Metagenomics for microbiomes
An analytics system uses metagenomics to generate predictions indicating performance of biological or physical samples. In an embodiment, a method includes determining sequence data of a soil sample. The method further includes determining a plurality of features of the soil sample using the sequence data. The plurality of features is determined based at least in part on a measure of a first microbe detected in the soil sample and a different measure of a second microbe detected in the soil sample. The method further includes inputting the plurality of features to a model trained using measures of the first microbe and the second microbe detected in a plurality of soil samples. The method further includes generating, by the model using the plurality of features, a prediction of physical attribute of a plant grown in the soil sample.
1. A method comprising:
receiving a soil sample from soil of a crop;
determining sequence data of the soil sample;
determining a first measure of a first microbe detected in the soil sample, wherein the first measure is associated with a first taxonomic level of a plurality of taxonomic levels including at least species, genus, and family;
determining a second measure of a second microbe detected in the soil sample, wherein the second measure is associated with a second taxonomic level of the plurality of taxonomic levels different than the first taxonomic level;
determining a plurality of features of the soil sample using the sequence data by aggregating the first measure of the first microbe detected in the soil sample and the second measure of the second microbe detected in the soil sample;
inputting the plurality of features to a model trained using measures of the first microbe and the second microbe detected in a plurality of soil samples;
generating, by the model using the plurality of features, a prediction of a physical attribute of the crop in the soil sample; and
providing, for display on a client device, a treatment to provide to the crop according to the prediction.
2. The method of claim 1 , further comprising:
determining an aggregate measure of organisms in the soil sample;
determining a first relative abundance of the first microbe by normalizing the measure using the aggregate measure, wherein the first measure is the first relative abundance; and
determining a second relative abundance of the second microbe by normalizing the different measure using the aggregate measure, wherein the second measure is the second relative abundance.
3. The method of claim 2 , further comprising:
determining a first product between a value of the first relative abundance and the value of the first relative abundance;
determining a second product between the value of the first relative abundance and a value of the second relative abundance; and
determining a third product between the value of the second relative abundance and the value of the second relative abundance.
4. The method of claim 2 , wherein the plurality of features further includes a third relative abundance of a third microbe associated with a third taxonomic level of the plurality of taxonomic levels different than the first taxonomic level and the second taxonomic level.
5. The method of claim 1 , wherein the plurality of taxonomic levels further includes at least phylum, class, and order.
6. The method of claim 1 , further comprising:
treating the soil sample according to the prediction.
7. A system comprising a computer processor and a memory, the memory storing computer program instructions that when executed by the computer processor cause the processor to perform steps comprising:
determining sequence data of a soil sample from soil of a crop;
determining a first measure of a first microbe detected in the soil sample, wherein the first measure is associated with a first taxonomic level of a plurality of taxonomic levels including at least species, genus, and family;
determining a second measure of a second microbe detected in the soil sample, wherein the second measure is associated with a second taxonomic level of the plurality of taxonomic levels different than the first taxonomic level;
determining a plurality of features of the soil sample using the sequence data by aggregating the first measure of the first microbe detected in the soil sample and the second measure of the second microbe detected in the soil sample;
inputting the plurality of features to a model trained using measures of the first microbe and the second microbe detected in a plurality of soil samples;
generating, by the model using the plurality of features, a prediction of a physical attribute of the crop in the soil sample; and
providing, for display on a client device, a treatment to provide to the crop according to the prediction.
8. The system of claim 7 , further comprising:
determining an aggregate measure of organisms in the soil sample;
determining a first relative abundance of the first microbe by normalizing the measure using the aggregate measure, wherein the first measure is the first relative abundance; and
determining a second relative abundance of the second microbe by normalizing the different measure using the aggregate measure, wherein the second measure is the second relative abundance.
9. The system of claim 8 , further comprising:
determining a first product between a value of the first relative abundance and the value of the first relative abundance;
determining a second product between the value of the first relative abundance and a value of the second relative abundance; and
determining a third product between the value of the second relative abundance and the value of the second relative abundance.
10. The system of claim 8 , wherein the plurality of features further includes a third relative abundance of a third microbe associated with a third taxonomic level of the plurality of taxonomic levels different than the first taxonomic level and the second taxonomic level.
11. The system of claim 7 , wherein the plurality of taxonomic levels further includes at least phylum, class, and order.
12. A non-transitory computer-readable storage medium storing instructions for controlling a computer system to:
determine sequence data of a soil sample from soil of a crop;
determine a first measure of a first microbe detected in the soil sample, wherein the first measure is associated with a first taxonomic level of a plurality of taxonomic levels including at least species, genus, and family;
determine a second measure of a second microbe detected in the soil sample, wherein the second measure is associated with a second taxonomic level of the plurality of taxonomic levels different than the first taxonomic level;
determine a plurality of features of the soil sample using the sequence data by aggregating the first measure of the first microbe detected in the soil sample and the second measure of the second microbe detected in the soil sample;
input the plurality of features to a model trained using measures of the first microbe and the second microbe detected in a plurality of soil samples;
generate, by the model using the plurality of features, a prediction of a physical attribute of the crop in the soil sample; and
provide, for display on a client device, a treatment to provide to the crop according to the prediction.
13. The non-transitory computer-readable storage medium of claim 12 , storing further instructions for controlling the computer system to:
determine an aggregate measure of organisms in the soil sample;
determine a first relative abundance of the first microbe by normalizing the measure using the aggregate measure, wherein the first measure is the first relative abundance; and
determine a second relative abundance of the second microbe by normalizing the different measure using the aggregate measure, wherein the second measure is the second relative abundance.
14. The non-transitory computer-readable storage medium of claim 12 , storing further instructions for controlling the computer system to:
determine a first product between a value of the first relative abundance and the value of the first relative abundance;
determine a second product between the value of the first relative abundance and a value of the second relative abundance; and
determine a third product between the value of the second relative abundance and the value of the second relative abundance.