{"gene":"FGF3","run_date":"2026-06-09T23:54:43","timeline":{"discoveries":[{"year":1994,"finding":"Mouse FGF3 is translated almost exclusively from an upstream CUG codon (rather than the AUG codon), producing a single protein that is distributed in both the nucleus and the secretory pathway. Secretion is mediated by cleavage adjacent to a signal peptide, whereas nuclear localization is determined by a classical bipartite nuclear localization motif together with upstream N-terminal sequences. These competing signals within the same protein determine its dual subcellular fate.","method":"Deletion and replacement mutants in reticulocyte lysates and transfected COS-1 cells; fusion to heterologous protein; subcellular fractionation","journal":"The EMBO journal","confidence":"High","confidence_rationale":"Tier 1 / Strong — in vitro translation, mutagenesis of multiple deletion/replacement constructs, and heterologous fusion proteins with multiple orthogonal readouts in one rigorous study","pmids":["8076608"],"is_preprint":false},{"year":1993,"finding":"Xenopus FGF3 (XFGF3) is secreted and glycosylated (31 kDa, signal-peptide cleaved), associates with cell surface and extracellular matrix via heparin-binding, and can be displaced by soluble heparin. It induces morphological transformation of NIH3T3 cells and stimulates DNA synthesis in cells expressing FGFR1 and FGFR2 isoforms. Chimeric proteins between XFGF3 and mouse FGF3 showed that the C-terminal region determines differences in receptor affinity, mitogenic potency, and transforming activity.","method":"COS-1 cell transfection, conditioned medium assays, heparin-Sepharose binding, NIH3T3 transformation assay, C57MG/BALB/MK mitogenesis assay, chimeric construct analysis","journal":"The EMBO journal","confidence":"High","confidence_rationale":"Tier 1 / Strong — reconstitution of secretion, heparin binding, and mitogenic activity with mutagenesis via chimeric constructs, multiple orthogonal methods in one study","pmids":["8223431"],"is_preprint":false},{"year":1996,"finding":"Zebrafish FGF3 (ZFGF3) is secreted as a heterogeneous set of glycoproteins (29–30.5 kDa), associates strongly with extracellular matrix, and binds the IIIb isoform of FGFR2 with higher affinity than the IIIc isoform (similar to mouse FGF3). Hybrid proteins between Xenopus and zebrafish FGF3 implicate the C-terminal region in determining receptor affinity differences, mitogenic potency, and transforming activity.","method":"COS-1 cell transfection, receptor binding assays with FGFR2-IIIb vs IIIc, NIH3T3 transformation assay, chimeric construct analysis, heparin displacement","journal":"Oncogene","confidence":"High","confidence_rationale":"Tier 1 / Strong — receptor binding with two isoforms, chimeric mutagenesis mapping C-terminal determinants, multiple orthogonal assays in one study","pmids":["8622866"],"is_preprint":false},{"year":2001,"finding":"SOX6 binds the key regulatory element PS4A in the Fgf-3 promoter and strongly represses Fgf-3 transcription. SOX6 recruits the co-repressor CtBP2 via a short PLNLSS motif, and SOX6 binding to CtBP2 is required for co-operative repression of the Fgf-3 promoter through PS4A.","method":"Yeast one-hybrid screen, reporter gene assays, yeast two-hybrid, co-immunoprecipitation in mammalian cells, mutational analysis of SOX6, in situ hybridization, co-expression in NIH3T3 cells","journal":"Nucleic acids research","confidence":"High","confidence_rationale":"Tier 2 / Strong — reciprocal yeast and mammalian Co-IP, mutagenesis of binding motif, reporter assays, multiple orthogonal methods","pmids":["11504872"],"is_preprint":false},{"year":2004,"finding":"SOX7 activates Fgf-3 transcription by binding the PS4A element of the Fgf-3 promoter, competing with GATA-4 for PS4A occupancy. In GATA-4-deficient ES cells, Fgf-3 expression upon differentiation depends on SOX7, as shown by RNAi knockdown of Sox7. SOX2, by contrast, is a poor activator and negatively modulates GATA-4-driven Fgf-3 activation when co-expressed.","method":"Reporter gene assays, RNAi knockdown, co-expression studies in F9 and ES cells, nuclear extract complexes on PS4A, in situ hybridization","journal":"The Journal of biological chemistry","confidence":"High","confidence_rationale":"Tier 2 / Strong — RNAi loss-of-function, reporter assays, nuclear complex detection, multiple orthogonal methods in one study","pmids":["15082719"],"is_preprint":false},{"year":2002,"finding":"GATA-4 binds two sites in the Fgf-3 promoter: PS4A (positive regulatory element) and PS13 (negative regulatory element near P3). Efficient binding to PS4A requires both zinc fingers and the basic domain of GATA-4 engaging a second flanking sequence, and this dual-zinc-finger binding is essential for Fgf-3 promoter activation. PS13 negative activity depends on its proximity to the transcription initiation site.","method":"Mutational analysis of GATA-4 truncation deletions, reporter gene assays, DNase-I footprinting, EMSA/DNA bending assays, promoter deletion constructs","journal":"Nucleic acids research","confidence":"High","confidence_rationale":"Tier 1 / Moderate — in vitro footprinting plus mutagenesis of binding domain plus functional reporter assays, multiple orthogonal methods","pmids":["11842118"],"is_preprint":false},{"year":1993,"finding":"The Fgf-3 promoter contains at least two positive and three negative regulatory elements. The PS4A element is essential for promoter activity in both undifferentiated and differentiated F9 cells, and deletions encompassing PS4A abolish retinoic acid inducibility and basal promoter activity.","method":"Stable and transient transfection of CAT reporter constructs, progressive and targeted deletion mutants, DNase-I footprinting in F9 embryonal carcinoma cells","journal":"Nucleic acids research","confidence":"High","confidence_rationale":"Tier 1 / Moderate — in vitro footprinting plus systematic deletion mutagenesis with functional reporter readout, multiple orthogonal methods","pmids":["8265348"],"is_preprint":false},{"year":2004,"finding":"A 5.7-kb enhancer upstream of mouse Fgf3 mediates embryonic expression in the midbrain, hindbrain, surface ectoderm, dorsal root ganglia, and CNS. Sonic hedgehog (Shh) signaling is required for Fgf3 expression in ventral CNS and DRG (Shh-dependent), whereas expression in cranial ganglion cells is Shh-independent.","method":"Transgenic reporter mice carrying Fgf3 genomic regions; deletional analysis; breeding into Shh mutant background; in situ hybridization","journal":"Developmental dynamics","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — transgenic enhancer dissection with deletion series and genetic epistasis with Shh mutants, single lab","pmids":["15108308"],"is_preprint":false},{"year":2002,"finding":"In zebrafish, FGF3 and FGF8 are both expressed in rhombomere 4 (r4) and together are required for development of adjacent rhombomeres 5 and 6. Transplantation of r4 cells or misexpression of either FGF3 or FGF8 can induce r5/r6 marker expression, establishing r4 as an FGF-mediated signaling center for early hindbrain patterning.","method":"Antisense morpholino knockdown, cell transplantation, misexpression experiments, time-lapse imaging, in situ hybridization for r5/r6 markers","journal":"Development (Cambridge, England)","confidence":"High","confidence_rationale":"Tier 2 / Strong — reciprocal gain- and loss-of-function, cell transplantation, replicated across multiple groups (PMID 12121619, 12135921)","pmids":["12135921","12121619"],"is_preprint":false},{"year":2002,"finding":"In zebrafish, combined loss of Fgf3 and Fgf8 via morpholino knockdown causes complete failure of otic placode formation and absence of early placode markers (pax2.1, dlx3), without affecting cell division or death. Either factor alone produces only partial reduction; the temporal requirement for FGF signaling is between 60% epiboly and tailbud stages. The earliest otic event, pax8 expression, does not require Fgf3/Fgf8, placing their action downstream of initial otic territory specification.","method":"Antisense morpholino knockdown (fgf3 and fgf8 single and double), FGFR inhibitor SU5402 time-window experiments, otic marker in situ hybridization, cell death/proliferation assays","journal":"Development (Cambridge, England)","confidence":"High","confidence_rationale":"Tier 2 / Strong — double morpholino epistasis, pharmacological inhibitor time-window, multiple otic markers; replicated across multiple independent groups (PMIDs 11437442, 11959820, 12385757)","pmids":["11959820","11437442","12385757"],"is_preprint":false},{"year":2003,"finding":"In mice, Fgf3 and Fgf10 act redundantly and in a dose-sensitive manner for otic placode induction: single mutants have partial defects, but double Fgf3/Fgf10 mutants fail to form otic vesicles. Fgf3 is expressed in hindbrain neurectoderm while Fgf10 is expressed in underlying mesenchyme, indicating that FGF signals for otic induction emanate from both sources.","method":"Genetic double knockout (Fgf3 and Fgf10 null alleles), compound heterozygote allelic series, otic marker gene expression analysis, cell proliferation and survival assays","journal":"Development (Cambridge, England)","confidence":"High","confidence_rationale":"Tier 2 / Strong — genetic double null and allelic dosage series, replicated across two independent studies (PMIDs 12810586, 14623822)","pmids":["12810586","14623822"],"is_preprint":false},{"year":2000,"finding":"Ectopic expression of FGF3 in chick embryos induces formation of ectopic otic placodes expressing otic marker genes, which subsequently form vesicles with inner ear gene expression patterns. FGF2 under the same conditions has no effect, demonstrating specificity of FGF3 in inducing inner ear fate.","method":"In ovo electroporation-based gene transfer for ectopic FGF3 expression in chick, ectopic FGF2 control, otic marker in situ hybridization","journal":"Development (Cambridge, England)","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — gain-of-function with specificity control (FGF2 negative), single lab","pmids":["10769226"],"is_preprint":false},{"year":2007,"finding":"In mouse, Fgf3 expressed in hindbrain neurectoderm is required for dorsal otic patterning and endolymphatic duct formation. Fgf3 mutants show altered molecular patterning of the otic vesicle, and Fgf3 prevents ventral expansion of r5-6 Wnt3a, thereby focusing inductive WNT signals on the dorsal otic vesicle. Epistasis analysis places Fgf3 between hindbrain-expressed Hoxa1/Mafb and otic vesicle-expressed Gbx2 in the WNT-initiated cascade for dorsal otic patterning.","method":"Fgf3 null mouse genetic analysis, morphological and molecular otic patterning markers, Wnt3a expression analysis, genetic epistasis with Hoxa1, Mafb, and Gbx2 mutants","journal":"Development (Cambridge, England)","confidence":"High","confidence_rationale":"Tier 2 / Strong — loss-of-function plus multi-gene epistasis analysis, multiple molecular markers, single lab with comprehensive pathway placement","pmids":["17855431"],"is_preprint":false},{"year":2004,"finding":"In zebrafish, Fgf3 signaling from the ventral diencephalon is required non-cell-autonomously for expression of pituitary specification genes (lim3, pit1) in adenohypophyseal progenitor cells. Without Fgf3, early specification fails and adenohypophyseal cells subsequently die by apoptosis. Shh can induce adenohypophyseal cells ectopically but cannot rescue pituitary development in fgf3 mutants, indicating Fgf3 does not act via Shh.","method":"lia/fgf3 null mutant analysis, in situ hybridization for pituitary markers, epistasis with Shh pathway (Shh rescue experiments), apoptosis assays","journal":"Development (Cambridge, England)","confidence":"High","confidence_rationale":"Tier 2 / Strong — null mutant, molecular marker analysis, genetic epistasis with Shh, multiple orthogonal methods","pmids":["15229178"],"is_preprint":false},{"year":2005,"finding":"In zebrafish, Fgf3 derived specifically from pharyngeal endodermal pouches is required for neurogenesis (not initial induction) of epibranchial placodes. Tissue transplants demonstrate endoderm is the cellular source of the neurogenic signal. Ectopic fgf3 expression is sufficient to induce phox2a-positive neurons even in endoderm-deficient embryos, but neither endoderm nor Fgf3 is required for initial placode induction (foxi1 expression is unaffected).","method":"Morpholino knockdown of fgf3, endoderm ablation, mosaic cell transplantation, ectopic fgf3 overexpression, placode marker in situ hybridization","journal":"Development (Cambridge, England)","confidence":"High","confidence_rationale":"Tier 2 / Strong — mosaic transplantation establishing tissue source, gain- and loss-of-function, marker dissection of induction vs neurogenesis steps, multiple methods","pmids":["16077091"],"is_preprint":false},{"year":2010,"finding":"In chick hindbrain, FGF3 (acting through the MAPK/Erk1/2 pathway) is required for upregulation of the ETS-domain transcription factor Pea3, which in turn is necessary for expression of Krox20 in rhombomeres 3 and 5. FGF signaling is a major contributor to ERK1/2 activation and downstream Pea3/Erm target expression in the hindbrain.","method":"Morpholino knockdown, pharmacological FGFR inhibition, in situ hybridization for FGF pathway components (ligands, receptors, MAPK components), Krox20 and Pea3 expression analysis","journal":"Developmental biology","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — morpholino loss-of-function plus pharmacological inhibition, pathway component atlas, single lab","pmids":["20553903"],"is_preprint":false},{"year":2008,"finding":"In chick hindbrain, BMP activity antagonizes FGF3 expression: blocking follistatin translation with morpholinos or overexpressing BMP strongly inhibits FGF3 expression, while adding follistatin increases FGF3 levels. FGF3 expression also requires FGF activity itself, suggesting an autoregulatory loop. This BMP-FGF3 antagonism is required for correct expression of Krox20, Hoxb1, and EphA4.","method":"Morpholino knockdown of follistatin, BMP overexpression, follistatin protein addition, in situ hybridization for FGF3 and segmentation genes","journal":"Developmental biology","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — morpholino loss-of-function, gain-of-function with BMP, rescue with follistatin protein; single lab","pmids":["18823972"],"is_preprint":false},{"year":2016,"finding":"In mouse, PSM-derived FGF3 restrains BMP signaling in the adjacent neuroepithelium. Loss of FGF3 elevates BMP signals, causing increased neuroepithelium proliferation, delayed neural tube closure, and premature neural crest specification. Increasing BMP signaling (by removing one Noggin copy in Fgf3 mutants) exacerbates all phenotypes; decreasing BMP signaling (by removing BMP receptor) alleviates them. Elevated BMP4 depletes PSM progenitors in vitro, phenocopying the Fgf3 mutant axis defect.","method":"Fgf3 null mouse, genetic epistasis with Noggin and BMP receptor mutants, BMP4 in vitro treatment of PSM explants, neural crest/tube marker analysis, apoptosis/proliferation assays","journal":"PLoS genetics","confidence":"High","confidence_rationale":"Tier 2 / Strong — multi-gene genetic epistasis (gain and loss of BMP pathway), in vitro phenocopy, multiple orthogonal methods establishing FGF3-BMP axis","pmids":["27144312"],"is_preprint":false},{"year":1998,"finding":"FGF3 localizes to the otocyst epithelium in mouse, and antisense oligonucleotides against FGF3 suppress otic capsule chondrogenesis in cultured periotic mesenchyme, establishing FGF3 as an otocyst-derived signal capable of initiating chondrogenesis of surrounding mesenchyme.","method":"Endogenous FGF3 localization (immunostaining), antisense oligonucleotide knockdown in periotic mesenchyme/otocyst co-culture system, chondrogenesis assay","journal":"Growth factors (Chur, Switzerland)","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — antisense knockdown with functional chondrogenesis readout, localization by immunostaining; single lab","pmids":["9570039"],"is_preprint":false},{"year":2002,"finding":"Cell-surface-associated FGF3 (via heparan sulfate proteoglycan) is required for NIH3T3 cell transformation: dominant-negative FGFR2(IIIb) reverts the transformed phenotype more efficiently than IIIc, consistent with FGF3's higher affinity for the IIIb isoform. Attaching FGF3 to a GPI membrane anchor (independent of heparan sulfate) greatly increases its transforming potential, indicating that the mode of cell-surface presentation determines biological activity.","method":"Dominant-negative FGFR2(IIIb vs IIIc) expression in transformed DMI cells, GPI-anchored FGF3 mutant construction and transformation assay, heparin displacement, soft agar anchorage-independent growth","journal":"The Journal of biological chemistry","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — dominant-negative receptor specificity, GPI-anchor mutagenesis with functional transformation readout; single lab","pmids":["12084721"],"is_preprint":false},{"year":2008,"finding":"In zebrafish, FGF3 signal from the ventral diencephalon delineates the melanotrope/corticotrope lineage boundary in the developing pituitary. Hypomorphic FGF3 morpholino knockdown specifically defects pars intermedia POMC cells while leaving pars distalis POMC, growth hormone, and prolactin expression intact. This lineage-specific role is independent of Lim3/Pit1 expression, indicating a function distinct from early progenitor specification.","method":"Hypomorphic fgf3 morpholino knockdown, time-lapse confocal live imaging with GFP:pomc reporter zebrafish, in situ hybridization for pituitary lineage markers","journal":"Developmental biology","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — morpholino loss-of-function with live lineage tracing, marker dissection; single lab","pmids":["18514643"],"is_preprint":false},{"year":2008,"finding":"In Ciona intestinalis, FGF3 expressed in the floor plate of the developing nerve cord directs notochord convergent extension (CE) via non-MAPK FGF signaling. A dominant-negative FGF receptor suppresses polarized actin-rich protrusions in notochord cells, resulting in defective CE. In Xenopus mesoderm explants, inhibiting FGF signaling perturbs CE and disrupts membrane localization of Dishevelled (Dsh), a PCP/CE regulator, placing FGF3 upstream of PCP components.","method":"Dominant-negative FGFR expression in Ciona, inhibition of Ciona FGF3 activity, actin protrusion imaging, Xenopus CE explant assay, Dishevelled membrane localization","journal":"Development (Cambridge, England)","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — dominant-negative and ligand inhibition with cellular morphology readout, cross-species validation; single study","pmids":["19036800"],"is_preprint":false},{"year":2019,"finding":"In zebrafish, Fgf3 controls the number of serotonergic and dopaminergic CSF-contacting cells in the posterior hypothalamus by regulating proliferation and cell survival. Fgf3 acts via the ETS-domain transcription factor etv5b (a known FGF downstream target) to control serotonergic progenitor proliferation. Loss of fgf3 also upregulates its own expression, suggesting a self-compensatory mechanism.","method":"Fgf3 morpholino knockdown (null mutant analysis), immunostaining for serotonergic/dopaminergic/neuroendocrine markers, proliferation and apoptosis assays, etv5b expression analysis, hypothalamic transcriptome analysis","journal":"Biology open","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — null/morpholino loss-of-function, multiple marker analysis, transcriptome supporting etv5b pathway; single lab","pmids":["31036752"],"is_preprint":false},{"year":2024,"finding":"Fgf3 mRNA is upregulated in mouse vagal ganglia under acute metabolic stress. Vagal sensory neuron-derived FGF3 enhances glucose-stimulated insulin secretion (GSIS) and improves glucose metabolism. Restriction of Fgf3 overexpression to pancreas-projecting vagal sensory neurons recapitulates the insulinotropic effect, and genetic ablation of Fgf3 in pancreatic vagal afferents exacerbates high-fat diet-induced glucose intolerance and blunts GSIS.","method":"Conditional vagal sensory overexpression and genetic ablation of Fgf3, glucose tolerance tests, GSIS assays, electrostimulation of vagal afferents","journal":"Developmental cell","confidence":"High","confidence_rationale":"Tier 2 / Strong — conditional gain-of-function (restricted to pancreas-projecting neurons), conditional loss-of-function, electrostimulation control; multiple orthogonal approaches","pmids":["39413782"],"is_preprint":false},{"year":2023,"finding":"FGF3 expressed in the chick ventral diencephalon (hypothalamus) acts as a concentration-dependent guidance cue for thalamocortical axons (TCAs): 100 ng/mL is attractant while 500 ng/mL is repellent. Inhibition of FGF3 function disrupts correct navigation of thalamic axons in vitro.","method":"In vitro chick explant guidance assays with recombinant FGF3 at different concentrations, inhibition of FGF3 signaling, expression analysis","journal":"Developmental neuroscience","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — in vitro explant guidance assay with dose-response and loss-of-function; single lab","pmids":["33684917"],"is_preprint":false},{"year":2023,"finding":"FGF3 expressed in the chick hypothalamus acts as a chemorepellent for neighboring prethalamic GABAergic axons. This guidance function is mediated through FGFR1 downstream signaling, as demonstrated by gene expression analysis and FGFR1 loss-of-function studies.","method":"In vitro chick explant guidance assays, FGF3 inhibition, FGFR1 expression analysis, FGFR1 loss-of-function, GABAergic axon tracing","journal":"International journal of molecular sciences","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — in vitro explant assay plus FGFR1 pathway loss-of-function; single lab","pmids":["37834446"],"is_preprint":false},{"year":2023,"finding":"In TA2 mice, MMTV-activated FGF3 promotes spontaneous mammary tumorigenesis via the FGF3/FGFR1/STAT3 signaling pathway. FGF3 physically binds FGFR1 (demonstrated by co-immunoprecipitation). FGF3 or FGFR1 knockdown decreases STAT3 and Akt phosphorylation. STAT3 and Akt mutually activate each other's phosphorylation, and inhibiting either increases FGFR1 expression.","method":"Co-immunoprecipitation of FGF3-FGFR1, shRNA knockdown of FGF3 and FGFR1, pharmacological STAT3/Akt inhibitors, proliferation/migration/invasion assays, xenograft tumor assay","journal":"Frontiers in oncology","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — direct Co-IP plus shRNA knockdown plus pharmacological inhibition; single lab","pmids":["37496658"],"is_preprint":false},{"year":2012,"finding":"In parthenogenetic mouse embryos, Fgf3 is strongly upregulated and drives excessive Fgfr2 phosphorylation, which promotes primitive endoderm differentiation at the expense of epiblast identity (increased Gata4, decreased Sox2/Nanog). Inhibition of Fgfr2 with SU5402 in parthenotes restores normal Nanog/Gata4 levels without affecting Fgf3 expression, placing Fgf3 upstream of Fgfr2 in this pathway.","method":"FGFR2 inhibition with SU5402, immunostaining for lineage markers (Sox2, Nanog, Gata4), RT-qPCR for Fgf3/Fgfr2, analysis of Fgfr2 phosphorylation","journal":"Developmental dynamics","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — pharmacological epistasis placing Fgf3 upstream of Fgfr2, marker analysis; single lab","pmids":["22930543"],"is_preprint":false},{"year":1998,"finding":"FGF-3 (but not FGF-4) expressed in mouse mammary myoepithelial cells strongly stimulates production of pro-MMP-9 and pro-MMP-2, and upregulates plasminogen activators, contributing to matrix invasion. FGF-3-producing cells are invasive in Matrigel-coated chambers. FGF-4 has no effect on these protease secretions.","method":"Retroviral FGF-3 and FGF-4 expression in EF43 cells, Matrigel invasion assay, gelatin zymography for MMPs, plasminogen activator assays, tumorigenicity assays in syngeneic mice","journal":"Oncogene","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — stable expression with functional assays (invasion, zymography, PA assays), specificity shown by FGF-4 comparison; single lab","pmids":["9798677"],"is_preprint":false},{"year":2015,"finding":"Fgf3 expression in zebrafish pharyngeal pouches is regulated downstream of Wnt5b/Wntless (Wls) secretion. In wls morphants and wnt5b mutants, fgf3 expression is reduced in pharyngeal pouches along the anteroposterior axis. Introducing fgf3 mRNA rescues jaw cartilage defects in Wnt5b- and Wls-deficient larvae. Wls is required for Wnt5b but not Wnt11 secretion in pharyngeal tissue, and fgf3 regulates chondrogenic cell proliferation downstream of Wnt5b/Wls.","method":"Morpholino knockdown of wls and wnt9a/wnt11, wnt5b mutant analysis, fgf3 mRNA rescue, cell proliferation assays, pharyngeal cartilage staining","journal":"Journal of cell science","confidence":"Medium","confidence_rationale":"Tier 2 / Moderate — mRNA rescue epistasis, morpholino knockdown of multiple Wnts, proliferation assays; single lab","pmids":["25934698"],"is_preprint":false}],"current_model":"FGF3 is a secreted heparin-binding growth factor (with an alternative CUG-initiated form that also traffics to the nucleus via a competing NLS) that signals through FGFR2-IIIb to activate MAPK/ERK, and functions as a paracrine morphogen during embryogenesis—acting cooperatively with FGF8 and FGF10 to induce the otic placode and pattern the hindbrain, driving otic/inner ear morphogenesis by regulating WNT signaling and downstream transcription factors (Krox20 via Pea3), specifying epibranchial placode neurogenesis from pharyngeal endoderm, directing adenohypophyseal progenitor specification, guiding axonal pathfinding, and controlling insulin secretion via vagal afferent neurons; its transcription is regulated by GATA-4, SOX7 (activators), and SOX6/CtBP2 (repressors) acting on the PS4A promoter element, with BMP signaling as an additional repressive input; in the posterior embryonic axis FGF3 restrains BMP signals to coordinate neural tube closure and neural crest specification; and dysregulation via MMTV insertion or gene amplification drives mammary tumorigenesis through FGF3/FGFR1/STAT3 signaling."