Published
OCT 2026
Category
Institutional Grant
Scope
FINEP · CNPq · FAPEG · MCTI
Reading time
4 min read
OCT 2026 · Institutional Grant
Iterchem secures public research & innovation funding to advance EndoXplain
Backed by FINEP, FAPEG, CNPq, and MCTI, Iterchem is advancing EndoXplain to bridge predictive computational toxicology and operational R&D decision-making.
Iterchem has been selected for public scientific research and technological innovation funding supported by FINEP, FAPEG, CNPq, and MCTI (under the Programa Centelha 3 GO framework) to accelerate the development and operational validation of EndoXplain—our explainable AI platform for endocrine disruptor risk screening and preclinical prioritization.
The Structural Bottleneck in Chemical R&D
Across pharmaceuticals, agrochemicals, cosmetics, food contact materials, and industrial chemicals, research and regulatory teams face three persistent operational bottlenecks:
- Fragmented R&D Decisions: Biological activity, toxicological hazard, and exposure context are rarely evaluated together early in discovery. Synthesis teams optimize candidates for potency while safety liabilities surface too late in the pipeline.
- Costly, Unranked Experimentation: Candidate molecules and formulation alternatives routinely advance to expensive in vitro and experimental assays without systematic computational prioritization.
- Slow Operational Transfer: High-value predictive models developed in academic and computational research remain locked in isolated scripts, never reaching the day-to-day operational and regulatory workflows of industry teams.
“Our objective with EndoXplain is to move from hypothesis to product with traceable evidence—enabling teams to select higher-confidence molecules, anticipate endocrine risks early, and guide experimental validation.”
What We Are Building with EndoXplain
The institutional grant supports the full-stack engineering and scientific validation required to bring EndoXplain to operational maturity (TRL 7), focusing on three integrated pillars:
- Multimodal Intelligence: Integrating chemical structure curation (
SMILES,SDF, and batchCSVlibraries), bioassay distributions, and safety descriptors into a unified screening workflow. - Explainable AI & Uncertainty Quantification: Moving beyond opaque “black-box” scores by delivering calibrated risk probabilities alongside explicit uncertainty indicators and structural rationale—so toxicologists and chemists can inspect why a candidate was flagged.
- Traceable Technical & Regulatory Reports: Generating structured, exportable PDF reports with full model versioning and submission history to support internal stage-gate decisions and regulatory evaluations before ANVISA, IBAMA, MAPA, and international authorities.
Next Milestones
Over the current development cycle, Iterchem is expanding multi-tenant enterprise isolation, asynchronous batch screening queues, and pilot co-development workflows with industry partners holding active molecular portfolios.
Further reading
Beyond black-box QSAR: Explainable AI and uncertainty in endocrine screening
Why standalone probability scores fail in regulatory toxicology—and how combining structural explainability with explicit uncertainty improves candidate triage.
New Approach Methodologies (NAMs): Connecting predictive models to regulatory workflows
How auditable in silico toxicology supports animal-free safety substantiation across cosmetics, agrochemicals, packaging, and pharmaceutical discovery.