Questions & Answers

Frequently asked questions and related answers are listed below. Did we forget an important question? Please let us know…

Applications

What does Novo Silico do?

We offer computational solutions and services for molecule design and pathway engineering in biopharma R&D, agroscience, energy, utilities and many other industries. Our prior project experience comprises development and validation of new bioproducts, and targeted upgrade and extension of existing ones.

Our computational work is enabled by a proprietary, evolving in silico platform. It comprises numerous physics- and AI-based functions and features driving molecule and pathway development, validation and iterative optimization. The platform accelerates productization and facilitates targeted, layered IP strategies.

What molecules do we design?

Well-designed molecules are at the core of many innovative biosolutions, in life science and in other industries. Our proprietary platform supports targeted and efficient, yet also creative in silico design, augmentation, simulation and validation of such new molecules and molecule types.

Such molecOur platform also enables de novo design of such molecules. It also allows augmentation, re- and multi-purposing, combination or merely characterization of existing proprietary and/or published third-party molecules. Design functions range from molecule generation, structure determination, conjugation, docking and perturbation to ADMET-profiling and approval-filtering. Design extensions include polypharmacology mapping and molecule re- and multipurposing.

les include biological antibodies, vaccines and enzymes, with targeted functions and features. Yet, our molecule design functions are not purely conditioned on proteins. They also cover lipids, glycans, nucleic acids and biological or biocompatible polymers and conjugates, including binders, linkers and payloads. For enzymes, such conjugates include cofactors and immobilizing matrices and scaffolds.

Past and ongoing projects with different partners include:

Designing novel antibody-drug-conjugate (ADC) binding to a heavily glycosylated antigen, linked to a polymer carrier, for diagnostic and therapeutic purposes in oncology.
Designing novel nanobodies (V_HH) for therapeutic strategies in oncology, penetrating blood-brain-barrier and targeting brain tumor cells with cytostatic payload.
Simulating and visualizing specified polymer carrier with polyethylene glycol dimethacrylate (PEG-DMA) units, including radioisotopes in DOTA chelators.
Modifying alginate lyase enzyme for accelerated cleaving of the mannuronic acid (M) and guluronic acid (G) polymer in pelagic brown algae Sargassum fluitans III.
Simulating fatty acid photodecarboxylase (FAP) photoenzyme, powered by light and heat, targeting biofuel production from biomass in photobioreactors (PBR).
Augmenting several biocatalysts, including MHETase metalloenzymes e.g. with metal-switching for more efficient degradation of polyester plastics and textiles in domestic waste.

What pathways do we engineer?

Many biotech solutions require diligently engineered biochemical pathways. Such pathways may be biosynthetic, incorporating feedstock input in a bioreactor and creating a product output. Other pathways may deliver drugs through the human body and eventually metabolize reactants. Other, related pathways may be immunizing and/or signaling.

In silico technology can greatly support and accelerate pathway engineering by simulating and validating pathway candidates, spotting bottlenecks and toxic intermediates, identifying and testing alternative (or no) catalysts. This reduces experimental burden, saving time, material and analytical resources. Therefore, our proprietary platform is providing the necessary simulation, refinement and molecular and ambient validation, visualization and documentation functions and features.

Note, that our approach to pathway simulation is partly based on a robust, noise-tolerant stochastic process model, replacing approximative, deterministic differential equations (ODEs).

Past and ongoing projects with different partners include:

Engineering pharmacokinetic pathway for nanobody-drug-conjugate (NDC) life cycle supporting anti-cancer diagnostic and therapeutic objectives.
Simulating, visualizing, stabilizing and optimizing an established pathway for anaerobic digestion of agricultural biomass feedstock and production of methane in an industrial fermenter.
Initiating development of a microbial polyester degradation pathway for household biomass, involving augmented esterase, lipase and cutinase enzymes.

What are example applications?

Five example applications are presented below:

1. Biopharma applications…

Your Situation: Human longevity is constrained. Constraints include cardiovascular and neurodegenerative diseases and many types of cancer. Developing targeted therapies against such diseases requires substantial dedicated resources over several years and bears attrition risk throughout the entire development cycle. The challenging cost and risk profile of biopharmaceutical development, in particular during clinical trials, is limiting R&D capacities and constraining capabilities.

