machine learning prediction

2 articles · search the full text for this term

• Published Subscription Review Article 5 May 2026

  Integrative Structural-Functional Genomics of Fc and Fab: Precision Models for Monoclonal Antibody Stability and Anti-Aggregation Engineering

  By Tapaswi Ram Khajuria, Prof (Dr.) Atul Khajuria, KIRAN KUMARI

  Abstract: Monoclonal antibodies (mAbs) represent the cornerstone of biotherapeutics, yet aggregation propensity compromises up to 50% of candidates during development, driven by Fab hypervariability and Fc vulnerabilities.(1,2) This review integrates functional genomics from OAS (4B+ sequences)(5) and structural databases (SAbDab: 10K+ structures)(6) with machine learning models achieving R=0.97 for SAP prediction.(11) We dissect biophysical mechanisms, benchmark predictive tools (DeepSP, ESM2), and engineering strategies (YTE, FW mutations) that enhance Tm by 5-10°C …

  Published in International Journal of Molecular Biotechnological Research · Vol. 4, Issue 1, 2026 Read article →

• Published Subscription Original Research Special issue 30 Aug 2025

  Tribological Performance and Wear Coefficient Prediction of AA2024–TiC Composites via Python-Based Machine Learning

  By Sumit Srivastava, Shanmugha Pillai Balaji, Mayur Dilip Jakhete, S. Vinoth Kumar, L. Ganesh Babu, Sandeep Chinta, Goutam Kumar Mahato, Ram Subbiah

  Abstract: Determining wear coefficient accurately serves as a critical factor to maximize engineering materials' tribological characteristics. The experiment examines the wear characteristics of TiC-reinforced AA2024 aluminum alloy subjected to different tribological operating conditions. A pin-on-disc tribometer performed wear tests under different conditions of load and TiC weight fraction and sliding speed and duration. ANOVA statistical results show that load intensity and TiC reinforcement density stand out as principal variables that affect …

  Published in Journal of Polymer & Composites · Vol. 13, Issue 6, 2025 · pp. 1099–1112 Read article →