Life Sciences & Pharmaceuticals
Accelerate Drug Discovery and Decrease Risk of Side Effects
Hardware acceleration for analytics drives compound similarity and real-world evidence research in pharma and biotech
REDUCE TIME-TO-MARKET AND RISKS OF LIFE-SAVING TREATMENTS WITH INFRA PURPOSE-BUILT FOR ANALYTICS
The benefits and costs of data analytics for life sciences — more than for any other industry — can equate to life and death for as many as millions of patients around the world. While pharmaceutical and biotechnology companies have long relied on the quality of testing and trials to determine efficacy, risk, secondary use cases, and regulatory compliance, the scale and efficiency of data capabilities have become much more impactful as medical companies and research institutions have become more reliant on predictive analytics to determine the viability and benefits of their compounds.
By eliminating typical input/output, compute, and memory bottlenecks for drug-target interaction predictions, Speedata’s APU completed a pharmaceutical simulation analysis for 9 million compounds in 19 minutes compared to 90 hours for CPUs on the same 100 servers. Another simulation found the same workload could run on a single APU server overnight, compared to four days on 100 CPU servers, equating to a 99% total cost savings. By increasing the rate at which compounds can be analyzed, it not only speeds up the time-to-market of potentially life-saving drugs, but also expands the breadth of testing to find more or better compounds.
IMPROVE DRUG DISCOVERY BY ACCELERATING COMPOUND SIMILARITY ANALYSIS 280x
REDUCE QUERY TIME 20x TO DECREASE RISK OF SIDE EFFECTS
As analytics have improved life sciences’ risk management, drug efficacy is increasingly impacted by the scalability and efficiency of the infrastructure powering long-run ETL processes. The APU has achieved 95% speedups of Spark queries for evaluating unexpected interactions and complications compared to CPUs. Speedata shortens real-world evidence research cycles by accelerating the runtime of loading and transforming raw patient data to identify side effects. For an ETL workload that costs $1 million, that would mean saving $950,000 in operating costs and unlocking insights that would improve countless lives.
“I saw firsthand how Speedata's APU is opening the door for breakthroughs... With the unprecedented performance of this accelerator, analyzing data for drug discovery can be done in minutes, not hours — with endless lifesaving implications. This is only the beginning of hardware acceleration use cases.”