},"narrative":{"mechanistic_narrative":"FGF3 is a secreted heparin-binding growth factor that acts as a paracrine morphogen during embryogenesis, signaling preferentially through the FGFR2-IIIb isoform to drive otic, hindbrain, pituitary, and craniofacial patterning [PMID:8622866, PMID:11959820, PMID:11437442, PMID:12385757]. The mature protein is secreted, glycosylated, and tethered to the cell surface and extracellular matrix through heparan sulfate, from which it can be displaced by soluble heparin; its C-terminal region determines receptor affinity, mitogenic potency, and transforming activity [PMID:8223431, PMID:8622866]. FGF3 has an unusual dual subcellular fate: it is translated chiefly from an upstream CUG codon, and competing signals within the same protein—a cleaved signal peptide directing secretion versus a bipartite nuclear localization motif with upstream N-terminal sequences directing nuclear import—partition it between the secretory pathway and the nucleus [PMID:8076608]. The mode of cell-surface presentation governs biological output, as anchoring FGF3 independently of heparan sulfate markedly increases its transforming potential [PMID:12084721]. In development, FGF3 cooperates with FGF8 and FGF10 as an inductive signal: with FGF8 it establishes rhombomere 4 as a hindbrain signaling center patterning r5/r6, and with FGF10 it acts redundantly and dose-dependently for otic placode induction and otic vesicle formation [PMID:12135921, PMID:12121619, PMID:11959820, PMID:11437442, PMID:12385757, PMID:12810586, PMID:14623822, PMID:10769226]. It refines dorsal otic patterning by restraining ventral expansion of Wnt3a and operates within a Hoxa1/Mafb→Fgf3→Gbx2 WNT cascade [PMID:17855431]. FGF3 specifies adenohypophyseal progenitors and pituitary lineage boundaries from the ventral diencephalon, drives epibranchial placode neurogenesis from pharyngeal endoderm, and signals through MAPK/ERK to upregulate Pea3 and thereby Krox20 in the hindbrain [PMID:15229178, PMID:16077091, PMID:20553903, PMID:18514643]. Along the posterior axis FGF3 restrains BMP signaling to coordinate neural tube closure and neural crest timing, while BMP reciprocally antagonizes FGF3 expression [PMID:18823972, PMID:27144312]. Its transcription is controlled at the PS4A promoter element by GATA-4 and SOX7 as activators and SOX6—which recruits the co-repressor CtBP2 via a PLNLSS motif—as a repressor [PMID:11504872, PMID:15082719, PMID:11842118, PMID:8265348]. Postnatally, vagal sensory neuron-derived FGF3 enhances glucose-stimulated insulin secretion, and dysregulated FGF3 promotes mammary tumorigenesis through an FGF3/FGFR1/STAT3 axis with direct FGF3–FGFR1 binding [PMID:39413782, PMID:37496658].","teleology":[{"year":1993,"claim":"Establishing FGF3 as a bona fide secreted, heparin-binding, receptor-activating growth factor answered whether it functions extracellularly like other FGFs and mapped its activity determinants.","evidence":"COS-1 secretion and glycosylation analysis, heparin-Sepharose binding, NIH3T3 transformation and mitogenesis assays, and chimeric FGF3 constructs","pmids":["8223431"],"confidence":"High","gaps":["Receptor isoform preference not yet defined","Endogenous developmental sites of action not addressed"]},{"year":1994,"claim":"Resolving the dual subcellular fate of FGF3 explained how a single CUG-initiated protein can be both secreted and nuclear, revealing competing trafficking signals within one polypeptide.","evidence":"In vitro translation, deletion/replacement mutagenesis, heterologous fusion proteins, and subcellular fractionation in COS-1 cells","pmids":["8076608"],"confidence":"High","gaps":["Functional role of the nuclear pool not defined","Physiological regulation of CUG vs AUG initiation in vivo unknown"]},{"year":1996,"claim":"Defining FGFR2-IIIb as the preferred receptor and mapping C-terminal affinity determinants established the receptor specificity underlying FGF3 signaling.","evidence":"FGFR2-IIIb vs IIIc binding assays, Xenopus/zebrafish chimeric proteins, transformation and heparin displacement assays in COS-1/NIH3T3 cells","pmids":["8622866"],"confidence":"High","gaps":["Structural basis of IIIb selectivity not resolved","In vivo receptor usage across tissues not tested"]},{"year":2001,"claim":"Dissecting the Fgf3 promoter answered how its transcription is positively and negatively controlled, identifying PS4A as the central regulatory hub and a GATA-4/SOX7 activator versus SOX6/CtBP2 repressor logic.","evidence":"DNase-I footprinting, deletion reporter assays in F9 cells, yeast one/two-hybrid, mammalian Co-IP, RNAi, and EMSA across multiple studies","pmids":["11504872","15082719","11842118","8265348"],"confidence":"High","gaps":["How these factors are coordinated in specific developmental contexts unclear","Chromatin-level regulation not addressed"]},{"year":2002,"claim":"Genetic and pharmacological studies in zebrafish and mouse established FGF3, acting with FGF8 and FGF10, as the inductive signal for hindbrain segmentation and otic placode formation, defining its core morphogen role.","evidence":"Single and double morpholino knockdown, genetic double nulls, SU5402 time-window inhibition, cell transplantation, and ectopic expression with otic/rhombomere marker analysis","pmids":["12135921","12121619","11959820","11437442","12385757","12810586","14623822","10769226"],"confidence":"High","gaps":["Relative contribution of secreted vs cell-surface FGF3 in vivo unresolved","Quantitative dose thresholds for distinct outcomes undefined"]},{"year":2007,"claim":"Epistasis in the mouse otic vesicle placed FGF3 in a WNT-initiated cascade, showing it restrains Wnt3a to focus inductive signals and patterns dorsal otic identity between Hoxa1/Mafb and Gbx2.","evidence":"Fgf3 null mouse analysis with Wnt3a expression and multi-gene epistasis against Hoxa1, Mafb, and Gbx2 mutants","pmids":["17855431"],"confidence":"High","gaps":["Direct molecular link between FGF3 signaling and Wnt3a restriction unknown","Receptor mediating dorsal otic patterning not identified"]},{"year":2008,"claim":"Studies of pituitary and hindbrain development extended FGF3's role to lineage specification and target gene control, showing it specifies adenohypophyseal progenitors, sets pituitary lineage boundaries, and drives Pea3→Krox20 via MAPK/ERK.","evidence":"Zebrafish fgf3 mutant/morphant analysis with lineage markers, Shh epistasis, live POMC reporter imaging, chick morpholino knockdown and FGFR inhibition with Pea3/Krox20 analysis","pmids":["15229178","18514643","20553903","18823972"],"confidence":"Medium","gaps":["Direct transcriptional targets of FGF3-driven ERK in each context not fully enumerated","Single-lab findings for several contexts"]},{"year":2016,"claim":"Mouse genetics established a reciprocal FGF3–BMP antagonism along the posterior axis, defining FGF3 as a restraint on BMP signaling that coordinates neural tube closure and neural crest timing.","evidence":"Fgf3 null mouse with Noggin and BMP receptor epistasis, in vitro BMP4 treatment of PSM explants, and neural crest/tube marker and proliferation analysis","pmids":["27144312","18823972"],"confidence":"High","gaps":["Molecular mechanism by which FGF3 limits BMP signaling not defined","Receptor used in PSM-to-neuroepithelium signaling unknown"]},{"year":2023,"claim":"Newer work added postnatal and disease functions, showing vagal-derived FGF3 enhances insulin secretion, FGF3 acts as a dose-dependent axon guidance cue via FGFR1, and dysregulated FGF3 drives mammary tumorigenesis through direct FGF3–FGFR1 binding and STAT3/Akt signaling.","evidence":"Conditional vagal overexpression/ablation with glucose and GSIS assays, chick explant guidance assays with FGFR1 loss-of-function, and FGF3–FGFR1 Co-IP with shRNA knockdown and xenograft assays","pmids":["39413782","33684917","37834446","37496658"],"confidence":"Medium","gaps":["FGFR1 (vs FGFR2-IIIb) usage across contexts not reconciled","Mechanism of concentration-dependent attraction vs repulsion unresolved","Tumor findings from single model/lab"]},{"year":null,"claim":"The function of the nuclear FGF3 pool and how receptor choice (FGFR2-IIIb vs FGFR1) and cell-surface presentation are selected to produce distinct developmental and pathological outcomes remain unresolved.","evidence":"","pmids":[],"confidence":"Medium","gaps":["No assigned function for nuclear FGF3","No unified model linking receptor/co-receptor context to specific cellular outcomes","Structural basis of signaling not determined"]}],"mechanism_profile":{"molecular_activity":[{"term_id":"GO:0048018","term_label":"receptor ligand activity","supporting_discovery_ids":[1,2,26]},{"term_id":"GO:0060089","term_label":"molecular transducer activity","supporting_discovery_ids":[2,19,26]},{"term_id":"GO:0008092","term_label":"cytoskeletal protein binding","supporting_discovery_ids":[1,2]}],"localization":[{"term_id":"GO:0005576","term_label":"extracellular region","supporting_discovery_ids":[1,2]},{"term_id":"GO:0031012","term_label":"extracellular matrix","supporting_discovery_ids":[1,2]},{"term_id":"GO:0005634","term_label":"nucleus","supporting_discovery_ids":[0]},{"term_id":"GO:0005886","term_label":"plasma membrane","supporting_discovery_ids":[19]}],"pathway":[{"term_id":"R-HSA-162582","term_label":"Signal Transduction","supporting_discovery_ids":[15,26,27]},{"term_id":"R-HSA-1266738","term_label":"Developmental Biology","supporting_discovery_ids":[8,9,10,12]},{"term_id":"R-HSA-1643685","term_label":"Disease","supporting_discovery_ids":[26,28]}],"complexes":[],"partners":["FGFR2","FGFR1","FGF8","FGF10"],"other_free_text":[]}},"prefetch_data":{"uniprot":{"accession":"P11487","full_name":"Fibroblast growth factor 3","aliases":["Heparin-binding growth factor 3","HBGF-3","Proto-oncogene Int-2"],"length_aa":239,"mass_kda":26.9,"function":"Plays an important role in the regulation of embryonic development, cell proliferation, and cell differentiation. Required for normal ear development","subcellular_location":"Secreted","url":"https://www.uniprot.org/uniprotkb/P11487/entry"},"depmap":{"release":"DepMap","has_data":true,"is_common_essential":false,"resolved_as":"","url":"https://depmap.org/portal/gene/FGF3","classification":"Not Classified","n_dependent_lines":4,"n_total_lines":1208,"dependency_fraction":0.0033112582781456954},"opencell":{"profiled":false,"resolved_as":"","ensg_id":"","cell_line_id":"","localizations":[],"interactors":[],"url":"https://opencell.sf.czbiohub.org/search/FGF3","total_profiled":1310},"omim":[{"mim_id":"612202","title":"SRY-BOX 7; SOX7","url":"https://www.omim.org/entry/612202"},{"mim_id":"610706","title":"DEAFNESS, CONGENITAL, WITH INNER EAR AGENESIS, MICROTIA, AND MICRODONTIA","url":"https://www.omim.org/entry/610706"},{"mim_id":"610108","title":"ANOCTAMIN 1, CALCIUM-ACTIVATED CHLORIDE CHANNEL; ANO1","url":"https://www.omim.org/entry/610108"},{"mim_id":"608687","title":"SPINOCEREBELLAR ATAXIA 20; SCA20","url":"https://www.omim.org/entry/608687"},{"mim_id":"607224","title":"ORAL CANCER OVEREXPRESSED GENE 1; ORAOV1","url":"https://www.omim.org/entry/607224"}],"hpa":{"profiled":true,"resolved_as":"","reliability":"","locations":[],"tissue_specificity":"Tissue enriched","tissue_distribution":"Detected in single","driving_tissues":[{"tissue":"brain","ntpm":5.2}],"url":"https://www.proteinatlas.org/search/FGF3"},"hgnc":{"alias_symbol":["HBGF-3"],"prev_symbol":["INT2"]},"alphafold":{"accession":"P11487","domains":[{"cath_id":"2.80.10.50","chopping":"43-140_147-195","consensus_level":"high","plddt":94.6827,"start":43,"end":195}],"viewer_url":"https://alphafold.ebi.ac.uk/entry/P11487","model_url":"https://alphafold.ebi.ac.uk/files/AF-P11487-F1-model_v6.cif","pae_url":"https://alphafold.ebi.ac.uk/files/AF-P11487-F1-predicted_aligned_error_v6.png","plddt_mean":78.31},"mouse_models":{"mgi_url":"https://www.informatics.jax.org/marker/summary?nomen=FGF3","jax_strain_url":"https://www.jax.org/strain/search?query=FGF3"},"sequence":{"accession":"P11487","fasta_url":"https://rest.uniprot.org/uniprotkb/P11487.fasta","uniprot_url":"https://www.uniprot.org/uniprotkb/P11487/entry","alphafold_viewer_url":"https://alphafold.ebi.ac.uk/entry/P11487"}},"corpus_meta":[{"pmid":"12810586","id":"PMC_12810586","title":"Fgf3 and Fgf10 are required for mouse otic placode induction.","date":"2003","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/12810586","citation_count":239,"is_preprint":false},{"pmid":"11437442","id":"PMC_11437442","title":"Zebrafish fgf3 and fgf8 encode redundant functions required for otic placode induction.","date":"2001","source":"Developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/11437442","citation_count":211,"is_preprint":false},{"pmid":"11066089","id":"PMC_11066089","title":"Associations of FGF-3 and FGF-10 with signaling networks regulating tooth morphogenesis.","date":"2000","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/11066089","citation_count":209,"is_preprint":false},{"pmid":"11959820","id":"PMC_11959820","title":"Fgf3 and Fgf8 are required together for formation of the otic placode and vesicle.","date":"2002","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/11959820","citation_count":202,"is_preprint":false},{"pmid":"12385757","id":"PMC_12385757","title":"Fgf8 and Fgf3 are required for zebrafish ear placode induction, maintenance and inner ear patterning.","date":"2002","source":"Mechanisms of development","url":"https://pubmed.ncbi.nlm.nih.gov/12385757","citation_count":187,"is_preprint":false},{"pmid":"12135921","id":"PMC_12135921","title":"FGF3 and FGF8 mediate a rhombomere 4 signaling activity in the zebrafish