scholarly journals Explainable machine learning models of major crop traits from satellite-monitored continent-wide field trial data

2021 ◽  
Author(s):  
Saul Justin Newman ◽  
Robert T Furbank
Keyword(s):  
Machine Learning ◽  
Field Experiments ◽  
Agronomic Traits ◽  
Biological Data ◽  
Wide Field ◽  
Learning Models ◽  
Crop Species ◽  
Complex Interactions ◽  
Machine Learning Models

AbstractFour species of grass generate half of all human-consumed calories1. However, abundant biological data on species that produce our food remains largely inaccessible, imposing direct barriers to understanding crop yield and fitness traits. Here, we assemble and analyse a continent-wide database of field experiments spanning ten years and hundreds of thousands of machine-phenotyped populations of ten major crop species. Training an ensemble of machine learning models, using thousands of variables capturing weather, ground-sensor, soil, chemical and fertiliser dosage, management, and satellite data, produces robust cross-continent yield models exceeding R2 = 0.8 prediction accuracy. In contrast to ‘black box’ analytics, detailed interrogation of these models reveals fundamental drivers of crop behaviour and complex interactions predicting yield and agronomic traits. These results demonstrate the capacity of machine learning models to build unified, interpretable, and explainable models of crop behaviour, and highlight the powerful role of data in the future of food.

scholarly journals Machine Learning Data Augmentation as a Tool to Enhance Quantitative Composition–Activity Relationships of Complex Mixtures. A New Application to Dissect the Role of Main Chemical Components in Bioactive Essential Oils

Molecules ◽  
2021 ◽  
Vol 26 (20) ◽  
pp. 6279
Author(s):  
Alessio Ragno ◽  
Anna Baldisserotto ◽  
Lorenzo Antonini ◽  
Manuela Sabatino ◽  
Filippo Sapienza ◽  
...  
Keyword(s):  
Machine Learning ◽  
Essential Oils ◽  
Data Augmentation ◽  
Biological Data ◽  
Chemical Components ◽  
Quantitative Composition ◽  
Chemical Compositions ◽  
Learning Models ◽  
Machine Learning Models

Scientific investigation on essential oils composition and the related biological profile are continuously growing. Nevertheless, only a few studies have been performed on the relationships between chemical composition and biological data. Herein, the investigation of 61 assayed essential oils is reported focusing on their inhibition activity against Microsporum spp including development of machine learning models with the aim of highlining the possible chemical components mainly related to the inhibitory potency. The application of machine learning and deep learning techniques for predictive and descriptive purposes have been applied successfully to many fields. Quantitative composition–activity relationships machine learning-based models were developed for the 61 essential oils tested as Microsporum spp growth modulators. The models were built with in-house python scripts implementing data augmentation with the purpose of having a smoother flow between essential oils’ chemical compositions and biological data. High statistical coefficient values (Accuracy, Matthews correlation coefficient and F1 score) were obtained and model inspection permitted to detect possible specific roles related to some components of essential oils’ constituents. Robust machine learning models are far more useful tools to reveal data augmentation in comparison with raw data derived models. To the best of the authors knowledge this is the first report using data augmentation to highlight the role of complex mixture components, in particular a first application of these data will be for the development of ingredients in the dermo-cosmetic field investigating microbial species considering the urge for the use of natural preserving and acting antimicrobial agents.

scholarly journals Assessing the performance of a suite of machine learning models for daily river water temperature prediction

PeerJ ◽  
2019 ◽  
Vol 7 ◽  
pp. e7065 ◽  
Author(s):  
Senlin Zhu ◽  
Emmanuel Karlo Nyarko ◽  
Marijana Hadzima-Nyarko ◽  
Salim Heddam ◽  
Shiqiang Wu
Keyword(s):  
Machine Learning ◽  
Water Temperature ◽  
River Water ◽  
Minor Role ◽  
Learning Models ◽  
Temperature Prediction ◽  
Flow Discharge ◽  
River Water Temperature ◽  
Machine Learning Models

