Converging XGboost Machine Learning and Molecular Docking Strategies to Identify Attractants for Ceratitis capitata: Molecular Characterization and Database Curation of Natural Ligands for In Vitro/In Vivo Tests

  • 0Laboratory of Molecular Modelling Applied to Pharmacy (LAMMAF)-Graduate Program in Biosciences; Graduate Program in Health and Biological Sciences, Federal University of Vale do São Francisco, Petrolina, Pernambuco, Brazil.

|

|

Summary

This summary is machine-generated.

Researchers used computational methods to identify potential attractants for the Mediterranean fruit fly, creating a database of 206 natural products for sustainable pest control strategies.

Area Of Science

  • Agricultural Entomology
  • Computational Chemistry
  • Pest Management

Background

  • The Mediterranean fruit fly (Ceratitis capitata) is a major agricultural pest causing significant economic damage.
  • Conventional insecticides pose environmental and health risks, necessitating sustainable alternatives like semiochemicals.
  • Understanding insect olfaction, particularly the role of Odorant Binding Proteins (OBPs), is key to developing novel attractants.

Purpose Of The Study

  • To computationally identify potential molecular attractants for Ceratitis capitata.
  • To develop a curated database of natural products with potential attractant properties.
  • To prioritize candidate molecules for experimental validation in pest management strategies.

Main Methods

  • Integrated computational approaches: Machine Learning (ML)-based Quantitative Structure-Activity Relationships (QSAR), molecular docking, and Molecular Dynamics (MD) simulations.
  • Developed an XGBoost model using the Bee Colony Algorithm to identify key molecular descriptors for attractant effects.
  • Screened the NuBBE database of Brazilian natural products for potential attractants using QSAR and docking.

Main Results

  • Identified five essential molecular descriptors explaining attractant effects of known compounds.
  • Generated a curated database of 206 potential attractant molecules from over 2000 natural products.
  • 16 of the top 20 docked compounds were predicted as attractors by the XGBoost model, indicating strong agreement between methods.

Conclusions

  • Computational methods effectively prioritize natural products as potential attractants for Ceratitis capitata.
  • The curated database of 206 compounds serves as a valuable resource for selecting molecules for experimental testing.
  • This study advances sustainable pest management by providing a cost-effective approach to discover novel semiochemicals.

Related Concept Videos

Ligand Binding Sites 02:40

14.9K

Proteins are dynamic macromolecules that carry out a wide variety of essential processes; however, the activities of most proteins depend on their interactions with other molecules or ions, known as ligands.
Protein-ligand interactions are quite specific; even though numerous potential ligands surround a cellular protein at any given time, only a particular ligand can bind to that protein. Moreover, a ligand binds only to a dedicated area on the surface of the protein, known as the...

The Equilibrium Binding Constant and Binding Strength 02:18

14.9K

The equilibrium binding constant (Kb) quantifies the strength of a protein-ligand interaction. Kb can be calculated as follows when the reaction is at equilibrium:

where  P and L are the unbound protein and ligand, respectively, and PL is the protein-ligand complex. 
As the amount of bound ligand is also related to the rate of ligand binding, experiments can also determine Kb by examining the rates of protein-ligand association (kon) and dissociation (koff) using the following ratio:

Thus,...

Conserved Binding Sites 01:49

5.0K

Many proteins’ biological role depends on their interactions with their ligands, small molecules that bind to specific locations on the protein known as ligand-binding sites. Ligand-binding sites are often conserved among homologous proteins as these sites are critical for protein function.
Binding sites are often located in large pockets, and if their location on a protein’s surface is unknown, it can be predicted using various approaches. The energetic method computationally...