hindbrain.","date":"2002","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/12135921","citation_count":186,"is_preprint":false},{"pmid":"14623822","id":"PMC_14623822","title":"Requirements for FGF3 and FGF10 during inner ear formation.","date":"2003","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/14623822","citation_count":172,"is_preprint":false},{"pmid":"7789270","id":"PMC_7789270","title":"Multiple roles for FGF-3 during cranial neural development in the chicken.","date":"1995","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/7789270","citation_count":161,"is_preprint":false},{"pmid":"17906623","id":"PMC_17906623","title":"Duplication of FGF3, FGF4, FGF19 and ORAOV1 causes hair ridge and predisposition to dermoid sinus in Ridgeback dogs.","date":"2007","source":"Nature genetics","url":"https://pubmed.ncbi.nlm.nih.gov/17906623","citation_count":156,"is_preprint":false},{"pmid":"12121619","id":"PMC_12121619","title":"Establishment of hindbrain segmental identity requires signaling by FGF3 and FGF8.","date":"2002","source":"Current biology : CB","url":"https://pubmed.ncbi.nlm.nih.gov/12121619","citation_count":129,"is_preprint":false},{"pmid":"1425349","id":"PMC_1425349","title":"Developmental expression of the Xenopus int-2 (FGF-3) gene: activation by mesodermal and neural induction.","date":"1992","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/1425349","citation_count":128,"is_preprint":false},{"pmid":"22890726","id":"PMC_22890726","title":"FGF3/FGF4 amplification and multiple lung metastases in responders to sorafenib in hepatocellular carcinoma.","date":"2013","source":"Hepatology (Baltimore, Md.)","url":"https://pubmed.ncbi.nlm.nih.gov/22890726","citation_count":127,"is_preprint":false},{"pmid":"12668634","id":"PMC_12668634","title":"Fgf3 and Fgf8 dependent and independent transcription factors are required for otic placode specification.","date":"2003","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/12668634","citation_count":122,"is_preprint":false},{"pmid":"8631508","id":"PMC_8631508","title":"The role of FGF-3 in early inner ear development: an analysis in normal and kreisler mutant mice.","date":"1996","source":"Developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/8631508","citation_count":114,"is_preprint":false},{"pmid":"8076608","id":"PMC_8076608","title":"Competition between nuclear localization and secretory signals determines the subcellular fate of a single CUG-initiated form of FGF3.","date":"1994","source":"The EMBO journal","url":"https://pubmed.ncbi.nlm.nih.gov/8076608","citation_count":110,"is_preprint":false},{"pmid":"10769226","id":"PMC_10769226","title":"Induction of inner ear fate by FGF3.","date":"2000","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/10769226","citation_count":109,"is_preprint":false},{"pmid":"12900450","id":"PMC_12900450","title":"Unique and combinatorial functions of Fgf3 and Fgf8 during zebrafish forebrain development.","date":"2003","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/12900450","citation_count":106,"is_preprint":false},{"pmid":"15229178","id":"PMC_15229178","title":"Fgf3 signaling from the ventral diencephalon is required for early specification and subsequent survival of the zebrafish adenohypophysis.","date":"2004","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/15229178","citation_count":106,"is_preprint":false},{"pmid":"17601531","id":"PMC_17601531","title":"Differential requirements for FGF3, FGF8 and FGF10 during inner ear development.","date":"2007","source":"Developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/17601531","citation_count":82,"is_preprint":false},{"pmid":"17855431","id":"PMC_17855431","title":"Fgf3 is required for dorsal patterning and morphogenesis of the inner ear epithelium.","date":"2007","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/17855431","citation_count":77,"is_preprint":false},{"pmid":"9879707","id":"PMC_9879707","title":"Expression and functions of FGF-3 in Xenopus development.","date":"1998","source":"The International journal of developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/9879707","citation_count":76,"is_preprint":false},{"pmid":"8800419","id":"PMC_8800419","title":"Expression of Fgf-3 in relation to hindbrain segmentation, otic pit position and pharyngeal arch morphology in normal and retinoic acid-exposed mouse embryos.","date":"1996","source":"Anatomy and embryology","url":"https://pubmed.ncbi.nlm.nih.gov/8800419","citation_count":74,"is_preprint":false},{"pmid":"8831628","id":"PMC_8831628","title":"Gene defect in hypodontia: exclusion of EGF, EGFR, and FGF-3 as candidate genes.","date":"1996","source":"Journal of dental research","url":"https://pubmed.ncbi.nlm.nih.gov/8831628","citation_count":65,"is_preprint":false},{"pmid":"11504872","id":"PMC_11504872","title":"SOX6 binds CtBP2 to repress transcription from the Fgf-3 promoter.","date":"2001","source":"Nucleic acids research","url":"https://pubmed.ncbi.nlm.nih.gov/11504872","citation_count":64,"is_preprint":false},{"pmid":"16077091","id":"PMC_16077091","title":"Endoderm-derived Fgf3 is necessary and sufficient for inducing neurogenesis in the epibranchial placodes in zebrafish.","date":"2005","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/16077091","citation_count":58,"is_preprint":false},{"pmid":"12399318","id":"PMC_12399318","title":"An expanded domain of fgf3 expression in the hindbrain of zebrafish valentino mutants results in mis-patterning of the otic vesicle.","date":"2002","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/12399318","citation_count":53,"is_preprint":false},{"pmid":"19036800","id":"PMC_19036800","title":"FGF3 in the floor plate directs notochord convergent extension in the Ciona tadpole.","date":"2008","source":"Development (Cambridge, England)","url":"https://pubmed.ncbi.nlm.nih.gov/19036800","citation_count":53,"is_preprint":false},{"pmid":"15082719","id":"PMC_15082719","title":"SOX7 and GATA-4 are competitive activators of Fgf-3 transcription.","date":"2004","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/15082719","citation_count":50,"is_preprint":false},{"pmid":"9626498","id":"PMC_9626498","title":"Crouzon-like craniofacial dysmorphology in the mouse is caused by an insertional mutation at the Fgf3/Fgf4 locus.","date":"1998","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/9626498","citation_count":49,"is_preprint":false},{"pmid":"7999362","id":"PMC_7999362","title":"Targeted disruption of int-2 (fgf-3) causes developmental defects in the tail and inner ear.","date":"1994","source":"Molecular reproduction and development","url":"https://pubmed.ncbi.nlm.nih.gov/7999362","citation_count":47,"is_preprint":false},{"pmid":"17656375","id":"PMC_17656375","title":"SNP genome scanning localizes oto-dental syndrome to chromosome 11q13 and microdeletions at this locus implicate FGF3 in dental and inner-ear disease and FADD in ocular coloboma.","date":"2007","source":"Human molecular genetics","url":"https://pubmed.ncbi.nlm.nih.gov/17656375","citation_count":46,"is_preprint":false},{"pmid":"20018768","id":"PMC_20018768","title":"Modulation of Fgf3 dosage in mouse and men mirrors evolution of mammalian dentition.","date":"2009","source":"Proceedings of the National Academy of Sciences of the United States of America","url":"https://pubmed.ncbi.nlm.nih.gov/20018768","citation_count":46,"is_preprint":false},{"pmid":"7685625","id":"PMC_7685625","title":"Amplified region of chromosome band 11q13 in breast and squamous cell carcinomas encompasses three CpG islands telomeric of FGF3, including the expressed gene EMS1.","date":"1993","source":"Genes, chromosomes & cancer","url":"https://pubmed.ncbi.nlm.nih.gov/7685625","citation_count":44,"is_preprint":false},{"pmid":"8654946","id":"PMC_8654946","title":"The zebrafish Fgf-3 gene: cDNA sequence, transcript structure and genomic organization.","date":"1996","source":"Gene","url":"https://pubmed.ncbi.nlm.nih.gov/8654946","citation_count":43,"is_preprint":false},{"pmid":"21664901","id":"PMC_21664901","title":"Redundant and dosage sensitive requirements for Fgf3 and Fgf10 in cardiovascular development.","date":"2011","source":"Developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/21664901","citation_count":41,"is_preprint":false},{"pmid":"18435799","id":"PMC_18435799","title":"Homozygous FGF3 mutations result in congenital deafness with inner ear agenesis, microtia, and microdontia.","date":"2008","source":"Clinical genetics","url":"https://pubmed.ncbi.nlm.nih.gov/18435799","citation_count":41,"is_preprint":false},{"pmid":"27144312","id":"PMC_27144312","title":"An FGF3-BMP Signaling Axis Regulates Caudal Neural Tube Closure, Neural Crest Specification and Anterior-Posterior Axis Extension.","date":"2016","source":"PLoS genetics","url":"https://pubmed.ncbi.nlm.nih.gov/27144312","citation_count":40,"is_preprint":false},{"pmid":"8223431","id":"PMC_8223431","title":"FGF3 from Xenopus laevis.","date":"1993","source":"The EMBO journal","url":"https://pubmed.ncbi.nlm.nih.gov/8223431","citation_count":32,"is_preprint":false},{"pmid":"11331772","id":"PMC_11331772","title":"Phenotypic consequences of lung-specific inducible expression of FGF-3.","date":"2001","source":"Proceedings of the National Academy of Sciences of the United States of America","url":"https://pubmed.ncbi.nlm.nih.gov/11331772","citation_count":32,"is_preprint":false},{"pmid":"8494710","id":"PMC_8494710","title":"First experience with FGF-3 (INT-2) amplification in women with epithelial ovarian cancer.","date":"1993","source":"British journal of cancer","url":"https://pubmed.ncbi.nlm.nih.gov/8494710","citation_count":31,"is_preprint":false},{"pmid":"18823972","id":"PMC_18823972","title":"Inhibition of BMPs by follistatin is required for FGF3 expression and segmental patterning of the hindbrain.","date":"2008","source":"Developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/18823972","citation_count":30,"is_preprint":false},{"pmid":"19232109","id":"PMC_19232109","title":"Boundary cells regulate a switch in the expression of FGF3 in hindbrain rhombomeres.","date":"2009","source":"BMC developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/19232109","citation_count":29,"is_preprint":false},{"pmid":"9798677","id":"PMC_9798677","title":"FGF-3 and FGF-4 elicit distinct oncogenic properties in mouse mammary myoepithelial cells.","date":"1998","source":"Oncogene","url":"https://pubmed.ncbi.nlm.nih.gov/9798677","citation_count":28,"is_preprint":false},{"pmid":"18701883","id":"PMC_18701883","title":"Syndromic congenital sensorineural deafness, microtia and microdontia resulting from a novel homoallelic mutation in fibroblast growth factor 3 (FGF3).","date":"2008","source":"European journal of human genetics : EJHG","url":"https://pubmed.ncbi.nlm.nih.gov/18701883","citation_count":28,"is_preprint":false},{"pmid":"29073177","id":"PMC_29073177","title":"Hypomethylated Fgf3 is a potential biomarker for early detection of oral cancer in mice treated with the tobacco carcinogen dibenzo[def,p]chrysene.","date":"2017","source":"PloS one","url":"https://pubmed.ncbi.nlm.nih.gov/29073177","citation_count":26,"is_preprint":false},{"pmid":"20553903","id":"PMC_20553903","title":"Analysis of expression and function of FGF-MAPK signaling components in the hindbrain reveals a central role for FGF3 in the regulation of Krox20, mediated by Pea3.","date":"2010","source":"Developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/20553903","citation_count":25,"is_preprint":false},{"pmid":"8622866","id":"PMC_8622866","title":"Secretion and mitogenic activity of zebrafish FGF3 reveal intermediate properties relative to mouse and Xenopus homologues.","date":"1996","source":"Oncogene","url":"https://pubmed.ncbi.nlm.nih.gov/8622866","citation_count":24,"is_preprint":false},{"pmid":"24661680","id":"PMC_24661680","title":"BMP4 and FGF3 haplotypes increase the risk of tendinopathy in volleyball athletes.","date":"2014","source":"Journal of science and medicine in sport","url":"https://pubmed.ncbi.nlm.nih.gov/24661680","citation_count":22,"is_preprint":false},{"pmid":"12169667","id":"PMC_12169667","title":"Inducible expression of FGF-3 in mouse mammary gland.","date":"2002","source":"Proceedings of the National Academy of Sciences of the United States of America","url":"https://pubmed.ncbi.nlm.nih.gov/12169667","citation_count":22,"is_preprint":false},{"pmid":"15108308","id":"PMC_15108308","title":"Regulatory analysis of the mouse Fgf3 gene: control of embryonic expression patterns and dependence upon sonic hedgehog (Shh) signalling.","date":"2004","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/15108308","citation_count":22,"is_preprint":false},{"pmid":"19950373","id":"PMC_19950373","title":"A FGF3 mutation associated with differential inner ear malformation, microtia, and microdontia.","date":"2010","source":"The Laryngoscope","url":"https://pubmed.ncbi.nlm.nih.gov/19950373","citation_count":21,"is_preprint":false},{"pmid":"25934698","id":"PMC_25934698","title":"Control of Wnt5b secretion by Wntless modulates chondrogenic cell proliferation through fine-tuning fgf3 expression.","date":"2015","source":"Journal of cell science","url":"https://pubmed.ncbi.nlm.nih.gov/25934698","citation_count":21,"is_preprint":false},{"pmid":"15942670","id":"PMC_15942670","title":"Comparative