In this study, different versions of feedforward neural network (FFNN), Gaussian process regression (GPR), and decision tree (DT) models were developed to estimate daily river water temperature using air temperature (Ta), flow discharge (Q), and the day of year (DOY) as predictors. The proposed models were assessed using observed data from eight river stations, and modelling results were compared with the air2stream model. Model performances were evaluated using four indicators in this study: the coefficient of correlation (R), the Willmott index of agreement (d), the root mean squared error (RMSE), and the mean absolute error (MAE). Results indicated that the three machine learning models had similar performance when only Ta was used as the predictor. When the day of year was included as model input, the performances of the three machine learning models dramatically improved. Including flow discharge instead of day of year, as an additional predictor, provided a lower gain in model accuracy, thereby showing the relatively minor role of flow discharge in river water temperature prediction. However, an increase in the relative importance of flow discharge was noticed for stations with high altitude catchments (Rhône, Dischmabach and Cedar) which are influenced by cold water releases from hydropower or snow melting, suggesting the dependence of the role of flow discharge on the hydrological characteristics of such rivers. The air2stream model outperformed the three machine learning models for most of the studied rivers except for the cases where including flow discharge as a predictor provided the highest benefits. The DT model outperformed the FFNN and GPR models in the calibration phase, however in the validation phase, its performance slightly decreased. In general, the FFNN model performed slightly better than GPR model. In summary, the overall modelling results showed that the three machine learning models performed well for river water temperature modelling.

Machine learning predictive models of LDL-C in the population of eastern India and its comparison with directly measured and calculated LDL-C

2021 ◽  
pp. 000456322110468
Author(s):  
Anudeep P P ◽  
Suchitra Kumari ◽  
Aishvarya S Rajasimman ◽  
Saurav Nayak ◽  
Pooja Priyadarsini
Keyword(s):  
Machine Learning ◽  
Linear Regression ◽  
Random Forests ◽  
Predictive Performance ◽  
Support Vector ◽  
Learning Models ◽  
Complex Interactions ◽  
Clinical Biochemistry Laboratory ◽  
Study Laboratory ◽  
Machine Learning Models

Background LDL-C is a strong risk factor for cardiovascular disorders. The formulas used to calculate LDL-C showed varying performance in different populations. Machine learning models can study complex interactions between the variables and can be used to predict outcomes more accurately. The current study evaluated the predictive performance of three machine learning models—random forests, XGBoost, and support vector Rregression (SVR) to predict LDL-C from total cholesterol, triglyceride, and HDL-C in comparison to linear regression model and some existing formulas for LDL-C calculation, in eastern Indian population. Methods The lipid profiles performed in the clinical biochemistry laboratory of AIIMS Bhubaneswar during 2019–2021, a total of 13,391 samples were included in the study. Laboratory results were collected from the laboratory database. 70% of data were classified as train set and used to develop the three machine learning models and linear regression formula. These models were tested in the rest 30% of the data (test set) for validation. Performance of models was evaluated in comparison to best six existing LDL-C calculating formulas. Results LDL-C predicted by XGBoost and random forests models showed a strong correlation with directly estimated LDL-C (r = 0.98). Two machine learning models performed superior to the six existing and commonly used LDL-C calculating formulas like Friedewald in the study population. When compared in different triglycerides strata also, these two models outperformed the other methods used. Conclusion Machine learning models like XGBoost and random forests can be used to predict LDL-C with more accuracy comparing to conventional linear regression LDL-C formulas.

scholarly journals Machine learning for prediction of immunotherapy efficacy in non-small cell lung cancer from simple clinical and biological data

2021 ◽  
Author(s):  
Sébastien Benzekry ◽  
Mathieu Grangeon ◽  
Mélanie Karlsen ◽  
Maria Alexa ◽  
Isabella Bicalho-Frazeto ◽  
...  
Keyword(s):  
Machine Learning ◽  
Lung Cancer ◽  
Random Forest ◽  
Predictive Value ◽  
Performance Status ◽  
Small Cell ◽  
Biological Data ◽  
Learning Models ◽  
Small Cell Lung ◽  
Machine Learning Models

