{{define "new-job.html"}} New similarity search · SciMesh
← Back to control room

New computation

Similarity search, end to end

Upload a ChEMBL-style TSV. Workers calculate shard candidates; after every shard succeeds, SciMesh merges the exact global top-k into one final CSV.

Required columns: chembl_id and canonical_smiles.

Use a valid SMILES. The coordinator shares this exact query with every shard.

How many final molecules to retain.

Smaller shards make more visible tasks.

Leave blank to rank every valid candidate.

“Less” helps explore dissimilar molecules.

Only the first N data rows become shards; the original upload remains stored by the coordinator.

Ready to plan a run.
Select a TSV to see the file that will be sent to the coordinator.
{{end}}