokes a specific response.

A "harmful organism" is an organism which acts as a causative organism or transmitter of diseases in humans or animals or which is capable of damaging crop plant, adversely affecting the harvesting of the crop plant, or competing with the crop plant for natural resources. Examples of harmful organisms are vectors, broadleaf weeds, gramineous weeds, animal pests such as beetles, mites, spiders, caterpillars, nematodes, arachnids, snails, slugs, and worms, and pathogenic microorganisms like fungi, bacteria, oomycetes, and viruses. Although viruses, biologically speaking, are not counted as organisms, they are nevertheless intended presently to come under the heading of harmful organisms. A harmful organism may also be a weed. In one embodiment the species of the harmful organism is provided or received. In another embodiment, the strain, cultivar or subtype of a species is provided or received. Strain, cultivars or subtypes represent genetic variations within a species.

The term "weed" (plural: weeds) refers to plants of the spontaneous accompanying vegetation (segetal flora) in stands of crop plants, on grassland or in gardens, these plants being not deliberately grown in those settings and developing, for example, from the soil seed potential or being airborne. The term is not confined to broadleaf plants in the strict sense, but instead also encompasses grasses, fems, mosses, or woody plants. In the area of crop protection, another term frequently utilized is "gramineous weed" (plural: gramineous weeds), in order to clarify a delimitation from the herbaceous plants. In the present text, the term "weed" is used as a generic term, intended also to encompass the term gramineous weed, unless reference is made to specific broadleaf or gramineous weeds.

The term “efficacy” means the ability to produce a desired or intended result. With respect to the present disclosure, "efficacy" preferably means the ability of an active ingredient or crop protection product to exert its effect on a harmful organism, i.e., to weaken, kill, or render the harmful organism harmless. Efficacy may be measured by any method suitable to determine

than one, variant sites within the gene sequence. Other terms known in the art to be equivalent to "variants" include mutations and single nucleotide polymorphisms (SNPs). Reference to the presence of a variant or variants means particular variants, i.e., particular nucleotides at particular polymorphic sites, rather than just the presence of any variant in the gene. Variants is one embodiment of genetic information. In one embodiment a variant relates to genetic information describing the resistance of an organism against crop protection products.

Genetic information means any information on the genetic properties of an organism, including but not limited to DNA, sequence, RNA sequence, parts of DNA and/or RNA sequences, molecular structure of DNA or RNA, epigenetic information (e.g. methylation of DNA parts), information on gene mutations, information on gene copy number variation, information on overexpression of a gene, in formation on expression level of a gene, information on gene shifting, information on the ratio between wild type and mutants, information on the ratio between different mutants, information on the ratio between mutants and other variants (e.g. epigenetic variants), information on the ratio of different variants (e.g. epigenetic variants), information on a type of plant disease (e.g. Septoria, yellow rust, Asian soybean rust) or other diseases. In the context of the present invention, the term "genetic information" also includes the information that certain wild types, mutants, or variants (e.g. epigenetic variants) or DNA/RNA sequences, or parts of the DNA/RNA sequences, or specific epigenetic information are absent In the context of the present invention, the term "genetic information" also includes the information that specific genetic information is absent (e.g. that the information that a specific type of Septoria is absent is also a genetic information). In a preferred embodiment of the present invention, genetic information" is at least one of the following information: DNA sequence, RNA sequence, parts of DNA and/or RNA sequences, molecular structure of DNA and/or RNA, epigenetic information (e.g. methylation of DNA parts), information on gene mutations, information on gene copy number variation, information on overexpression of a gene, information on expression level of a gene, information on gene shifting, information on the ratio between wild type and mutants, information on the ratio between different mutants, information on the ratio between mutants and other variants (e.g. epigenetic variants), information on the ratio of different variants (e.g. epigenetic variants), information on a type of plant disease (e.g. Septoria, yellow rust, Asian soybean rust) or other diseases. In another preferred embodiment of the present invention, genetic information" is at least one of the following information: DNA sequence, RNA sequence, molecular structure of DNA and/or RNA, parts of DNA and/or RNA sequences, epigenetic information (e.g. methylation of DNA parts). In another preferred embodiment of the present invention, genetic information" is at least one of the following information: DNA sequence, RNA sequence. In another preferred embodiment of the present invention, genetic information" is at least one of the following information: information on gene mutations, information on gene copy number variation, information on overexpression of a gene, information on expression level of a gene, information on gene shifting, information on the ratio between wild type and mutants, information on the ratio between different mutants, information on the ratio between mutants and other variants (e.g epigenetic variants), information on the ratio of different variants (e.g. epigenetic variants), information on a type of plant disease (e.g. Septoria, yellow rust, Asian soybean rust) or other diseases. In another preferred embodiment of the present invention, genetic information" is at least one of the following information: information on gene mutations, information on gene copy number variation, information on overexpression of a gene, information on expression level of a gene, information on gene shifting. In another preferred embodiment of the present invention, genetic information" is at least one of the following information: information on the ratio between wild type and mutants, information on the ratio between different mutants, information on the ratio between mutants and other variants (e.g. epigenetic variants), information on the ratio of different variants (e.g. epigenetic variants).

"Isoform" as used herein means a particular form of a gene, mRNA, cDNA or the protein encoded thereby, distinguished from other forms by its particular sequence and/or structure.

"Haplotype" means a genetic variant or combination of variants carried on at least one chromosome of one strain of a harmful organism. A haplotype often includes multiple contiguous polymorphic loci. All parts of a haplotype as used herein occur on the same copy of a chromosome or haploid DNA molecule. Absent evidence to the contrary, a haplotype is presumed to represent a combination of multiple loci that are likely to be transmitted together during meiosis. Each harmful organism carries at least one haplotype for any given genetic locus, consisting of sequences inherited on the homologous chromosomes from the parents. These haplotypes may be identical or may represent one or more different genetic variants for the given locus. Haplotyping is a process for determining one or more haplotypes in an individual. Haplotyping may include use of family pedigrees, molecular techniques and/or statistical inference.

"Polymorphism" means the existence of two or more different nucleotide sequences at a particular locus in the DNA of the genome. Polymorphisms can serve as genetic markers and may also be referred to as variants. Polymorphisms include nucleotide substitutions, insertions, deletions and microsatellites, and may, but need not, result in detectable differences in gene expression or protein function. A polymorphic site is a nucleotide position within a locus at which the nucleotide sequence varies from a reference sequence in at least one individual in a population. A "deletion/insertion polymorphism" or "DIP" as used herein is an insertion of one or more nucleotides in one version of a sequence relative to another. If it is known which of the alleles represent minor alleles, the term "deletion" is used when the minor allele is a deletion of a nucleotide, and the term "insertion" is used when the minor allele is an addition of a nucleotide. The term "deletion/insertion polymorphism" is also used when there are multiple forms or lengths and the minor allele is not apparent. For example, for the poly-T polymorphisms described herein, multiple lengths of polymorphisms are observed. "Genetic locus" or "locus" as used herein means a location on a chromosome or DNA molecule, often corresponding to a gene or a physical or phenotypic feature or to a particular nucleotide or stretch of nucleotides. Loci is the plural form of locus.

The genetic profile is preferably in the form of digital data. "Digital" means that the data can be processed by a machine, for example a computer system.

The term “receive data” means accept, retrieve, and/or obtain data from one or more sources. The genetic profile can be entered into the computer system of the present disclosure by a user thereof (e.g., by a farmer), and/or may be read from one or more data storage devices, and/or may be transmitted from one or more separate computer systems and/or devices (for example, a device for the sequencing of genes in a sample).

In order to generate a genetic profile in a first step, a sample has to be collected from an agricultural or horticultural area.

A sample may comprise soil, water, air, a plant, a seedling or a plant part such as a leave, stem, flower, root, seed either being a weed or infected or in the danger of being infect by a harmful organism such as pests, fungi, bacteria, oomycete, or virus.

The term "collecting" should not be understood in any way as limiting. One example of a synonymous term is the term "sampling".

The sampling that takes place may be automated. "Automated" means that the sampling is accomplished without human input, by a machine or by a plurality of machines. Analogously, the steps of ascertaining geocoordinates, processing the sample, sequencing, analyzing DNA and/or RNA sequences, and/or entering information about resistance into a resistance map may also be automated.