ABSTRACTBackgroundImmune checkpoint inhibitors (ICIs) are now a therapeutic standard in advanced non-small cell lung cancer (NSCLC), but strong predictive markers for ICIs efficacy are still lacking. We evaluated machine learning models built on simple clinical and biological data to individually predict response to ICIs.MethodsPatients with metastatic NSCLC who received ICI in second line or later were included. We collected clinical and hematological data and studied the association of this data with disease control rate (DCR), progression free survival (PFS) and overall survival (OS). Multiple machine learning (ML) algorithms were assessed for their ability to predict response.ResultsOverall, 298 patients were enrolled. The overall response rate and DCR were 15.3 % and 53%, respectively. Median PFS and OS were 3.3 and 11.4 months, respectively. In multivariable analysis, DCR was significantly associated with performance status (PS) and hemoglobin level (OR 0.58, p<0.0001; OR 1.8, p<0.001). These variables were also associated with PFS and OS and ranked top in random forest-based feature importance. Neutrophils-to-lymphocytes ratio was also associated with DCR, PFS and OS. The best ML algorithm was a random forest. It could predict DCR with satisfactory efficacy based on these three variables. Ten-fold cross-validated performances were: accuracy 0.68 ± 0.04, sensitivity 0.58 ± 0.08; specificity 0.78 ± 0.06; positive predictive value 0.70 ± 0.08; negative predictive value 0.68 ± 0.06; AUC 0.74 ± 0.03.ConclusionCombination of simple clinical and biological data could accurately predict disease control rate at the individual level.Highlights-Machine learning applied to a large set of NSCLC patients could predict efficacy of immunotherapy with a 69% accuracy using simple routine data-Hemoglobin levels and performance status were the strongest predictors and significantly associated with DCR, PFS and OS-Neutrophils-to-lymphocyte ratio was also associated with outcome-Benchmark of 8 machine learning models

scholarly journals DeepHE: Accurately Predicting Human Essential Genes based on Deep Learning

2020 ◽  
Author(s):  
Xue Zhang ◽  
Wangxin Xiao ◽  
Weijia Xiao
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Essential Gene ◽  
Gene Prediction ◽  
Biological Data ◽  
Essential Genes ◽  
Learning Models ◽  
Imbalanced Learning ◽  
Ppi Network ◽  
Machine Learning Models

AbstractMotivationAccurately predicting essential genes using computational methods can greatly reduce the effort in finding them via wet experiments at both time and resource scales, and further accelerate the process of drug discovery. Several computational methods have been proposed for predicting essential genes in model organisms by integrating multiple biological data sources either via centrality measures or machine learning based methods. However, the methods aiming to predict human essential genes are still limited and the performance still need improve. In addition, most of the machine learning based essential gene prediction methods are lack of skills to handle the imbalanced learning issue inherent in the essential gene prediction problem, which might be one factor affecting their performance.ResultsWe proposed a deep learning based method, DeepHE, to predict human essential genes by integrating features derived from sequence data and protein-protein interaction (PPI) network. A deep learning based network embedding method was utilized to automatically learn features from PPI network. In addition, 89 sequence features were derived from DNA sequence and protein sequence for each gene. These two types of features were integrated to train a multilayer neural network. A cost-sensitive technique was used to address the imbalanced learning problem when training the deep neural network. The experimental results for predicting human essential genes showed that our proposed method, DeepHE, can accurately predict human gene essentiality with an average AUC higher than 94%, the area under precision-recall curve (AP) higher than 90%, and the accuracy higher than 90%. We also compared DeepHE with several widely used traditional machine learning models (SVM, Naïve Bayes, Random Forest, Adaboost). The experimental results showed that DeepHE greatly outperformed the compared machine learning models.ConclusionsWe demonstrated that human essential genes can be accurately predicted by designing effective machine learning algorithm and integrating representative features captured from available biological data. The proposed deep learning framework is effective for such task.Availability and ImplementationThe python code will be freely available upon the acceptance of this manuscript at https://github.com/xzhang2016/[email protected]

Persistent spectral hypergraph based machine learning (PSH-ML) for protein-ligand binding affinity prediction

