AI will be embedded into everyday research
“AI in biopharma research: A time to focus and scale,”
The AI-driven drug discovery industry continues to grow, fueled by new entrants in the market, significant capital investment, and technology maturation. We’ve identified more than 250 companies working in the industry. More than half of them are based in the United States, but key hubs are emerging in Western Europe and Southeast Asia as well.
The best of these companies will fully integrate AI into research workflows, as the exhibit shows. By putting AI at the center of the research engine, companies can transform research at scale—and bring about dramatic improvements in patient outcomes.
For the full article, see:
About 11,000 satellites
have been launched in
the 64 years since
Sputnik 1 in 1957
O3b mPower
90
AST & Science
170
Inmarsat
175
Viasat
290
KLEO
300
Kepler
360
Mangata
790
Telesat
1,600
Kupier
3,400
OneWeb
6,400
Other
15,000
Starlink
42,000
Parts of a high-throughput screening (HTS) process embedded with AI technology
Charting the future
1. High-throughput screen commenced
with diverse compound sets
Scientist selects diverse compound sets
(a set of chemical compounds with a wide range of chemical structures) as first
high-throughput screen
In silico/
on-the-chip
simulations
1
2
3
4
5
6
In-vitro/
‘wet lab’
experiments
6. Automated compound selection
based on ML recommendations
ML recommendations are automatically queued and used in the next round of HTS. The cycle continues, with the algorithm continuously learningfrom “real world” outputs. Recommendations trigger scientists to explore new chemical space and begin downstream screening processes more quickly. These recommendations feed into the selection of chemical compounds in step 1
5. Compound library inferencing
and prioritization
ML algorithm then scans the remainder of the library compounds and predicts which plates should be prioritized to identify the highest number of hits in the next screen
4. Automated machine learning (ML) model training from screen outcomes
Information from HTS for first few plates is automatically transferred into an ML pipeline, which “learns” how cells respond to each kind of chemical structure
3. Computer-vision-based hit selection
Cell response to each compound is measured using microscope analysis (eg, through computer vision techniques); promising compounds are labeled “hits”
2. Automated compound selection
and transfer
Using HTS machinery, individual compounds are transferred to individual wells of cells under experimental conditions
October 2022.