China's Biotech Industry

sunnymaxi said:

130 Billions USD is a lot money. Chinese biotech firms literally printing money.

the scary thing is, This is just the beginning. with this money they will invest more in R&D.

Click to expand...

sunnymaxi said:

130 Billions USD is a lot money. Chinese biotech firms literally printing money.

the scary thing is, This is just the beginning. with this money they will invest more in R&D.

Click to expand...

sunnymaxi said:

130 Billions USD is a lot money. Chinese biotech firms literally printing money.

the scary thing is, This is just the beginning. with this money they will invest more in R&D.

Click to expand...

Research establishes brain normative references for Chinese population​

A study by a Chinese research team has established normative references for brain structure throughout the entire lifespan of Chinese individuals, thereby enhancing diagnostic standards for neurological disorders among patients.

Click to expand...

Charting brain morphology in international healthy and neurological populations​

Click to expand...

This research presents DrugCLIP, a contrastive learning framework that enables ultra-fast and accurate virtual screening, 10 million times faster than docking, while consistently outperforming various baselines in computational benchmarks.

In wet lab validation, DrugCLIP achieved a 15% hit rate for norepinephrine transporter and identified the structures of two known inhibitors in complexes with the target protein. For thyroid hormone receptor interacting protein 12, a target lacking full structure and small molecule binders, DrugCLIP achieved a 17.5% hit rate using only AlphaFold2-predicted structures. Finally, the researchers released GenomeScreenDB, an open database providing pre-computed results for approximately 10,000 human proteins screened against 500 million compounds, pioneering a post-AlphaFold era drug discovery paradigm.

Click to expand...

At its core, DrugCLIP's breakthrough is in reformulating traditional molecular docking as a high-efficiency semantic search for protein pockets and small molecules in vector space. Running on a computing node with a 128-core CPU and 8 GPUs, the platform can score trillions of protein pocket-small molecule pairs daily, delivering a million-fold speed increase over conventional docking approaches.

Click to expand...

In its inaugural genome-scale screening project, the team applied DrugCLIP to approximately 10,000 protein targets and 20,000 protein pockets, analyzing over 500 million small, drug-like molecules. The effort yielded more than 2 million potential active molecules, resulting in the largest known protein-ligand screening database to date.

Click to expand...

DrugCLIP has achieved the first genome-scale virtual screening for human targets, covering over 10,000 human protein targets with a 500 million compound library.


The system, outlined in

Please, Log in or Register to view URLs content!

, uses an AI contrastive deep learning framework to rapidly identify small-molecule ligands for every druggable target in the human genome.

The team behind it have made their genome-scale virtual, screening database freely available to researchers worldwide at

Please, Log in or Register to view URLs content!

, with one-click access and no coding required.

Click to expand...

Screening a billion compounds for a single target using traditional docking requires over two weeks even with 10,000 central processing unit cores. This makes it enormously time consuming to virtual screen numerous targets in the human genome.

To accelerate the process, Liu and team developed DrugCLIP as a ground-breaking, ultra-fast AI virtual screening engine powered by contrastive learning.

DrugCLIP encodes protein pockets and small molecules into a shared latent space using both large-scale synthetic data and experimentally determined protein-ligand complex structures.


It then uses dense retrieval to instantly identify potential active molecules, eliminating the need for one-to-one docking.

DrugCLIP outperformed traditional docking and machine learning methods even with noisy structures, novel targets, Apostructures and AlphaFold-predicted structures, while still delivering precision and efficacy.

The system was applied for around 10,000 human proteins against 500 million compounds, scoring more than 10 trillion protein-ligand pairs in under 24 hours using only eight graphics protein units.

Click to expand...