Our Proposal: We propose an affordable R&D capability enhancement, exploring a larger space of potential therapies in less time with given resources, combined with earliest-possible indication of pre-clinical or clinical attrition. Such new capability is driven by the progressing analytical, predictive and generative power and accuracy of bioinformatics. With novel proprietary algorithms, we are able to…

… design complex therapeutic molecules of increasing strength, versatility and selectivity;
… validate their on-target affinity, specificity and robustness with higher accuracy;
… simulate their ADME life cycle in the human body at higher level of detail;
… reduce remaining attrition risk in pre-clinical, clinical and approval stages to a minimum.

Based on our proprietary software, we are currently augmenting therapy development projects in silico in their exploratory and pre-clinical phases. Through ambitious, automated multicriteria screening and selection, we are further minimizing attrition risk of subsequent clinical and approval phases.

2. Biocontrol applications…

Your Situation: Successful crop management requires targeted protection against pests and diseases. Historically, such protection has involved chemical pesticides, such as herbicides, fungicides or insecticides, sometimes with negative off-target effects. Such effects may contaminate the environment, degrade biodiversity and/or jeopardize human health.

In the context of organic and low-residue farming, we seek to protect against pests and diseases with precision-designed Biocontrolants with minimal bioaccumulation. Yet, legacy approaches by wet-lab-driven iterations are laborious and unaffordable for many applications, particularly for region-specific or low-profit crop hazards in developing countries. Examples are banana fusarium wilt fungus, East African maize lethal necrosis (MLN) or West African cocoa swollen shoot disease (CSSD).

Our Proposal: We propose rational precision design of crop Biocontrolants in silico can accelerate and partly replace legacy wet-lab-driven in vitro and in vivo iterations.

Commercially, in silico projects shorten development timelines, from months to days, and render crop Biocontrolants more scalable, competitive and affordable. They furthermore accelerate IP protection.
Technically, in silico approaches let us explore pathogen biology and molecular interactions at speed, depth and visibility impossible in the lab alone. They also support environmental impact modeling, bioprotectant resistance assessments and mitigation strategies.

3. Biogas applications…

Your Situation: With ongoing efforts to achieve net zero carbon emissions, the controlled methanization of biomass in biogas facilities is becoming increasingly important. The natural anaerobic fermentation process is very well understood, relevant microbes are known, and quantitative models publically available. Yet, the natural process efficiency of biogas facilities is limited. Even with costly mechanical or chemical preprocessing of biomass substrate, the commercial appeal of biogas-based power generation is often below competing fossil-fired, hydro- or wind-powered generation.

Our Proposal: We deliver process acceleration and efficiency enhancement in three stages:

Extend input: We design suitable catalysts and pathways to process new or additional substrate types, or to degrade substrate contaminants. These include for instance plastics and textiles in domestic waste, as input for digesters in biogas production;
Optimize process: We compute optimal operational parameters such as flow rate, temperature, pH, required additional microbes and/or enzymes based on observed substrate input and scheduled biogas output. We validate these results in silico by suitable simulation before feeding them live;
Accelerate output: For given substrate types and biogas demand, we determine biochemical reaction sequence and rates. We infer constraints and inhibitors limiting these rates, based on known and validated anaerobic digestion models. We determine and simulate operational parameters to enhance these rates.

4. Biofuel applications…

Your Situation: With the progressing impact of climate change, the replacement of fossil fuels by renewable biofuels is becoming increasingly urgent. Maritime biofuel requirements appear relatively relaxed, allowing variants such as fatty acid methyl ester (FAME), hydrotreated vegetable oil (HVO), purified & liquefied biogas (bio-LNG), alcohols and ammonia. The chemical, performance and emission specifications for automotive and aviation biofuel are much more restrictive. Production of sustainable aviation fuel (SAF) by certified biochemical and thermochemical technologies, in particular, is limited by availability of suitable substrates. Certified renewable lipid substrate (e.g. vegetable oil, animal fat), for instance, is highly insufficient for any substantial coverage of air traffic.

Our Proposal: We design new biochemical or thermochemical pathways for certified biofuel production based on new types of biomass substrates.

In a recent project, we have designed an augmented alginate lyase enzyme in silico for accelerated conversion of brown algae Sargassum natans to pyruvate for microalgal production of alkane-based SAF.
Brown algae are currently abundantly available in the Caribbean, with a total annual supply of 30m metric tons.
This algal SAF production pathway can also be applied to green algae Ulva lactuca, with ample annual supply e.g. in China and Brittany.
The processed macroalgal substrate can also be fermented to alcohol and thermochemically converted to SAF with the well-established alcohol-to-jet (AtJ) pathway.

