CBX1 · ENST00000225603.9

TRUNCATED 163 aa (canonical 185 aa) · UniProt P83916 · CDLMPS

chr17:48076938:-:GTG:ENST00000225603.9

AI summary N-terminal 23-aa loss leaves the chromodomain, localization, and biophysics essentially untouched despite the region's conservation.

How it diverges

The truncation removes a 23-residue N-terminal tail entirely outside the chromo and chromo-shadow domains (which begin at residue ~20 in the canonical numbering and are unaffected), and no real InterPro domain, localization signal, or whole-protein biophysical property changes as a result. DeepLoc calls both canonical and isoform Nucleus with matching high confidence and an intact NLS, so there is no localization conflict; the moderate pLDDT of the removed tail (0.74) suggests weak local structure but it is unintegrated with the rest of the fold (PAE ~25 Å) and carries no annotated function.

Why it matters

CBX1/HP1-beta's known activities — H3K9me3 reading via the chromodomain, SUV39H1/PRC2 partnership, and CK2/Chk2-regulated chromatin mobilization — all map to the chromo and chromo-shadow domains and their phosphorylation sites, none of which lie in this removed N-terminal stretch. With domain architecture, nuclear localization, and biophysical character all preserved, this truncation has no clear mechanistic bearing on any of CBX1's documented functions.

LLM confidence low

No mass-spec validation of the truncated peptide and the shared-region structural model is low-confidence (pTM <0.5, shared pLDDT 0.63), so structural claims about the retained core are not usable evidence either way.

Folding

Canonical (185 aa)

Download CIF

Isoform (163 aa)

Download CIF

Coloured by ESMFold2 pLDDT confidence (blue = high, orange/red = low). Differential region — residues 1–23 (lost from canonical) — recoloured on a yellow→purple pLDDT ramp so it stands out. Drag to rotate · scroll to zoom · download a CIF to explore in your own viewer.

Canonical PAE

Isoform PAE

Predicted aligned error: expected Cα error (Å) at residue j when the fold is superposed on residue i. Dark = confident relative placement; bright = uncertain. The dashed outline marks the differential region (1–23).

Evidence — click any tile for the differential-region detail

C Conservation Interesting

LLM reasoning

The N-terminal 23-aa segment removed by this truncation is under strong purifying selection across mammals, arguing its loss is likely to be functionally consequential rather than a neutral truncation artifact. Amino-acid identity is 100% across both 25 primate and 20 mammalian species, essentially matching (slightly exceeding) the canonical region's own identity (99.5% primates, 97.8% mammals), so the removed segment is conserved to the same high standard as the rest of the protein. Absolute phyloP over the unique region is 4.95, well above the ~2 threshold for strong constraint, and closely matches the shared-region phyloP (4.94), indicating the lost segment is held under selection just as tightly as the retained coding sequence. Together these point to the removed N-terminal stretch being genuine, evolutionarily constrained coding sequence whose loss in this truncation is likely to matter functionally.

Unique region 100.0% similar across primates

Conservation metric	Canonical ORF	Differential ORF
Mean AA identity	100%	100%
Frame intact (fraction of species)	84%	100%
Species aligned	25	25
Species frame-intact	21	25
Start codon conserved	100%	100%
Deepest intact species	Propithecus_coquereli	Microcebus_murinus
Phylo depth (MRCA)	7	7

Unique region 100.0% similar across mammals

Conservation metric	Canonical ORF	Differential ORF
Mean AA identity	98%	100%
Frame intact (fraction of species)	15%	100%
Species aligned	20	20
Species frame-intact	3	20
Start codon conserved	100%	100%
Deepest intact species	Callithrix_jacchus	Loxodonta_africana
Phylo depth (MRCA)	6	12

Unique region PhyloP: 4.95 — purifying selection

Track	Differential	Shared	vs shared
phyloP mean	4.95	4.94	1
phastCons mean	0.966	0.913	—

Property	Canonical	Isoform
Start codon	ATG	GTG
Kozak context (−9..+4)	GCGGGCACTATGG	GAATATGTGGTGG
phyloP at start codon	6.43	4.52
phastCons at start codon	1	1
phyloP over Kozak window	6.31	5.02
phastCons over Kozak window	1	0.994
Kozak mismatch — full consensus	3	8
Kozak window GC content	0.692	0.462

