DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Conotoxin Prediction: New Features to Increase Prediction Accuracy

Journal Article · · Toxins
ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [2]; ORCiD logo [2]; ORCiD logo [1]; ORCiD logo [1]
  1. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States). Bioscience Division
  2. Los Alamos National Laboratory (LANL), Los Alamos, NM (United States). Theoretical Division

Conotoxins are toxic, disulfide-bond-rich peptides from cone snail venom that target a wide range of receptors and ion channels with multiple pathophysiological effects. Conotoxins have extraordinary potential for medical therapeutics that include cancer, microbial infections, epilepsy, autoimmune diseases, neurological conditions, and cardiovascular disorders. Despite the potential for these compounds in novel therapeutic treatment development, the process of identifying and characterizing the toxicities of conotoxins is difficult, costly, and time-consuming. This challenge requires a series of diverse, complex, and labor-intensive biological, toxicological, and analytical techniques for effective characterization. While recent attempts, using machine learning based solely on primary amino acid sequences to predict biological toxins (e.g., conotoxins and animal venoms), have improved toxin identification, these methods are limited due to peptide conformational flexibility and the high frequency of cysteines present in toxin sequences. This results in an enumerable set of disulfide-bridged foldamers with different conformations of the same primary amino acid sequence that affect function and toxicity levels. Consequently, a given peptide may be toxic when its cysteine residues form a particular disulfide-bond pattern, while alternative bonding patterns (isoforms) or its reduced form (free cysteines with no disulfide bridges) may have little or no toxicological effects. Similarly, the same disulfide-bond pattern may be possible for other peptide sequences and result in different conformations that all exhibit varying toxicities to the same receptor or to different receptors. We present here new features, when combined with primary sequence features to train machine learning algorithms to predict conotoxins, that significantly increase prediction accuracy.

Research Organization:
Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
Grant/Contract Number:
89233218CNA000001
OSTI ID:
2329253
Report Number(s):
LA-UR-23-30106
Journal Information:
Toxins, Vol. 15, Issue 11; ISSN 2072-6651
Publisher:
MDPICopyright Statement
Country of Publication:
United States
Language:
English

References (41)

Structural and Dynamic Characterization of ω-Conotoxin MVIIA:  The Binding Loop Exhibits Slow Conformational Exchange, journal March 2000
Recent Advances in Conotoxin Classification by Using Machine Learning Methods journal June 2017
Structural and functional insights into the inhibition of human voltage-gated sodium channels by μ-conotoxin KIIIA disulfide isomers journal March 2022
A strategy to apply machine learning to small datasets in materials science journal May 2018
Voltage-gated potassium channels as therapeutic targets journal December 2009
Amino acid encoding for deep learning applications journal June 2020
Protein Secondary Structure Classification Revisited: Processing DSSP Information with PSSC journal June 2014
A New Level of Conotoxin Diversity, a Non-native Disulfide Bond Connectivity in α-Conotoxin AuIB Reduces Structural Definition but Increases Biological Activity journal October 2002
ClanTox: a classifier of short animal toxins journal May 2009
Announcing the worldwide Protein Data Bank journal December 2003
TOXIFY: a deep learning approach to classify animal venom proteins journal June 2019
Biological Magnetic Resonance Data Bank journal December 2022
Antitumoral Potential of Tunisian Snake Venoms Secreted Phospholipases A2 journal January 2013
Dictionary of protein secondary structure: Pattern recognition of hydrogen-bonded and geometrical features journal December 1983
A series of PDB related databases for everyday needs journal November 2010
Prediction of the types of ion channel-targeted conotoxins based on radial basis function network journal March 2013
SMOTE: Synthetic Minority Over-sampling Technique journal January 2002
Factors governing selective formation of specific disulfides in synthetic variants of .alpha.-conotoxin journal November 1991
Structure determination of the three disulfide bond isomers of α-conotoxin GI: a model for the role of disulfide bonds in structural stability 1 1Edited by P. E. Wright journal May 1998
Machine Learning Model for Identifying Antioxidant Proteins Using Features Calculated from Primary Sequences journal October 2020
Toxicity Testing in the 21st Century: A Vision and a Strategy journal June 2010
Ziconotide: Neuronal Calcium Channel Blocker for Treating Severe Chronic Pain journal December 2004
Geometric SMOTE a geometrically enhanced drop-in replacement for SMOTE journal October 2019
Predicting the Types of Ion Channel-Targeted Conotoxins Based on AVC-SVM Model journal January 2017
From Mollusks to Medicine: A Venomics Approach for the Discovery and Characterization of Therapeutics from Terebridae Peptide Toxins journal April 2016
Collision Cross Section Calculations Using HPCCS book November 2019
Toxins from cone snails: properties, applications and biotechnological production journal March 2008
MLACP: machine-learning-based prediction of anticancer peptides journal August 2017
Solution structure and proposed binding mechanism of a novel potassium channel toxin κ-conotoxin PVIIA journal December 1997
XGBoost: A Scalable Tree Boosting System conference January 2016
PDB2PQR: an automated pipeline for the setup of Poisson-Boltzmann electrostatics calculations journal July 2004
Voltage gated sodium channels as drug discovery targets journal July 2015
In Silico Approach for Predicting Toxicity of Peptides and Proteins journal September 2013
ConoServer: updated content, knowledge, and discovery tools in the conopeptide database journal November 2011
PDB2PQR: expanding and upgrading automated preparation of biomolecular structures for molecular simulations journal May 2007
Random Forests journal January 2001
Incremental Feature Selection journal November 1998
Clinical Text Mining book January 2018
Snake venoms: attractive antimicrobial proteinaceous compounds for therapeutic purposes journal May 2013
PredCSF: An Integrated Feature-Based Approach for Predicting Conotoxin Superfamily journal March 2011
Force Fields for Protein Simulations book January 2003