Sampling may take place with the aid of a portable device carried by a human or by means of a vehicle which, for example, moves or is moved in a field for crop plants and/or moves or is moved over the field. Conceivable, for example, is the use of a (preferably unmanned) land machine and/or of a (preferably unmanned) aircraft (e.g., a drone) and/or of a robot. Sampling may alternatively be accomplished by one or more devices which are constructed in stationary form at a location. It is conceivable, furthermore, for a user to carry with them a mobile device, to carry out sampling themselves, and to supply the sample to the device.

The nature of the sample is dependent on the harmful organism for which the aim is to examine whether individuals are present which are developing or have developed resistance to one or more crop protection products. The sample comprises one or more harmful organism or part of one or more harmful organisms. Sampling may be assisted by image recognition techniques. It is conceivable, for example, for a camera to generate digital images of the plants in the field, and for the images to be transmitted to an image analysis unit. The image analysis unit is configured to identify features in the images that point to the presence of a harmful organisms such as broadleaf/gramineous weed and/or crops infested with one or more harmful organisms. The images may be analyzed using, for example, techniques of pattern recognition or else selflearning systems (e.g., artificial neural networks). It is conceivable forthe image analysis unit to be configured to recognize one or more defined gramineous/broadleaf weed species and/or symptoms caused by the one or more harmful organisms. Also conceivable is for the image analysis unit to be configured to recognize that a plant in the image is not the crop plant being grown (and hence is a plant which may compete with the crop plant for resources and/or affect the quality of the harvest). Methods and systems for recognition of broadleaf/gramineous weeds and/or crops infested with one or more harmful organisms are described in the prior art (see, for example, WO2017/194398A1, WO2017/194399A1). Also conceivable, however, is for a sample to be taken from a plant which can be assumed to be a broadleaf/gramineous weed, because, for example, it is growing in a place where no crop plant has been planted/sown or it has already developed to a further stage than the crop plants planted/sown in the field.

Where the harmful organism is a fungus, virus, oomycete or bacterium, a sample is preferably taken from the infested organism (in/on which the fungus or the virus or the bacterium is located). The infested organism may be identified, for example, by image recognition techniques; for example, the company Peat GmbH offers, on a commercial basis, a software application ("app") for identifying plant diseases on the basis of image recognition techniques (https://plantix.net/de).

Where the harmful organism is an animal pest - such as, for example, an insect (in the various stages of eggs, larva, caterpillar, pseudocaterpillar through to the adult stage), a slug or snail, a worm (nematodes), or an arachnid - it is possible to use a trap to catch the animal pest, to then supply said pest (or parts of it) for analysis. For the capture of animal harmful organisms there are a multiplicity of options, such as, for example, glue-coated panels, pan traps (pans filled with water and a surfactant, for example), and the like. A trap may be provided with a bait to attract the animal pest.

In one embodiment the sample is taken from air, water and/or soil samples in which harmful organisms are located. Sampling of animal excretions is also conceivable.

In one embodiment the reason for the sampling is that a harmful organism has been observed - for example, by inspection or automatically by means of image recognition techniques.

In one embodiment the sampling has taken place as a result of the suspected incidence of the harmful organism. It is conceivable, for example, that, using a forecast model, a risk of infestation with the harmful organism has been ascertained, the risk lying above a defined threshold value. It is conceivable that infestation has been observed in the vicinity of the location at which a sample is collected.

In one embodiment the reason for the sampling is a suspicion of existing or oncoming resistance. It is conceivable, for example, for an observation to have been made, when controlling a harmful organism with a crop protection product, that the crop protection product is not developing the desired effect.

In one embodiment one or more samples may be taken at a single location. In one embodiment one or more samples are taken each at more than one location.

For those locations at which one or more samples are/have been taken, the geocoordinates associated with the location are ascertained. This is important to enable information concerning a resistance to be associated with the corresponding location and entered in a resistance map.

The geocoordinates are typically ascertained using a positional determination system. One known positional determination system is a satellite navigation system such as NAVSTAR GPS, GLONASS, Galileo, or Beidou, for example. Given that the abbreviation GPS (Global Positioning System) is established in everyday language as a generic designation for all satellite navigation systems, the term GPS is used hereinafter as a collective designation for all positional determination systems.

In one embodiment the sampling device possesses a GPS sensor. A mobile device may move, for example, through a field for crop plants, take one or more samples at a plurality of locations, use the GPS sensor to ascertain the geocoordinates of the locations at which samples have been taken, and store this information in a data memory of the device and/or transmit this information via a (mobile) network to an external computer system. It is also conceivable for the mobile device to travel, using the GPS sensor, to one or more locations defined beforehand. For example, a forecast model might have ascertained one or more locations at which there is an increased risk of the incidence of (resistant) harmful organisms. These locations could be found by the mobile device, in order to take one or more samples at these locations. When a sample has been taken and when the sample has been analyzed, the result of the analysis may be stored together with the geocoordinates in a data memory of the device and/or transmitted via a (mobile) network to an external computer system.

In one embodiment a mobile device may be moved by a user. At the location at which the user is taking a sample, the geocoordinates of the sampling location are ascertained/logged. It is conceivable for the user to be guided, with the aid of a GPS sensor, by the mobile device to locations defined beforehand. In that case the user may be assisted by technologies of augmented reality. With these technologies, a real world is displayed on a screen and this display is extended optically by computer-generated pieces of extra information. It is conceivable, for example, to display the real world on the screen of a computer system (e.g., smartphone) in what is called live mode and to augment this display with virtual objects which represent the traps that have been set and are to be found. Also conceivable is the use of a head-up display or of a head-mounted display (e.g., video glasses (Eye Tap)). Also conceivable is that the user is guided to traps for harmful organisms that have been set beforehand, the guidance being carried out using GPS sensor and, optionally, technologies of augmented reality.

Where the device for sampling is a stationary unit, that may likewise be equipped with a GPS sensor in order to be able to log/ascertain its position. Preferably, however, its position is already determined or confirmed at the time the device is set up. It may be the case, for example, that a device is set up at a location and then with a (separate) GPS sensor the geocoordinates of the location of the set-up device are determined. Also conceivable is that the geocoordinates of a location at which a device is to be set up are determined, and then the device is set up at the position determined accordingly. The situation of the device may for example be/have been noted in a database and/or on a digital map. It may be the case that a device possesses an unambiguous identifier (for example, an ID number). Where such a device transmits information about a sample to an external computer system, it authenticates itself by means of the unambiguous identifier, for example. A database may contain a record of the position at which a particular device with a particular identifier has been set up. Consequently, by interrogating the database using the unambiguous identifier, it is likewise possible to ascertain the position of a device.

An advantage of site determination by means of a global satellite navigation system is the great accuracy. An alternative method, better but less precise, utilizes a radio standard for site determination. A mobile phone (cell phone) may be used for positioning. In mobile radio, the simplest type of site determination is based on the fact that the cell within which a mobile phone is located is known. Since, for example, a switched-on mobile phone is in communication with a base station, the position of the mobile phone can be assigned at least to one mobile cell (cell ID). With the aid of GSM (Global System for Mobile Communications), the site of a transmitting unit can be determined to an accuracy of several hundred meters. In cities, the site can be determined to an accuracy of 100 to 500 m; in rural areas, the radius increases to 10 km or more. If the information via the cell ID is combined with the TA parameter (TA: Timing Advance), then the accuracy can be enhanced. The greater this value, the further away the transmitting unit is from the base station. Using the EOTD method (EOTD: Enhanced Observed Time Difference), a transmitting unit can be located with even greater accuracy. In that case the differences in transit time of the signals between the transmitting unit and a number of receiving units are determined.

In one embodiment, the transmission of information and the site determination take place by way of the Sigfox network. Sigfox is a low-power, wide-area network (LPWAN) and is designed specifically for small data packets and a very power-economical operation. Sigfox base stations are able to communicate over long distances, without being affected by disruptions. The range of an individual base station, which may administer up to one million transmitting units, is 3 to 5 km in densely populated centers and 30 to 70 km in rural domains. With Sigfox, the data packets from all base stations in the transmitting zone are received. In this way it is possible to determine the position of a transmitting unit.

The geocoordinates are ascertained preferably with an accuracy of at least 100 meters. In one embodiment the geocoordinates are ascertained preferably with an accuracy of at least 1, 2, 5, 10, 20, 25, 50 or 75 metres.

