Industrial Consultancy & Sponsored Research (IC&SR) , IIT Madras
System and Method for Predicting Binding Affinity of Small Molecules to RNA Targets
Categories for this Invention
Technology: Predicting binding affinity of small molecules to RNA targets;
Industry & Application: Pharmaceutical, Biotechnology, Cellular & Biological Simulation,
Drug Discovery & Disease Modelling
Market: The global computational biology market is projected to grow $31.5Bn by 2031, at a CAGR of 19.5% during the forecast period (2024-31).
Image Gallery
Problem Statement
- In the existing approaches like Computer-Aided Drug Design (CADD) have primarily been focused on the development of scoring functions or models, which can predict the in vitro activity of any given small molecule against a specific target protein or nucleic acid.
- The technical problem, underlying the present invention, may be regarded as the absence of generic quantitative prediction models for predicting binding affinity of RNA targets of different RNA families with small molecules.
- Hence, said invention provides suitable solution by addressing the issues efficiently.
Technology
- Present invention provides a system and method for predicting binding affinity of small molecules to Ribo-Nucleic Acid (RNA) targets. (Refer Figs. 1, 2 & 3)
- Said system comprises a memory & a processor wherein the processor is configured to receive an input from a user & predict a binding affinity of the small molecule to the RNA target of the sub-type, using a prediction model.
- In the embodiment, the one/more modules may be communicatively coupled to the processor for performing the functions of the binding affinity predicting system, wherein the modules comprises a receiving module, an RNA feature calculation module, a small molecule feature calculation module, a prediction model generating module, a prediction model, an executing module and other modules.
- The prediction model generating module is configured to identify a plurality of non-correlated features from the plurality of RNA sequence-based features & the plurality of small molecule features.
- A method for predicting binding affinity of small molecules to RNA targets, comprising a few steps shown in flow chart depicted in Fig. 2
Key Features / Value Proposition
Important Features:
- The system predicts the binding of affinity of novel small molecules to RNA targets from six RNA subtypes using only the RNA sequence as input.
- The RNA sequence-based features data may be classified into three categories like oligonucleotide or K-tuple nucleotide composition, pseudo-nucleotide composition & structure composition.
- The prediction model generating module may identify the final feature combination as the feature combination with the smallest number of features, offering optimal performance, wherein the performance variables may be Pearson correlation coefficient (r) & Mean Absolute Error (MAE).
- Facilitates an improved performance of the binding affinity predicting system & also provides a reduction in the feature calculation load for the binding affinity predicting system. (Refer Fig 4 and Table 1)
- The experimental software model of RNA–small molecule binding affinity predictor is shown in Fig. 3.
Questions about this Technology?
Contact For Licensing
sm-marketing@imail.iitm.ac.in
ipoffice2@iitm.ac.in
Research Lab
Prof. Michael Gromiha M
Department of Biotechnology
Intellectual Property
IITM IDF Ref. 2554
Patent Application No. 202341049440
Technology Readiness Level
TRL-4
Proof of Concept ready, tested and validated in Laboratory