001tmf/blatant-why
21 subagents
Subagent
by-campaignPlan design campaigns. Analyze research, select modality, choose scaffolds, estimate costs, create campaign state, and present structured plan for user approval.by-designGenerate protein/antibody designs using available compute providers (Tamarind, local GPU). Creates tool inputs, submits jobs, and monitors progress.by-diversityAnalyze sequence and structural diversity across a design set. Sequence clustering, structural clustering, Pareto front analysis, scaffold balance, phylogenetic dendrograms, and diverse panel…by-environmentDiscover available tools, compute providers, GPU access, API keys, and configuration. Produces structured environment.json for use by all other agents.by-epitopeDeep epitope analysis agent. Maps binding interfaces from PDB structures, classifies epitope type, assesses druggability, identifies cryptic sites, cross-references SAbDab, and generates hotspot…by-epitope-researcherParallel epitope surface analysis. Identifies druggable sites, hotspot residues, scores epitope accessibility and druggability. Lighter-weight than the full by-epitope agent.by-evaluatorIndependent structural evaluation of designs. Deep structural analysis including refolding validation, interface quality, comparison to known binders, confidence decomposition, aggregation risk, and…by-formatterFormat designs for downstream use. scFv conversion, Fab assembly, expression vector design, codon optimization hints, multi-format output (FASTA/GenBank/entities YAML), and Adaptyv Bio submission…by-humanizationHumanize non-human antibody sequences for therapeutic development. Framework analysis, CDR grafting onto human germlines, back-mutation identification, T-cell epitope prediction, humanness scoring,…by-knowledgeQuery and update the learning system. Store campaign outcomes, query similar campaigns, get scaffold rankings, record failures, and generate recommendations.by-labHandle Adaptyv Bio lab submissions with triple safety gate. Presents cost estimates, validates approval chain, and submits only when all three gates pass.by-liability-engineerActively propose mutations to fix identified sequence liabilities. Score mutations for structural impact, consider framework vs CDR context, generate ranked mutation panels with predicted impact, and…by-plan-checkerReview campaign plans for completeness and correctness before user approval. Checks fold validation, cost estimates, modality selection, parameters, and scaffold justification.by-prior-art-researcherParallel prior art research via SAbDab, PubMed, bioRxiv, and literature. Finds existing binders, antibodies, nanobodies against the target. Maps the competitive landscape.by-researchTarget analysis, literature review, prior art search, epitope identification using PDB, UniProt, SAbDab, and research MCP tools.by-research-synthesizerSynthesizes outputs from 4 parallel research agents into a unified target report. Reads target_structures.json, target_sequence.json, prior_art.json, and epitope_analysis.json. Produces…by-screeningScore, filter, and rank designs. Run liability screening, developability checks, and composite scoring (ipSAE, ipTM, pLDDT). Present ranked candidates.by-sequence-researcherParallel target sequence research via UniProt. Identifies canonical sequence, domains, PTMs, variants, functional regions, and druggability indicators.by-structure-researcherParallel target structure research via PDB. Finds best resolution crystal structures, identifies chains, interfaces, binding surfaces, and downloads the optimal structure for design.by-verifierIndependent quality gate checker. Verifies structural metrics, screening completeness, and candidate integrity before results are presented to the user.by-visualizationGenerate PyMOL and ChimeraX session scripts for structural visualization. Creates publication-quality views of targets, designed complexes, interfaces, CDR loops, electrostatic surfaces, and clash…