After a sample has been taken, it is processed. This can be conducted by DNA isolation from crude or purified samples, direct or targeted DNA amplification, purification, potentially barcoded for multiplexing several samples and subsequently sequencing in individual or multiplex format. The purpose of the processing is to prepare for subsequent determination of the genetic profile. By means of the processing, the entire or part of one or multiple samples are therefore processed and/or prepared in such a way that it can be passed on the generation of a genetic profile. The corresponding processing measures are described in the prior art (see, for example, R. P. Schaudies (Ed.): Biological Identification, Woodhead Publishing Series in Electronic and Optical Materials: Number 59, Elsevier 2014, ISBN 978-0-85709-501-5; Jianping Xu: Next-generation Sequencing, Caister Academic Press 2014, ISBN 978-1-908230-33-1; Vijai Bhadauria: Next-generation Sequencing and Bioinformatics for Plant Science, Caister Academic Press 2017, ISBN 978-1-910190-65-4).

Processing can take place at the same location at which the sample was taken or, alternatively, the sample can be stored appropriately for later processing at different location. This means that the sample, immediately or at a later timepoint after having been collected, is passed on for further processing and generating of a genetic profile.

The analysis of the variants which are present in a genetic profile may be carried out by direct sequencing of the genomic DNA or RNA region of interest, with an oligonucleotide probe labeled with a suitable group, and/or by means of an amplification reaction such as a polymerase chain reaction or ligase chain reaction (the product of which amplification reaction may then be analyzed with a labeled oligonucleotide probe or a number of other techniques). In one embodiment a method for sequencing is described in WO-A 2021/228578.

In one embodimentthe sequencing may be performed by using one or more of sequencing technologies including Sanger sequencing, next generation sequencing, pyrosequencing, nanopore sequencing, GenapSys sequencing, sequencing by ligation (SOLID sequencing), single-molecule real-time sequencing, Ion semiconductor (Ion Torrent sequencing) sequencing, sequencing by synthesis (Illumina), combinatorial probe anchor synthesis (cPAS- BGI/MGI) — , nanopore technology, microarray technology, graphene biosensor technology, PCR (polymerase chain reaction) technology, fast PCR technology, and other DNA/RNA amplification, technologies such as isothermal amplification such as LAMP (Loop mediated amplification), RPA (Recombinase Polymerase Amplification), Nucleic Acid Sequenced Based Amplification (NASBA) and Transcription Mediated Amplification (TMA), as well as epigenetic analysis such as DNA methylation, DNA- Protein interaction analysis, and Chromatin accessibility analysis.

"Amplification" as applied to nucleic acids herein refers to any method that results in the formation of one or more copies of a nucleic acid, where preferably the amplification is exponential. One such method for enzymatic amplification of specific sequences of DNA is known as the polymerase chain reaction (PCR), as described by Saiki et al., 1986, Science 230: 1350-1354. Primers used in PCR normally vary in length from about 10 to 50 or more nucleotides, and are typically selected to be at least about 15 nucleotides to ensure sufficient specificity. The double stranded fragment that is produced is called an "amplicon," and may vary in length from as few as about 30 nucleotides, to 20,000 or more. A "genetic marker" as used herein is a known variation of a DNA sequence at a particular locus. The variation may be present in an individual due to mutation or inheritance. A genetic marker may be a short DNA sequence, such as a sequence surrounding a single base-pair change (single nucleotide polymorphism, SNP), or a long one, like minisatellites. Genetic markers can be used to study the relationship between an inherited disease and its genetic cause (for example, a particular mutation of a gene that results in a defective or otherwise undesirable form of protein).

Further, the analyzing step may include the step of analyzing whether the subject is heterozygous or homozygous for a certain variant. Numerous different oligonucleotide probe assay formats are known which may be employed to carry out the present invention. See, e.g., US 4,302,204, US 4,358,535 US 4,563,419, and US 4,994,373.

In one embodiment, analysis may include multiplex amplification of the DNA (e.g., allele-specific fluorescent PCR). In some embodiments, analysis may include hybridization to a microarray (a chip, beads, etc.). In some embodiments, analysis may include sequencing appropriate portions of the gene containing the haplotypes sought to be analyzed. In some embodiments, haplotypes that change susceptibility to digestion by one or more endonuclease restriction enzymes may be used for analysis. For example, restriction fragment length polymorphism (RFLP), which refers to the digestion pattern when various restriction enzymes are applied to DNA, may be used. In some embodiments, the presence of one or more haplotypes can be determined by allele specific amplification. In some embodiments, the presence of haplotypes can be determined by primer extension. In some embodiments, the presence of haplotypes can be determined by oligonucleotide ligation. In some embodiments, the presence of haplotypes can be determined by hybridization with a labeled probe. Amplification of a selected, or target, nucleic acid sequence of one or more variant may be carried out by any suitable means on DNA isolated from biological samples. Examples of suitable amplification techniques include, but are not limited to, polymerase chain reaction, ligase chain reaction, strand displacement amplification, transcription-based amplification, self-sustained sequence replication (or "3 SR"), nucleic acid sequence-based amplification (or "NASBA"), the repair chain reaction (or "RCR"), and boomerang DNA amplification (or "BDA"). Polymerase chain reaction is currently preferred.

DNA amplification techniques such as the foregoing can involve the use of a probe, a pair of probes, or two pairs of probes which specifically bind to DNA encoding a certain target gene, but do not bind to DNA encoding a different family member of that target gene under the same hybridization conditions, and which serve as the primer or primers for the amplification of the target gene DNA or a portion thereof in the amplification reaction.

Similarly, one may use a probe, a pair of probes, or two pairs of probes which specifically bind to DNA encoding a variant of interest, but do not bind to other haplotypes under the same hybridization conditions.

In general, an oligonucleotide probe which is used to analyze DNA encoding a target gene is an oligonucleotide probe which binds to DNA encoding the haplotype of interest but does not bind to DNA encoding other haplotypes under the same hybridization conditions. The oligonucleotide probe is labeled with a suitable group, such as those set forth below in connection with antibodies.

Polymerase chain reaction (PCR) may be carried out in accordance with known techniques. See, e.g., US 4,683,195; 4,683,202; 4,800,159; and 4,965,188. In general, PCR involves, first, treating a nucleic acid sample (e.g., in the presence of a heat stable DNA polymerase) with one oligonucleotide primer for each strand of the specific sequence to be analyzed under hybridizing conditions so that an extension product of each primer is synthesized which is complementary to each nucleic acid strand, with the primers sufficiently complementary to each strand of the specific sequence to hybridize therewith so that the extension product synthesized from each primer, when it is separated from its complement, can serve as a template for synthesis of the extension product of the other primer, and then treating the sample under denaturing conditions to separate the primer extension products from their templates if the sequence or sequences to be analysed are present. These steps are cyclically repeated until the desired degree of amplification is obtained. Analysis of the amplified sequence may be carried out by adding to the reaction product an oligonucleotide probe capable of hybridizing to the reaction product (e.g., an oligonucleotide probe of the present invention), the probe carrying a label, and then analyzing the label in accordance with known techniques, or by direct visualization on a gel.

When PCR conditions allow for amplification of all allelic types of a certain variant, the types can be distinguished by hybridization with allelic specific probe, by restriction endonuclease digestion, by electrophoresis on denaturing gradient gels, or other techniques. A PCR protocol for determining the genotype of a target gene is described in Wenham et al. (1991).

The term "genotype” means the particular allelic form of a gene, which can be defined by the particular nucleotide(s) present in a nucleic acid sequence at a particular site(s). Genotype may also indicate the pair of alleles present at one or more polymorphic loci. For diploid organisms, such as humans, two haplotypes make up a genotype.

“Genotyping” is any process for determining a genotype of an individual, e.g., by nucleic acid amplification, nucleic acid sequencing, antibody binding, or other chemical analysis. The resulting genotype may be unphased, meaning that the sequences found are not known to be derived from one parental chromosome or the other.

In the next step the results of the genetic analysis of the variants present in a sample are summarized within the genetic profile which lists all variants of that sample and optionally the respective sequence information, the organism the variant originates from and/or the percentage of a variant in that sample.

