Related Experiment Video
Updated: May 3, 2026
Author Spotlight: A Computational Approach to Decipher Amino Acid Preferences in Multispecific Protein-Protein Interactions
Published on: January 26, 2024
An improved predictive recognition model for Cys(2)-His(2) zinc finger proteins
Ankit Gupta1, Ryan G Christensen, Heather A Bell
1Program in Gene Function and Expression, University of Massachusetts Medical School, Worcester, MA 01605, USA, Department of Biochemistry and Molecular Pharmacology, University of Massachusetts Medical School, Worcester, MA 01605, USA, Department of Genetics, Washington University School of Medicine, St Louis, MO 63108, USA, Department of Biochemistry and Biology and Biotechnology, Worcester Polytechnic Institute, Worcester, MA 01609, USA, Molecular Pathology Unit, Center for Computational and Integrative Biology, and Center for Cancer Research, Massachusetts General Hospital, Charlestown, MA 02129, USA, Department of Molecular Medicine, University of Massachusetts Medical School, Worcester, MA 01605, USA and Department of Pathology, Harvard Medical School, Boston, MA 02115, USA.
Scientists developed a new model to predict DNA-binding specificity for zinc finger proteins (ZFPs). This random forest model accurately estimates ZFP recognition, improving upon existing methods for these important transcription factors.
Area of Science:
- Molecular Biology
- Genomics
- Bioinformatics
Background:
- Cys(2)-His(2) zinc finger proteins (ZFPs) are the largest and most diverse family of transcription factors in higher metazoans.
- The DNA-binding specificity of most ZFPs is unknown and difficult to predict due to diverse recognition residues within individual fingers.
Purpose of the Study:
- To develop a comprehensive predictive model for estimating ZFP DNA-binding specificity based on amino acid sequence.
- To create a tool with great utility for understanding the vast number of unique zinc fingers across eukaryotes.
Main Methods:
- Utilized DNA-binding specificities from 678 two-finger modules (natural and artificial).
- Constructed a random forest-based predictive model for ZFP recognition.
Main Results:
- The developed recognition model outperforms previous determinant-based models for ZFPs.
- The model successfully estimates the specificity of naturally occurring ZFPs with known specificities.
Conclusions:
- A robust random forest model can accurately predict ZFP DNA-binding specificity from amino acid sequences.
- This predictive model offers significant advancements for ZFP research and applications in genomics.
More Related Videos
11:24Direct Protein Delivery to Mammalian Cells Using Cell-permeable Cys2-His2 Zinc-finger Domains
Published on: March 25, 2015
06:38High Sensitivity Measurement of Transcription Factor-DNA Binding Affinities by Competitive Titration Using Fluorescence Microscopy
Published on: February 7, 2019