genomics on mammalian Fgf3-Fgf4 locus.","date":"2005","source":"International journal of oncology","url":"https://pubmed.ncbi.nlm.nih.gov/15942670","citation_count":21,"is_preprint":false},{"pmid":"10853025","id":"PMC_10853025","title":"Detection of c-erbB-2 and FGF-3 (INT-2) gene amplification in epithelial ovarian cancer.","date":"2000","source":"International journal of oncology","url":"https://pubmed.ncbi.nlm.nih.gov/10853025","citation_count":21,"is_preprint":false},{"pmid":"8386870","id":"PMC_8386870","title":"Activation of both Wnt-1 and Fgf-3 by insertion of mouse mammary tumor virus downstream in the reverse orientation: a reappraisal of the enhancer insertion model.","date":"1993","source":"Virology","url":"https://pubmed.ncbi.nlm.nih.gov/8386870","citation_count":21,"is_preprint":false},{"pmid":"7892157","id":"PMC_7892157","title":"Int-2/FGF3 amplification is a better independent predictor of relapse than c-myc and c-erbB-2/neu amplifications in primary human breast cancer.","date":"1994","source":"Modern pathology : an official journal of the United States and Canadian Academy of Pathology, Inc","url":"https://pubmed.ncbi.nlm.nih.gov/7892157","citation_count":21,"is_preprint":false},{"pmid":"23213398","id":"PMC_23213398","title":"Expression of hindbrain boundary markers is regulated by FGF3.","date":"2011","source":"Biology open","url":"https://pubmed.ncbi.nlm.nih.gov/23213398","citation_count":20,"is_preprint":false},{"pmid":"7784081","id":"PMC_7784081","title":"The proto-oncogene FGF-3 is constitutively expressed in tumorigenic, but not in non-tumorigenic, clones of a human colon carcinoma cell line.","date":"1995","source":"Oncogene","url":"https://pubmed.ncbi.nlm.nih.gov/7784081","citation_count":20,"is_preprint":false},{"pmid":"21306635","id":"PMC_21306635","title":"Variable expressivity of FGF3 mutations associated with deafness and LAMM syndrome.","date":"2011","source":"BMC medical genetics","url":"https://pubmed.ncbi.nlm.nih.gov/21306635","citation_count":19,"is_preprint":false},{"pmid":"8265348","id":"PMC_8265348","title":"Identification of positive and negative regulatory elements involved in the retinoic acid/cAMP induction of Fgf-3 transcription in F9 cells.","date":"1993","source":"Nucleic acids research","url":"https://pubmed.ncbi.nlm.nih.gov/8265348","citation_count":19,"is_preprint":false},{"pmid":"26995070","id":"PMC_26995070","title":"Fgf3 and Fgf16 expression patterns define spatial and temporal domains in the developing chick inner ear.","date":"2016","source":"Brain structure & function","url":"https://pubmed.ncbi.nlm.nih.gov/26995070","citation_count":18,"is_preprint":false},{"pmid":"23549991","id":"PMC_23549991","title":"Candidate gene studies in hypodontia suggest role for FGF3.","date":"2013","source":"European archives of paediatric dentistry : official journal of the European Academy of Paediatric Dentistry","url":"https://pubmed.ncbi.nlm.nih.gov/23549991","citation_count":18,"is_preprint":false},{"pmid":"24358375","id":"PMC_24358375","title":"Fgf3 and Fgf10a work in concert to promote maturation of the epibranchial placodes in zebrafish.","date":"2013","source":"PloS one","url":"https://pubmed.ncbi.nlm.nih.gov/24358375","citation_count":17,"is_preprint":false},{"pmid":"11896623","id":"PMC_11896623","title":"Ectopic expression of FGF-3 results in abnormal prostate and Wolffian duct development.","date":"2002","source":"Oncogene","url":"https://pubmed.ncbi.nlm.nih.gov/11896623","citation_count":17,"is_preprint":false},{"pmid":"23789101","id":"PMC_23789101","title":"Fgf22 regulated by Fgf3/Fgf8 signaling is required for zebrafish midbrain development.","date":"2013","source":"Biology open","url":"https://pubmed.ncbi.nlm.nih.gov/23789101","citation_count":16,"is_preprint":false},{"pmid":"9570039","id":"PMC_9570039","title":"Role of FGF3 in otic capsule chondrogenesis in vitro: an antisense oligonucleotide approach.","date":"1998","source":"Growth factors (Chur, Switzerland)","url":"https://pubmed.ncbi.nlm.nih.gov/9570039","citation_count":16,"is_preprint":false},{"pmid":"24120895","id":"PMC_24120895","title":"Increased FGF3 and FGF4 gene dosage is a risk factor for craniosynostosis.","date":"2013","source":"Gene","url":"https://pubmed.ncbi.nlm.nih.gov/24120895","citation_count":15,"is_preprint":false},{"pmid":"35814257","id":"PMC_35814257","title":"LY2874455 and Abemaciclib Reverse FGF3/4/19/CCND1 Amplification Mediated Gefitinib Resistance in NSCLC.","date":"2022","source":"Frontiers in pharmacology","url":"https://pubmed.ncbi.nlm.nih.gov/35814257","citation_count":14,"is_preprint":false},{"pmid":"18942154","id":"PMC_18942154","title":"Differential requirements for Fgf3 and Fgf8 during mouse forebrain development.","date":"2008","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/18942154","citation_count":14,"is_preprint":false},{"pmid":"11167010","id":"PMC_11167010","title":"The zebrafish fth1, slc3a2, men1, pc, fgf3 and cycd1 genes define two regions of conserved synteny between linkage group 7 and human chromosome 11q13.","date":"2000","source":"Gene","url":"https://pubmed.ncbi.nlm.nih.gov/11167010","citation_count":14,"is_preprint":false},{"pmid":"8962718","id":"PMC_8962718","title":"Aberrant FGF-2, FGF-3, FGF-4 and C-erb-B2 gene copy number in human ovarian, breast and endometrial tumours.","date":"1996","source":"Growth factors (Chur, Switzerland)","url":"https://pubmed.ncbi.nlm.nih.gov/8962718","citation_count":14,"is_preprint":false},{"pmid":"26323695","id":"PMC_26323695","title":"Screening a novel FGF3 antagonist peptide with anti-tumor effects on breast cancer from a phage display library.","date":"2015","source":"Molecular medicine reports","url":"https://pubmed.ncbi.nlm.nih.gov/26323695","citation_count":13,"is_preprint":false},{"pmid":"18514643","id":"PMC_18514643","title":"In vivo time-lapse imaging delineates the zebrafish pituitary proopiomelanocortin lineage boundary regulated by FGF3 signal.","date":"2008","source":"Developmental biology","url":"https://pubmed.ncbi.nlm.nih.gov/18514643","citation_count":13,"is_preprint":false},{"pmid":"18412219","id":"PMC_18412219","title":"Retinoic acid-induced inner ear teratogenesis caused by defective Fgf3/Fgf10-dependent Dlx5 signaling.","date":"2008","source":"Birth defects research. Part B, Developmental and reproductive toxicology","url":"https://pubmed.ncbi.nlm.nih.gov/18412219","citation_count":12,"is_preprint":false},{"pmid":"10845805","id":"PMC_10845805","title":"Progression in MCF-7 breast cancer cell tumorigenicity: compared effect of FGF-3 and FGF-4.","date":"2000","source":"Breast cancer research and treatment","url":"https://pubmed.ncbi.nlm.nih.gov/10845805","citation_count":11,"is_preprint":false},{"pmid":"9645456","id":"PMC_9645456","title":"Evaluation of the tumorigenic and angiogenic potential of human fibroblast growth factor FGF3 in nude mice.","date":"1998","source":"Journal of cancer research and clinical oncology","url":"https://pubmed.ncbi.nlm.nih.gov/9645456","citation_count":11,"is_preprint":false},{"pmid":"22297612","id":"PMC_22297612","title":"The original family revisited after 37 years: odontoma-dysphagia syndrome is most likely caused by a microduplication of chromosome 11q13.3, including the FGF3 and FGF4 genes.","date":"2013","source":"Clinical oral investigations","url":"https://pubmed.ncbi.nlm.nih.gov/22297612","citation_count":10,"is_preprint":false},{"pmid":"22334445","id":"PMC_22334445","title":"A novel method for retinoic acid administration reveals differential and dose-dependent downregulation of Fgf3 in the developing inner ear and anterior CNS.","date":"2012","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/22334445","citation_count":10,"is_preprint":false},{"pmid":"36934406","id":"PMC_36934406","title":"Identification of a homozygous frameshift mutation in the FGF3 gene in a consanguineous Iranian family: First report of labyrinthine aplasia, microtia, and microdontia syndrome in Iran and literature review.","date":"2023","source":"Molecular genetics & genomic medicine","url":"https://pubmed.ncbi.nlm.nih.gov/36934406","citation_count":9,"is_preprint":false},{"pmid":"11842118","id":"PMC_11842118","title":"GATA-4 interacts distinctively with negative and positive regulatory elements in the Fgf-3 promoter.","date":"2002","source":"Nucleic acids research","url":"https://pubmed.ncbi.nlm.nih.gov/11842118","citation_count":9,"is_preprint":false},{"pmid":"26666435","id":"PMC_26666435","title":"Fgf3-Fgf4-cis: A new mouse line for studying Fgf functions during mouse development.","date":"2016","source":"Genesis (New York, N.Y. : 2000)","url":"https://pubmed.ncbi.nlm.nih.gov/26666435","citation_count":8,"is_preprint":false},{"pmid":"33684917","id":"PMC_33684917","title":"FGF3 from the Hypothalamus Regulates the Guidance of Thalamocortical Axons.","date":"2021","source":"Developmental neuroscience","url":"https://pubmed.ncbi.nlm.nih.gov/33684917","citation_count":8,"is_preprint":false},{"pmid":"24697712","id":"PMC_24697712","title":"Studies of genes involved in craniofacial development and tumorigenesis: FGF3 contributes to isolated oral clefts and may interact with PAX9.","date":"2014","source":"Acta odontologica Scandinavica","url":"https://pubmed.ncbi.nlm.nih.gov/24697712","citation_count":8,"is_preprint":false},{"pmid":"28012573","id":"PMC_28012573","title":"FGF2, FGF3 and FGF4 expression pattern during molars odontogenesis in Didelphis albiventris.","date":"2016","source":"Acta histochemica","url":"https://pubmed.ncbi.nlm.nih.gov/28012573","citation_count":6,"is_preprint":false},{"pmid":"37834446","id":"PMC_37834446","title":"FGF3 Directs the Pathfinding of Prethalamic GABAergic Axons.","date":"2023","source":"International journal of molecular sciences","url":"https://pubmed.ncbi.nlm.nih.gov/37834446","citation_count":6,"is_preprint":false},{"pmid":"31036752","id":"PMC_31036752","title":"Fgf3 is crucial for the generation of monoaminergic cerebrospinal fluid contacting cells in zebrafish.","date":"2019","source":"Biology open","url":"https://pubmed.ncbi.nlm.nih.gov/31036752","citation_count":6,"is_preprint":false},{"pmid":"39413782","id":"PMC_39413782","title":"Vagal sensory neuron-derived FGF3 controls insulin secretion.","date":"2024","source":"Developmental cell","url":"https://pubmed.ncbi.nlm.nih.gov/39413782","citation_count":5,"is_preprint":false},{"pmid":"9375020","id":"PMC_9375020","title":"Identification of a MMTV insertion mutation within the coding region of the Fgf-3 protooncogene.","date":"1997","source":"Virology","url":"https://pubmed.ncbi.nlm.nih.gov/9375020","citation_count":5,"is_preprint":false},{"pmid":"34719815","id":"PMC_34719815","title":"Inactivation of Fgf3 and Fgf4 within the Fgf3/Fgf4/Fgf15 gene cluster reveals their redundant requirement for mouse inner ear induction and embryonic survival.","date":"2021","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/34719815","citation_count":4,"is_preprint":false},{"pmid":"37496658","id":"PMC_37496658","title":"Fibroblast growth factor 3 promotes spontaneous mammary tumorigenesis in Tientsin albino 2 mice via the FGF3/FGFR1/STAT3 pathway.","date":"2023","source":"Frontiers in oncology","url":"https://pubmed.ncbi.nlm.nih.gov/37496658","citation_count":4,"is_preprint":false},{"pmid":"22930543","id":"PMC_22930543","title":"Ectopic expression of Fgf3 leads to aberrant lineage segregation in the mouse parthenote preimplantation embryos.","date":"2012","source":"Developmental dynamics : an official publication of the American Association of Anatomists","url":"https://pubmed.ncbi.nlm.nih.gov/22930543","citation_count":4,"is_preprint":false},{"pmid":"31574782","id":"PMC_31574782","title":"Polymorphisms in FGF3, FGF10, and FGF13 May Contribute to the Presence of Temporomandibular Disorders in Patients Who Required Orthognathic Surgery.","date":"2019","source":"The Journal of craniofacial surgery","url":"https://pubmed.ncbi.nlm.nih.gov/31574782","citation_count":4,"is_preprint":false},{"pmid":"25202691","id":"PMC_25202691","title":"Predicting responsiveness to sorafenib: can the determination of FGF3/FGF4 amplifications enrich for clinical benefit?","date":"2014","source":"Hepatobiliary surgery and nutrition","url":"https://pubmed.ncbi.nlm.nih.gov/25202691","citation_count":4,"is_preprint":false},{"pmid":"37741710","id":"PMC_37741710","title":"Primer on FGF3.","date":"2023","source":"Differentiation; research in biological diversity","url":"https://pubmed.ncbi.nlm.nih.gov/37741710","citation_count":3,"is_preprint":false},{"pmid":"12084721","id":"PMC_12084721","title":"FGF3 attached to a phosholipid membrane anchor gains a high transforming capacity. Implications of microdomains for FGF3 cell transformation.","date":"2002","source":"The Journal of biological chemistry","url":"https://pubmed.ncbi.nlm.nih.gov/12084721","citation_count":3,"is_preprint":false},{"pmid":"21567063","id":"PMC_21567063","title":"The effect of fgf-3 int-2 on growth and transformation of mcf-10a normal human mammary epithelial-cells is distinct from fgf-1 and fgf-2.","date":"1994","source":"International journal of oncology","url":"https://pubmed.ncbi.nlm.nih.gov/21567063","citation_count":3,"is_preprint":false},{"pmid":"39483301","id":"PMC_39483301","title":"Neuroanatomical anomalies due to a defect in the FGF3 gene, associated with the