In one embodiment a genetic profile may comprise one or more of the following variants:

The leter represents the amino acid according to the international single leter amino acid code (htps://www.fao.Org/3/y2775e/y2775e0e.htm). The number describes the position of the respective amino acid in the gene. The first leter is the amino acid present in the wildtype strain or cultivar of the harmful organism, the second leter represents a genetic variant.

In a further step one or more biological targets are determined based on the genetic profile.

The genetic profile provides information on whether one or more harmful organisms are present and, if so, which species, in particular which strain or subtype of harmful organism(s) are present in the sample. The sequence information of the variants comprising the genetic profile can be used to identify the corresponding DNA, RNA or protein sequence information of biological targets in sequence repositories such as GenBank, Uniprot, Ensembl using publicly available software such as Basic Local Alignment Search Tool (BLAST; Altschul et al. (1990). This information can be used to identify the one or more respective gene or protein sequences encoding one or more biological targets in the harmful organism that can be addressed to combat the harmful organism. Lor example, the information about which biological target can be addressed in a harmful organism, which DNA, RNA or protein sequences are encoding for such a biological target may be stored in a database. It is known for a variety of harmful organisms which biological targets can be addressed to control them (see, e.g., X. Li et al.: Review on Structures of Pesticide Targets, Int. J. Mol. Sci. 2020, 21, 7144). It is also for a wide range of genetic variants already known which is the biological target (see publications of the FUNGICIDE RESISTANCE ACTION COMMITTEE at https://www.frac.info/knowledge-database/downloads or the INSECTICIDE RESISTANCE ACTION COMMITTEE (htps://irac-online.org/ ) or the HERBICIDE RESISTANCE ACTION COMMITTEE (htps://www.hracglobal.com/). This publicly available information can be compiled and stored in one or more databases.

In a further step one or more active ingredients targets are determined that address(es) the one or more biological targets. Just as there is information about the biological targets of harmful organisms, there is information about a variety of active ingredient as to which biological targets they address (see, e.g., L.-C. Mei et al.: Pesticide Informatics Platform (PIP): An International Platform for Pesticide Discovery, Residue, and Risk Evaluation, J. Agric. Food Chem. 2022, 70, 6617-6623; publications of the FUNGICIDE RESISTANCE ACTION COMMITTEE at https://www.frac.info/knowledge-database/downloads or the INSECTICIDE RESISTANCE ACTION COMMITTEE (htps://irac-online.org/) or the HERBICIDE RESISTANCE ACTION COMMITTEE (htps://www.hracglobal.com/). This information can also be collected and stored in one or more databases from which it can be read. It is also conceivable that the step “determining one or more biological targets based on the genetic profile” and the step “determining one or more active ingredients addressing the one or more biological targets” are carried out in one step, i.e., based on the one or more identified harmful organisms, one or more active ingredients are directly identified (e.g., obtained from one or more databases) that can be used to control the one or more harmful organisms.

In a further step, an expected efficacy of a crop protection product comprising the one or more active ingredients is determined.

Determining the expected efficacy is done using a model in which, for a multitude of crop protection products, their efficacy is related to one or more variants and/or one or more genetic profiles of one or more harmful organisms. In other words, the model links the efficacy of a crop protection product against a harmful organism to a variant or a genetic profile of the harmful organism.

The efficacy of a pesticide is significantly influenced by whether a variant of a harmful organism that has developed or evolved resistance to the pesticide is present in the field.

"Resistance" means an acquired, heritable reduction in sensitivity of a harmful organism to a specific mode of action. There are two types of resistance: locus-specific resistance, also called target site resistance, and metabolic resistance, also called non-target site resistance. The present disclosure relates to both types of resistance.

Since the genetic profile includes information on existing variants, emerging or existing resistances can be inferred from the genetic profile.

The genetic analysis of the variants present in the genetic profile looks at whether there are variants present which have been analyzed quantitatively or qualitatively in the sample which indicate that the harmful organism may develop, is developing, or has developed resistance to one or more active ingredients and/or crop protection products. In the identification of variants, it is possible to look at whether there are variants in the sample that are known to be responsible for resistance. In the case of metabolic resistances, moreover, it is possible to use the quantity of the corresponding RNA comprising one or more variants in the harmful organism as a resistance marker. In one embodiment a variant is identified which coincides neither with known resistance markers nor with variants of the nonresistant harmful organism. This new type of variant might point to a newly forming resistance and/or might indicate a new resistance marker.

A "resistance marker" as used herein means a genetic variant that is associated with increased resistance to one or more crop protection products. It may also refer to a genetic variant that is associated with a particular response to one or more crop protection products. By sequencing and analysis of one or more variants as described above one or more resistance markers may be identified in a sample.

Which variant indicates that the harmful organisms have or are developing resistance in a target to a crop protection product are known for a multiplicity of harmful organisms . A variant of this kind and/or the quantity thereof is a resistance marker in the sense of the present disclosure. A number of examples are set out below - including for the purpose of illustrating the procedure for finding variants which represent new resistance markers.

Acetolactate synthase (ALS or AHAS for short) is an enzyme which in many prokaryotes and eukaryotes is involved in the formation of the branched-chain amino acids valine, leucine, and isoleucine. This enzyme is the locus of action (target) for a range of herbicide classes, known under the designation of ALS-inhibiting herbicides: sulfonylureas, imidazolinones, triazolopyrimidines, pyrimidinyl-thiobenzoates, and sulfonyl- aminocarbinyltriazolinones. There are now a multiplicity of broadleaf/gramineous weeds known which display resistance to the ALS-inhibiting herbicides (http://www.weedscience.org). J. Rey-Caballero et al. studied the causes of the resistance of Papaver rhoeas (com poppy) to the ALS-inhibiting herbicides (Pesticide Biochemistry and Physiology 138 (2017) 57-65). It was found that in three multiply resistant populations, six amino acids were exchanged. The gene sequences correspondent with the amino acids are resistance markers in the sense of the present invention.

J. A. C. Gardin et al. showed which genetic factors are responsible in the case of Alopecurus myosuroides for resistance to ALS-inhibiting herbicides (BMC Genomics (2015) 16:590). These can be used as resistance markers in the sense of the present invention.

There are numerous studies relating to the gene families in plants (broadleaf/gramineous weeds) which encode cytochrome P450, glutathione S-transferases, glycosyltransferases, and ABC transporters, and their involvement in the development of non-target site resistances to herbicides (see, for example, J. S. Yuan et al.: Non-target-site herbicide resistance: a family business, TRENDS in Plant Science Vol. 12 No. 1 (2006) pages 6 to 13, and the publications cited therein). The resistance-causing genes and gene families disclosed therein are resistance markers in the sense of the present invention.

R. H. ffrench-Constant gives an overview of the genes and gene families involved in the development of resistances in insects to insecticides (Genetics, Vol. 194 (2013) 807-815). The resistance-causing genes and gene families disclosed therein are resistance markers in the sense of the present invention.

So-called diamide insecticides (http://www.alanwood.net/pesticides/class_insecticides.html) are especially effective control agents on butterflies and moths (Lepidoptera), an example being the tomato leafminer moth. In the case of the species Tuta absoluta, resistances have increasingly been observed with respect to diamide insecticides. E. Roditakis et al. were able to pinpoint specific mutations as the genetic causes of the development of resistance (Insect Biochemistry and Molecular Biology 80 (2017) 11-20). The DNA sequences affected by the mutations are resistance markers in the sense of the present invention.

Y. Pan et al. show which genetic factors are responsible in the case of the aphid Aphis gossypii for resistance to the insecticide spirotetramat (Insect Molecular Biology (2017) 26(4), 383-391 doi: 10.1111). These factors may be used as resistance markers in the sense of the present invention.

Z. Ma et al. were able to show that a resistance to DMI fungicides in the case of the fungus Blumeriella jaapii is mediated by overexpression of the CYP51 gene (Applied and Environmental Microbiology, Apr. 2006, p. 2581-2585). An overexpression of the CYP51 gene is a resistance markr in the sense of the present invention.

S. Omrane et al. showed which genetic factors in the case of the fungus Zymoseptoria tritici are responsible for a resistance to a multiplicity of fungicides (mSphere2:e00393-17. https://doi.Org/10.l 128/mSphere.00393- 17). These factors can be used as resistance markers in the sense of the present invention.

