Human limits in machine learning: prediction of potato yield and disease using soil microbiome data

Abstract Background The preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide one of the first comprehensive investigations into the predictive potential of machine learning models for understa...

Full description

Saved in:
Bibliographic Details
Main Authors: Rosa Aghdam, Xudong Tang, Shan Shan, Richard Lankau, Claudia Solís-Lemus
Format: Article
Language:English
Published: BMC 2024-11-01
Series:BMC Bioinformatics
Subjects:
Online Access:https://doi.org/10.1186/s12859-024-05977-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846147351423483904
author Rosa Aghdam
Xudong Tang
Shan Shan
Richard Lankau
Claudia Solís-Lemus
author_facet Rosa Aghdam
Xudong Tang
Shan Shan
Richard Lankau
Claudia Solís-Lemus
author_sort Rosa Aghdam
collection DOAJ
description Abstract Background The preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide one of the first comprehensive investigations into the predictive potential of machine learning models for understanding the connections between soil and biological phenotypes. We investigate an integrative framework performing accurate machine learning-based prediction of plant performance from biological, chemical, and physical properties of the soil via two models: random forest and Bayesian neural network. Results Prediction improves when we add environmental features, such as soil properties and microbial density, along with microbiome data. Different preprocessing strategies show that human decisions significantly impact predictive performance. We show that the naive total sum scaling normalization that is commonly used in microbiome research is one of the optimal strategies to maximize predictive power. Also, we find that accurately defined labels are more important than normalization, taxonomic level, or model characteristics. ML performance is limited when humans can’t classify samples accurately. Lastly, we provide domain scientists via a full model selection decision tree to identify the human choices that optimize model prediction power. Conclusions Our study highlights the importance of incorporating diverse environmental features and careful data preprocessing in enhancing the predictive power of machine learning models for soil and biological phenotype connections. This approach can significantly contribute to advancing agricultural practices and soil health management.
format Article
id doaj-art-6525ebd742914ad1aa1c5a17ca490b4f
institution Kabale University
issn 1471-2105
language English
publishDate 2024-11-01
publisher BMC
record_format Article
series BMC Bioinformatics
spelling doaj-art-6525ebd742914ad1aa1c5a17ca490b4f2024-12-01T12:47:36ZengBMCBMC Bioinformatics1471-21052024-11-0125113310.1186/s12859-024-05977-2Human limits in machine learning: prediction of potato yield and disease using soil microbiome dataRosa Aghdam0Xudong Tang1Shan Shan2Richard Lankau3Claudia Solís-Lemus4Wisconsin Institute for Discovery, University of Wisconsin-MadisonWisconsin Institute for Discovery, University of Wisconsin-MadisonDepartment of Plant Pathology, University of Wisconsin-MadisonDepartment of Plant Pathology, University of Wisconsin-MadisonWisconsin Institute for Discovery, University of Wisconsin-MadisonAbstract Background The preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide one of the first comprehensive investigations into the predictive potential of machine learning models for understanding the connections between soil and biological phenotypes. We investigate an integrative framework performing accurate machine learning-based prediction of plant performance from biological, chemical, and physical properties of the soil via two models: random forest and Bayesian neural network. Results Prediction improves when we add environmental features, such as soil properties and microbial density, along with microbiome data. Different preprocessing strategies show that human decisions significantly impact predictive performance. We show that the naive total sum scaling normalization that is commonly used in microbiome research is one of the optimal strategies to maximize predictive power. Also, we find that accurately defined labels are more important than normalization, taxonomic level, or model characteristics. ML performance is limited when humans can’t classify samples accurately. Lastly, we provide domain scientists via a full model selection decision tree to identify the human choices that optimize model prediction power. Conclusions Our study highlights the importance of incorporating diverse environmental features and careful data preprocessing in enhancing the predictive power of machine learning models for soil and biological phenotype connections. This approach can significantly contribute to advancing agricultural practices and soil health management.https://doi.org/10.1186/s12859-024-05977-2Soil microbiomePhenotype predictionMicrobiome networks analysisMachine learningBayesian neural networks
spellingShingle Rosa Aghdam
Xudong Tang
Shan Shan
Richard Lankau
Claudia Solís-Lemus
Human limits in machine learning: prediction of potato yield and disease using soil microbiome data
BMC Bioinformatics
Soil microbiome
Phenotype prediction
Microbiome networks analysis
Machine learning
Bayesian neural networks
title Human limits in machine learning: prediction of potato yield and disease using soil microbiome data
title_full Human limits in machine learning: prediction of potato yield and disease using soil microbiome data
title_fullStr Human limits in machine learning: prediction of potato yield and disease using soil microbiome data
title_full_unstemmed Human limits in machine learning: prediction of potato yield and disease using soil microbiome data
title_short Human limits in machine learning: prediction of potato yield and disease using soil microbiome data
title_sort human limits in machine learning prediction of potato yield and disease using soil microbiome data
topic Soil microbiome
Phenotype prediction
Microbiome networks analysis
Machine learning
Bayesian neural networks
url https://doi.org/10.1186/s12859-024-05977-2
work_keys_str_mv AT rosaaghdam humanlimitsinmachinelearningpredictionofpotatoyieldanddiseaseusingsoilmicrobiomedata
AT xudongtang humanlimitsinmachinelearningpredictionofpotatoyieldanddiseaseusingsoilmicrobiomedata
AT shanshan humanlimitsinmachinelearningpredictionofpotatoyieldanddiseaseusingsoilmicrobiomedata
AT richardlankau humanlimitsinmachinelearningpredictionofpotatoyieldanddiseaseusingsoilmicrobiomedata
AT claudiasolislemus humanlimitsinmachinelearningpredictionofpotatoyieldanddiseaseusingsoilmicrobiomedata