IIT Madras researchers develop machine learning-based predictor for protein mutations

New Delhi: Researchers at the Indian Institute of Technology (IIT), Madras have developed a machine learning-based predictor for protein mutations which has surpassed existing methods that are time-consuming and expensive, according to officials.

The artificial intelligence-based tool, 'DeepPPAPredMut', includes a user-friendly web server that enhances accessibility for researchers. The findings of the research have been published in the prestigious peer-reviewed journal 'Bioinformatics'.

According to the officials, the study of proteins, often referred to as 'building blocks of life', is important as they play a crucial role in cell signalling and immune response and cell cycle.

They can exist as enzymes to catalyse biochemical reactions. They also have structural and mechanical functions like those of actin and myosin in muscle.

"Problems arise when mutations occur in these protein-protein complexes, which affects the stability of the complex and disturbs the functionality, thus leading to diseases. A property of protein-protein complexes is the binding of two or more proteins."

"This interaction is known as 'binding affinity', the strength of the interaction between two or more molecules of proteins, is crucial when assessing how mutations affect protein-protein complexes," M Michael Gromiha, Professor at Department of Biotechnology, IIT Madras, told PTI.

Gromiha explained that there are several methods to detect the effect of mutation on the binding affinity of protein-protein complexes, but these are labour-intensive, time-consuming and expensive.

"There is therefore a need for computational methods to predict the binding free energy changes upon mutation in protein-protein complexes. Currently, there are two computational methods to study mutation in protein-protein complexes, namely 'structure-based' and 'sequence-based' methods."

"But these methods too have limitations. Structure-based methods, which use the structural properties from protein complexes to predict the change in binding affinity upon mutation, are limited because of the lack of availability of experimentally known structures of protein-protein complexes," he said.

Sequence-based methods have been developed for predicting changes in binding affinity upon mutation.

In this study, the researchers addressed these limitations and developed 'DeepPPAPredMut', which takes a protein sequence and mutation as input from the user and predicts the change in the binding affinity upon mutation in the protein complex.

Rahul Nikam, Department of Biotechnology, IIT Madras said protein-protein interactions underpin many cellular processes and their disruption due to mutations can lead to diseases.

"With the evolution of protein structure prediction methods like AlphaFold2 and the availability of extensive experimental affinity data, there is a pressing need for updated computational tools that can efficiently predict changes in binding affinity caused by mutations in protein-protein complexes," he said.