{ "study_id": "STUDY-26-BIOLUMINESCENCE-LUCIFERASE-PHOTOPROTEIN", "discovery_id": 103, "slug": "bioluminescence-luciferase-photoprotein-evolution", "validation_set_id": "VAL-SET-036-BIOLUMINESCENCE-LUCIFERASE-PHOTOPROTEIN-32COHORT", "generated_at": "2026-11-04T05:28:00Z", "tier_trajectory": "Full Step-Up Trajectory (Tier 1 Exploratory -> Tier 2 Blinded Validation -> Tier 3 Scientific Synthesis)", "prior_beaker_depth": 5, "posterior_beaker_rating": 5, "posterior_z_score": 6.76, "stage_1_tier1_exploratory": { "tier": 1, "taxa_count": 34, "sequence_volume_mb": 2.18, "convergent_systems_surveyed": [ { "system": "Coleopteran D-Luciferin ANL-Superfamily Luciferases (Lampyridae, Elateridae, Phengodidae; PDB: 1LCI)", "unpartitioned_rcfv": 0.164, "partitioned_rcfv": 0.020, "rcfv_reduction_pct": 87.8, "unpartitioned_ufboot_pct": 39.0, "partitioned_ufboot_pct": 100.0, "key_finding": "Separates convergent active-site pocket substitutions (Res 240-351) from the conserved N-domain + 110-aa C-terminal K529/K443 140-deg rotation lid and -SKL peroxisomal SLiM, proving independent recruitment in Lampyridae vs. Elateridae/Phengodidae" }, { "system": "Cnidarian & Ctenophore Ca2+-Regulated Coelenterazine Photoproteins (Obelin, Aequorin, Mnemiopsin, Berovin; PDB: 1JF0, 1SL8)", "unpartitioned_rcfv": 0.172, "partitioned_rcfv": 0.020, "rcfv_reduction_pct": 88.4, "unpartitioned_ufboot_pct": 42.0, "partitioned_ufboot_pct": 99.8, "key_finding": "Phase-locks canonical Ca2+-binding EF-hands I/III/IV vs. substrate-binding EF-hand II and retains the C-terminal His175-Tyr190-Trp179 triad + Pro195 cap SLiM, rejecting the false Coelenterata photoprotein artifact" }, { "system": "Dinoflagellate 3-Domain Tetrapyrrole Luciferases (LCF D1-D2-D3 + 4-His pH Gate; PDB: 1VPR)", "unpartitioned_rcfv": 0.181, "partitioned_rcfv": 0.021, "rcfv_reduction_pct": 88.4, "unpartitioned_ufboot_pct": 44.0, "partitioned_ufboot_pct": 99.6, "key_finding": "Eliminates 1,256-aa D1-D2-D3 tandem register shifts while preserving the 48-aa N-terminal four-histidine (H899/H909/H924/H930) pH 6.0 helical gate SLiM" } ] }, "stage_2_tier2_blinded_validation": { "tier": 2, "cohorts_total": 32, "dev_cohorts": 24, "reserve_cohorts": 8, "sequence_volume_mb": 3.64, "concordant_cohorts": 28, "mean_concordant_d_ctx": 0.08, "untouched_reserve_posterior_z": 6.41, "context_anomalies_isolated": [ { "blind_token": "BLIND-BIOLUM-06", "taxa": "Pyrophorus plagiophthalamus (Elateridae Click Beetle) vs. Photinus pyralis (Lampyridae Firefly)", "repository_label": "Monophyletic beetle luciferase ortholog clade (unpartitioned tree UFBoot = 84% for false sister grouping)", "pass1_blinded_extrapolation": "Independent paralog recruitments from distinct elateroid peroxisomal acyl-CoA synthetase (ACSL) ancestors; convergent active-site pocket (S247/I288/T343) routed to Track 2 spectral vector", "z_blind": 6.32, "z_ctx": 0.44, "d_ctx": 5.88 }, { "blind_token": "BLIND-BIOLUM-14", "taxa": "Mnemiopsis leidyi (Ctenophora Mnemiopsin-1) vs. Obelia geniculata / Aequorea victoria (Hydrozoa Obelin/Aequorin)", "repository_label": "Shared Cnidaria+Ctenophora ('Coelenterata') photoprotein clade or horizontal gene transfer", "pass1_blinded_extrapolation": "Distinct basal metazoan EF-hand paralogs with convergent hydroperoxycoelenterazine cavity remodeling; EF-hand I-IV phase-locking drops RCFV 0.172 -> 0.020", "z_blind": 6.18, "z_ctx": 0.52, "d_ctx": 5.66 }, { "blind_token": "BLIND-BIOLUM-21", "taxa": "Phrixothrix hirtus Red Head Organ Luciferase (lambda_max = 622 nm) vs. Ventral Green Organ (546 nm)", "repository_label": "Generic firefly-like green-emitting beetle luciferase (Single-Track masked active-site loop)", "pass1_blinded_extrapolation": "Track 2 active-site loop electrostatic & Arg337/Tyr257 cavity polarity vector predicts 76-nm bathochromic red shift (622 nm vs. 546 nm)", "z_blind": 6.48, "z_ctx": 0.29, "d_ctx": 6.19 }, { "blind_token": "BLIND-BIOLUM-29", "taxa": "Noctiluca scintillans Dual-Domain LCF-Scintillon Fusion vs. Lingulodinium polyedra Tri-Domain LCF (PDB: 1VPR)", "repository_label": "Truncated pseudogene of 3-domain dinoflagellate luciferase", "pass1_blinded_extrapolation": "Functional ancestral basal dinoflagellate fusion combining a single catalytic beta-barrel + 4-His pH gate with a C-terminal luciferin-binding protein (LBP) domain (dN/dS = 0.042)", "z_blind": 6.08, "z_ctx": 0.34, "d_ctx": 5.74 } ] }, "stage_3_tier3_scientific_synthesis": { "tier": 3, "taxa_count": 76, "sequence_volume_mb": 6.94, "cumulative_superfamilies": 28, "cumulative_taxa": 588, "cumulative_sequence_mb": 33.80, "hypotheses_ledger": [ { "id": "H1", "system": "Coleopteran ANL Luciferase Independent Recruitment & Red/Green Tuning (PDB: 1LCI)", "rcfv_drop": "0.164 -> 0.020 (-87.8%)", "track2_spectral_recovery_pct": 99.4, "delta_lnl": 592.4, "crown_ufboot_pct": 100.0, "posterior_z": 6.76 }, { "id": "H2", "system": "Hydrozoan Obelin/Aequorin vs. Ctenophore Berovin/Mnemiopsin EF-Hand Cage (PDB: 1JF0, 1SL8)", "rcfv_drop": "0.172 -> 0.020 (-88.4%)", "track2_spectral_recovery_pct": 99.2, "delta_lnl": 468.2, "crown_ufboot_pct": 99.8, "posterior_z": 6.38 }, { "id": "H3", "system": "Dinoflagellate D1-D2-D3 Beta-Barrel & 4-His pH 6.0 Scintillon Gate (PDB: 1VPR)", "rcfv_drop": "0.181 -> 0.021 (-88.4%)", "track2_spectral_recovery_pct": 99.1, "delta_lnl": 412.6, "crown_ufboot_pct": 99.6, "posterior_z": 6.14 }, { "id": "H4", "system": "Fungal Luz/Hispidin Caffeic-Acid Cycle & Bacterial LuxAB FMNH2 Outgroup Synthesis", "rcfv_drop": "0.156 -> 0.021 (-86.5%)", "track2_spectral_recovery_pct": 99.3, "delta_lnl": 1473.2, "crown_ufboot_pct": 99.7, "posterior_z": 6.54 } ], "runie_model_comparison": [ { "rank": "1st (Best)", "architecture": "Minimizer Synteny -> Coupled Dual-Track Plan-7 HMM (Track 1: Core + K529/K443 Lid, Tyr190 Cap & 4-His pH Gate SLiMs [+] Track 2: Spectral lambda_max & Tandem D1-D3 Vector) -> Kabsch 3D (1LCI/1JF0/1SL8/1VPR) -> Potts DCA -> Goldman-Yang dN/dS -> RP16 Supermatrix -> BIONJ ML Tree (LG+C60+F+R4)", "marginal_lnl": -186420.2, "delta_lnl": 0.0, "rcfv": 0.020, "posterior_z": 6.76 }, { "rank": "2nd (Nearest)", "architecture": "Single-Track Sub-Domain Partitioning (Track 1 Core + SLiM Kept; Active-Site Spectral Loop & D1-D3 Concerted Vector Masked) -> *MAFFT L-INS-i -> *US-align 3D -> *IQ-TREE 2 (LG+F+G4)", "marginal_lnl": -186812.6, "delta_lnl": -392.4, "rcfv": 0.020, "posterior_z": 5.38 }, { "rank": "3rd (Medium)", "architecture": "*HMMER3 Strict Pfam Core-Only Cropping (110-aa K529/K443 C-Term Lid, Tyr190/Pro195 Photoprotein Cap & 4-His pH Helical Gate Stripped) -> *MAFFT -> *IQ-TREE 2", "marginal_lnl": -187168.4, "delta_lnl": -748.2, "rcfv": 0.024, "posterior_z": 3.52 }, { "rank": "4th (Rejected)", "architecture": "Unpartitioned Full-Length *MAFFT / Gotoh MSA (EF-Hand Register Shifts, D1-D2-D3 Paralog Mixing & Convergent Pocket LBA Retained) -> *IQ-TREE 2 (LG+F+G4)", "marginal_lnl": -187893.4, "delta_lnl": -1473.2, "rcfv": 0.172, "posterior_z": 1.14 } ] } }