Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Neural Regulation

Neural Regulation

Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.

Regression Toward the Mean

Regression Toward the Mean

Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when researchers try to extrapolate results...

Residuals and Least-Squares Property

Residuals and Least-Squares Property

The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...

Neural Regulation of Blood Pressure

Neural Regulation of Blood Pressure

The neural regulation of blood pressure involves intricate interactions between the autonomic nervous system (ANS) and cardiovascular system, ensuring adequate perfusion of tissues. This regulation primarily occurs through baroreceptor and chemoreceptor reflexes, involving both short-term and long-term mechanisms.
Baroreceptor Reflex
Baroreceptors, located in the carotid sinuses and aortic arch, detect changes in blood pressure. When blood pressure rises, these stretch-sensitive receptors...

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

De novo Drug Design - Ye olde Scoring Problem Revisited.

Molecular informatics·2017

Same author

Surface-water Interface Induces Conformational Changes Critical for Protein Adsorption: Implications for Monolayer Formation of EAS Hydrophobin.

Frontiers in molecular biosciences·2015

Same author

Robust modelling of solubility in supercritical carbon dioxide using Bayesian methods.

Journal of molecular graphics & modelling·2010

Same author

The broader applications of neural and genetic modelling methods.

Drug discovery today·2001

Search research articles

Related Experiment Videos

Bayesian regularization of neural networks.

Frank Burden¹, Dave Winkler

¹Scimetrics, Carlton North, Victoria, Australia.

Methods in Molecular Biology (Clifton, N.J.)

|December 11, 2008

Summary

Bayesian regularized artificial neural networks (BRANNs) offer a more robust alternative to standard neural networks, reducing the need for extensive cross-validation in QSAR modeling. These networks improve model reliability and variable selection through automatic relevance determination.

Related Experiment Videos

Area of Science:

Computational Chemistry
Cheminformatics
Machine Learning

Background:

Standard artificial neural networks often require extensive cross-validation, which can be computationally intensive.
Back-propagation networks can be prone to overfitting and may struggle with model robustness.
Quantitative Structure-Activity Relationship (QSAR) modeling benefits from robust and efficient predictive techniques.

Purpose of the Study:

To introduce and detail the Bayesian regularized artificial neural network (BRANN) method for QSAR modeling.
To highlight the advantages of BRANNs over standard back-propagation networks, particularly in terms of robustness and validation.
To demonstrate the application of BRANNs for improving model selection, validation, and network architecture optimization.

Main Methods:

Bayesian regularization is applied to convert nonlinear regression into a well-posed statistical problem, akin to ridge regression.
BRANNs inherently reduce overfitting by training on an effective number of parameters, deactivating irrelevant weights.
Automatic Relevance Determination (ARD) is employed to assess and prioritize the importance of input variables.

Main Results:

BRANNs demonstrate superior robustness compared to standard back-propagation networks.
The need for lengthy and computationally expensive cross-validation is significantly reduced or eliminated.
ARD effectively identifies and neglects irrelevant or highly correlated input variables, highlighting key predictors for activity data.

Conclusions:

BRANNs offer a robust and efficient approach to QSAR modeling, simplifying the validation process.
The method addresses key challenges in QSAR, including model selection, robustness, and architecture optimization.
BRANNs with ARD provide an objective criterion for training and enhance the interpretability of QSAR models by identifying crucial variables.