70 to 90% of Your Pipeline Can't Dissolve
70-90% of drug candidates in development pipelines exhibit poor aqueous solubility, creating a fundamental bottleneck that costs the industry billions annually in failed candidates, reformulation expenses, and lost therapeutic potential.
Executive Overview: The 70-90% Crisis
Modern drug discovery is good at finding potent, selective molecules. It is bad at making them dissolvable. Current estimates put 40-70% of commercialised drugs and 70-90% of drug candidates in development stages as poorly soluble in aqueous media, limiting bioavailability, reducing therapeutic effect, and forcing dose escalation that worsens side effects.
The scale of this problem is hard to overstate. Only about 8% of novel chemical entities show both good permeability and solubility. The rest sit in what formulators call the "developability graveyard." Failed late-stage candidates attributable to solubility cost the industry an estimated $2-3 billion per year, and patients lose access to therapies that worked in vitro but could not be delivered in vivo.
AI-powered formulation prediction is changing the calculus. Machine learning models now exceed 92% accuracy in predicting drug-polymer compatibility for amorphous solid dispersions. Platforms like Quadrant 2 and FormulationAI show that rational solubility enhancement is no longer theoretical; it is operational, given the right computational infrastructure.
Of drug candidates in development pipelines have poor aqueous solubility. This single factor accounts for roughly 40% of all drug development failures and remains the largest addressable inefficiency in pharmaceutical R&D.
Source: Industry Analysis, BCS Classification Studies, Development Pipeline DataThe BCS Classification Reality
The Biopharmaceutics Classification System (BCS), developed by Gordon Amidon in 1995, sorts drugs into four classes by aqueous solubility and intestinal permeability. Together, these two properties determine whether an orally administered drug reaches therapeutic concentrations in the bloodstream.
BCS classification has direct consequences for regulatory pathways, manufacturing requirements, and commercial viability. A BCS Class I drug and a Class IV drug face entirely different development trajectories, yet modern discovery pipelines keep filling the problematic classes.
BCS Class | Solubility | Permeability | Pipeline % | Development Challenge |
|---|---|---|---|---|
| Class I | High | High | ~8% | Minimal (Ideal candidates) |
| Class II | Low | High | ~35-40% | Dissolution-rate limited; ASD candidates |
| Class III | High | Low | ~20-25% | Permeability enhancement required |
| Class IV | Low | Low | ~30-35% | Dual challenge; often requires advanced delivery |
Why Modern Drug Discovery Produces Insoluble Molecules
This problem is a direct byproduct of how modern drug discovery works. High-throughput screening, combinatorial chemistry, and structure-based drug design have made it far easier to find potent, selective compounds. But these same methods bias toward molecules with higher molecular weights, greater lipophilicity, and more structural complexity -- all of which correlate with poor aqueous solubility.
Medicinal chemists call it the "lipophilicity trap." Compounds optimised for target binding affinity depend on hydrophobic interactions with protein binding sites. Each optimisation cycle that improves potency tends to degrade solubility in parallel. By the time a candidate enters development, it may bind its target with high affinity but resist oral formulation entirely.
In early-stage work, teams rightly prioritise potency and efficacy. Solubility gets deferred. By late development, formulation options are narrow and reformulation costs climb steeply.
The "Brick Dust" vs "Grease Ball" Problem
Poorly soluble compounds fall into two categories, and each demands a different formulation strategy:
"Brick Dust" Molecules
High crystal lattice energy, high melting point, strong intermolecular forces. The molecule forms such stable crystals that it resists dissolution.
Solution: Amorphous solid dispersions, cocrystals, salt formation
"Grease Ball" Molecules
High lipophilicity, low melting point, weak crystal forces but extreme hydrophobicity. The molecule simply will not interact with water.
Solution: Lipid-based formulations, cyclodextrins, surfactant systems
Misidentifying the category leads to wasted development cycles. A "brick dust" approach will fail for "grease ball" molecules, and vice versa.
