For molecular modelers working with complex biomolecular systems, selecting specific atoms, residues, chains, or regions in a structure can be tedious and time-consuming—especially when working with large systems. Traditional selection often requires navigating a tree of molecular nodes or writing specific code-based filters. But what if you could just describe what you want to select in plain English?
With the /select command in SAMSON AI, you can do just that. This intelligent assistant allows users to interact with molecular data through natural language, simplifying many common tasks—including selection.
Solving Selection Complexity
Let’s say you’re interested in all side chains around a ligand within a certain distance. In most molecular modeling environments, this would require browsing selection rules or learning a scripting syntax. In SAMSON, simply type:
|
1 |
/select all side chains within 5 angstrom of the ligand |
The AI interprets your request, maps it to the Node Specification Language (NSL) behind the scenes, and highlights the appropriate nodes in your structure. No scripting—just describing what you want to do.
Here are more examples:
/select the binding site/select all lysines in chain B/select all carbon atoms in the selected residues
This feature saves time during exploratory analysis or when preparing systems for simulation, modifying structures, or performing visualization tasks.
Why This Matters
Working with molecular structures involves repetitive, detail-oriented tasks. Anything that streamlines this process translates directly into increased efficiency and reduced friction in scientific workflows. Natural-language-based selection is especially helpful in the early stages of molecular modeling, where you might be browsing a protein structure to formulate questions about its active site, binding pockets, or interface regions.
Behind the Scenes
When you issue a /select command, SAMSON AI converts your request to its underlying Node Specification Language, making it interpretable by the platform. This means your selection is not only visible immediately, but also programmable and reproducible—which can be helpful for scripting or automation workflows later on.
This is particularly useful in teaching environments, data preparation for simulations, or generating scripts for larger workflows.
One More Thing: It Learns
Because SAMSON AI supports commands for learning and referencing documents (/learn and /refer), combining that with /select opens the door to workflows where you can introduce structural info from external documents and instantly act on them inside the model. While this is more advanced, it’s a powerful corner of the SAMSON ecosystem worth exploring.
Interested in exploring more natural language commands? Learn more from the full documentation: https://documentation.samson-connect.net/users/latest/samson-ai/
SAMSON and all SAMSON Extensions are free for non-commercial use. You can get SAMSON at https://www.samson-connect.net.