2021 ◽  
Author(s):  
Xiang Liu ◽  
Huitao Feng ◽  
Jie Wu ◽  
Kelin Xia
Keyword(s):  
Machine Learning ◽  
Ligand Binding ◽  
Binding Affinity ◽  
Molecular Descriptors ◽  
Biological Data ◽  
Learning Models ◽  
Filtration Process ◽  
Binding Affinity Prediction ◽  
Affinity Prediction ◽  
Machine Learning Models

Abstract Molecular descriptors are essential to not only quantitative structure activity/property relationship (QSAR/QSPR) models, but also machine learning based chemical and biological data analysis. In this paper, we propose persistent spectral hypergraph (PSH) based molecular descriptors or fingerprints for the first time. Our PSH-based molecular descriptors are used in the characterization of molecular structures and interactions, and further combined with machine learning models, in particular gradient boosting tree (GBT), for protein-ligand binding affinity prediction. Different from traditional molecular descriptors, which are usually based on molecular graph models, a hypergraph-based topological representation is proposed for protein–ligand interaction characterization. Moreover, a filtration process is introduced to generate a series of nested hypergraphs in different scales. For each of these hypergraphs, its eigen spectrum information can be obtained from the corresponding (Hodge) Laplacain matrix. PSH studies the persistence and variation of the eigen spectrum of the nested hypergraphs during the filtration process. Molecular descriptors or fingerprints can be generated from persistent attributes, which are statistical or combinatorial functions of PSH, and combined with machine learning models, in particular, GBT. We test our PSH-GBT model on three most commonly used datasets, including PDBbind-2007, PDBbind-2013 and PDBbind-2016. Our results, for all these databases, are better than all existing machine learning models with traditional molecular descriptors, as far as we know.

scholarly journals ARL4C is A Key Driver of Gastric Cancer: An Integrative Analysis of ARL Family Members

2020 ◽  
Author(s):  
Ning Xie ◽  
Yunfan Bai ◽  
Lu Qiao ◽  
Yuru Bai ◽  
Jian Wu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gastric Cancer ◽  
Family Members ◽  
Enrichment Analysis ◽  
Great Promise ◽  
Learning Models ◽  
Tgf Β1 ◽  
Machine Learning Models

Abstract Background: As small GTP-binding proteins, ARL family members (ARLs) have been proved to regulate the malignant phenotypes of several cancers. However, the exact role of ARLs in gastric cancer (GC) remains elusive.Methods: The expression status, interactive relations, potential pathways and genetic variations of ARLs are analyzed by bioinformatics tools. Machine learning models and enrichment analysis are performed by R platform. The biological functions of ARL4C are demonstrated by in vitro and in vivo experiments. The nomogram is further constructed to validate the prognostic value of ARL4C for GC patients.Results: ARLs are significantly dysregulated in GC and involved in various cancer-related pathways. Subsequently, machine learning models identify ARL4C as one of the two most significant diagnostic and prognostic indicators among ARLs for GC. Furthermore, ARL4C silencing remarkably reverses the epithelial-mesenchymal transition (EMT) and inhibits the growth and metastasis of GC cells both in vitro and in vivo. Moreover, enrichment analysis indicates that TGF-β1 is highly correlated with ARL4C, while ARL4C-related genes are significantly enriched in the TGF-β1 signaling. Correspondingly, we demonstrate that TGF-β1 treatment dramatically increases ARL4C expression, and ARL4C knockdown reverses TGF-β1-induced EMT possibly by inhibiting the expression of Smads, downstream factors of TGF-β1. Meanwhile, the coexpression of ARL4C and TGF-β1 worsens the prognosis of GC patients both in Kaplan-Meier analysis and nomogram model.Conclusion: Our work is of significance for comprehensively understanding the crucial role of ARLs in the carcinogenesis of GC and the specific mechanisms underlying the GC-promoting effects of TGF-β1. More importantly, we uncover the great promise of ARL4C-targeted therapy in improving the efficacy of TGF-β1 inhibitors for GC patients.

Sign in / Sign up

Export Citation Format

Share Document