ai.nullary/nullary

Summary of the Layer-1 inactivity-scoring model registry: how many per-target models, split by family, and median scaffold-split ROC-AUC.

Coverage browse: the most heavily-pursued ('graveyard') targets, ranked by recorded negative findings. Optional family filter (kinase, gpcr, protease, nuclear_receptor, ion_channel, transporter, phosphatase, other).

ADC failures attributed to linker chemistry.

Small-molecule ADMET failures.

ADMET failures across ALL modalities.

Ancestry-specific CRISPR failures.

Bispecific format/engineering failures.

Antibody developability failures.

Drug-drug interaction failures.

ADCs that failed at any stage.

Bispecifics that failed at any stage.

Discontinued/terminated clinical antibodies.

Non-dependency / failed essentiality screens.

Failed/ineffective CRISPR guides.

ASOs/siRNAs that failed engagement/developability.

Failed peptide therapeutics.

PROTACs that failed degradation/ternary/permeability.

Findings that failed to replicate.

Small molecules that failed selectivity.

Failed/terminated vaccines (by pathogen/indication).

Inactive small-molecule compound-target pairs.

ALL failed approaches for an indication across every modality.

Approaches that failed for a mechanism (by target).

Oligonucleotide delivery failures.

Vaccine + antimicrobial + antibody failures for a pathogen.

Peptide stability/half-life failures.

PROTAC E3-ligase recruitment / ternary failures.

Clinical/preclinical safety failures across modalities.

ALL failed approaches against a target across every modality.

Failed vaccine immunogen designs.