Labyrinthine Aplasia, Microtia and Microdontia syndrome: insights from the placement of auditory brainstem implants in two siblings.","date":"2024","source":"Therapeutic advances in rare disease","url":"https://pubmed.ncbi.nlm.nih.gov/39483301","citation_count":2,"is_preprint":false},{"pmid":"10727086","id":"PMC_10727086","title":"Sequence analysis of the transcription control region upstream of the human FGF-3 gene.","date":"1999","source":"DNA sequence : the journal of DNA sequencing and mapping","url":"https://pubmed.ncbi.nlm.nih.gov/10727086","citation_count":2,"is_preprint":false},{"pmid":"21559693","id":"PMC_21559693","title":"Cooperation between mutant p53 and the ras, raf, erbb-2 and fgf-3 oncogenes for transformation of mammary epithelial-cells.","date":"1994","source":"International journal of oncology","url":"https://pubmed.ncbi.nlm.nih.gov/21559693","citation_count":1,"is_preprint":false},{"pmid":"39976283","id":"PMC_39976283","title":"Single-Gene Deletion of FGF3 in a Patient With Features of 11q13 Microdeletion Syndrome.","date":"2025","source":"American journal of medical genetics. Part A","url":"https://pubmed.ncbi.nlm.nih.gov/39976283","citation_count":0,"is_preprint":false}],"cost":{"stage1":{"model":"claude-sonnet-4-6","input_tokens":49815,"output_tokens":8740,"usd":0.140272,"stage1_stop_reason":"end_turn"},"stage2":{"model":"claude-opus-4-8","input_tokens":18208,"output_tokens":4094,"usd":0.096695,"stage2_stop_reason":"end_turn"},"total_usd":0.236967,"stage1_batch_id":"msgbatch_01AsR7g8dGTEiEw9U83bJeWn","stage2_batch_id":"msgbatch_01YV5ZyxtFNUZEjxRcpd9jzb","note":"batch pricing = 50% of standard"},"stage1_raw":"```json\n{\n  \"discoveries\": [\n    {\n      \"year\": 1994,\n      \"finding\": \"Mouse FGF3 is translated almost exclusively from an upstream CUG codon (rather than the AUG codon), producing a single protein that is distributed in both the nucleus and the secretory pathway. Secretion is mediated by cleavage adjacent to a signal peptide, whereas nuclear localization is determined by a classical bipartite nuclear localization motif together with upstream N-terminal sequences. These competing signals within the same protein determine its dual subcellular fate.\",\n      \"method\": \"Deletion and replacement mutants in reticulocyte lysates and transfected COS-1 cells; fusion to heterologous protein; subcellular fractionation\",\n      \"journal\": \"The EMBO journal\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Strong — in vitro translation, mutagenesis of multiple deletion/replacement constructs, and heterologous fusion proteins with multiple orthogonal readouts in one rigorous study\",\n      \"pmids\": [\"8076608\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1993,\n      \"finding\": \"Xenopus FGF3 (XFGF3) is secreted and glycosylated (31 kDa, signal-peptide cleaved), associates with cell surface and extracellular matrix via heparin-binding, and can be displaced by soluble heparin. It induces morphological transformation of NIH3T3 cells and stimulates DNA synthesis in cells expressing FGFR1 and FGFR2 isoforms. Chimeric proteins between XFGF3 and mouse FGF3 showed that the C-terminal region determines differences in receptor affinity, mitogenic potency, and transforming activity.\",\n      \"method\": \"COS-1 cell transfection, conditioned medium assays, heparin-Sepharose binding, NIH3T3 transformation assay, C57MG/BALB/MK mitogenesis assay, chimeric construct analysis\",\n      \"journal\": \"The EMBO journal\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Strong — reconstitution of secretion, heparin binding, and mitogenic activity with mutagenesis via chimeric constructs, multiple orthogonal methods in one study\",\n      \"pmids\": [\"8223431\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1996,\n      \"finding\": \"Zebrafish FGF3 (ZFGF3) is secreted as a heterogeneous set of glycoproteins (29–30.5 kDa), associates strongly with extracellular matrix, and binds the IIIb isoform of FGFR2 with higher affinity than the IIIc isoform (similar to mouse FGF3). Hybrid proteins between Xenopus and zebrafish FGF3 implicate the C-terminal region in determining receptor affinity differences, mitogenic potency, and transforming activity.\",\n      \"method\": \"COS-1 cell transfection, receptor binding assays with FGFR2-IIIb vs IIIc, NIH3T3 transformation assay, chimeric construct analysis, heparin displacement\",\n      \"journal\": \"Oncogene\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Strong — receptor binding with two isoforms, chimeric mutagenesis mapping C-terminal determinants, multiple orthogonal assays in one study\",\n      \"pmids\": [\"8622866\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2001,\n      \"finding\": \"SOX6 binds the key regulatory element PS4A in the Fgf-3 promoter and strongly represses Fgf-3 transcription. SOX6 recruits the co-repressor CtBP2 via a short PLNLSS motif, and SOX6 binding to CtBP2 is required for co-operative repression of the Fgf-3 promoter through PS4A.\",\n      \"method\": \"Yeast one-hybrid screen, reporter gene assays, yeast two-hybrid, co-immunoprecipitation in mammalian cells, mutational analysis of SOX6, in situ hybridization, co-expression in NIH3T3 cells\",\n      \"journal\": \"Nucleic acids research\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — reciprocal yeast and mammalian Co-IP, mutagenesis of binding motif, reporter assays, multiple orthogonal methods\",\n      \"pmids\": [\"11504872\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2004,\n      \"finding\": \"SOX7 activates Fgf-3 transcription by binding the PS4A element of the Fgf-3 promoter, competing with GATA-4 for PS4A occupancy. In GATA-4-deficient ES cells, Fgf-3 expression upon differentiation depends on SOX7, as shown by RNAi knockdown of Sox7. SOX2, by contrast, is a poor activator and negatively modulates GATA-4-driven Fgf-3 activation when co-expressed.\",\n      \"method\": \"Reporter gene assays, RNAi knockdown, co-expression studies in F9 and ES cells, nuclear extract complexes on PS4A, in situ hybridization\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — RNAi loss-of-function, reporter assays, nuclear complex detection, multiple orthogonal methods in one study\",\n      \"pmids\": [\"15082719\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2002,\n      \"finding\": \"GATA-4 binds two sites in the Fgf-3 promoter: PS4A (positive regulatory element) and PS13 (negative regulatory element near P3). Efficient binding to PS4A requires both zinc fingers and the basic domain of GATA-4 engaging a second flanking sequence, and this dual-zinc-finger binding is essential for Fgf-3 promoter activation. PS13 negative activity depends on its proximity to the transcription initiation site.\",\n      \"method\": \"Mutational analysis of GATA-4 truncation deletions, reporter gene assays, DNase-I footprinting, EMSA/DNA bending assays, promoter deletion constructs\",\n      \"journal\": \"Nucleic acids research\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Moderate — in vitro footprinting plus mutagenesis of binding domain plus functional reporter assays, multiple orthogonal methods\",\n      \"pmids\": [\"11842118\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1993,\n      \"finding\": \"The Fgf-3 promoter contains at least two positive and three negative regulatory elements. The PS4A element is essential for promoter activity in both undifferentiated and differentiated F9 cells, and deletions encompassing PS4A abolish retinoic acid inducibility and basal promoter activity.\",\n      \"method\": \"Stable and transient transfection of CAT reporter constructs, progressive and targeted deletion mutants, DNase-I footprinting in F9 embryonal carcinoma cells\",\n      \"journal\": \"Nucleic acids research\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 1 / Moderate — in vitro footprinting plus systematic deletion mutagenesis with functional reporter readout, multiple orthogonal methods\",\n      \"pmids\": [\"8265348\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2004,\n      \"finding\": \"A 5.7-kb enhancer upstream of mouse Fgf3 mediates embryonic expression in the midbrain, hindbrain, surface ectoderm, dorsal root ganglia, and CNS. Sonic hedgehog (Shh) signaling is required for Fgf3 expression in ventral CNS and DRG (Shh-dependent), whereas expression in cranial ganglion cells is Shh-independent.\",\n      \"method\": \"Transgenic reporter mice carrying Fgf3 genomic regions; deletional analysis; breeding into Shh mutant background; in situ hybridization\",\n      \"journal\": \"Developmental dynamics\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — transgenic enhancer dissection with deletion series and genetic epistasis with Shh mutants, single lab\",\n      \"pmids\": [\"15108308\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2002,\n      \"finding\": \"In zebrafish, FGF3 and FGF8 are both expressed in rhombomere 4 (r4) and together are required for development of adjacent rhombomeres 5 and 6. Transplantation of r4 cells or misexpression of either FGF3 or FGF8 can induce r5/r6 marker expression, establishing r4 as an FGF-mediated signaling center for early hindbrain patterning.\",\n      \"method\": \"Antisense morpholino knockdown, cell transplantation, misexpression experiments, time-lapse imaging, in situ hybridization for r5/r6 markers\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — reciprocal gain- and loss-of-function, cell transplantation, replicated across multiple groups (PMID 12121619, 12135921)\",\n      \"pmids\": [\"12135921\", \"12121619\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2002,\n      \"finding\": \"In zebrafish, combined loss of Fgf3 and Fgf8 via morpholino knockdown causes complete failure of otic placode formation and absence of early placode markers (pax2.1, dlx3), without affecting cell division or death. Either factor alone produces only partial reduction; the temporal requirement for FGF signaling is between 60% epiboly and tailbud stages. The earliest otic event, pax8 expression, does not require Fgf3/Fgf8, placing their action downstream of initial otic territory specification.\",\n      \"method\": \"Antisense morpholino knockdown (fgf3 and fgf8 single and double), FGFR inhibitor SU5402 time-window experiments, otic marker in situ hybridization, cell death/proliferation assays\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — double morpholino epistasis, pharmacological inhibitor time-window, multiple otic markers; replicated across multiple independent groups (PMIDs 11437442, 11959820, 12385757)\",\n      \"pmids\": [\"11959820\", \"11437442\", \"12385757\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2003,\n      \"finding\": \"In mice, Fgf3 and Fgf10 act redundantly and in a dose-sensitive manner for otic placode induction: single mutants have partial defects, but double Fgf3/Fgf10 mutants fail to form otic vesicles. Fgf3 is expressed in hindbrain neurectoderm while Fgf10 is expressed in underlying mesenchyme, indicating that FGF signals for otic induction emanate from both sources.\",\n      \"method\": \"Genetic double knockout (Fgf3 and Fgf10 null alleles), compound heterozygote allelic series, otic marker gene expression analysis, cell proliferation and survival assays\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — genetic double null and allelic dosage series, replicated across two independent studies (PMIDs 12810586, 14623822)\",\n      \"pmids\": [\"12810586\", \"14623822\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2000,\n      \"finding\": \"Ectopic expression of FGF3 in chick embryos induces formation of ectopic otic placodes expressing otic marker genes, which subsequently form vesicles with inner ear gene expression patterns. FGF2 under the same conditions has no effect, demonstrating specificity of FGF3 in inducing inner ear fate.\",\n      \"method\": \"In ovo electroporation-based gene transfer for ectopic FGF3 expression in chick, ectopic FGF2 control, otic marker in situ hybridization\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — gain-of-function with specificity control (FGF2 negative), single lab\",\n      \"pmids\": [\"10769226\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2007,\n      \"finding\": \"In mouse, Fgf3 expressed in hindbrain neurectoderm is required for dorsal otic patterning and endolymphatic duct formation. Fgf3 mutants show altered molecular patterning of the otic vesicle, and Fgf3 prevents ventral expansion of r5-6 Wnt3a, thereby focusing inductive WNT signals on the dorsal otic vesicle. Epistasis analysis places Fgf3 between hindbrain-expressed Hoxa1/Mafb and otic vesicle-expressed Gbx2 in the WNT-initiated cascade for dorsal otic patterning.\",\n      \"method\": \"Fgf3 null mouse genetic analysis, morphological and molecular otic patterning markers, Wnt3a expression analysis, genetic epistasis with Hoxa1, Mafb, and Gbx2 mutants\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — loss-of-function plus multi-gene epistasis analysis, multiple molecular markers, single lab with comprehensive pathway placement\",\n      \"pmids\": [\"17855431\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2004,\n      \"finding\": \"In zebrafish, Fgf3 signaling from the ventral diencephalon is required non-cell-autonomously for expression of pituitary specification genes (lim3, pit1) in adenohypophyseal progenitor cells. Without Fgf3, early specification fails and adenohypophyseal cells subsequently die by apoptosis. Shh can induce adenohypophyseal cells ectopically but cannot rescue pituitary development in fgf3 mutants, indicating Fgf3 does not act via Shh.