Drug Discovery and Development

  • Home Drug Discovery and Development
  • Drug Discovery
  • Women in Pharma and Biotech
  • Oncology
  • Neurological Disease
  • Infectious Disease
  • Resources
    • Video features
    • Podcast
    • Voices
    • Views
    • Webinars
  • Pharma 50
    • 2025 Pharma 50
    • 2024 Pharma 50
    • 2023 Pharma 50
    • 2022 Pharma 50
    • 2021 Pharma 50
  • Advertise
  • SUBSCRIBE

University of Miami achieves 10x speedup in HIV drug research with new compute alliance

By Drug Discovery Editor | April 10, 2025

The ALAFIA AIVAS Supercomputer accelerates complex molecular dynamics and AI applications, delivering performance boosts of 80-100X for researchers.
The ALAFIA AIVAS desktop supercomputer accelerates complex molecular dynamics and AI applications, delivering performance speedups as high as 80-100X for some research applications.

Researchers at the University of Miami have achieved a roughly 10x acceleration in complex HIV drug simulations, thanks to a new compute alliance with Miami-based ALAFIA. This dramatic speedup, powered by ALAFIA’s AIVAS Supercomputer, marks a potential breakthrough by enabling large-scale molecular dynamics modeling previously out of reach for the lab.

Molecular dynamics simulations are vital in the early stages of drug discovery, allowing scientists to predict how potential drug candidates might bind to and inhibit viral proteins essential for HIV replication. Yet these simulations are computationally intensive. Before this collaboration, the University of Miami lab faced limitations performing such timely, large-scale simulations. That reality hindered the pace of R&D and the ability to efficiently test multiple compounds or refine drug designs.

The ALAFIA AIVAS computer (shown above) helps tackle this challenge. Supporting more than 1,000 trillion operations per second, it provides the massive local processing power needed within the lab itself. This enables researchers to handle secure, encrypted workloads in real-time, sidestepping the latency and sometimes unpredictable costs associated with relying solely on cloud-based high-performance computing.

By overcoming previous computational bottlenecks, the AIVAS system allows UM researchers to explore more potential drug candidates, iterate on designs faster, and identify the most promising compounds for laboratory testing far more efficiently.


Filed Under: machine learning and AI

 

Related Articles Read More >

Aqemia bets physics-driven AI can deliver novel drugs, not faster me-too molecules
Lilly
Lilly and NVIDIA unveil $1B co-innovation lab in South San Francisco
Insilico, newly listed in Hong Kong, strikes up to $888M oncology deal with Servier
AI disrupted the job interview. In pharma, it’s redefining research… up to a point.
“ddd
EXPAND YOUR KNOWLEDGE AND STAY CONNECTED
Get the latest news and trends happening now in the drug discovery and development industry.

MEDTECH 100 INDEX

Medtech 100 logo
Market Summary > Current Price
The MedTech 100 is a financial index calculated using the BIG100 companies covered in Medical Design and Outsourcing.
Drug Discovery and Development
  • MassDevice
  • DeviceTalks
  • Medtech100 Index
  • Medical Design Sourcing
  • Medical Design & Outsourcing
  • Medical Tubing + Extrusion
  • Subscribe to our E-Newsletter
  • Contact Us
  • About Us
  • R&D World
  • Drug Delivery Business News
  • Pharmaceutical Processing World

Copyright © 2026 WTWH Media LLC. All Rights Reserved. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of WTWH Media
Privacy Policy | Advertising | About Us

Search Drug Discovery & Development

  • Home Drug Discovery and Development
  • Drug Discovery
  • Women in Pharma and Biotech
  • Oncology
  • Neurological Disease
  • Infectious Disease
  • Resources
    • Video features
    • Podcast
    • Voices
    • Views
    • Webinars
  • Pharma 50
    • 2025 Pharma 50
    • 2024 Pharma 50
    • 2023 Pharma 50
    • 2022 Pharma 50
    • 2021 Pharma 50
  • Advertise
  • SUBSCRIBE