Artificial Intelligence Analysis of Protein Compositions on Engineered Nanomaterials

Authors P. William1 , N. Yogeesh2, Lingaraju2, R. Chetana3, T.N. Vasanthakumar2, V. Verma4
Affiliations

1Department of Information Technology, Sanjivani College Engineering, Kopargaon, SPPU, Pune, India

2Department of Mathematics, Government First Grade College, Tumkur, Karnataka, India

3Department of Mathematics, Siddaganga Institute of Technology, Tumkur, Karnataka, India

4Department of Computer Science and Engineering, Bhilai Institute of Technology, Raipur, Chhattisgarh, India

Е-mail william160891@gmail.com
Issue Volume 16, Year 2024, Number 4
Dates Received 20 April 2024; revised manuscript received 22 August 2024; published online 27 August 2024
Citation P. William, N. Yogeesh, Lingaraju, et al., J. Nano- Electron. Phys. 16 No 4, 04037 (2024)
DOI https://doi.org/10.21272/jnep.16(4).04037
PACS Number(s) 07.05.Mh
Keywords Engineered Nanomaterial (ENM), Protein Compositions, Artificial Intelligence (AI), and Polypeptide chemical reaction optimized resilient logistic regression model (PCRO-RLRM).
Annotation

Protein compositions applied on Engineered Nanomaterials (ENM) require the presence of nanoscale protein molecules for multiple biochemical uses. Potential toxicity hazards and the requirement for full safety evaluations caused by the complex interactions between nanoparticles and biological systems are issues.Effectively Fluorescamine approaches for predicting protein composition on synthetic nanomaterials ENM can clarify biochemical findings from ENMs that are in biological structures without needing long-term protein composition tests. The Polypeptide Chemical Reaction Optimised Resistant Logistic Regression Model (PCRO-RLRM) is an innovative Artificial Intelligence (AI) technology that would be utilized in this research. The protein composition is analyzed using the Z-score normalization technique. The key elements from the normalized data that are useful for studying proteins or amino acid areas are extracted using the Position-Specific Scoring Matrix, or PSSM. Applying Polypeptide Chemical Reaction Optimisation (PCRO) to modify the algorithm's parameters improves the predicted performance of the RLRM method. The findings reveal that the PCRO-RLRM combination is superior to the analysis of Protein Composition algorithm in accuracy (96.57%), sensitivity (94.5%), and specificity (98.03%). This novel approach has the potential to promote findings in biochemistry based on nanomaterials and to improve bioengineering techniques.

List of References