5. Biopolymers applications…

Your situation: Many biologics, such as nutrients, catalysts, therapeutics or immune modulators, do not reach their target on their own. On the way to their target, they may be degraded or cause off-target effects or even toxicity. Natural and/or artificial biodelivery systems resolve such challenges by protecting the molecule, carrying it to its target, overcoming barriers, and releasing it safely at the right time and dose.

Smart natural biodelivery systems also include viruses! They are protein-based nanocapsids delivering DNA or RNA into target cells.

As the complexity of biologics design increases, the importance and sophistication of biodelivery increasing as well. Yet, creating suitable biodelivery solutions is time-consuming and costly, with a substantial experimental burden. Optimizing stability and release kinetics by trial and error in the wet lab, in particular, can be prohibitive.

Our Proposal: In silico technology allows rapid prototyping of molecule carriers, screening millions of candidate designs and securing suitable targeting, stability and biodistribution. In particular, in silico tools allow simulation of how molecules, carriers, biological environments and off-targets interact, before testing in the lab. This may allow more efficient, accurate and affordable biodelivery solutions.

Particular focus is given to prediction of…

…polymer carrier behavior and performance;
…cell membrane, protein and tissue interactions;
…drug release timing & dosing profiles;
…polymer networks changing properties and releasing, triggered by pH, temperature and/or enzymes smart hydrogels)
…clinically relevant outcomes, e.g. tumor penetration or nanoparticle clearance.

Such prediction is done before in vitro or in vivo testing is started.

What do we deliver?

We are developing innovative biosolutions as an in silicoservice. This may include the design of new molecules and/or the engineering of novel biochemical pathways. Such in silico service can be delivered in various different formats. The standard format is a sequential funneling, where first a target is identified, then a matching biosolution is created and optimized, followed by in silico validation and eventually by a wetlab confirmation.

Biosolution deliverables strongly depend on the domain of application. Medical antibodies and industrial enzymes, for instance, have very different validation, prioritization and selection criteria. Such criteria are important, since key biosolution deliverables are typically listings of validated, prioritized and/or selected lead candidates:

Validated through a selection of automated in silico functions;
Prioritized according to multiple scientific and commercial objectives;
Complemented with detailed biosolution candidate profiles and illustrations;
Discussed with key decision makers, scientific and commercial;
Open to additional simulations and what-if analyses, if required or requested.

Preferred biosolution candidates are often highly robust and versatile, with bi- or polyspecific binding or reactivity, suitable for broad commercialization. Yet, most candidates are subject to multiple challenging trade-offs, for instance:

Molecular stability vs. developability;
Target affinity vs. specificity;
Solution payload vs. bioavailability.

Such trade-offs can often be satisfactorily resolved. Yet, a fundamental challenge of in silico biosolution design remains: the trade-off between computational tractability vs. biological realism.

What do we patent?

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.

How do we differentiate?

As a focused in silico solution and service provider, we are offering dedicated collaborations, exclusive partnerships and joint ventures. We differentiate from other providers with such offerings in terms of application breadth, quantitative scrutiny and solution scope. These three features may be critical success factors for your biosolution development and/or productization project…

Breadth of Application
We are serving multiple industrial segments, including life science, chemicals, energy, utilities, food, textiles and construction material. The versatility and scalability of our in silico technology is anchored in the joint biological and chemical principles of the diverse industry applications.

Resulting benefits:
- Our in silico platform allows cross-industry benchmarking and validation, re-purposing of bioproducts, and extended data utilization and machine learning.
- Our in silico platform allows efficient configuration to new and completed applications, without the burden of complexity-driving and time-consuming customization.
- Our in silico platform promotes out-of-the-box thinking and guides cross-discipline innovation on a shared scientific basis.
  .
Quantitative Scrutiny
Data acquisition in vivo or in vitro, through lab experiments, typically comes at a high price. In silico technologies can compute insightful parameters and indicators with lower time and resource spending. Yet, type and accuracy of these parameters strongly depends on the underlying in silico technology. Some AI approaches generate only heuristic data. Stochastic approaches yield probabilities. Not all scores meet decision makers’ expectations.

Our approach:
- We are offering advanced metrics supporting design decisions at various levels. These metrics are scientifically grounded, explainable, understandable, justifiable and comparable.
- For these metrics, we are offering proprietary and/or syndicated benchmarks, internal experience and external reference values.
- We are monitoring consistency between metrics and benchmarks, securing plausibility of the overall design parameters, and engineering trust in the solution, conclusion and insights.
  .
Scope of Solution
Computational development of biosolutions does not end with proven molecule manufacturability, affinity and function. In silico technology takes biosolution development on a journey much further and broader, leading from early target projection via molecule design and pathway engineering to a computational validation, trial and/or approval simulation and finally to IP protection.