For the identification of resistance markers in the field on the basis of DNA and/or RNA sequencing, methods have been published (WO2011/067559A1, WO2012/042226A1, WO2013/041878A1, WO2013/098561A1, WO2013/121224A1, WO2014/064443A1, WO2015/140535A1, WO2015/150786A1, WO2015/173587A1, WO2016/059436A1, WO201/6059427A1, WO2017/203269A1). The company Oxford Nanopore Technologies Ltd. makes available, on a commercial basis, corresponding sequencing tools (see, for example, https://nanoporetech.com; M. Loose et al: Real-time selective sequencing using nanopore technology, Nature Methods Vol. 13 No. 9 (2016) 751-758).

The model may be or comprise one or more databases that store efficacy data for a plurality of crop protection products or a plurality of active ingredients with respect to control of one or more harmful organisms and/or one or more variant of harmful organisms.

The efficacy data for a crop protection product or an active ingredient may comprise EC50 values, mortality, lowest effective rate, disease incident, disease severity and/or crop (e.g., harvest) loss.

Efficacy data may be generated in field trials, greenhouse trials, in-vitro experiments or in-vivo experiments in a laboratory.

EC50 values can be measured in a laboratory, for example. In the laboratory, the efficacy of one or more crop protection products in controlling one or more genetic variants of one or more harmful organisms can be measured under controlled conditions. The measured values can be stored in a database. If a particular variant of a harmful organism is found in a sample, the EC50 value(s) for one or more crop protection products can be retrieved from the database in relation to this variant. If different variants of a harmful organism are present in a sample, an EC50 value for each variant can be retrieved from the database for one or more crop protection products and/or one or more active ingredients.

Similarly, in the case of several different harmful organisms in a sample, an EC50 value for one or more crop protection products can be retrieved from the database for each of these harmful organisms.

If the genetic profile includes quantitative information on the amounts of different harmful organisms and/or different variants of a harmful organism, an effective EC50 value can be calculated from the individual EC50 values, indicating how effective a crop protection product is against all harmful organisms and/or variants present.

For example, the effective EC50 value may be the sum of the individual EC50 values multiplied by a proportion factor. For example, if a first harmful organism (or a first variant of a harmful organism) is present in a sample at a proportion of Xl% (based on the number of individuals of harmful organisms present in the sample) and a second harmful organism (or a second variant of the harmful organism) is present at a proportion of X2% (based on the number of individuals of harmful organisms present in the sample), and the EC50 value of a crop protection product for controlling the first harmful organism (or variant) is EC50(l) and the EC50 value of the crop protection product for controlling the second harmful organism (or variant) is EC50(2), then the effective EC50 value can be calculated using the following equation:

EC50^eff = XI ■ EC50(l) + X2 ■ EC50(2)

The statements in the previous section apply mutatis mutandis to other quantities that can be used to describe the efficacy of a crop protection product, not only to EC50 values.

The efficacy of a crop protection product can also be determined in an agricultural or horticultural area. For example, it is possible to determine the proportion of crops that are damaged or destroyed by one or more harmful organisms (or variants) despite application of a crop protection product.

If the efficacy of a crop protection product is determined based on the crop loss attributable to the presence of one or more harmful organisms despite application of the crop protection product, historical crop loss data can also be used to correlate the genetic profile of one or more harmful organisms with the efficacy of a crop protection product, provided that genetic profiles of the harmful organisms that were present at the time are also available. In one embodiment determining the expected efficacy is done using a model in which, for a multitude of crop protection products, in addition to their efficacy related to one or more variant and/or one or more genetic profiles of one or more harmful organisms additional agricultural data are used. Such additional agricultural data will allow an even more precise determination of the expected efficacy. Agricultural data may comprise (a) information on the timepoint of sampling; (b) further information on the variant such as the frequency of that variant in populations of harmful organisms, information whether the variant has been characterized regarding its impact on structure or binding properties of the biological target; (c) further information on the crop protection product such as application parameters, the formulation type, the amount of the one and more active ingredients, further ingredients in the formulation such as solvents, emulsifiers; (d) additional information on efficacy such as efficacy from present or historic experiments or trials in greenhouse, laboratories or agricultural or horticultural areas; additional information on location such as GPS data for the variant to be analyzed or for the efficacy data of (d); (f) current or historic weather data for the one or more agricultural or horticultural areas; (g) environmental data for the one or more agricultural or horticultural areas such as soil data; vegetation data such as vegetation index; (h) additional information regarding the harmful organism such as species, life cycle stage.

Of particular interest as a type of agricultural data is the so called fitness penalty associated with a variant. Variants may lead to either in change in the expression of the biological target in which is variant is identified or in the structure of that biological target. Consequently, a crop protection product addressing the biological target may show a change in efficacy. In addition, as biological targets fulfil often a main or even essential function in a harmful organism. Therefore, a variant may also lead to a change in function of that biological target which may have an effect on the fitness of a harmful organism. Fitness is defined as the ability of an organism to survive and reproduce. The fitness penalty or fitness costs therefore refer to the impact the variant has in the organism’s fitness in the presence or absence of one or more active ingredient or one or more crop protection product (Hawkins and Fraaije, Annual Review of Phytopathology 2018, Vol 56, pp 339 - 360 (https://doi.org/10.1146/annurev-phyto-080417-050012). For example, a variant causing overexpression of the biological target has a cost associated with the additional allocation of resources for that expression which is not necessary in the absence of a crop protection product addressing that target. Methods for assessing fitness penalties are mutagenesis studies, growth, sporulation or pathogenicity assays for single isolates of harmful organisms collected in agricultural or horticultural areas, isogenic transformants or where such assays may encompass different growth temperatures, growth media, osmotic or oxidative stress.

Therefore, in one embodiment a method is disclosed in which an expected efficacy of a crop protection product comprising the one or more active ingredients is determined by using a model in which, for a multitude of crop protection products, their efficacy and one or more fitness penalties associated with one or more variants is related to one or more genetic profiles of one or more harmful organisms.

The model may also be or include a machine learning model. Such a “machine learning model”, as used herein, may be understood as a computer implemented data processing architecture. The machine learning model can receive input data and provide output data based on that input data and on parameters of the machine learning model. The machine learning model can learn a relation between input data and output data through training. In training, parameters of the machine learning model may be adjusted in order to provide a desired output for a given input.

The process of training a machine learning model involves providing a machine learning algorithm (that is the learning algorithm) with training data to learn from. The term “trained machine learning model” refers to the model artifact that is created by the training process. The training data must contain the correct answer, which is referred to as the target. The learning algorithm finds patterns in the training data that map input data to the target, and it outputs a trained machine learning model that captures these patterns.

In the training process, training data are inputted into the machine learning model and the machine learning model generates an output. The output is compared with the (known) target. Parameters of the machine learning model are modified in order to reduce the deviations between the output and the (known) target to a (defined) minimum.

In general, a loss function can be used fortraining, where the loss function can quantify the deviations between the output and the target. The loss function may be chosen in such a way that it rewards a wanted relation between output and target and/or penalizes an unwanted relation between an output and a target. Such a relation can be, e.g., a similarity, or a dissimilarity, or another relation.

If, for example, the output and the target are numbers, the loss function could be the difference between these numbers. In this case, a high absolute value of the loss function can mean that a parameter of the model needs to undergo a strong change.

In the case of vector-valued outputs, for example, difference metrics between vectors such as the root mean square error, a cosine distance, a norm of the difference vector such as a Euclidean distance, a Chebyshev distance, an Lp-norm of a difference vector, a weighted norm or any other type of difference metric of two vectors can be chosen. These two vectors may for example be the desired output (target) and the actual output. In the case of higher dimensional outputs, such as two-dimensional, three-dimensional or higher-dimensional outputs, for example an element-wise difference metric can be used. Alternatively or additionally, the output data may be transformed, for example to a one-dimensional vector, before computing a loss.

The modification of model parameters and the reduction of the loss can be done in an optimization procedure, for example in a gradient descent procedure.

The model of the present disclosure may by trained on training data. The training data may comprise for each agricultural or horticultural area of a multitude of agricultural or horticultural areas i) one or more genetic profiles of one or more harmful organisms in one or more samples taken in the agricultural or horticultural area as input data and ii) data describing the efficacy of one or more crop protection products on the one or more harmful organisms as target data.

