Jonathan Fine
Papers
2
Total Citations
131
H-Index
2
About
Jonathan Fine is a pioneering researcher at the intersection of chemistry and artificial intelligence, whose work is transforming how scientists identify molecular structures. His primary research areas include spectral deep learning, cheminformatics, and the application of machine learning to analytical chemistry. Fine’s major contribution lies in developing state-of-the-art deep learning models that can automatically predict the functional groups present in unknown chemical compounds from spectroscopic data—a task traditionally requiring the expertise of a skilled spectroscopist. His landmark 2020 paper, "Spectral deep learning for prediction and prospective validation of functional groups," has garnered 122 citations, demonstrating its significant impact on the field. By training neural networks on Fourier Transform Infra-Red (FTIR), Mass Spectroscopy (MS), and Nuclear Magnetic Resonance (NMR) data, Fine has dramatically accelerated the identification process, reducing it from hours of expert analysis to seconds of computation. His work not only promises to democratize access to advanced chemical analysis but also opens new avenues for high-throughput screening in drug discovery and materials science. Fine’s research exemplifies how AI can augment human expertise, making complex chemical characterization faster, more accurate, and more accessible.
Research Focus
Key Achievements
Top Papers
- 1
- 2