We differentiate by supporting a fairly large portion of this in silico capability spectrum:
- Project Targets: Mine biological data sets, screen patent databases and identify targets. Prioritize targets based on scientific insight, technological possibilities and commercial opportunity.
- Design Molecules: Generate hit and lead molecules for a given purpose. Determine their natural structure(s), ascertain their function(s) (QSAR) and preview properties (ADME) in their target environment.
- Engineer Pathways: Determine how molecules behave in their biological network. Consider molecule features (e.g. solubility, permeability, stability, toxicity) and interaction (e.g. activation, inhibition, catalysis) along their metabolic or regulatory, human or industrial pathway. Adjust the pathway by modifying molecule(s), ambient conditions etc.
- Simulate Trials (currently not implemented on our platform): Model cells, tissue, organs, patients and cohort permutations in a virtual clinical trial environment. Predict outcomes and adjust original model parameters to secure clinical and approval success.
- Protect IP: Secure the ultimate commercial success of your innovation by utilizing in silico technology for patent formulation. This may even be extended to peparing regulatory registration, certification or approval, hazard classification, etc.

Collaboration

How do we collaborate in drug discovery?

As an in silico biosolutions & services provider, we collaborate with our partners predominantly in a project format. Most projects comprise periodical on-site and web-based workshops, work sessions and status presentations. While we are very flexible on project scope and timeline, we do contribute a standardized and validated in silico workflow with scalable and cybersecure computational infrastructure:

We collaborate on target identification:
- We help identify promising disease targets and favorable market spaces through predictive disease response modeling, chemical and patent space screening, etc.
- These techniques augment scientific and commercial expertise and proprietary (possibly data-based) insights in the pursued therapeutic segments.
For identified targets, we discover and/or optimize molecules and pathways in silico:
- Multi-objective biosolution discovery and optimization in silico includes pre-clinical and clinical criteria that facilitate and expedite subsequent project steps;
- This multiobjective clinical-horizon approach replaces the iterative trial-and-error legacy with repeated target-to-hit, hit-to-lead and lead optimizations.
We facilitate IP protection and patenting of the biosolution developed in silico:
- Driving strategic patent-mapping, targeting and claiming;
- Realizing a layered IP strategy, finally extended by in vitro and in vivo insights,
Our partners enjoy a strongly minimized attrition risk profile:
- For any subsequent experimental validation, for licensing purposes;
- For clinical development and regulatory approval.

What shortened delivery formats do we offer?

Our in silico development of biosolutions can be shortened to…

…pure in silico design of biological of biocompatible molecules;
…pure in silico engineering of biochemical or thermochemical pathways;
…pure optimization or evolution of existing biosolutions;
…pure simulations-as-a-service, involving simulated with molecular dynamics (MD), pharmacokinetics and/or digital twins;
…pure predictions-as-a-service, involving criteria (e.g. affinity, specificity, toxicity etc.) predicted for a specified molecule and target;
…pure visualizations-as-a-service, with interactive 3D-or-higher visualization of a molecule in action (e.g. binding to target, cleaving target etc.).

Have another format in mind? Feel free to contact us…

What alternative delivery formats do we offer?

In silico biosolutions & services can be delivered in various different formats. Beyond the aforementioned standard format, the alternative formats with varying level of creativity are:

Concurrent engineering, in vitro vs. in silico: In vitro and in silico projects for biosolution design are run in parallel, to monitor their strengths and weaknesses. When progress or confidence stalls on either side, the projects may swap interim results or fuse entirely;
In silico retrospection: An in silico project root-cause-analyzes an unsuccessfully concluded in vitro project and explains how it can be most efficiently revived, upgraded, redirected and/or have its results recycled;
In silico (risk) monitoring: An in silico project monitors and validates an in vitro project and/or anticipates and explains interim and final results, and/or estimates success likelihoods of future working steps, trials or approval;
Expert-augmented in silico: In silico technology periodically visualizes interim results and requests human expert input, judgment, triage and consensus or compromise or possibly even supervised training to progress to the next step;
Concurrent engineering in silico vs. in silico: Two independent in silico design projects run in parallel. Intermediate and final results are compared, cross-validated, ultimately based on wetlab results;
Wetlab digital twin: Ever wondered about the accuracy of your wetlab experimental results, proving or disproving biosolution designed in vitro or in silico? Would it make sense to have a speedy, automated second opinion? Simulation technology, in particular digital twins, could help…

How do we make your project successful?

