Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Extraction: Partition and Distribution Coefficients01:14

Extraction: Partition and Distribution Coefficients

3.8K
The distribution law or Nernst's distribution law is the law that governs the distribution of a solute between two immiscible solvents. This law, also known as the partition law, states that if a solute is added to the mixture of two immiscible solvents at a constant temperature, the solute is distributed between the two solvents in such a way that the ratio of solute concentrations in the solvents remains constant at equilibrium.
For extracting a solute from an aqueous phase into an...
3.8K
Predicting Molecular Geometry02:27

Predicting Molecular Geometry

38.5K
VSEPR Theory for Determination of Electron Pair Geometries
38.5K
One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation01:24

One-Compartment Open Model: Wagner-Nelson and Loo Riegelman Method for ka Estimation

843
This lesson introduces two critical methods in pharmacokinetics, the Wagner-Nelson and Loo-Riegelman methods, used for estimating the absorption rate constant (ka) for drugs administered via non-intravenous routes. The Wagner-Nelson method relates ka to the plasma concentration derived from the slope of a semilog percent unabsorbed time plot. However, it is limited to drugs with one-compartment kinetics and can be impacted by factors like gastrointestinal motility or enzymatic degradation.
On...
843
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

145
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...
145
Compacting Factor test01:22

Compacting Factor test

331
The compacting factor test is a method used to assess the workability of concrete. It is  especially suitable for concrete mixes containing aggregates up to one and a half inches in size. This test involves specialized equipment consisting of two truncated cone-shaped hoppers and a cylinder, all with polished interior surfaces to minimize friction.
The procedure begins by placing concrete into the upper hopper without any compaction. Once filled, the bottom door of this hopper is opened,...
331
Cluster Sampling Method01:20

Cluster Sampling Method

13.4K
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
13.4K

You might also read

Related Articles

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

Sort by
Same author

Computational Drug Repurposing for Alzheimer's Disease via Sheaf Theoretic Population-Scale Analysis of snRNA-Seq Data.

Journal of medicinal chemistry·2026
Same author

Conformation Driven Enhancement of Neurolysin Activity in Presence of a Small Molecule Activator.

bioRxiv : the preprint server for biology·2026
Same author

Undirected Exploration of Binding Pockets with Flexible Topology.

Journal of chemical theory and computation·2025
Same author

Characterization of the Two-Domain Peptide Binding Mechanism of the Human CGRP Receptor for CGRP and the Ultrahigh Affinity ssCGRP Variant.

Biochemistry·2025
Same author

Markov State Models with Weighted Ensemble Simulation: How to Eliminate the Trajectory Merging Bias.

Journal of chemical theory and computation·2025
Same author

AGDIFF: Attention-Enhanced Diffusion for Molecular Geometry Prediction.

Journal of chemical information and modeling·2025

Related Experiment Video

Updated: Oct 31, 2025

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry
12:11

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Published on: April 8, 2020

8.4K

Predicting partition coefficients for the SAMPL7 physical property challenge using the ClassicalGSG method.

Nazanin Donyapour1, Alex Dickson2,3

  • 1Department of Computational Mathematics, Science and Engineering, Michigan State University, East Lansing, MI, USA.

Journal of Computer-Aided Molecular Design
|June 28, 2021
PubMed
Summary

Geometric Scattering for Graphs (GSG) accurately predicts molecule properties for the SAMPL challenge. Models using MMFF94 force field parameters achieved top rankings, demonstrating improved prediction accuracy.

Keywords:
Chemical featuresGeometric scattering for graphsLog PMachine learningMolecular representationsNeural networksPartition coefficientSAMPL7 challenge

More Related Videos

Online Size-exclusion and Ion-exchange Chromatography on a SAXS Beamline
11:09

Online Size-exclusion and Ion-exchange Chromatography on a SAXS Beamline

Published on: January 5, 2017

17.6K
Assembly and Characterization of Polyelectrolyte Complex Micelles
08:44

Assembly and Characterization of Polyelectrolyte Complex Micelles

Published on: March 2, 2020

11.1K

Related Experiment Videos

Last Updated: Oct 31, 2025

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry
12:11

Computation of Atmospheric Concentrations of Molecular Clusters from ab initio Thermochemistry

Published on: April 8, 2020

8.4K
Online Size-exclusion and Ion-exchange Chromatography on a SAXS Beamline
11:09

Online Size-exclusion and Ion-exchange Chromatography on a SAXS Beamline

Published on: January 5, 2017

17.6K
Assembly and Characterization of Polyelectrolyte Complex Micelles
08:44

Assembly and Characterization of Polyelectrolyte Complex Micelles

Published on: March 2, 2020

11.1K

Area of Science:

  • Computational chemistry and cheminformatics
  • Machine learning applications in drug discovery

Background:

  • Accurate prediction of molecule properties is crucial for drug discovery and development.
  • The Statistical Assessment of the Modeling of Proteins and Ligands (SAMPL) challenges benchmark prediction methods.
  • Existing methods often require extensive feature engineering or complex model training.

Purpose of the Study:

  • To evaluate the Geometric Scattering for Graphs (GSG) method for predicting molecule properties, specifically [Formula: see text] values.
  • To assess the performance of GSG when applied to the unique chemical space of the SAMPL7 challenge, featuring sulfonyl moieties.
  • To compare the efficacy of different classical molecular force fields as input for GSG models.

Main Methods:

  • Utilized Geometric Scattering for Graphs (GSG) to convert atomic attributes (partial charges, Lennard-Jones parameters) into molecular features.
  • Trained neural networks using GSG features on a large dataset of over 41,000 [Formula: see text] values.
  • Developed specialized models by filtering the training data based on chemical types and the presence of sulfonyl groups for SAMPL7.

Main Results:

  • The ranked GSG prediction achieved 5th place in the SAMPL7 challenge with an RMSE of 0.77 and MAE of 0.62.
  • A non-ranked GSG prediction secured 1st place among all submissions, achieving an RMSE of 0.55 and MAE of 0.44.
  • Models trained using Merck Molecular Force Field 94 (MMFF94) atomic attributes demonstrated superior accuracy compared to those using CGenFF.

Conclusions:

  • Geometric Scattering for Graphs (GSG) is a highly effective method for predicting molecule properties, outperforming many other approaches.
  • The GSG method, particularly when combined with MMFF94 force field parameters, shows significant promise for end-to-end [Formula: see text] prediction.
  • The findings highlight the importance of selecting appropriate atomic attributes and force fields for optimizing machine learning models in cheminformatics.