scholarly journals Lignin Biorefinery Optimization Through Machine Learning

2021 ◽  
Author(s):  
Joakim Löfgren ◽  
Dmitry Tarasov ◽  
Taru Koitto ◽  
Patrick Rinke ◽  
Mikhail Balakshin ◽  
...  
Keyword(s):  
Machine Learning ◽  
Predictive Models ◽  
Model Building ◽  
Paper Industry ◽  
2D Nmr ◽  
Hydrothermal Pretreatment ◽  
Bayesian Optimization ◽  
Learning Framework ◽  
Point Analysis ◽  
Data Points

Lignin is an abundant biomaterial that currently emerges as a low value by-product in the pulp and paper industry but could be repurposed for high-value products as part of the ongoing global transition to a sustainable society. To increase lignins value, rational and efficient approaches to optimizing lignin biorefineries to produce high value bioproducts are required. Here, we report the optimization of the AquaSolv Omni (AqSO) Biorefinery, a newly introduced biorefinery concept based on hydrothermal pretreatment and solvent extraction. We employ a machine-learning framework based on Bayesian optimization, to provide sample-efficient and guided data collection as well as surrogate model building. The surrogate models allow us to map multiple experimental outputs, including the extracted lignin yield and main structural properties obtained by 2D NMR, as functions of the hydrothermal pretreatment reaction severity and temperature. Our results show that with Bayesian optimization, predictive models can be converged with only 21 data points to within a margin of error comparable to the underlying experimental error. By applying a Pareto point analysis, we demonstrate how the predictive models can be used in tandem to identify optimal extraction conditions for concrete applications in lignin valorization.

scholarly journals Automated clinical computational biology: an interpretable machine learning framework to predict disease severity and stratify patients from clinical data

2018 ◽  
Author(s):  
soumya banerjee
Keyword(s):  
Machine Learning ◽  
Disease Severity ◽  
Clinical Data ◽  
Model Building ◽  
Learning Experience ◽  
Machine Learning Algorithms ◽  
Close Collaboration ◽  
Learning Framework ◽  
Novel Biomarkers ◽  
Automated Machine Learning

We outline an automated computational and machine learning framework that predicts disease severity andstratifies patients. We apply our framework to available clinical data. Our algorithm automatically generatesinsights and predicts disease severity with minimal operator intervention. The computational frameworkpresented here can be used to stratify patients, predict disease severity and propose novel biomarkers fordisease. Insights from machine learning algorithms coupled with clinical data may help guide therapy,personalize treatment and help clinicians understand the change in disease over time. Computationaltechniques like these can be used in translational medicine in close collaboration with clinicians and healthcareproviders. Our models are also interpretable, allowing clinicians with minimal machine learning experience toengage in model building. This work is a step towards automated machine learning in the clinic.

scholarly journals Flame: an open source framework for model development, hosting, and usage in production environments

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Manuel Pastor ◽  
José Carlos Gómez-Tamayo ◽  
Ferran Sanz
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Predictive Models ◽  
Web Application ◽  
Model Building ◽  
Molecular Descriptor ◽  
Model Development ◽  
Graphic Interface ◽  
Chemical Structures ◽  
Production Environments

AbstractThis article describes Flame, an open source software for building predictive models and supporting their use in production environments. Flame is a web application with a web-based graphic interface, which can be used as a desktop application or installed in a server receiving requests from multiple users. Models can be built starting from any collection of biologically annotated chemical structures since the software supports structural normalization, molecular descriptor calculation, and machine learning model generation using predefined workflows. The model building workflow can be customized from the graphic interface, selecting the type of normalization, molecular descriptors, and machine learning algorithm to be used from a panel of state-of-the-art methods implemented natively. Moreover, Flame implements a mechanism allowing to extend its source code, adding unlimited model customization. Models generated with Flame can be easily exported, facilitating collaborative model development. All models are stored in a model repository supporting model versioning. Models are identified by unique model IDs and include detailed documentation formatted using widely accepted standards. The current version is the result of nearly 3 years of development in collaboration with users from the pharmaceutical industry within the IMI eTRANSAFE project, which aims, among other objectives, to develop high-quality predictive models based on shared legacy data for assessing the safety of drug candidates.

scholarly journals Accelerated design and discovery of perovskites with high conductivity for energy applications through machine learning

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Pikee Priya ◽  
N. R. Aluru
Keyword(s):  
Machine Learning ◽  
Charge Carriers ◽  
Total Conductivity ◽  
Learning Tools ◽  
Robust Learning ◽  
Energy Applications ◽  
Learning Framework ◽  
Average Ionic Radius ◽  
Data Points ◽  
A Site

AbstractWe use machine learning tools for the design and discovery of ABO3-type perovskite oxides for various energy applications, using over 7000 data points from the literature. We demonstrate a robust learning framework for efficient and accurate prediction of total conductivity of perovskites and their classification based on the type of charge carrier at different conditions of temperature and environment. After evaluating a set of >100 features, we identify average ionic radius, minimum electronegativity, minimum atomic mass, minimum formation energy of oxides for all B-site, and B-site dopant ions of the perovskite as the crucial and relevant predictors for determining conductivity and the type of charge carriers. The models are validated by predicting the conductivity of compounds absent in the training set. We screen 1793 undoped and 95,832 A-site and B-site doped perovskites to report the perovskites with high conductivities, which can be used for different energy applications, depending on the type of the charge carriers.