The term multitude means at least ten, preferably more than a hundred.

The training of the machine learning model may comprise: inputting the input data into the machine learning model; receiving from the machine learning model a predicted efficacy for one or more crop protection products; determining a loss, the loss quantifying a deviation between the predicted efficacy and the target data; modifying parameters of the machine learning model to minimize the loss.

The machine learning model may be trained on training data for which variants are determined in a multitude of agricultural and/or horticultural areas at different locations and/or at different time points during the vegetation period and/or over multiple years. Additional data taken into account are the efficacy data of one or more crop protection products of interest at those locations and/or time points.

The machine learning model may be or comprise an artificial neural network. An “artificial neural network” (ANN) is a biologically inspired computational model. An ANN usually comprises at least three layers of processing elements: a first layer with input neurons (nodes), a layer with at least one output neuron (node), and k-2 inner layers, where k is a natural number greater than 2.

In such a network, the input neurons serve to receive the input data. If the input data constitute or comprise an ^-dimensional vector (e.g., a feature vector), with n being an integer equal to or greater than 1, there is usually one input neuron for each component of the vector. The output neurons serve to output at least one value. The processing elements of the layers are interconnected in a predetermined pattern with predetermined connection weights therebetween. Each network node represents a pre-defined calculation of the weighted sum of inputs from prior nodes and a non-linear output function. The combined calculation of the network nodes relates the inputs to the outputs. It should be noted that an ANN can also use connection biases b, i.e. the output y of a neuron given an input x is calculated as y = act(w x + b) where w denotes the weights and act denotes the activation function.

When trained, the connection weights between the processing elements in the ANN contain information regarding the relationship between the input data and the output data which can be used to predict new output data from new input data.

Training estimates network weights that allow the network to calculate output values close to the target values. The network weights can be initialized with small random values or with the weights of a prior partially trained network. The training data inputs are applied to the network and the output values are calculated for each training sample. The network output values are compared to the target values. A backpropagation algorithm can be applied to correct the weight values in directions that reduce the error between targeted and calculated outputs. The process is iterated until no further reduction in error can be made or until a predefined prediction accuracy has been reached.

A cross-validation method can be employed to split the data into training and validation data sets. The training data set is used in the backpropagation training of the network weights. The validation data set is used to verify that the trained network generalizes to make good predictions. The best network weight set can be taken as the one that best predicts the outputs of the training data. Similarly, varying the number of network hidden nodes and determining the network that performs best with the data sets optimizes the number of hidden nodes.

Further data can be included in the training of the machine learning model as input data, such as weather data, soil data, location information, data regarding the planted crop and variety, images showing the phenotype of an area, information about the crop protection product(s) used (e.g., information of active ingredients contains in crop protection product, formulation type), application parameters etc.

“Application parameter” means any value defining the application of one or more crop protection products including application rate, application method, application timing, application machinery, each for one or more crop protection products.

When further agricultural data are used, the model learns not only what influence the presence of one or more variants has on the efficacy of a crop protection product, but also what influence the further agricultural data has on the efficacy of the crop protection product. In one embodiment the model is or comprises a simulation model simulating the impact of one or more crop protection products on the one or more harmful organisms in the agricultural or horticultural area.

In one embodiment the model is or comprises a mechanistic efficacy model quantifying the efficacy of one or more crop protection products on the one or more species in the area.

In one embodiment the genetic profile data comprise information about the presence, amount and genotype of the variants from more than one harmful organism.

In one embodiment the harmful organism is selected from a fungal, bacterial, or plant species.

In one embodiment the efficacy of a crop protection product comprising one or more active ingredients is determined based on the level of resistance to that crop protection product for a certain variant or a certain genetic profile.

The expected efficacy of the crop protection product can be outputted, e.g., displayed on a display of the computer system of the present disclosure, printed via a printing device, stored in a data memory and/or transmitted to a separate computer system.

Based on the outputted expected efficacy, a user (e.g., a farmer) can see whether the crop protection product for which the expected efficacy has been outputted is a suitable product to control the harmful organisms in the agricultural or horticultural area or whether the efficacy is too low, e.g. because harmful organisms are present in the agricultural or horticultural area that have developed resistance to the crop protection product.

The user can display expected efficacies of a plurality of crop protection products to determine which crop protection product has the highest efficacy.

The computer system/computer program of the present disclosure may also be configured to determine the efficacy of a plurality of crop protection products and identify a number of crop protection products that have the highest efficacies, e.g., a number of 1, 2, 3, 4, or 5 or more crop protection products.

The computer system/computer program of the present disclosure may be configured to output the number of pesticides with the highest efficacies.

In addition to one or more crop protection products, a quantity or quantities may be outputted that should be applied to effectively control harmful organisms and prevent resistance.

If different harmful organisms or different variants of one or more harmful organisms have been identified at different locations in the agricultural or horticultural area, the computer system/computer program may be configured to output, for each location, one or more crop protection products that are most effective in controlling the harmful organisms or variants at the location.

For example, a map of the agricultural or horticultural area can be output showing, for different subareas of the agricultural or horticultural area, which crop protection products have the highest efficacies against harmful organisms or variants in the subarea.

The user may be prompted to select a crop protection product from a list of crop protection products for each subarea. However, it is also possible that the computer system/computer program is configured to select only one crop protection product for each subarea (e.g., the one with the highest efficacy) and list it on a map of the agricultural or horticultural area.

The computer system/computer program may also be configured to specify, for subareas, the amounts of a crop protection product in which it should be applied to the subarea to control the harmful organisms present there.

The computer system/computer program may also be configured to output an application map, i.e., a map of the agricultural or horticultural area in which for subareas the amount of one or more crop protection products is specified which are to be applied in the subareas to control one or more harmful organisms and/or to prevent resistance.

Such an application map can also be transmitted over a network to an agricultural or horticultural machinery such as a vehicle, drone, or robot that performs the application of the one or more crop protection products according to the application map. Such an application map is also referred to as prescription.

A “prescription” means a script capable of executing commands on one or more type of agricultural machinery so that the agricultural machinery performs its function both in time and location, optionally by automatic steering using a GPS signal to steer the agricultural machinery. In one embodiment the agricultural machinery is a spraying device. Examples for spraying devices are self-propelled sprayers, tractor mounted spraying devices, backpack spraying devices, ATV spraying devices. In one embodiment a prescription is used to control a spraying device suitable to spray one or more crop protection products to spray certain amounts of one or more crop protection products at a certain time and/ or a certain location with certain application parameters. Those application parameters include the type of spraying device recommended, additional components for the spraying device such as boom type, nozzles, the spraying timing and location direction, the speed of the travelling spraying device, the number of passes for an application, the application rate, or the cell size. The spraying devices may be equipped with selective or automatic section control allowing to avoid double spray over overlap eg at field ends. They may also be equipped with rate control systems such as pulse with modulation allowing spraying a uniform volume. The cell size is an important parameter in a prescription, it is the size of the cell of the grid which is layered on top of a resistance or genetic profde map to determine whether a crop protection product should be applied in that cell (JC Mayer “USING PRESCRIPTION MAPS FOR IN FIELD EVALUATION OF PARAMETERS AFFECTING SPRAYING ACCURACY OF A SELF A PROPELLED SPRAYER“, Master Thesis North Dacota State University of Agriculture and Applied Science, 2021). A prescription may be machine readable or may be read by humans as well.

In one embodiment the time period between the sampling of harmful organisms, the analysis of the genetic profile from those samples, the generation of the prescription and the spraying is less than 24 hours. In another embodiment it is less than 18, 12, 10, 8, 6, 5, 4, 3, 2, or 1 hour.

In one embodiment the time period between the sampling of harmful organisms, the analysis of the genetic profile from those samples, the generation of the prescription and the spraying is less than one hour.

In one embodiment genetic profiles are generated using a portable platform.

In one embodiment genetic profiles are used to predict the occurrence of a harmful organism in an agricultural or horticultural area before the visual appearance of that harmful organism in that area.

