The Cost of Selecting the Wrong Lead

Pursuing a poorly behaving antibody is one of the most expensive mistakes in drug discovery.
Sequence and structural filtering minimizes this risk.

$11K-$16K Average daily out-of-pocket cost for the early development of a biotherapeutic lead candidate .

60% Phase 2 antibody candidates with developability issues .

$800K Lost value per day of delay due to poor developability .

"The cost of engineering an antibody at the discovery stage is significantly lower than the cost of optimizing process and formulation at the development stage ."

"Application of rank ordering and stability optimization is a proven method for antibody therapeutic design ."

Randal R. Ketchem, Ph.D.

Computational Analysis & Output

Fv Attributes

Germline: V-Gene identity and origin mapping.
Humanness: Log-likelihood scoring against 130M+ human sequences.
Numbering: IMGT/Kabat/Martin/AHo numbering assignment.
CDR Detection: IMGT/Chothia/Kabat/North CDR region detection.
Alignment: Numbering system-based alignments for direct residue comparisons.
Clading: Ensure sequence diversity amongst lead candidates.

Lead Selection

KBC Score: Aggregate developability score weighted by severity allows for cross-trait rank ordering and targeted lead selection.
Optimization Engineering: Detailed per residue liabilities allows for targeted optimization designs.
MOE Liability Mapping: Export of CCG MOE SVL files quickly indicates liability positions on the antibody structure.
Assembler: Assemble new antibody modalities across multiple Fv regions simultaneously.

Liability Scanning

Chemical Liabilities: Deamidation, Isomerization, Oxidation (Met/Trp), N-GLyc, Hydrolysis, Fragmentation .
Structure Display: In-browser display of liabilities on structure model.
Isoelectric Point: Avoid serum pH instability and select for optimal formulation.
Physical Properties: Evaulation of physical properties for lead panels.
Positional Analysis: Evaluation of per-residue positional frequencies by germline and LLM likelihoods to aid engineering selections.

Structural Stability

AbLang & AbLang2: Machine learning-based likelihood scores (Full Fv & Framework) predict potential impacts to stability such as titer, yield, aggregation, particulation, low pH stability, and more.
Cysteine Analysis: Identification of unpaired, missing, or unusual cysteines, ensuring stable fold and disulfide pairing.
Stability Motifs: Disrupted HC-CDR3 Salt Bridge, which have been shown to impact HC-CDR3 stability and efficacy .

Surface Properties

Surface Hydrophobicity (SPH): Aggregation propensity, stickyness risk for column selection and potential polyreactivity.
Positive Charge Patches (SPP): Potential for faster clearance rates, potential polyreactivity.
Negative Charge Patches (SPN): Potential for high viscosity, potential polyreactivity.
Fv Charge Dipole (SPCD): Potential for high viscosity.

Fv Optimization

Stability Violation Repair: Stability may impact titer, yield, aggregation, particulation, low pH stability, and more.
PTM Liability Repair: Stress and storage may impact PTM formation, leading to potential loss of efficacy.
Missing or Unusual Cysteine Repair: Free cysteines can for cross-chain disulfides for undesired pairings.
Surface Repair: Surfaces may be repaired while seeking to limit the introduction of instabilities or PTMs.
Humanization: Germline template humanization allows for discovery in alternate species.
Observations: Record past IMGT-positioned residue observations to aid lead selection and optimization engineering based on previous experiments.

Sample Application Screenshots

Comprehensive Project Analysis

Comprehensive Project Analysis

Multi-Sequence Alignment

Sequence Clustering and Diversity Analysis

Physical Properties Evaluation

Structural Liability Mapping

Positional Frequency and ML Model Analysis

Lead Optimization and Engineering

Combinatorial Variant Design

Humanization

Assembler

Observations

References

ASPE Report, "Estimation of Drug Development Costs," (Updated Sept 2024 / March 2025).
Wouters et al., "Estimated Research and Development Investment Needed to Bring a New Therapeutic Product to Market, 2009-2018," JAMA (2020), with updated 2024 methodology analysis.
Jain, T. et al., "Biophysical properties of the clinical-stage antibody landscape." Proc. Natl. Acad. Sci. U.S.A. 114 (5) 944-949 (2017).
"Quantifying the Value of a Day of Delay in Drug Development." Tufts Center for the Study of Drug Development (CSDD) Impact Report (2024).
Zhang et al., "Developability assessment at early-stage discovery to enable development of antibody-derived therapeutics." Antibody Therapeutics (2023).
Kerwin et al., "Framework Mutations of the 10-1074 bnAb Increase Conformational Stability, Manufacturability, and Stability While Preserving Full Neutralization Activity." Journal of Pharmaceutical Sciences (2020).
Williams et al., "A candidate antibody drug for prevention of malaria." Nature Medicine (2024).
Sajadi et al., "A comprehensive engineering strategy improves potency and manufacturability of a near pan-neutralizing antibody against HIV." Structure (2025).
Liability, Humanness, Numbering: AntPack Documentation.
Liability motifs: Satława et al., PLoS Comp Biol (2024).
AbLang: Olsen et al., Bioinformatics Advances (2022).
AbLang2: Olsen et al., bioRxiv (2024).
Surface Properties (Tap-like method): Raybould et al., PNAS (2019).

Ketchem Biotherapeutics Consulting LLC

AbLead

Developability by Design