“High speed” and “low cost” may be appealing features of in-silico-augmented projects. Yet, these features per se do not yet guarantee project success. The key contributors of in silico technology to successful biosolution design projects are rather:

Flexibility: Many projects are getting started before all specifics are known or ready. In silico workflows allow fast rework of project tasks, if initial specifics and tentative parameters are updated. Once a workflow has been created, the effort of updating project tasks is limited to computational time and cost.
Quantification: With the use of in silico functions, attributes such as “legendary”, “truly amazing”, “highly promising”, “somewhat risky” and “increasingly challenging” need to be further clarified and quantified, using measures, figures and criteria. These improve project communication and avoid misunderstandings.
Transparency: In silico functions help efficiently track, report and present project status and deliverables. Key measures such as proximity-to-project-completion, quality-of-result, number-of-optimizing-iterations-needed and likelihood-of-rework boost project transparency.
Reproducibility: In silico functions, workflows and pipelines should be inherently reproducible and also explainable. Not all in silico methodology is living up to that expectation. Some in silico functions provide no tractability or reproducibility improvement over in vitro and in vivo experimentation.
Horizon: The strongest in silico success contributor for biosolution design may be the size of the chemical search space systematically explored and exploited:
- Small molecules obeying the laws of organic chemistry exceed 10⁶⁰;
- Mankind has explored in silico less than 10¹¹ of these molecules;
- Humanity has physically synthesized only about 10⁸ molecules;
- Less than 10⁴molecules have ever been approved.

Can we secure your commercial success?

Commercial success has a monetary measure. Completed in silico projects, even with promising quantitative results and impressive scientific insights, provide no guarantees for regulatory approval and commercial success. Yet, first indicators for commercial success can be licensing interest, partnership offers, investor term sheets or other financial commitments triggered or driven by convincing in silico deliverables.

While in silico deliverables cannot secure such fortunate opportunities, in silico technology can boil down remaining post-project clinical and commercial risk to a minimum. For instance, by securing…

…IP defensibility;
…Freedom-to-operate (FOP);
…Biological performance at scale;
…Manufacturability;
…Cost-of-goods feasibility;
…Competitive differentiation;
…Adoption scenarios;
…Market fit;

…for a foreseeable future time horizon.

Some of the items listed above are already challenging and stretching the scope of in silico technology into market and competitor analysis. In silico technology is an important contributor and complement, but certainly not a replacement, for commercial models and therapeutic market and competitor analysis.

How to get started?

We are happy to discuss topics for potential collaboration or partnership. We typically set up an introductory web conference (e.g. MS Teams or Google Meet) to discuss your specific situation and needs and/or to review our related capabilities and references. A potential agenda could be:

Intro of participants (10’)
Review of Novo Silico capabilities (10’)
Online demo of reference & results (10’)
Discussion of your specific situation (10’)
Formulation of in silico requirements (10’)
Exploration of opportunity for collaboration (5’)
Next Steps (5’)

Such web conference…
…may be preceded by a brief call;
…is typically succeeded by follow-up communication.

There are other dialog formats for next steps, such as…
…a preliminary, confidential on-site consultation on your ongoing project work;
…a deep dive of our capabilities in a very specific in silico segment;
…a tentative, informal online brainstorming regarding a technology need;
…pure e-mail correspondence, for clarification.

Please contact us to discuss…

Technology

What are functions & features of our platform?

Functions and features can be described for molecule design, pathway engineering and evolutionary optimization:

1. Molecule Design…

Our proprietary platform allows in silico molecule design for specific medical and industrial application. Key functions and features for molecule design include:

Generation
1. Generative AI methods:
  - Conditional diffusion model;
  - Variational autoencoder (VAE);
  - Generative adversarial network (GAN);
  - Graph neural network (GNN) generator.
2. Evolutionary algorithm (on SMILES, graph structures, latent vectors, etc.)
  .
Structure Determination
1. Conditional on biomolecule class & type (proteins, glycans, lipids, biocompatible polymers, e.g. PEG, PLA, PCL);
2. For proteins: Apply homology & AI-based algorithms;
3. For all: Apply rule-, force field- & molecular dynamics-based algorithms.
  .
Conjugation
1. For antibody drug conjugation:
  - Target conjugation & cleavage strategy;
  - Enhance binder(s) (e.g. for click chemistry);
  - Complement payload (e.g. by NHS ester, DBCO, maleimide);
  - Optimize conjugation (e.g. for efficiency, specificity, binder folding preservation);
  - Cross-validate results (e.g. molecular size, weight, energy); Simulate cleavage (e.g. by enzyme assumed available).
2. For enzyme immobilization:
  - Target conjugation type (e.g. covalent, affinity, adsorption, entrapment);
  - Ascertain enzyme stability, activity, compatibility;
  - Modify support (e.g. membrane, polymer, e.g. by NHS ester, aldehyde, epoxy);
  - Ascertain conjugation parameters (time, pH, temperature, ionic strength);
  - Cross-validate results (e.g. load efficiency, thermal & pH stability, catalysis cycles).
    .
Docking
1. Determine…
  - …binding pose, epitope & paratope;
  - …binding affinity & function;
  - …association & dissociation;
  - …buried surface area;
  - …∆ energy (shape, desolvation, vdWaals, electrostatics, ionic bonds, H-bonds).
2. Consider…
  - …conformational change of binding molecule;
  - …enthalpic and entropic parameters;
  - …different force field models;
  - …competing binding poses, epitopes & paratopes;
  - …other ligands covering this pose.
3. Observe…
  - …signaling;
  - …cleavage;
  - …activation;
  - …inhibition.
    .
Perturbation
1. Trigger
  - …structure change (e,g, bond rotation, residue mutation, monomer addition);
  - …ambient change (e.g. pH, temperature, solvent);
  - …interaction (e.g. binding partner, ligand concentration);
  - …signaling (i.e. propagating disturbance through interaction network).
2. Monitor
  - …atomic coordinates;
  - …bonding topology;
  - …torsion angles & rotamers;
  - …electron density & partial charges;
  - …free energy, enthalpy & entropy.
3. Consider
  - …different free energy models;
  - …different molecular dynamics parameters.
    .
Toxicity Prediction
1. Observe…
  - …chemical structure & functional groups;
  - …absorption, accumulation, solubility;
  - …partial charges, electron density, reactivity indices;
  - …binding affinity to toxicity targets;
  - …activation of toxicity pathways.
2. Mitigate…
  - …by removing toxicophores (with QSAR guidance);
  - …by substituting fragments (with safer analogs);
  - …by tuning charge distribution (reducing reactive metabolites);
  - …by modifying metabolic hotspots;
  - …by reducing accumulation in sensitive organs (e.g. liver & heart);
  - …by modifying binding affinity to hERG (avoiding cardiotoxicity).
    .
ADME Profiling
1. Determine…
  - …solubility;
  - …permeability;
  - …metabolic stability;
  - …CYP enzyme inhibition;
  - …mutagenicity;
  - …bioavailability;
  - …clearance.
2. Mitigate…
  - …limited solubility by adding or tuning ionizable groups, reducing lipophilicity;
  - …limited permeability by adding hydrophobic groups, reducing polar surface area, achieving passive diffusion, and reducing entropic penalty crossing membranes;
  - …limited biodistribution by reducing plasma protein binding, reducing aromatic surface, and adding polarity in non-critical regions;
  - …excessive metabolism by finding and blocking metabolic soft spots, adding small steric shields, and reducing easily oxidized motifs; …limited clearance by adding polar groups, and introducing metabolic soft spots.
    .
Approval Filtering
1. Design-pass: Using classic rules like Lipinski, Veber, Ghose, PAINS;
2. ADMET-suitability: Using rules from points (6) & (7) above;
3. Approval-likeliness: Proprietary VAE.
  .
Design Extension
1. Map polypharmacology: identify, predict and validate all molecular targets the compound interacts with, map and review related therapeutic and off‑target effects;
2. Re- & multi-purpose molecule: predict secondary targets, off-targets, beneficial multi-target profiles, and repurpose for new indications.

2. Pathway engineering…

Our proprietary platform allows in silico pathway engineering for specific medical and industrial application. Key functions and features include:

Molecule Transition Matrix
1. Define molecular space:
  - Input molecules (e.g. feedstock);
  - Output molecules (e.g. products);
  - Intermediates;
  - Catalysts (microbial or abiotic).
2. Set ambient parameters:
  - Temperature;
  - Pressure;
  - pH;
  - Light;
  - Etc.
3. Set reactor parameters:
  - Reactor volume;
  - Time in reactor;
  - Etc.
4. Estimate transition rates:
  - Quantities from stoichiometry;
  - Rates from dynamic ODEs, Michaelis-Menten, etc.
  - Activation effects;
  - Inhibition effects;
  - Saturation effects.
    .
Pathway Simulation
1. Equilibrate transition rates…
  - …by stepwise hyperplane relaxation;
  - …by max likelihood for missing entries.
2. Simulate by trajectory…
  - … possibilities (candidate model);
  - … probabilities (probabilistic model);
  - … rates (kinetic model).
    .
Simulation Refinement
1. Add, omit and/or augment molecules in matrix (NEA);
2. Adjust rates (MHM).
  .
Insights Validation
1. Analyze sensitivities to input parameters & assumptions;
2. Characterize (possibly toxic) intermediaries;
3. Analyze timing and delays;
4. Assess implications for…
  - …molecule design;
  - …ambient design;
  - …reactor design.

