Spirographic AI Launches First Commercial Platform to Predict Per-Transporter Drug Exposure in Fetal and Breast Milk Compartments — Achieving 96.4% and 93.7% Accuracy
The entire field predicts only whether a drug crosses — or estimates a bulk ratio. No commercial platform identifies which transporters are responsible, in which direction, or at what trimester. Spirographic AI does both — from SMILES input alone.
CORVALLIS, Ore., April 7, 2026 /PRNewswire/ — Spirographic AI, LLC today announced commercial availability of two proprietary prediction engines covering two of the most clinically sensitive pharmacokinetic compartments in medicine: the placental barrier and the mammary epithelium. The Placental Transporter Screening Engine achieved 96.4% overall accuracy across five transporters and 302 labeled drug-transporter pairs. The Breast Milk Transporter Screening Engine achieved 93.7% overall accuracy across seven transporters and 302 curated drug-transporter pairs, with P-gp protective modeling at 92.4%. Both platforms accept SMILES string input and return per-transporter predictions — fully automated, with no manual curation.
No commercial platform currently offers per-transporter mechanistic prediction for either compartment. The best published academic models for placental transfer predict only binary crossing status — whether a drug crosses the barrier at all — with no information about which transporters are involved, whether they are protective efflux or exposure-increasing influx, or how transporter expression changes across trimesters. For breast milk, the most advanced available tools predict only a bulk milk-to-plasma concentration ratio, and the field’s own validation studies explicitly exclude known transporter substrates because existing models cannot handle them. Spirographic AI predicts the full transporter picture the field has been routing around.
The clinical stakes for these populations are uniquely high. Pregnant and lactating women are systematically underrepresented in clinical trials, yet over 50% of women take medication during pregnancy and breastfeeding. Knowing that a drug crosses the placenta is necessary but insufficient — a drug pumped back to maternal blood by P-gp or BCRP carries categorically different fetal exposure risk than one actively transported inward by OCT3. Similarly, a drug concentrated into breast milk by BCRP or CNT3 presents a different infant exposure profile than one with a passive M/P ratio below 1. Transporter identity is the clinical signal that drives prescribing decisions, and it has not been available computationally — until now.
“The field has been stepping around transporter-mediated transfer for years because no one had solved it computationally,” said Brandy Stoffel, MSN, RN, founder of Spirographic AI. “Pregnant women and breastfeeding infants are the two populations that most need this information and have had the least access to it. We built what was missing.”
The Placental and Breast Milk Transporter Screening Engines are two modules within the broader Spirographic AI platform, which delivers comprehensive pharmacokinetic predictions from SMILES input alone — including CYP450 metabolite generation (94.4% across 56 drugs on two independent benchmarks), albumin binding site specificity (86.4%, first commercial platform to offer site-level prediction), blood-brain barrier, hepatic, renal, and pulmonary transporter substrates. The platform is available on a contract basis with zero data retention and is patent pending.
About Spirographic AI
Spirographic AI, LLC is an Oregon-based computational pharmaceutical transporter substrate and metabolite prediction platform founded by Brandy Stoffel, MSN, RN. The platform is patent pending and operates under a zero data retention policy.