\",\n      \"method\": \"lia/fgf3 null mutant analysis, in situ hybridization for pituitary markers, epistasis with Shh pathway (Shh rescue experiments), apoptosis assays\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — null mutant, molecular marker analysis, genetic epistasis with Shh, multiple orthogonal methods\",\n      \"pmids\": [\"15229178\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2005,\n      \"finding\": \"In zebrafish, Fgf3 derived specifically from pharyngeal endodermal pouches is required for neurogenesis (not initial induction) of epibranchial placodes. Tissue transplants demonstrate endoderm is the cellular source of the neurogenic signal. Ectopic fgf3 expression is sufficient to induce phox2a-positive neurons even in endoderm-deficient embryos, but neither endoderm nor Fgf3 is required for initial placode induction (foxi1 expression is unaffected).\",\n      \"method\": \"Morpholino knockdown of fgf3, endoderm ablation, mosaic cell transplantation, ectopic fgf3 overexpression, placode marker in situ hybridization\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — mosaic transplantation establishing tissue source, gain- and loss-of-function, marker dissection of induction vs neurogenesis steps, multiple methods\",\n      \"pmids\": [\"16077091\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2010,\n      \"finding\": \"In chick hindbrain, FGF3 (acting through the MAPK/Erk1/2 pathway) is required for upregulation of the ETS-domain transcription factor Pea3, which in turn is necessary for expression of Krox20 in rhombomeres 3 and 5. FGF signaling is a major contributor to ERK1/2 activation and downstream Pea3/Erm target expression in the hindbrain.\",\n      \"method\": \"Morpholino knockdown, pharmacological FGFR inhibition, in situ hybridization for FGF pathway components (ligands, receptors, MAPK components), Krox20 and Pea3 expression analysis\",\n      \"journal\": \"Developmental biology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — morpholino loss-of-function plus pharmacological inhibition, pathway component atlas, single lab\",\n      \"pmids\": [\"20553903\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2008,\n      \"finding\": \"In chick hindbrain, BMP activity antagonizes FGF3 expression: blocking follistatin translation with morpholinos or overexpressing BMP strongly inhibits FGF3 expression, while adding follistatin increases FGF3 levels. FGF3 expression also requires FGF activity itself, suggesting an autoregulatory loop. This BMP-FGF3 antagonism is required for correct expression of Krox20, Hoxb1, and EphA4.\",\n      \"method\": \"Morpholino knockdown of follistatin, BMP overexpression, follistatin protein addition, in situ hybridization for FGF3 and segmentation genes\",\n      \"journal\": \"Developmental biology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — morpholino loss-of-function, gain-of-function with BMP, rescue with follistatin protein; single lab\",\n      \"pmids\": [\"18823972\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2016,\n      \"finding\": \"In mouse, PSM-derived FGF3 restrains BMP signaling in the adjacent neuroepithelium. Loss of FGF3 elevates BMP signals, causing increased neuroepithelium proliferation, delayed neural tube closure, and premature neural crest specification. Increasing BMP signaling (by removing one Noggin copy in Fgf3 mutants) exacerbates all phenotypes; decreasing BMP signaling (by removing BMP receptor) alleviates them. Elevated BMP4 depletes PSM progenitors in vitro, phenocopying the Fgf3 mutant axis defect.\",\n      \"method\": \"Fgf3 null mouse, genetic epistasis with Noggin and BMP receptor mutants, BMP4 in vitro treatment of PSM explants, neural crest/tube marker analysis, apoptosis/proliferation assays\",\n      \"journal\": \"PLoS genetics\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — multi-gene genetic epistasis (gain and loss of BMP pathway), in vitro phenocopy, multiple orthogonal methods establishing FGF3-BMP axis\",\n      \"pmids\": [\"27144312\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1998,\n      \"finding\": \"FGF3 localizes to the otocyst epithelium in mouse, and antisense oligonucleotides against FGF3 suppress otic capsule chondrogenesis in cultured periotic mesenchyme, establishing FGF3 as an otocyst-derived signal capable of initiating chondrogenesis of surrounding mesenchyme.\",\n      \"method\": \"Endogenous FGF3 localization (immunostaining), antisense oligonucleotide knockdown in periotic mesenchyme/otocyst co-culture system, chondrogenesis assay\",\n      \"journal\": \"Growth factors (Chur, Switzerland)\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — antisense knockdown with functional chondrogenesis readout, localization by immunostaining; single lab\",\n      \"pmids\": [\"9570039\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2002,\n      \"finding\": \"Cell-surface-associated FGF3 (via heparan sulfate proteoglycan) is required for NIH3T3 cell transformation: dominant-negative FGFR2(IIIb) reverts the transformed phenotype more efficiently than IIIc, consistent with FGF3's higher affinity for the IIIb isoform. Attaching FGF3 to a GPI membrane anchor (independent of heparan sulfate) greatly increases its transforming potential, indicating that the mode of cell-surface presentation determines biological activity.\",\n      \"method\": \"Dominant-negative FGFR2(IIIb vs IIIc) expression in transformed DMI cells, GPI-anchored FGF3 mutant construction and transformation assay, heparin displacement, soft agar anchorage-independent growth\",\n      \"journal\": \"The Journal of biological chemistry\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — dominant-negative receptor specificity, GPI-anchor mutagenesis with functional transformation readout; single lab\",\n      \"pmids\": [\"12084721\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2008,\n      \"finding\": \"In zebrafish, FGF3 signal from the ventral diencephalon delineates the melanotrope/corticotrope lineage boundary in the developing pituitary. Hypomorphic FGF3 morpholino knockdown specifically defects pars intermedia POMC cells while leaving pars distalis POMC, growth hormone, and prolactin expression intact. This lineage-specific role is independent of Lim3/Pit1 expression, indicating a function distinct from early progenitor specification.\",\n      \"method\": \"Hypomorphic fgf3 morpholino knockdown, time-lapse confocal live imaging with GFP:pomc reporter zebrafish, in situ hybridization for pituitary lineage markers\",\n      \"journal\": \"Developmental biology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — morpholino loss-of-function with live lineage tracing, marker dissection; single lab\",\n      \"pmids\": [\"18514643\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2008,\n      \"finding\": \"In Ciona intestinalis, FGF3 expressed in the floor plate of the developing nerve cord directs notochord convergent extension (CE) via non-MAPK FGF signaling. A dominant-negative FGF receptor suppresses polarized actin-rich protrusions in notochord cells, resulting in defective CE. In Xenopus mesoderm explants, inhibiting FGF signaling perturbs CE and disrupts membrane localization of Dishevelled (Dsh), a PCP/CE regulator, placing FGF3 upstream of PCP components.\",\n      \"method\": \"Dominant-negative FGFR expression in Ciona, inhibition of Ciona FGF3 activity, actin protrusion imaging, Xenopus CE explant assay, Dishevelled membrane localization\",\n      \"journal\": \"Development (Cambridge, England)\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — dominant-negative and ligand inhibition with cellular morphology readout, cross-species validation; single study\",\n      \"pmids\": [\"19036800\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2019,\n      \"finding\": \"In zebrafish, Fgf3 controls the number of serotonergic and dopaminergic CSF-contacting cells in the posterior hypothalamus by regulating proliferation and cell survival. Fgf3 acts via the ETS-domain transcription factor etv5b (a known FGF downstream target) to control serotonergic progenitor proliferation. Loss of fgf3 also upregulates its own expression, suggesting a self-compensatory mechanism.\",\n      \"method\": \"Fgf3 morpholino knockdown (null mutant analysis), immunostaining for serotonergic/dopaminergic/neuroendocrine markers, proliferation and apoptosis assays, etv5b expression analysis, hypothalamic transcriptome analysis\",\n      \"journal\": \"Biology open\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — null/morpholino loss-of-function, multiple marker analysis, transcriptome supporting etv5b pathway; single lab\",\n      \"pmids\": [\"31036752\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2024,\n      \"finding\": \"Fgf3 mRNA is upregulated in mouse vagal ganglia under acute metabolic stress. Vagal sensory neuron-derived FGF3 enhances glucose-stimulated insulin secretion (GSIS) and improves glucose metabolism. Restriction of Fgf3 overexpression to pancreas-projecting vagal sensory neurons recapitulates the insulinotropic effect, and genetic ablation of Fgf3 in pancreatic vagal afferents exacerbates high-fat diet-induced glucose intolerance and blunts GSIS.\",\n      \"method\": \"Conditional vagal sensory overexpression and genetic ablation of Fgf3, glucose tolerance tests, GSIS assays, electrostimulation of vagal afferents\",\n      \"journal\": \"Developmental cell\",\n      \"confidence\": \"High\",\n      \"confidence_rationale\": \"Tier 2 / Strong — conditional gain-of-function (restricted to pancreas-projecting neurons), conditional loss-of-function, electrostimulation control; multiple orthogonal approaches\",\n      \"pmids\": [\"39413782\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"FGF3 expressed in the chick ventral diencephalon (hypothalamus) acts as a concentration-dependent guidance cue for thalamocortical axons (TCAs): 100 ng/mL is attractant while 500 ng/mL is repellent. Inhibition of FGF3 function disrupts correct navigation of thalamic axons in vitro.\",\n      \"method\": \"In vitro chick explant guidance assays with recombinant FGF3 at different concentrations, inhibition of FGF3 signaling, expression analysis\",\n      \"journal\": \"Developmental neuroscience\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — in vitro explant guidance assay with dose-response and loss-of-function; single lab\",\n      \"pmids\": [\"33684917\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"FGF3 expressed in the chick hypothalamus acts as a chemorepellent for neighboring prethalamic GABAergic axons. This guidance function is mediated through FGFR1 downstream signaling, as demonstrated by gene expression analysis and FGFR1 loss-of-function studies.\",\n      \"method\": \"In vitro chick explant guidance assays, FGF3 inhibition, FGFR1 expression analysis, FGFR1 loss-of-function, GABAergic axon tracing\",\n      \"journal\": \"International journal of molecular sciences\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — in vitro explant assay plus FGFR1 pathway loss-of-function; single lab\",\n      \"pmids\": [\"37834446\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2023,\n      \"finding\": \"In TA2 mice, MMTV-activated FGF3 promotes spontaneous mammary tumorigenesis via the FGF3/FGFR1/STAT3 signaling pathway. FGF3 physically binds FGFR1 (demonstrated by co-immunoprecipitation). FGF3 or FGFR1 knockdown decreases STAT3 and Akt phosphorylation. STAT3 and Akt mutually activate each other's phosphorylation, and inhibiting either increases FGFR1 expression.\",\n      \"method\": \"Co-immunoprecipitation of FGF3-FGFR1, shRNA knockdown of FGF3 and FGFR1, pharmacological STAT3/Akt inhibitors, proliferation/migration/invasion assays, xenograft tumor assay\",\n      \"journal\": \"Frontiers in oncology\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — direct Co-IP plus shRNA knockdown plus pharmacological inhibition; single lab\",\n      \"pmids\": [\"37496658\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2012,\n      \"finding\": \"In parthenogenetic mouse embryos, Fgf3 is strongly upregulated and drives excessive Fgfr2 phosphorylation, which promotes primitive endoderm differentiation at the expense of epiblast identity (increased Gata4, decreased Sox2/Nanog). Inhibition of Fgfr2 with SU5402 in parthenotes restores normal Nanog/Gata4 levels without affecting Fgf3 expression, placing Fgf3 upstream of Fgfr2 in this pathway.\",\n      \"method\": \"FGFR2 inhibition with SU5402, immunostaining for lineage markers (Sox2, Nanog, Gata4), RT-qPCR for Fgf3/Fgfr2, analysis of Fgfr2 phosphorylation\",\n      \"journal\": \"Developmental dynamics\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — pharmacological epistasis placing Fgf3 upstream of Fgfr2, marker analysis; single lab\",\n      \"pmids\": [\"22930543\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 1998,\n      \"finding\": \"FGF-3 (but not FGF-4) expressed in mouse mammary myoepithelial cells strongly stimulates production of pro-MMP-9 and pro-MMP-2, and upregulates plasminogen activators, contributing to matrix invasion. FGF-3-producing cells are invasive in Matrigel-coated chambers. FGF-4 has no effect on these protease secretions.