Market Growth
Solubility enhancement excipients market (2024)
5.7% CAGR to $5.33B (2030)ASD Approvals
FDA-approved ASD products (2012-2023)
Failure Rate
NCEs fail due to solubility/bioavailability issues
Current Technologies and Their Limitations
Several solubility enhancement strategies exist, each with trade-offs that determine when and where they apply. Choosing the wrong one burns time and budget.
- Salt Formation
Converting neutral drugs to ionised salt forms is the first-line approach and can improve solubility by 10-1000 fold. But roughly 40% of drugs lack ionisable groups, ruling salt formation out. When it is feasible, salt forms can still present polymorphism, hygroscopicity, and bioequivalence problems.
First-line approach
Limited to ionisable drugs
- Amorphous Solid Dispersions (ASDs)
ASDs disrupt the crystalline lattice, producing a higher-energy amorphous form with much faster dissolution. 48 FDA-approved products used ASDs between 2012-2023. The core challenge is thermodynamic instability: the amorphous form tends to recrystallise, demanding careful polymer selection and tight manufacturing process control.
Proven technology
Stability challenges
Manufacturing complexity
- Lipid-Based Drug Delivery Systems (LBDDS)
SEDDS/SMEDDS solubilise lipophilic drugs in lipid matrices that form emulsions spontaneously in the GI tract -- a strong fit for "grease ball" molecules. Downsides include extensive excipient compatibility work, potential GI irritation, and a typical requirement for gelatin capsules that limits dose flexibility.
Ideal for lipophilic drugs
Excipient compatibility issues
- Nanoparticle Technologies
Reducing particle size to the nanometre range increases surface area-to-volume ratio and speeds dissolution. Nanosuspensions and nanocrystals underpin several commercial products, but aggregation, Ostwald ripening, and scale-up difficulties have kept wider adoption in check.
High surface area
Scale-up challenges
- Cyclodextrin Complexation
Cyclodextrins form inclusion complexes: a hydrophilic exterior encapsulates the lipophilic drug in the cavity. The approach is well-established with strong regulatory precedent. The drawback is stoichiometric: large cyclodextrin quantities are often needed, which adds cost and can cause GI side effects at high doses.
Well-established
High excipient load
The small group of commercial polymers available for ASDs is not sufficiently structurally diverse to enable systematic study of structure-activity relationships, and these polymers were not specifically designed for ASD formulation, but rather were repurposed from other pharmaceutical applications.
Source: Pharmaceutical Research Literature, 2024
AI/ML Breakthroughs in Solubility Prediction
AI is replacing trial-and-error screening with predictive formulation science. Machine learning models trained on historical formulation data, molecular descriptors, and thermodynamic parameters now reach accuracy levels that compress development timelines from months to weeks.
One study combined high-throughput screening with machine learning across 1,272 binary and ternary solid dispersions, identifying 188 successful ASDs against 1,084 crystalline formations. ML models trained on this data reduced screening time by 90% and flagged successful polymer combinations that traditional approaches would have missed.
AI/ML Prediction Performance
Drug-polymer compatibility
Chemical stability (XGBoost)
R-squared solubility prediction
Time reduction vs screening
These numbers mark a shift from empirical experimentation to predictive formulation science, allowing confident decisions weeks into development rather than months.
Emerging AI Platforms
- Quadrant 2: ML platform predicting drug-polymer miscibility at >90% accuracy using molecular descriptors and thermodynamic parameters. Validated across 200+ API-polymer combinations.
- FormulationAI: Deep learning approach that pairs SMILES-based molecular representation with gradient boosting for formulation outcome prediction. Outperforms traditional Hansen/Flory-Huggins methods.
- Bayesian Optimisation: Active learning methods that explore formulation space efficiently, identifying optimal conditions with minimal experimental runs. Cuts screening from 100+ experiments to 10-15.
