Patenting Biosolutions

Innovative biosolutions created in silico can and should be effectively patented. This includes newly designed biomolecules and engineered pathways. It even includes innovative therapeutic cell lines or novel microbes for bioremediation. Patenting helps ensure exclusivity and secure investments for commercialization.

Drafting submission-ready patents for biosolutions designed in silico is part of our offering. For such in silico filing, advanced criteria must be met. This clearly includes predictable biosynthesis. The accurate and reproducible biological implementation of the patented innovation must be secured. Yet, patent applications are filed even before in vitro or in vivo results and insights become available. A biological specimen is typically not part of the submission process.

In silico biosolutions are constrained by physics, function and creativity, not by what already exists. Thereby, in silico technology natively unlocks the freedom to operate (FOP) biosolutions. This native mechanism is driving strategic patent-mapping, targeting and claiming.

Given that we are an in silico business, we use generative AI to automate crafting patent-ready disclosures, claims and specifications subsequently filed and prosecuted by patent attorneys. To facilitate the actual submission and examination process, we are collaborating with a trusted partner.

What to observe when filing in silico patents?


Patents for biosolutions may be filed purely based on computational evidence in silico. To file an in silico patent for a new molecule, in absence of in vitro or in vivo evidence, acceptance criteria include:

  • Plausibility (for EU): The patent application must render the claimed technical effect believable, with a credible rationale, based on in silico information and data provided, without speculating and hypothesizing;
  • Enablement (for US): The patent application must provide enough information so that a skilled scientist can actually create the molecule experimentally and verify its claims.

Patents for pathways can be filed in silico as well, as these are typically artificially designed and not naturally discovered pathways. Yet, since multi-component pathways have higher functional complexity than single molecules, pure in silico applications need high predictability and detailed mechanistic evidence and validation. To provide purely computational evidence, we additionally focus on:

  • Reproducibility: We formulate architecture, detailed methods and parameters for the biosolution at sufficient level of detail, along with public or published validation data;
  • Benchmarking: In lieu of in vitro experiments, we cross-validate and compare with public datasets, and validate retrospectively using historical experiments with published data. 

We render the patenting process particularly efficient by including patentability as a design criterion for molecules and pathways during the biosolution design phase already.

How do we secure patentability in silico?


For novel biosolutions, we compute, compare and benchmark protectability and patentability indices. For a new molecule, for instance, such indices are:

  1. Novelty – Difference of molecule from prior art:
    • Tanimoto similarity (< 85% for small molecules);
    • Sequence identity (< 80% for proteins, nanobodies);
    • Novel epitope & binding interface;
    • Novel conjugation site (for conjugates).
  2. Inventive Step Predictive Gap (ISPG) – Deviation of molecule from skilled person’s expectation:
    • Unexpected affinity delta (> 10×);
    • Unexpected stability delta (∆T > 5°C);
    • Unexpected selectivity shift (> 5× target vs. off-target);
    • Non-intuitive linker geometry (for conjugates).
  3. Computational Plausibility Scores (CPS) – Degree of credibility of molecule’s effect:
    • Docking score (< -7 kcal/mol);
    • MD stability RMSD (< 2 Å over 100 ns);
    • Binding free energy MM-GBSA (< 30 kcal / mol);
    • Predicted IC30 / EC50 within biological range;
    • Cross dataset validation (TCGA, GTEx, GEO).
  4. Enablement Reproducibility Index (ERI) – Degree of skilled person’s reproducibility of invention:
    • Parametrization of computational pipeline (100%);
    • Sequence disclosure (≥ 1 sequence & variants);
    • Description linker chemistry (100%);
    • Reproducibility linker chemistry (100%);
    • Examples with numerical output (≥ 1).
  5. Scope-Support Ratio (SSR) – Breadth of claims supported by disclosure:
    • Exemplified species vs. claimed genus (5-20 per 10s to 100s);
    • Sequence diversity coverage (10-60% depending on predictability);
    • Range of linkers & payloads supported (3-6 linkers, 2-4 payload classes);
    • Validated binding modes (≥ 1, preferably 2-3).

For more complex biosolutions, such as new pathways or gene regulatory networks (GRN) for cell reprogramming, these indices are being adjusted.

How do we layer IP in silico?


A patent filed with in silico specifications can subsequently be extended and strengthened based on in vitro and in vivo insights:

  • Once additional wet-lab data becomes available, a continuation or continuation-in-part (CIP) can be filed to include claims in the original in-silico-related patent that requires biological data;
  • This can broaden or narrows the scope of the original patent, or add new embodiments or technical effects of the original patent;
  • Also, a divisional can be filed to support new therapeutic uses, pathway interactions or molecule variants with in vitro or in vivo data.

In conclusion, in silico filing may be just an initial basis of a layered IP strategy, proceeding with in vivo and in vitro extensions:

  • Starting with in silico evidence to secure priority;
  • Generating in vitro data for a continuation or CIP to…
    • …support affinity, activity, stability;
    • …claim additional features;
  • Generating in vivo data for another continuation, to…
    • …support efficacy, toxicity, PK/PD; …claim therapeutic uses, dosing, formulations.

▷▷▷ Contact us to learn more?