At #UNCChapelHill, chemistry Ph.D. student #Idanwekhai is using #machinelearning to transform how #viruses — the microscopic couriers of genetic medicine — are #purified, making the process #faster, #cheaper & more #precise.
college.unc.edu/2026/03/kelv...
college.unc.edu/2026/03/kelv...
Chemistry student uses machine learning to transform gene therapy production - College of Arts and Sciences
Ph.D. student Kelvin Idanwekhai is using machine learning to transform how viruses — the microscopic couriers of genetic medicine — are purified, making the process faster, cheaper and more precise.
college.unc.edu
March 16, 2026 at 1:25 PM
At #UNCChapelHill, chemistry Ph.D. student #Idanwekhai is using #machinelearning to transform how #viruses — the microscopic couriers of genetic medicine — are #purified, making the process #faster, #cheaper & more #precise.
college.unc.edu/2026/03/kelv...
college.unc.edu/2026/03/kelv...
Idanwekhai, Kelestemur, Strickland, Hart, Davidsson, Angelopoulos, Alterovitz, DeLuca, Tropsha: A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization https://arxiv.org/abs/2608.11483 https://arxiv.org/pdf/2608.11483 https://arxiv.org/html/2608.11483
August 14, 2026 at 6:39 AM
Idanwekhai, Kelestemur, Strickland, Hart, Davidsson, Angelopoulos, Alterovitz, DeLuca, Tropsha: A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization https://arxiv.org/abs/2608.11483 https://arxiv.org/pdf/2608.11483 https://arxiv.org/html/2608.11483
A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization
Kelvin P. Idanwekhai et al.
#arXiv #cs.AI #cs.LG #q-bio.QM
Kelvin P. Idanwekhai et al.
#arXiv #cs.AI #cs.LG #q-bio.QM
A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization
Hit-to-lead optimization requires iterative design of hit analogs across competing potency, selectivity, physicochemical, pharmacokinetic, safety, and synthetic constraints. We present SABLE (Synthetically-accessible Agentic Bayesian Ligand Exploration), an open-source framework that employs natura…
arxiv.org
August 13, 2026 at 6:15 PM
Idanwekhai, Kelestemur, Strickland, Hart, Davidsson, Angelopoulos, Alterovitz, DeLuca, Tropsha: A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization https://arxiv.org/abs/2608.11483 https://arxiv.org/pdf/2608.11483 https://arxiv.org/html/2608.11483
August 13, 2026 at 6:39 AM
Idanwekhai, Kelestemur, Strickland, Hart, Davidsson, Angelopoulos, Alterovitz, DeLuca, Tropsha: A Modular Agentic Framework for Synthetically Constrained Multi-Objective Hit-to-Lead Optimization https://arxiv.org/abs/2608.11483 https://arxiv.org/pdf/2608.11483 https://arxiv.org/html/2608.11483
Kelvin P. Idanwekhai, Valeriia Kaneva, Stefano Menegatti, Alexander Tropsha: BASIL: Bayesian Application for Scientific Iteration and Learning https://arxiv.org/abs/2606.21092 https://arxiv.org/pdf/2606.21092 https://arxiv.org/html/2606.21092
June 23, 2026 at 6:42 AM
Kelvin P. Idanwekhai, Valeriia Kaneva, Stefano Menegatti, Alexander Tropsha: BASIL: Bayesian Application for Scientific Iteration and Learning https://arxiv.org/abs/2606.21092 https://arxiv.org/pdf/2606.21092 https://arxiv.org/html/2606.21092