- COSMO-SAC Modelling: Quantum mechanics-aided activity coefficient prediction achieving 13% average absolute deviation in weight fraction solubility, correctly categorising polymer types by compatibility.
Regulatory Landscape: FDA Biowaivers and ICH M9
The regulatory framework around solubility-challenged compounds is still shifting. BCS-based biowaivers, once limited to Class I compounds, now cover certain Class III compounds under ICH M9, reducing the clinical study burden for qualifying formulations.
For Class II and IV compounds, regulatory pathways remain more involved. That said, the FDA has shown growing receptivity to AI/ML-supported development strategies. The 2025 FDA draft guidance on "Considerations for the Use of Artificial Intelligence to Support Regulatory Decision Making" directly addresses predictive models in formulation development.
The 48 FDA-approved ASD products between 2012-2023 set strong regulatory precedent for solubility enhancement technologies. PVPVA-based formulations make up 49% and HPMCAS 30% of those approvals, giving clear direction on acceptable polymer selection and manufacturing approaches.
Key Regulatory Developments
- ICH M9 (2019): Expanded BCS-based biowaiver eligibility to include Class III compounds meeting specific criteria
- FDA 2025 AI Guidance: Framework for AI/ML in regulatory decision-making, including formulation development applications
- Q12 Lifecycle Management: Encourages science-based approaches to post-approval changes, facilitating formulation optimisation
The AI-Powered Solution: DeepC's Approach
DeepC treats the solubility crisis as a computational problem with a computational answer. Instead of screening a limited set of polymer and formulation options by hand, the platform combines multiple predictive modalities to identify optimal solubility enhancement strategies.
The Formulation Agent runs molecular dynamics simulations for atomic-level interaction prediction, machine learning models trained on proprietary formulation datasets, and COSMO-SAC thermodynamic modelling to assess compatibility from first principles. The result: prediction accuracies above 92% with an experimental burden reduced by orders of magnitude.
For organisations developing amorphous solid dispersions, the MeltPrep VCM Agent screens drug-polymer combinations for hot melt extrusion and KinetiSol processing. It evaluates miscibility, thermal stability windows, processing parameters, and downstream tableting compatibility in a single workflow.
Formulation Agent
- BCS classification and strategy recommendation
- Drug-polymer compatibility prediction (>92% accuracy)
- Supersaturation maintenance modelling
- Manufacturing process compatibility assessment
MeltPrep VCM Agent
- Rapid ASD screening for HME/KinetiSol
- Thermal stability window prediction
- Processing parameter optimisation
- Long-term physical stability prediction
Strategic Implications
70-90% of pipeline candidates have poor aqueous solubility. Organisations that build rational formulation capabilities around this reality will move faster. Those still running trial-and-error screening will face rising costs, longer timelines, and avoidable late-stage failures.
The technology is ready. AI/ML models hit >92% accuracy in drug-polymer compatibility prediction. Regulators accept science-based formulation approaches. 48 FDA approvals confirm that computational formulation works at commercial scale. The remaining variable is adoption speed: how long can an empirical approach survive when competitors are using AI to compress their timelines?
For organisations with BCS Class II or IV compounds stalled in development, the path forward is straightforward:
- Implement predictive solubility screening: at candidate selection to avoid the "developability graveyard" before significant investment
- Deploy AI-powered polymer selection: to rationally identify optimal ASD carriers rather than exhaustive screening campaigns
- Integrate manufacturing process prediction: to ensure selected formulations are compatible with scale-up requirements from the outset
- Build regulatory-ready documentation: leveraging AI-generated mechanistic understanding to support submissions
The Bottom Line
The solubility crisis is solvable. AI-powered formulation prediction is no longer a research exercise; it is a production tool. Organisations that deploy it now get faster development, lower failure rates, and better patient outcomes. Organisations that wait will see competitors advance the molecules they shelved.
Contact Deepceutix using the form below for a solubility assessment of your BCS Class II/IV compounds.