An Introduction to the Federated Learning Standard

2022 ◽  
Vol 25 (3) ◽  
pp. 18-22
Author(s):  
Ticao Zhang ◽  
Shiwen Mao
Keyword(s):  
Machine Learning ◽  
Performance Evaluation ◽  
Data Privacy ◽  
Model Building ◽  
Evaluation Criteria ◽  
Regulatory Requirements ◽  
Privacy And Security ◽  
Learning Framework ◽  
Learning Tasks ◽  
Decentralized Learning

With the growing concern on data privacy and security, it is undesirable to collect data from all users to perform machine learning tasks. Federated learning, a decentralized learning framework, was proposed to construct a shared prediction model while keeping owners' data on their own devices. This paper presents an introduction to the emerging federated learning standard and discusses its various aspects, including i) an overview of federated learning, ii) types of federated learning, iii) major concerns and the performance evaluation criteria of federated learning, and iv) associated regulatory requirements. The purpose of this paper is to provide an understanding of the standard and facilitate its usage in model building across organizations while meeting privacy and security concerns.

scholarly journals Machine Learning With K-Means Dimensional Reduction for Predicting Survival Outcomes in Patients With Breast Cancer

2018 ◽  
Vol 17 ◽  
pp. 117693511881021 ◽  
Author(s):  
Melissa Zhao ◽  
Yushi Tang ◽  
Hyunkyung Kim ◽  
Kohei Hasegawa
Keyword(s):  
Breast Cancer ◽  
Gene Expression ◽  
Machine Learning ◽  
Predictive Models ◽  
Dimensional Reduction ◽  
Variable Importance ◽  
Classification Model ◽  
Support Vector ◽  
Knn Classification ◽  
Data Points

Objective: Despite existing prognostic markers, breast cancer prognosis remains a difficult subject due to the complex relationships between many contributing factors and survival. This study seeks to integrate multiple clinicopathological and genomic factors with dimensional reduction across machine learning algorithms to compare survival predictions. Methods: This is a secondary analysis of the data from a prospective cohort study of female patients with breast cancer enrolled in the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC). We constructed a series of predictive models: ensemble models (Gradient Boosting and Random Forest), support vector machine (SVM), and artificial neural networks (ANN) for 5-year survival based on clinicopathological and gene expression data after K-means clustering with K-nearest-neighbor (KNN) classification. Model performance was evaluated by receiver operating characteristic (ROC) curve, accuracy, and calibration slope (CS). Model stability was assessed over 10 random runs in terms of ROC, accuracy, CS, and variable importance. Results: The analytic cohort is composed of 1874 patients with breast cancer. Overall, the median age was 62 years; the 5-year survival rate was 75%. ROC and accuracy were not significantly different between models (ROC and accuracy around 0.67 and 0.72 across models, respectively). However, ensemble methods resulted in better fit (CS) with stable measures of variable importance across 10 random training/validation splits. K-means clustering of gene expression profiles on training data points along with KNN classification of validation data points was a robust method of dimensional reduction. Furthermore, the gene expression cluster with the highest mortality risk was an influential factor in model prediction. Conclusions: Using machine learning methods to construct predictive models for 5-year survival in patients with breast cancer, we demonstrated discrimination ability across models with new insight into the stability and utility of dimensional reduction on genomic features in breast cancer survival prediction.

scholarly journals Machine learning for financial forecasting, planning and analysis: recent developments and pitfalls

2021 ◽  
Author(s):  
Helmut Wasserbacher ◽  
Martin Spindler
Keyword(s):  
Machine Learning ◽  
Resource Allocation ◽  
Simulation Study ◽  
Machine Learning Techniques ◽  
Automated Extraction ◽  
Financial Forecasting ◽  
Learning Framework ◽  
Learning Techniques ◽  
Recent Developments ◽  
Data Points

AbstractThis article is an introduction to machine learning for financial forecasting, planning and analysis (FP&A). Machine learning appears well suited to support FP&A with the highly automated extraction of information from large amounts of data. However, because most traditional machine learning techniques focus on forecasting (prediction), we discuss the particular care that must be taken to avoid the pitfalls of using them for planning and resource allocation (causal inference). While the naive application of machine learning usually fails in this context, the recently developed double machine learning framework can address causal questions of interest. We review the current literature on machine learning in FP&A and illustrate in a simulation study how machine learning can be used for both forecasting and planning. We also investigate how forecasting and planning improve as the number of data points increases.

scholarly journals Flame: An Open Source Framework for Model Development, Hosting, and Usage in Production Environments

2020 ◽  
Author(s):  
Manuel Pastor ◽  
José Carlos Gómez-Tamayo ◽  
Ferran Sanz
Keyword(s):  
Machine Learning ◽  
Open Source ◽  
Predictive Models ◽  
Web Application ◽  
Model Building ◽  
Molecular Descriptor ◽  
Model Development ◽  
Graphic Interface ◽  
Chemical Structures ◽  
Production Environments

Abstract This article describes Flame, an open source software for building predictive models and supporting their use in production environments. Flame is a web application, with a Python backend and a web-based graphic interface, which can be used as a desktop application or installed in a server receiving requests from multiple users. Models can be built starting from any collection of biologically annotated chemical structures, since the software supports structural normalization, molecular descriptor generation and machine learning building, using predefined workflows. The model building workflow can be customized from the graphic interface, selecting the type of normalization, molecular descriptors, and machine learning algorithm to be used from a panel of state-of-the-art methods implemented natively. Moreover, Flame implements a mechanism allowing to extend its source code adding unlimited model customization. Models generated with Flame can be easily exported facilitating collaborative model development. All models are stored in a persistent model repository supporting model versioning. Models are identified by unique model IDs and include detailed documentation formatted using widely accepted standards. The current version is the result of nearly three years of development in collaboration with users from pharmaceutical industry within the IMI eTRANSAFE project, which aims, among other objectives, to develop high quality predictive models based on shared legacy data for assessing the safety of drug candidates.

Sign in / Sign up

Export Citation Format

Share Document