The result of the analysis may be also provided in a resistance map. A "resistance map" is a representation of part of the Earth's surface in which, for a plurality of locations on the Earth's surface, information is set down as to whether, at the corresponding location, a harmful organism has been observed, wherein there is resistance to a crop protection product or wherein a known or unknown potential resistance is developing. The resistance map is preferably a digital reference map. The term "digital" means that the map can be processed by a machine, generally a computer system. "Processing" refers to the known methods of electronic data processing (EDP). A "digital resistance map" is therefore a digital representation of part of the Earth's surface in which, for a plurality of locations on the Earth's surface, information is set down as to whether, at the corresponding location, a harmful organism has been observed, wherein there is resistance to a crop protection product or wherein a known or unknown potential resistance is developing. The digital resistance map is preferably a digital representation of a field, or of a field including adjacent fields, or of a region. Separate resistance maps may be generated for individual harmful organisms and/or for individual crop protection products or groups of crop protection products which exhibit the same active ingredient(s) or the same chemical/biological class (e.g., a chemical structural class) or the same mechanism of action or the same locus of action (target). It is possible to link separate digital resistance maps to one another, i.e., to superimpose them on one another virtually. In addition, digital resistance maps may indicate which crops grow in which areas and/or which crop protection products are suitable for controlling harmful organisms in the areas and/or what the efficacies of the respective crop protection products are.

In one embodiment, the timing or timings at which the respective analysis was carried out are recorded for each location on the digital resistance map for which there are one or more analytical results.

In one embodiment, a plurality of digital resistance maps are linked with one another in such a way as to show the development of one or more resistances over time.

It is possible, preferably, for digital resistance maps to be combined with other digital maps; for example, with digital maps relating to soil type, water level, crop plants grown, temperatures (at defined times and/or for defined timespans in the form, for example, of mean and/or minimum and/or maximum temperatures), precipitation levels (at defined times and/or for defined timespans in the form, for example, of mean and/or minimum and/or maximum precipitation levels), insolation, air mass movements (wind directions and wind forces), past infestations with one or more harmful organisms, agricultural measures taken (e.g., sowing, watering, plowing, application of crop protection agents, administration of nutrients, and the like), etc. The values of the parameters that are set down in a digital map may be measured values and/or predicted values.

The operations in accordance with the teachings herein may be performed by at least one computer system specially constructed for the desired purposes or general-purpose computer system specially configured for the desired purpose by at least one computer program stored in a typically non-transitory computer readable storage medium.

A “computer system” is a system for electronic data processing that processes data by means of programmable calculation rules. Such a system usually comprises a “computer”, that unit which comprises a processor for carrying out logical operations, and also peripherals.

In computer technology, “peripherals” refer to all devices which are connected to the computer and serve for the control of the computer and/or as input and output devices. Examples thereof are monitor (screen), printer, scanner, mouse, keyboard, drives, camera, microphone, loudspeaker, etc. Internal ports and expansion cards are, too, considered to be peripherals in computer technology.

Computer systems of today are frequently divided into desktop PCs, portable PCs, laptops, notebooks, netbooks and tablet PCs and so-called handhelds (e.g. smartphone); all these systems can be utilized for carrying out the invention.

The term “non-transitory” is used herein to exclude transitory, propagating signals or waves, but to otherwise include any volatile or non-volatile computer memory technology suitable to the application. The term “computer” should be broadly construed to cover any kind of electronic device with data processing capabilities, including, by way of non-limiting example, personal computers, servers, embedded cores, computing system, communication devices, processors (e.g., digital signal processor (DSP)), microcontrollers, field programmable gate array (FPGA), application specific integrated circuit (ASIC), etc.) and other electronic computing devices.

The term “process” as used above is intended to include any type of computation or manipulation or transformation of data represented as physical, e.g., electronic, phenomena which may occur or reside e.g., within registers and/or memories of at least one computer or processor. The term processor includes a single processing unit or a plurality of distributed or remote such units.

Fig. 1 illustrates a computer system (1) according to some example implementations of the present disclosure in more detail. The computer may include one or more of each of a number of components such as, for example, processing unit (20) connected to a memory (50) (e.g., storage device).

The processing unit (20) may be composed of one or more processors alone or in combination with one or more memories. The processing unit is generally any piece of computer hardware that is capable of processing information such as, for example, data, computer programs and/or other suitable electronic information. The processing unit is composed of a collection of electronic circuits some of which may be packaged as an integrated circuit or multiple interconnected integrated circuits (an integrated circuit at times more commonly referred to as a “chip”). The processing unit may be configured to execute computer programs, which may be stored onboard the processing unit or otherwise stored in the memory (50) of the same or another computer.

The processing unit (20) may be a number of processors, a multi-core processor or some other type of processor, depending on the particular implementation. Further, the processing unit may be implemented using a number of heterogeneous processor systems in which a main processor is present with one or more secondary processors on a single chip. As another illustrative example, the processing unit may be a symmetric multi-processor system containing multiple processors of the same type. In yet another example, the processing unit may be embodied as or otherwise include one or more ASICs, FPGAs or the like. Thus, although the processing unit may be capable of executing a computer program to perform one or more functions, the processing unit of various examples may be capable of performing one or more functions without the aid of a computer program. In either instance, the processing unit may be appropriately programmed to perform functions or operations according to example implementations of the present disclosure.

The memory (50) is generally any piece of computer hardware that is capable of storing information such as, for example, data, computer programs (e.g., computer-readable program code (60)) and/or other suitable information either on a temporary basis and/or a permanent basis. The memory may include volatile and/or non-volatile memory, and may be fixed or removable. Examples of suitable memory include random access memory (RAM), read-only memory (ROM), a hard drive, a flash memory, a thumb drive, a removable computer diskette, an optical disk, a magnetic tape or some combination of the above. Optical disks may include compact disk - read only memory (CD-ROM), compact disk - read/write (CD-R/W), DVD, Blu-ray disk or the like. In various instances, the memory may be referred to as a computer-readable storage medium. The computer-readable storage medium is a non-transitory device capable of storing information, and is distinguishable from computer-readable transmission media such as electronic transitory signals capable of carrying information from one location to another. Computer-readable medium as described herein may generally refer to a computer-readable storage medium or computer-readable transmission medium.

In addition to the memory (50), the processing unit (20) may also be connected to one or more interfaces for displaying, transmitting and/or receiving information. The interfaces may include one or more communications interfaces and/or one or more user interfaces. The communications interface(s) may be configured to transmit and/or receive information, such as to and/or from other computer(s), network(s), database(s) or the like. The communications interface may be configured to transmit and/or receive information by physical (wired) and/or wireless communications links. The communications interface(s) may include interface(s) (41) to connect to a network, such as using technologies such as cellular telephone, WiFi, satellite, cable, digital subscriber line (DSL), fiber optics and the like. In some examples, the communications interface(s) may include one or more short-range communications interfaces (42) configured to connect devices using short-range communications technologies such as NFC, RFID, Bluetooth, Bluetooth LE, ZigBee, infrared (e.g., IrDA) or the like.

The user interfaces may include a display (30). The display may be configured to present or otherwise display information to a user, suitable examples of which include a liquid crystal display (LCD), light-emitting diode display (LED), plasma display panel (PDP) or the like. The user input interface(s) (11) may be wired or wireless, and may be configured to receive information from a user into the computer system (1), such as for processing, storage and/or display. Suitable examples of user input interfaces include a microphone, image or video capture device, keyboard or keypad, joystick, touch-sensitive surface (separate from or integrated into a touchscreen) or the like. In some examples, the user interfaces may include automatic identification and data capture (AIDC) technology (12) for machine-readable information. This may include barcode, radio frequency identification (RFID), magnetic stripes, optical character recognition (OCR), integrated circuit card (ICC), and the like. The user interfaces may further include one or more interfaces for communicating with peripherals such as printers and the like. As indicated above, program code instructions may be stored in memory, and executed by processing unit that is thereby programmed, to implement functions of the systems, subsystems, tools and their respective elements described herein. As will be appreciated, any suitable program code instructions may be loaded onto a computer or other programmable apparatus from a computer-readable storage medium to produce a particular machine, such that the particular machine becomes a means for implementing the functions specified herein. These program code instructions may also be stored in a computer-readable storage medium that can direct a computer, processing unit or other programmable apparatus to function in a particular manner to thereby generate a particular machine or particular article of manufacture. The instructions stored in the computer-readable storage medium may produce an article of manufacture, where the article of manufacture becomes a means for implementing functions described herein. The program code instructions may be retrieved from a computer-readable storage medium and loaded into a computer, processing unit or other programmable apparatus to configure the computer, processing unit or other programmable apparatus to execute operations to be performed on or by the computer, processing unit or other programmable apparatus.

