Bezahlte Endpunkte für autonome Agenten. Abrechnung über x402 in USDC auf Base Mainnet.
/v1/protein-foldingChecks that a hydrophobic/polar sequence follows a self-avoiding unit-step lattice path, then counts non-consecutive hydrophobic contacts and assigns one negative energy unit per contact. It evaluates a supplied toy conformation only; it neither predicts a fold nor represents atomic chemistry, kinetics, solvent or biological function.
/v1/crispr-offtargetCompares one guide with caller-supplied candidate protospacers, weights mismatches in the guide’s final ten positions twice, applies a simple NGG PAM penalty, and ranks a transparent similarity score. It does not search a genome, model bulges, chromatin or nuclease-specific biology, and must not be used as a clinical or laboratory safety decision.
/v1/dna-storage-encodeMaps each two-bit group of caller-supplied UTF-8 bytes to A, C, G or T and reports a SHA-256 checksum of the original bytes. This reversible representation performs no biological synthesis, homopolymer balancing, GC optimization, addressing or error-correcting code.
/v1/microbiome-diversityNormalizes non-negative caller-supplied taxon counts and computes observed richness, natural-log Shannon entropy, Simpson diversity and Pielou evenness. It does not perform sequence classification, compositional correction, rarefaction, cohort comparison or medical interpretation.
/v1/pathogen-r0Multiplies per-contact transmission probability, effective contacts per day and infectious duration to obtain a simple basic reproduction number, then applies a susceptible fraction for an effective number. It is a classroom homogeneous-mixing calculation, not an outbreak estimate, fitted epidemiological model or public-health forecast.
/v1/biomarker-longevityStandardizes each supplied value against its supplied mean and standard deviation, flips markers whose favorable direction is lower, and computes a weighted composite mapped to a bounded 0–100 index. The references and weights come entirely from the caller; this is not a validated longevity score, diagnosis, prognosis or medical advice.
/v1/syn-yeast-yieldDivides each available substrate mass by its required mass per product mass, selects the limiting substrate, and applies a caller-supplied process efficiency. It does not model yeast metabolism, kinetics, oxygen transfer, toxicity, regulation or actual fermentation performance.
/v1/allergen-epitopeBuilds amino-acid k-mer sets, calculates Jaccard similarity, and finds the highest contiguous identity between each supplied epitope and any equal-length window of the query. It does not predict immune binding, allergenicity, cross-reactivity or clinical risk and cannot replace curated databases or laboratory testing.
/v1/phage-matchingSlides each caller-supplied spacer over a bounded phage sequence in both orientations, records its minimum Hamming distance and reports matches within a caller-selected mismatch threshold. It does not account for PAMs, phage taxonomy, infection biology, escape, host range or therapeutic suitability.
/v1/tissue-scaffoldUses the Kozeny-Carman relation with supplied porosity and pore diameter, then applies Darcy’s law with supplied thickness, viscosity and pressure drop. It is an idealized homogeneous porous-medium calculation, not scaffold design validation, cell-transport modeling, biocompatibility assessment or medical guidance.
tools/list ohne Zahlung