3. Evolutionary Optimization…

Developing biotech solutions, including new biomolecules and/or pathways, is typically an iterative process. Solutions are initialized and iteratively improved, gradually converging to an optimum. Such optimum could be highest binding affinity to a cancer antigen, highest degradation rate of plastic waste, or highest number of biofuel molecules produced.

Since biotech solutions often pursue more than one objective, the optimum may be indicated by more than one parameter, e.g. binding affinity of a nanobody to a brain tumor antigen and nanobody permeability of the blood-brain-barrier. Such parameters may be subject to a trade-off.

Based on in vitro and in vivo technologies, an iterative optimization process consumes substantial time and budget. Each iteration loop requires lab or field experiments to determine the goodness of the best solution. With progressing in silico technology, the time and budget requirements for iterative optimization drops significantly, as tests are fully computational. An iterative physical process of several weeks and months can be accelerated or even replaced by an iterative virtual process, running in a matter of hours, and eventually completed after a few days.

The iterative in silico optimization capability of our platform is virtually mimicking a process of population-based natural evolution, yielding an optimal combination of pathway and supporting molecules, with highest expected success in practice. Such evolutionary optimization (EO) approach has proven robust to uncertainty and noise (common in biological systems) and successful for many medical and industrial applications since the 1980s. It has been particularly successful for optimizing bioprocesses where mechanistic models are unavailable or incomplete.

What are key challenges addressed by molecule design?

This question triggers a vast variety of comments, leaning towards very different answers. In our experience to date, the major challenges are revolving around molecular complexity in practice, in particular regarding conjugation and polymerization.

Complexity

For complex and information-dense molecules, such as large glycans, multi-domain proteins, or DNA, the computational burden for an in silico platform may be significant.

Some enzymes, such as fatty acid synthases, are large, multi-domain proteins, performing multi-step catalysis with unstable intermediates, pivotal in many metabolic pathways;
Large, glycosylated tumor antigens such as CA-125 in ovarian, pancreatic and lung tumors reach sizes exceeding 20’000 residues, with masses of 2-3MDa, due to repeat sections;
Human ingestion of microplastic is involving large polymer chains, such as polyethylene terephthalate (PET), with an efficient degradation pathway yet to be developed.

An in silico platform must master molecules of significant size and complexity to meet growing in silico expectations and needs. Generative modeling, perturbation and/or simulation of such molecules, e.g. for docking or cleavage, requires efficient representation, a suitable and scalable platform architecture, and generous hardware.

Conjugates

The ideal molecule solving your tasks may not be a pure protein, glycan, lipid or nucleic acid. Although each molecule type has its standard applications, nature tends to conjugate molecules for additional stability and functional properties.

Your ideal antibody and its target antigen may be naturally glycosylated.
This may significantly condition epitope and paratope, impact binding affinities etc.
Your ideal enzymes may have a metal cofactor, with crucial oxidative functions.
Such metalloenzymes may cleave even non-biological molecules, such as polyethylene.
Your ideal drug molecule’s permeability, solubility and bioavailability may benefit
from linked esters. These may augment your drug’s entire ADME pathway.

Hence, in silico tools and techniques should master properties and features of natural and artificial conjugates to realize their benefits in practice. Puristic protein design alone may not offer the molecular solution space needed for most practice applications.

Polymers

Many in silico applications involve polymers in a driving or supportive, intended or unintended role:

The ideal molecule solving your tasks may have been designed as monomer, but oligomerize in practice, by nature. This may significantly impact the functionality and bioavailability of your molecule. The likelihood and extend of oligomerization and the oligomer structure and function can typically be determined in silico.
On the other hand, your ideal molecule may have been designed as oligomer or polymer. This is the case for nanobody-polymer-conjugates, with the polymer carrying cytotoxic drugs or radioisotopes. In silico tasks include development of optimally sized polymers with high internal drug compatibility, external bioavailability and suitable release kinetics.
Furthermore, your ideal molecule may be targeting polymers. This is the case for many enzymes cleaving polymers back to oligo- and monomers. Such as cellulase cleaving cellulose to glucose or cutinases cleaving polyethylene to ethylene glycole and terephthalic acid. Finally, your ideal molecule, such as the aforementioned enzymes, may need to be immobilized and/or stabilized by a polymer serving as scaffold or forming a polymer-enzyme-composite.