Retrieval, loading and execution of the program code instructions may be performed sequentially such that one instruction is retrieved, loaded and executed at a time. In some example implementations, retrieval, loading and/or execution may be performed in parallel such that multiple instructions are retrieved, loaded, and/or executed together. Execution of the program code instructions may produce a computer-implemented process such that the instructions executed by the computer, processing circuitry or other programmable apparatus provide operations for implementing functions described herein.

Execution of instructions by processing unit, or storage of instructions in a computer-readable storage medium, supports combinations of operations for performing the specified functions. In this manner, a computer system (1) may include processing unit (20) and a computer-readable storage medium or memory (50) coupled to the processing circuitry, where the processing circuitry is configured to execute computer- readable program code (60) stored in the memory. It will also be understood that one or more functions, and combinations of functions, may be implemented by special purpose hardware-based computer systems and/or processing circuitry which perform the specified functions, or combinations of special purpose hardware and program code instructions.

Fig. 2 shows schematically by way of example one embodiment of the computer-implemented method of the present disclosure in the form of a flow chart.

The method (100) comprises the steps:

(110) receiving a genetic profile of one or more harmful organisms from an agricultural or horticultural area, the genetic profile comprising one or more variants; (120) determining one or more biological targets based on the genetic profile;

(130) determining one or more active ingredients addressing the one or more biological targets;

(140) determining an expected efficacy of a crop protection product comprising the one or more active ingredients using a model in which, for a multitude of crop protection products, their efficacy is related to one or more genetic profiles of one or more harmful organisms;

(150) outputting the expected efficacy of the crop protection product

expected efficacy data eED are compared with the efficacy data ED. This is done by using a loss function LF, the loss function quantifying the deviations between the expected efficacy data eED and the efficacy data ED. For each pair of expected efficacy data eED and efficacy data ED, a loss value is computed. During training the model parameters are modified in a way that reduces the loss values to a defined minimum. The aim of the training is to let the machine learning model generate for each input data an output which comes as close to the corresponding target as possible. Once the defined minimum is reached, the (now fully trained) machine learning model can be used to predict an output for new input data (input data which have not been used during training and for which the target is usually not (yet) known).

Claims

Claims:

1. A computer implemented method comprising receiving a genetic profile of one or more harmful organisms from an agricultural or horticultural area, the genetic profile comprising one or more variants; determining one or more biological targets based on the genetic profile; determining one or more active ingredients addressing the one or more biological targets; determining an expected efficacy of a crop protection product comprising the one or more active ingredients using a model in which, for a multitude of crop protection products, their efficacy is related to one or more genetic profiles of one or more harmful organisms; outputting the expected efficacy of the crop protection product.

2. The method of claim 1 further comprising: selecting from the one or more crop protection products at least one crop protection product based on the expected efficacy on the one or more harmful organisms; outputting additional application information about the at least one selected crop protection product.

3. The method of claim 1 or 2 further comprising generating a prescription comprising one or more crop protection products for use on each agricultural or horticultural area suitable to be executed on agricultural machinery.

4. The method of any of claims 1 to 3, in which, when determining the expected efficacy, additional agricultural data is related to the one or more genetic profiles.

5. The method of any of claims 3 to 4 further comprising one or more of the following steps: displaying the prescription to a user; executing an automatic order of the one or more crop protection products comprised by the prescription; applying the one or more crop protection products identified comprised by the prescription in each agricultural or horticultural area; generating a resistance map based on the prescription, wherein the resistance map specifies an application of the crop protection products comprised by the prescription in the agricultural or horticultural area, and displaying and/or storing the resistance map and/or transmitting the resistance map to a device for applying the one or more plant protection products comprised by the prescription; wherein any of these steps may be occur in any order.

6. The method according to any of claims 1 to 5, wherein the model is or comprises a trained machine learning model trained on training data comprising one or more agricultural data sets including i) one or more genetic profiles of one or more harmful organisms in an agricultural or horticultural area as input data and ii) efficacy data about the efficacy of one or more crop protection products on the one or more harmful organisms as target data, wherein the training of the machine learning model comprises: (a) inputting the one or more genetic profiles into the machine learning model; (b) receiving from the machine learning model predicted efficacy data; (c) determining a loss, the loss quantifying a deviation between the predicted efficacy data and the efficacy data of the target data; (d) modifying parameters of the machine learning model to minimize the loss.

7. The method according to any of claims 1 to 6, wherein the model is or comprises a simulation model simulating the impact of one or more crop protection products on the one or more harmful organisms.

8. The method according to any of claims 1 to 6, wherein the model is or comprises a mechanistic efficacy model quantifying the efficacy of the one or more crop protection products on the one or more harmful organisms.

9. A computer system comprising a processor; and a memory storing an application program configured to perform, when executed by the processor, an operation, the operation comprising: receiving a genetic profile of one or more harmful organisms from an agricultural or horticultural area, the genetic profile comprising one or more variants; determining one or more biological targets based on the genetic profile; determining one or more active ingredients addressing the one or more biological targets; determining an expected efficacy of a crop protection product comprising the one or more active ingredients using a model in which, for a multitude of crop protection products, their efficacy is related to one or more genetic profiles of one or more harmful organisms; outputting the expected efficacy of the crop protection product.

10. The computer system of claim 9, the operation further comprising: selecting from the one or more crop protection products at least one crop protection product based on the expected efficacy on the one or more harmful organisms; outputing additional application information about the at least one selected crop protection product.

11. The computer system of claim 9 or 10 further comprising generating a prescription comprising the one or more crop protection products for use on each agricultural or horticultural area suitable to be executed on agricultural machinery.

12. The computer system of any of claim 9 to 11, in which, when determining an expected efficacy, additional agricultural data is related to the one or more genetic profiles.

13. The computer system of any of claim 11 or 12 further comprising one or more of the following steps: displaying the prescription to a user; executing an automatic order of the one or more crop protection products comprised by the prescription; applying the one or more crop protection products comprised by the prescription in each agricultural or horticultural area; generating a resistance map based on the prescription, wherein the resistance map specifies an application of the one or more crop protection products comprised by the prescription in the agricultural or horticultural area, and displaying and/or storing the resistance map and/or transmiting the resistance map to a device for applying the one or more plant protection products comprised by the prescription; wherein any of these steps may be occur in any order.

14. The method according to any of claims 1 to 8, wherein the model is or comprises a trained machine learning model trained on training data comprising one or more agricultural data sets including i) one or more genetic profiles of one or more harmful organisms from an agricultural or horticultural as input data and ii) efficacy data about the efficacy of one or more crop protection products on the one or more harmful organism as target data, wherein the training of the machine learning model comprises: (a) inputing the one or more genetic profiles into the machine learning model; (b) receiving from the machine learning model predicted efficacy data; (c) determining a loss, the loss quantifying a deviation between the predicted efficacy data and the efficacy data of the target data; (d) modifying parameters of the machine learning model to minimize the loss.

15. The method according to any of claims 1 to 8, wherein the model is or comprises a simulation model simulating the impact of the one or more crop protection products on the one or more harmful organisms.

16. The method according to any of claims 1 to 8, wherein the model is or comprises a mechanistic efficacy model quantifying the efficacy of the one or more crop protection products on the one or more harmful organisms.

17. The method according to any of claims 9 to 13, wherein the model is or comprises a trained machine learning model trained on training data comprising one or more agricultural data sets including i) one or more genetic profiles of one or more harmful organisms from an agricultural or horticultural as input data and ii) efficacy data about the efficacy of one or more crop protection products on the one or more harmful organism as target data, wherein the training of the machine learning model comprises: (a) inputting the one or more genetic profiles into the machine learning model; (b) receiving from the machine learning model predicted efficacy data; (c) determining a loss, the loss quantifying a deviation between the predicted efficacy data and the efficacy data of the target data; (d) modifying parameters of the machine learning model to minimize the loss.

18. The method according to any of claims 9 to 13, wherein the model is or comprises a simulation model simulating the impact of the one or more crop protection products on the one or more harmful organisms.

19. The method according to any of claims 9 to 13, wherein the model is or comprises a mechanistic efficacy model quantifying the efficacy of the one or more crop protection products on the one or more harmful organisms.