Related Experiment Video
Updated: Aug 13, 2026
06:50
Computational Prediction of Amino Acid Preferences of Potentially Multispecific Peptide-Binding Domains Involved in Protein-Protein Interactions
Published on: January 26, 2024
STRUMP-I: Structure-Based Machine Learning Approach to pMHC-I Binding Prediction Using Force Field Energy Features
Adam Voshall1,2, Jeongjun Chae3, Honglan Li4
1Division of Genetics and Genomics, Boston Children's Hospital, Boston, MA, USA.
Computational and Structural Biotechnology Journal
|August 12, 2026
Summary
STRUMP-I accurately predicts peptide-MHC class I binding using structural data, outperforming traditional methods for underrepresented alleles. This advances cancer immunotherapy by improving neoantigen identification.
Area of Science:
- Immunology
- Computational Biology
- Bioinformatics
Background:
- The adaptive immune system uses peptide-MHC class I (pMHC-I) complexes to detect abnormal cells.
- Accurate prediction of peptide binding to MHC-I is crucial for developing cancer immunotherapies targeting neoantigens.
Purpose of the Study:
- To develop a novel computational tool, STRUMP-I, for predicting pMHC-I binding.
- To overcome limitations of existing sequence-based and structure-based prediction methods.
Main Methods:
- STRUMP-I utilizes a structure-based approach incorporating force-field-derived energy terms as machine learning features.
- The tool was evaluated against benchmark datasets and compared with state-of-the-art sequence-based models.
Main Results:
- STRUMP-I achieved performance comparable to leading sequence-based models on standard benchmarks.
- The tool demonstrated superior performance for MHC alleles with limited or imbalanced training data.
- STRUMP-I improved precision and offered a better precision-recall tradeoff when used to complement sequence-based methods.
Conclusions:
- STRUMP-I is a valuable structure-informed method for prioritizing potential neoantigens.
- The tool shows particular promise for analyzing underrepresented MHC alleles.
- STRUMP-I can enhance existing prediction pipelines by filtering false positives and improving accuracy.
Related Concept Videos
02:21Globular and Fibrous Proteins
Many proteins can be classified into two distinct subtypes - globular or fibrous. These two types differ in their shapes and solubilities.
Globular proteins are also known as spheroproteins and typically are approximately round in shape. They contain a mix of amino acid types and contain differing sequences in their primary structures. Globular proteins have many different functions, such as enzymes, cellular messengers, and molecular transporters. These roles often require the proteins to be...
Globular proteins are also known as spheroproteins and typically are approximately round in shape. They contain a mix of amino acid types and contain differing sequences in their primary structures. Globular proteins have many different functions, such as enzymes, cellular messengers, and molecular transporters. These roles often require the proteins to be...
02:18The Equilibrium Binding Constant and Binding Strength
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:
01:49Conserved Binding Sites
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 analyses the...
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 analyses the...