While deterministic or stochastic polymer generation and drug loading in silico is well understood, it requires substantial computational resources for creation and perturbation due to molecule size and combinatorial complexity.

What are examples of iterative optimization in silico?

We are providing here examples for enzymes, small molecules and double-stranded RNA (dsRNA):

Synthetic fermentation pathway for ethanol production
Enzyme example: PDC & ADH

Enzymes such as pyruvate decarboxylase (PDC) and alcohol dehydrogenase (ADH) determine ethanol productivity and robustness in industrial fermenters. EO has evolved bacterial PDC and ADH and their pathway through iterative in silico rounds of mutation and selection to enhance thermostability.

EO has integrated a stabilized PDC…
- …into the established fermentation pathway;
- …at a high-flux glycolysis, high-stress, chemically extreme node of fermentation;
- …at 10^{3 –}fold improved half-life at 75°C (from losing > 90% activity above 45°C);
- …subject to high ethanol, low pH, reactive metabolites and TPP cofactor imbalance.
EO has integrated a matching ADH…
- …achieving 50-fold improved half-life at 60°C;
- …increasing final alcohol titers by factor 2-10;
- …preventing by-product formation;
- …reducing toxic aldehydes faster than conventional ADH.

Signaling pathway for cell proliferation and differentiation
Small molecules example: TKI

Mutated or overexpressed tyrosine kinases may facilitate uncontrolled cell growth in cancer cells. EO has enabled iterative de novo in silico design of tyrosine kinase inhibitors (TKI), evolving scaffolds and substituents to improve potency and selectivity of newly designed small molecules competing against ATP.

EO has evolved small molecule candidates by mutating, recombining and selecting chemical structures that bind kinase active sites with high affinity and good drug likeness;
EO has overcome challenges such as the large chemical space to be searched, and multiple objectives (affinity, selectivity, ADMET);
EO has mastered constraints such as ADME properties, binding-site localization, H-bond requirements, toxicity filters and substructure rules;
EO has optimized concurrent targets like affinity, selectivity and ADMET.

RNA interference (RNAi) pathway for plant virus defense
dsRNA example: SIGS

Cocoa trees in West Africa are threatened by the cocoa swollen shoot virus (CSSV). CSSV is a badnavirus, injected by mealy bugs into the cocoa trees’ phloem. The virus is integrating its RNA into the cocoa tree genome. To avoid complete removal of infected trees, a spray-induced gene silencing (SIGS) treatment is being developed. Iterative EO is facilitating design of matching solution components:

Externally applied dsRNA targeting CSSV genes for replication, movement and coat protein to be silenced. The dsRNA is processed into siRNA inside the cocoa tree;
Heat-, sun-, water- and enzyme resistant lipid nanocarrier encapsulating the siRNA, sprayed onto cocoa tree leaves in combination with other fungicides and insecticides;
Stable spray solution (pH, ionic strength) with optimized droplet size, coverage, decay.

How do we compare solutions in silico?

Our proprietary in silico platform allows tracking multiple target criteria for optimality. This is done in every iteration of our multiobjective evolver, permitting a multiobjective comparison…

…of new molecules and pathways designed de novo or ex stuctura from a template or scaffold;
…against competing molecules and pathways, possibly developed by trial and error in the lab;
…and against syndicated benchmarks.

Our quantitative criteria for evaluation and comparison are computed entirely in silico. We thereby allow prioritization and optimization before going into the lab. We consider criteria with…

…same force field, solvent model and temperature;
…same MD protocol, including equilibrium, production length and analysis windows;
…same physical validation basis, including binding energy, stability and specificity.

We thereby prove that solutions evolved and optimized in silico exceed known syndicated benchmarks and are more promising than other solutions at hand, based on suitable and consistent criteria.

IP Protection

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:

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).
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).
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).
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).
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.

Next Steps

What next steps do we suggest?

Intro of participants (10’)
Review of Novo Silico capabilities (10’)
Online demo of reference & results (10’)
Discussion of your specific situation (10’)
Formulation of in silico requirements (10’)
Exploration of opportunity for collaboration (5’)
Next Steps (5’)