SMA Research Platform

Evidence graph for Spinal Muscular Atrophy

Biology-first target discovery
Christian Fischer / Bryzant Labs
Targets
Trials
Drugs
Datasets
Sources
Claims
Evidence
Hypotheses

Drug Screening

COMPUTATIONAL

This pipeline computationally filters thousands of ChEMBL compounds down to the best candidates for SMA drug discovery. The process runs in six steps: (1) ChEMBL query — compounds bioactive against top-scored SMA targets are fetched with their SMILES strings; (2) RDKit descriptor calculation — molecular weight, LogP, rotatable bonds, H-bond donors/acceptors, TPSA, and QED are computed from SMILES; (3) Lipinski Rule of 5— MW < 500, LogP < 5, HBD ≤ 5, HBA ≤ 10; (4) BBB permeability estimate— TPSA < 90 Ų and MW < 450; (5) CNS MPO score — 0–6 composite tuned for CNS drug development; (6) PAINS filter — substructure alerts for pan-assay interference compounds.

Why BBB penetration matters for SMA:SMA motor neurons reside in the anterior horn behind the blood-brain barrier. Risdiplam succeeds partly because of its BBB-permeable profile. Compounds with TPSA > 90 Ų or MW > 500 Da are unlikely to achieve meaningful CNS exposure.

Score glossary: Lipinski — binary pass/fail. BBB — heuristic estimate (TPSA + MW). CNS MPO — 0–6; ≥ 4 is CNS-optimized. QED — 0–1 drug-likeness; ≥ 0.5 is high quality. PAINS — substructure alert for reactive scaffolds.

How does Computational Drug Screening work?

The screening library starts from ChEMBL compounds with known bioactivity against SMA-relevant targets. Compounds pass through sequential filters:

  • Lipinski Ro5 — MW ≤500, LogP ≤5, HBD ≤5, HBA ≤10
  • BBB heuristic— TPSA < 90 Ų, MW < 450
  • CNS MPO ≥ 4 — composite CNS optimization score
  • QED ≥ 0.5 — drug-likeness estimate
  • PAINS-free — no pan-assay interference alerts

* QED, CNS MPO, and PAINS columns are estimated values (heuristic from pChEMBL, MW/LogP thresholds). Not RDKit-computed. Use /screen/smiles for exact values.

Loading screening results…
Login → Command Center