\",\n      \"method\": \"Retroviral FGF-3 and FGF-4 expression in EF43 cells, Matrigel invasion assay, gelatin zymography for MMPs, plasminogen activator assays, tumorigenicity assays in syngeneic mice\",\n      \"journal\": \"Oncogene\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — stable expression with functional assays (invasion, zymography, PA assays), specificity shown by FGF-4 comparison; single lab\",\n      \"pmids\": [\"9798677\"],\n      \"is_preprint\": false\n    },\n    {\n      \"year\": 2015,\n      \"finding\": \"Fgf3 expression in zebrafish pharyngeal pouches is regulated downstream of Wnt5b/Wntless (Wls) secretion. In wls morphants and wnt5b mutants, fgf3 expression is reduced in pharyngeal pouches along the anteroposterior axis. Introducing fgf3 mRNA rescues jaw cartilage defects in Wnt5b- and Wls-deficient larvae. Wls is required for Wnt5b but not Wnt11 secretion in pharyngeal tissue, and fgf3 regulates chondrogenic cell proliferation downstream of Wnt5b/Wls.\",\n      \"method\": \"Morpholino knockdown of wls and wnt9a/wnt11, wnt5b mutant analysis, fgf3 mRNA rescue, cell proliferation assays, pharyngeal cartilage staining\",\n      \"journal\": \"Journal of cell science\",\n      \"confidence\": \"Medium\",\n      \"confidence_rationale\": \"Tier 2 / Moderate — mRNA rescue epistasis, morpholino knockdown of multiple Wnts, proliferation assays; single lab\",\n      \"pmids\": [\"25934698\"],\n      \"is_preprint\": false\n    }\n  ],\n  \"current_model\": \"FGF3 is a secreted heparin-binding growth factor (with an alternative CUG-initiated form that also traffics to the nucleus via a competing NLS) that signals through FGFR2-IIIb to activate MAPK/ERK, and functions as a paracrine morphogen during embryogenesis—acting cooperatively with FGF8 and FGF10 to induce the otic placode and pattern the hindbrain, driving otic/inner ear morphogenesis by regulating WNT signaling and downstream transcription factors (Krox20 via Pea3), specifying epibranchial placode neurogenesis from pharyngeal endoderm, directing adenohypophyseal progenitor specification, guiding axonal pathfinding, and controlling insulin secretion via vagal afferent neurons; its transcription is regulated by GATA-4, SOX7 (activators), and SOX6/CtBP2 (repressors) acting on the PS4A promoter element, with BMP signaling as an additional repressive input; in the posterior embryonic axis FGF3 restrains BMP signals to coordinate neural tube closure and neural crest specification; and dysregulation via MMTV insertion or gene amplification drives mammary tumorigenesis through FGF3/FGFR1/STAT3 signaling.\"\n}\n```","stage2_raw":"{\n  \"mechanistic_narrative\": \"FGF3 is a secreted heparin-binding growth factor that acts as a paracrine morphogen during embryogenesis, signaling preferentially through the FGFR2-IIIb isoform to drive otic, hindbrain, pituitary, and craniofacial patterning [#2, #9]. The mature protein is secreted, glycosylated, and tethered to the cell surface and extracellular matrix through heparan sulfate, from which it can be displaced by soluble heparin; its C-terminal region determines receptor affinity, mitogenic potency, and transforming activity [#1, #2]. FGF3 has an unusual dual subcellular fate: it is translated chiefly from an upstream CUG codon, and competing signals within the same protein\\u2014a cleaved signal peptide directing secretion versus a bipartite nuclear localization motif with upstream N-terminal sequences directing nuclear import\\u2014partition it between the secretory pathway and the nucleus [#0]. The mode of cell-surface presentation governs biological output, as anchoring FGF3 independently of heparan sulfate markedly increases its transforming potential [#19]. In development, FGF3 cooperates with FGF8 and FGF10 as an inductive signal: with FGF8 it establishes rhombomere 4 as a hindbrain signaling center patterning r5/r6, and with FGF10 it acts redundantly and dose-dependently for otic placode induction and otic vesicle formation [#8, #9, #10, #11]. It refines dorsal otic patterning by restraining ventral expansion of Wnt3a and operates within a Hoxa1/Mafb\\u2192Fgf3\\u2192Gbx2 WNT cascade [#12]. FGF3 specifies adenohypophyseal progenitors and pituitary lineage boundaries from the ventral diencephalon, drives epibranchial placode neurogenesis from pharyngeal endoderm, and signals through MAPK/ERK to upregulate Pea3 and thereby Krox20 in the hindbrain [#13, #14, #15, #20]. Along the posterior axis FGF3 restrains BMP signaling to coordinate neural tube closure and neural crest timing, while BMP reciprocally antagonizes FGF3 expression [#16, #17]. Its transcription is controlled at the PS4A promoter element by GATA-4 and SOX7 as activators and SOX6\\u2014which recruits the co-repressor CtBP2 via a PLNLSS motif\\u2014as a repressor [#3, #4, #5, #6]. Postnatally, vagal sensory neuron-derived FGF3 enhances glucose-stimulated insulin secretion, and dysregulated FGF3 promotes mammary tumorigenesis through an FGF3/FGFR1/STAT3 axis with direct FGF3\\u2013FGFR1 binding [#23, #26].\",\n  \"teleology\": [\n    {\n      \"year\": 1993,\n      \"claim\": \"Establishing FGF3 as a bona fide secreted, heparin-binding, receptor-activating growth factor answered whether it functions extracellularly like other FGFs and mapped its activity determinants.\",\n      \"evidence\": \"COS-1 secretion and glycosylation analysis, heparin-Sepharose binding, NIH3T3 transformation and mitogenesis assays, and chimeric FGF3 constructs\",\n      \"pmids\": [\"8223431\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Receptor isoform preference not yet defined\", \"Endogenous developmental sites of action not addressed\"]\n    },\n    {\n      \"year\": 1994,\n      \"claim\": \"Resolving the dual subcellular fate of FGF3 explained how a single CUG-initiated protein can be both secreted and nuclear, revealing competing trafficking signals within one polypeptide.\",\n      \"evidence\": \"In vitro translation, deletion/replacement mutagenesis, heterologous fusion proteins, and subcellular fractionation in COS-1 cells\",\n      \"pmids\": [\"8076608\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Functional role of the nuclear pool not defined\", \"Physiological regulation of CUG vs AUG initiation in vivo unknown\"]\n    },\n    {\n      \"year\": 1996,\n      \"claim\": \"Defining FGFR2-IIIb as the preferred receptor and mapping C-terminal affinity determinants established the receptor specificity underlying FGF3 signaling.\",\n      \"evidence\": \"FGFR2-IIIb vs IIIc binding assays, Xenopus/zebrafish chimeric proteins, transformation and heparin displacement assays in COS-1/NIH3T3 cells\",\n      \"pmids\": [\"8622866\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Structural basis of IIIb selectivity not resolved\", \"In vivo receptor usage across tissues not tested\"]\n    },\n    {\n      \"year\": 2001,\n      \"claim\": \"Dissecting the Fgf3 promoter answered how its transcription is positively and negatively controlled, identifying PS4A as the central regulatory hub and a GATA-4/SOX7 activator versus SOX6/CtBP2 repressor logic.\",\n      \"evidence\": \"DNase-I footprinting, deletion reporter assays in F9 cells, yeast one/two-hybrid, mammalian Co-IP, RNAi, and EMSA across multiple studies\",\n      \"pmids\": [\"11504872\", \"15082719\", \"11842118\", \"8265348\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"How these factors are coordinated in specific developmental contexts unclear\", \"Chromatin-level regulation not addressed\"]\n    },\n    {\n      \"year\": 2002,\n      \"claim\": \"Genetic and pharmacological studies in zebrafish and mouse established FGF3, acting with FGF8 and FGF10, as the inductive signal for hindbrain segmentation and otic placode formation, defining its core morphogen role.\",\n      \"evidence\": \"Single and double morpholino knockdown, genetic double nulls, SU5402 time-window inhibition, cell transplantation, and ectopic expression with otic/rhombomere marker analysis\",\n      \"pmids\": [\"12135921\", \"12121619\", \"11959820\", \"11437442\", \"12385757\", \"12810586\", \"14623822\", \"10769226\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Relative contribution of secreted vs cell-surface FGF3 in vivo unresolved\", \"Quantitative dose thresholds for distinct outcomes undefined\"]\n    },\n    {\n      \"year\": 2007,\n      \"claim\": \"Epistasis in the mouse otic vesicle placed FGF3 in a WNT-initiated cascade, showing it restrains Wnt3a to focus inductive signals and patterns dorsal otic identity between Hoxa1/Mafb and Gbx2.\",\n      \"evidence\": \"Fgf3 null mouse analysis with Wnt3a expression and multi-gene epistasis against Hoxa1, Mafb, and Gbx2 mutants\",\n      \"pmids\": [\"17855431\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Direct molecular link between FGF3 signaling and Wnt3a restriction unknown\", \"Receptor mediating dorsal otic patterning not identified\"]\n    },\n    {\n      \"year\": 2008,\n      \"claim\": \"Studies of pituitary and hindbrain development extended FGF3's role to lineage specification and target gene control, showing it specifies adenohypophyseal progenitors, sets pituitary lineage boundaries, and drives Pea3\\u2192Krox20 via MAPK/ERK.\",\n      \"evidence\": \"Zebrafish fgf3 mutant/morphant analysis with lineage markers, Shh epistasis, live POMC reporter imaging, chick morpholino knockdown and FGFR inhibition with Pea3/Krox20 analysis\",\n      \"pmids\": [\"15229178\", \"18514643\", \"20553903\", \"18823972\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"Direct transcriptional targets of FGF3-driven ERK in each context not fully enumerated\", \"Single-lab findings for several contexts\"]\n    },\n    {\n      \"year\": 2016,\n      \"claim\": \"Mouse genetics established a reciprocal FGF3\\u2013BMP antagonism along the posterior axis, defining FGF3 as a restraint on BMP signaling that coordinates neural tube closure and neural crest timing.\",\n      \"evidence\": \"Fgf3 null mouse with Noggin and BMP receptor epistasis, in vitro BMP4 treatment of PSM explants, and neural crest/tube marker and proliferation analysis\",\n      \"pmids\": [\"27144312\", \"18823972\"],\n      \"confidence\": \"High\",\n      \"gaps\": [\"Molecular mechanism by which FGF3 limits BMP signaling not defined\", \"Receptor used in PSM-to-neuroepithelium signaling unknown\"]\n    },\n    {\n      \"year\": 2023,\n      \"claim\": \"Newer work added postnatal and disease functions, showing vagal-derived FGF3 enhances insulin secretion, FGF3 acts as a dose-dependent axon guidance cue via FGFR1, and dysregulated FGF3 drives mammary tumorigenesis through direct FGF3\\u2013FGFR1 binding and STAT3/Akt signaling.\",\n      \"evidence\": \"Conditional vagal overexpression/ablation with glucose and GSIS assays, chick explant guidance assays with FGFR1 loss-of-function, and FGF3\\u2013FGFR1 Co-IP with shRNA knockdown and xenograft assays\",\n      \"pmids\": [\"39413782\", \"33684917\", \"37834446\", \"37496658\"],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"FGFR1 (vs FGFR2-IIIb) usage across contexts not reconciled\", \"Mechanism of concentration-dependent attraction vs repulsion unresolved\", \"Tumor findings from single model/lab\"]\n    },\n    {\n      \"year\": null,\n      \"claim\": \"The function of the nuclear FGF3 pool and how receptor choice (FGFR2-IIIb vs FGFR1) and cell-surface presentation are selected to produce distinct developmental and pathological outcomes remain unresolved.\",\n      \"evidence\": \"\",\n      \"pmids\": [],\n      \"confidence\": \"Medium\",\n      \"gaps\": [\"No assigned function for nuclear FGF3\", \"No unified model linking receptor/co-receptor context to specific cellular outcomes\", \"Structural basis of signaling not determined\"]\n    }\n  ],\n  \"mechanism_profile\": {\n    \"molecular_activity\": [\n      {\"term_id\": \"GO:0048018\", \"supporting_discovery_ids\": [1, 2, 26]},\n      {\"term_id\": \"GO:0060089\", \"supporting_discovery_ids\": [2, 19, 26]},\n      {\"term_id\": \"GO:0008092\", \"supporting_discovery_ids\": [1, 2]}\n    ],\n    \"localization\": [\n      {\"term_id\": \"GO:0005576\", \"supporting_discovery_ids\": [1, 2]},\n      {\"term_id\": \"GO:0031012\", \"supporting_discovery_ids\": [1, 2]},\n      {\"term_id\": \"GO:0005634\", \"supporting_discovery_ids\": [0]},\n      {\"term_id\": \"GO:0005886\", \"supporting_discovery_ids\": [19]}\n    ],\n    \"pathway\": [\n      {\"term_id\": \"R-HSA-162582\", \"supporting_discovery_ids\": [15, 26, 27]},\n      {\"term_id\": \"R-HSA-1266738\", \"supporting_discovery_ids\": [8, 9, 10, 12]},\n      {\"term_id\": \"R-HSA-1643685\", \"supporting_discovery_ids\": [26, 28]}\n    ],\n    \"complexes\": [],\n    \"partners\": [\"FGFR2\", \"FGFR1\", \"FGF8\", \"FGF10\"],\n    \"other_free_text\": []\n  }\n}","audit_flag":null,"evaluation":{"pairwise":"win","faith_supported":10,"faith_total":10,"faith_pct":100.0}}