LM-VS™ screens 10 Billion Compounds— potentially active drug candidates.

Among the MD snapshots from Molecular Dynamic simulation in 10 ns time scale, the purine ring showed the least movement and was therefore selected as the scaffold, which is highlighted in red in Figure 1.

R1 cluster indicates that the red-colored dot (Purine ring) interacts most frequently with the protein residue, Y683 in Figure 2.

LM-VS™is a target-agnostic hit discovery platform because it is designed to perform screening even for the most challenging targets, GPCR, MG, TPD, as long as the target pocket contains residues that can serve as π-stacking anchors — such as TYR, PHE, TRP, ARG, or LYS.

By representing compound bonds within the pocket as 1D word strings and performing a Google-style inverted indexing search across a 10-billion-compound library, ultra-fast retrieval (as fast as 1/7,000 second) is possible.

Compounds selected based on 1D string similarity are then re-docked in 3D, and those filtered by binding energy and scaffold similarity are defined as hit candidates.

In each iteration, the top 200 candidates are used for subsequent searches, and by repeating this process for 50 to 100 cycles, it becomes possible to screen scaffold-derived analogs, derivatives that are synthetically accessible or commercially available.

1. Post-Analysis-View

This result visualizes the docking within the protein pocket, where the anchor residues (in yellow) interacting with the compound scaffold are fixed in position.The remaining portions of the compound are displayed as the screened derivatives, as shown in the figure.

2. Summary Report

(A) Hit Candidates Distribution – A 3D scatter plot illustrates the distribution of hit candidates according to CNNaffinity, CNNscore, and Ring Match Score.

(B) Accumulation of Hit Counts per Run – The cumulative number of strong and moderate hits is shown as the runs progress.

3. Excel Report & Function Rank

This report includes vendor information for compound synthesis and provides a functional score calculated from affinity parameters (CNNscore, CNNaffinity) and ADME descriptors (MW, LogP, HBA, HBD, MolMR, Solubility, Caco2 permeability, Rotatable Bonds, Strain Energy) according to the following formula.