DMAKit: A user-friendly web platform for bringing state-of-the-art data analysis techniques to non-specific users

Medina-Ortiz, David; Contreras, Sebastián; Quiroz, Cristofer; Asenjo, Juan A.; Olivera-Nappa, Álvaro

doi:10.1016/j.is.2020.101557

Cited by 17 publications

(13 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We first train a doc2vec autoencoder on the descriptions of the physicochemical properties in the AAIndex database and apply it over the same dataset to obtain embedding representations. We then explore different classical unsupervised learning algorithms and combinations of their hyperparameters (as described in the exploration stage in Medina-Ortiz et al (2020b , c) ) to obtain several candidate partitions of the dataset.…”

Section: Methodsmentioning

confidence: 99%

Generalized Property-Based Encoders and Digital Signal Processing Facilitate Predictive Tasks in Protein Engineering

Medina-Ortiz

Contreras

Amado-Hinojosa

et al. 2022

Front. Mol. Biosci.

Self Cite

View full text Add to dashboard Cite

Computational methods in protein engineering often require encoding amino acid sequences, i.e., converting them into numeric arrays. Physicochemical properties are a typical choice to define encoders, where we replace each amino acid by its value for a given property. However, what property (or group thereof) is best for a given predictive task remains an open problem. In this work, we generalize property-based encoding strategies to maximize the performance of predictive models in protein engineering. First, combining text mining and unsupervised learning, we partitioned the AAIndex database into eight semantically-consistent groups of properties. We then applied a non-linear PCA within each group to define a single encoder to represent it. Then, in several case studies, we assess the performance of predictive models for protein and peptide function, folding, and biological activity, trained using the proposed encoders and classical methods (One Hot Encoder and TAPE embeddings). Models trained on datasets encoded with our encoders and converted to signals through the Fast Fourier Transform (FFT) increased their precision and reduced their overfitting substantially, outperforming classical approaches in most cases. Finally, we propose a preliminary methodology to create de novo sequences with desired properties. All these results offer simple ways to increase the performance of general and complex predictive tasks in protein engineering without increasing their complexity.

show abstract

Section: Methodsmentioning

confidence: 99%

Generalized Property-Based Encoders and Digital Signal Processing Facilitate Predictive Tasks in Protein Engineering

Medina-Ortiz

Contreras

Amado-Hinojosa

et al. 2022

Front. Mol. Biosci.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Statistical analysis and parameter-fitting were performed in MATLAB version R2020a, using the Global Optimization and Statistics toolboxes, partially executed on the Chilean National Laboratory for High-Performance Computation (NLHPC) servers. Other exploratory and statistical analyses were performed using the DMAKit-Lib Python library ( 28 ). Model equations and parameters/NDNs are described in the Supplementary Material , Section 4.…”

Section: Methodsmentioning

confidence: 99%

Patient-Wise Methodology to Assess Glycemic Health Status: Applications to Quantify the Efficacy and Physiological Targets of Polyphenols on Glycemic Control

et al. 2022

Self Cite

View full text Add to dashboard Cite

A growing body of evidence indicates that dietary polyphenols could be used as an early intervention to treat glucose-insulin (G-I) dysregulation. However, studies report heterogeneous information, and the targets of the intervention remain largely elusive. In this work, we provide a general methodology to quantify the effects of any given polyphenol-rich food or formulae over glycemic regulation in a patient-wise manner using an Oral Glucose Tolerance Test (OGTT). We use a mathematical model to represent individual OGTT curves as the coordinated action of subsystems, each one described by a parameter with physiological interpretation. Using the parameter values calculated for a cohort of 1198 individuals, we propose a statistical model to calculate the risk of dysglycemia and the coordination among subsystems for each subject, thus providing a continuous and individual health assessment. This method allows identifying individuals at high risk of dysglycemia—which would have been missed with traditional binary diagnostic methods—enabling early nutritional intervention with a polyphenol-supplemented diet where it is most effective and desirable. Besides, the proposed methodology assesses the effectiveness of interventions over time when applied to the OGTT curves of a treated individual. We illustrate the use of this method in a case study to assess the dose-dependent effects of Delphinol® on reducing dysglycemia risk and improving the coordination between subsystems. Finally, this strategy enables, on the one hand, the use of low-cost, non-invasive methods in population-scale nutritional studies. On the other hand, it will help practitioners assess the effectiveness of an intervention based on individual vulnerabilities and adapt the treatment to manage dysglycemia and avoid its progression into disease.

show abstract

“…Then, we used the ModLamp library ( 19 ) to characterize the peptides based on physicochemical and thermodynamic properties. Statistical properties were obtained for each sequence using the DMAKit-Lib library ( 16 ). Finally, the amino acid frequency for each sequence was obtained through scripts implemented in Python v3.6.…”

Section: Methodsmentioning

confidence: 99%

“…Display components were optimized using Bootstrap 4. All the model members, including all service disposed in this work’s proposed tool, were developed using Python v3 programming language, supported by the libraries DMAKit-Lib ( 16 ) and Scikit-Learn ( 21 ). Both the proposed software architecture and implementation features are detailed in section 2 of Supplementary Information .…”

Section: Methodsmentioning

confidence: 99%

Peptipedia: a user-friendly web application and a comprehensive database for peptide research supported by Machine Learning approach

et al. 2021

Self Cite

View full text Add to dashboard Cite

Peptides have attracted attention during the last decades due to their extraordinary therapeutic properties. Different computational tools have been developed to take advantage of existing information, compiling knowledge and making available the information for common users. Nevertheless, most related tools available are not user-friendly, present redundant information, do not clearly display the data, and usually are specific for particular biological activities, not existing so far, an integrated database with consolidated information to help research peptide sequences. To solve these necessities, we developed Peptipedia, a user-friendly web application and comprehensive database to search, characterize and analyse peptide sequences. Our tool integrates the information from 30 previously reported databases with a total of 92 055 amino acid sequences, making it the biggest repository of peptides with recorded activities to date. Furthermore, we make available a variety of bioinformatics services and statistical modules to increase our tool’s usability. Moreover, we incorporated a robust assembled binary classification system to predict putative biological activities for peptide sequences. Our tools’ significant differences with other existing alternatives become a substantial contribution for developing biotechnological and bioengineering applications for peptides. Peptipedia is available for non-commercial use as an open-access software, licensed under the GNU General Public License, version GPL 3.0. The web platform is publicly available at peptipedia.cl. Database URL: Both the source code and sample data sets are available in the GitHub repository https://github.com/ProteinEngineering-PESB2/peptipedia

show abstract

DMAKit: A user-friendly web platform for bringing state-of-the-art data analysis techniques to non-specific users

Cited by 17 publications

References 26 publications

Generalized Property-Based Encoders and Digital Signal Processing Facilitate Predictive Tasks in Protein Engineering

Generalized Property-Based Encoders and Digital Signal Processing Facilitate Predictive Tasks in Protein Engineering

Patient-Wise Methodology to Assess Glycemic Health Status: Applications to Quantify the Efficacy and Physiological Targets of Polyphenols on Glycemic Control

Peptipedia: a user-friendly web application and a comprehensive database for peptide research supported by Machine Learning approach

Contact Info

Product

Resources

About