D Detection Neutral

LLM reasoning

This is a truncation removing the N-terminal 22 residues, so the alt start site itself shows reasonable ribosome-profiling support but there's no protein-level confirmation of the truncated product. The TIS is reproducibly detected in 2 of 6 cell lines (HeLa and RPE1-Async, both significant p-values) with a max initiation efficiency of 0.0995 in HeLa, above the 0.01 threshold, indicating real and somewhat efficient alternative initiation at the transcript/ribosome level. However, the only isoform-unique tryptic peptide identified was not validated by PepQuery2 (0/1), so there is no direct mass-spec confirmation that the shorter protein is actually produced and stable. Together this gives moderate ribosome-level detection but no orthogonal proteomic corroboration, so the evidence is mixed rather than clearly supportive or refuting.

detected in 2/6 cell lines

Cell line	Canonical	Isoform	p-value
HeLa	—	3.65	0.000687
RPE1 Async	—	0.676	0.00865

Max Initiation Efficiency: 0.0995

Cell line	Canonical	Isoform
HeLa	—	0.0995
RPE1 Async	—	0.0161

0/1 isoform-unique peptides validated

Feature	Canonical	Isoform
Tryptic peptides (in-silico)	28	1
Validated by mass-spec	0	0
Isoform-unique peptides	—	1

L Localization Not interesting

LLM reasoning

Loss of this N-terminal 23-residue segment (removed in the truncation) does not alter predicted subcellular fate: both canonical and isoform are called Nucleus with high and near-identical confidence (0.927 vs 0.933), retain the same annotated nuclear localization signal, and remain soluble/non-membrane-associated. No secretory signal peptide or mitochondrial transit peptide is predicted for either form, and the SignalP/TargetP probability deltas are negligible (on the order of 1e-4). The evidence argues against any functional consequence of this truncation in the localization dimension.

iso: Nucleus | canon: Nucleus

Property	Canonical	Isoform
Predicted location	Nucleus	Nucleus
Sorting signals	Nuclear localization signal	Nuclear localization signal
Membrane	Soluble	Soluble

iso: noTP | canon: noTP

Predictor	Canonical	Isoform
TargetP	noTP	noTP
SignalP	OTHER	OTHER

M Mutation Landscape Not interesting

LLM reasoning

Nothing in this category argues for functional consequence of the truncated N-terminal region. There are zero ClinVar pathogenic/likely-pathogenic variants anywhere on this isoform (unique or shared), and the 14 ClinVar variants of any significance are diffusely spread across a 5-176 residue span with no clustering (top position holds only 2 of 14 records). COSMIC recurrence is similarly thin and spread — the top hit is a frameshift with only 5 samples near canonical residue 2, and missense COSMIC hits scattered from position 15 to 175 with 1-3 samples each, none concentrated in the removed N-terminal segment. Germline data reinforces tolerance rather than constraint: the unique region carries 1.65x more gnomAD variants (density-normalized) than the shared core, and ESM-C finds zero constrained positions in either region. Both constraint signals and the disease-density signal converge on the same negative conclusion — this removed 23-residue segment shows no evidence of being disease-critical or under selective constraint.

gnomAD variants 1.65× more in unique region — tolerant

Variant set	Differential	Shared	Depletion ratio
gnomAD variants	35	157	1.7×

Property	Differential	Shared	Enrichment
ESM-C mean LLR	-0.00177	-0.0078	—
Constrained positions	0	0	—

Variant set	Differential	Shared	Enrichment
Scorable variants	33	155	1.5×
Damaging variants	24	79	2.2×
— of which loss-of-function	1	12	0.59×
AlphaMissense-pathogenic	10	48	1.5×

Property	Differential	Shared
Mean ΔLLR (ESM-C)	-7.1	-5.32
Min ΔLLR (ESM-C)	-12.3	-13.1
Mean AlphaMissense	0.516	0.592

Disease variants 1.20× less in unique region — depleted

Variant set	Differential	Shared	Enrichment
Disease variants	9	80	0.83×
Pathogenic	0	0	—

Variant set	Differential	Shared	Enrichment
Scorable variants	9	79	0.81×
Damaging variants	8	58	0.98×
— of which loss-of-function	2	7	2×
AlphaMissense-pathogenic	3	40	0.53×

Property	Differential	Shared
Mean ΔLLR (ESM-C)	-8.45	-7.44
Min ΔLLR (ESM-C)	-11.4	-13.9
Mean AlphaMissense	0.604	0.686

P Predicted Structure Not interesting

LLM reasoning

No structural signal survives scrutiny. The removed N-terminal 23 residues of the canonical protein are pure coil (0 helices, 0 strands confirmed directly), so there is no secondary element being deleted. The unique-region fold confidence (mean pLDDT 0.739) looks moderate but sits right at the disorder/confident boundary, and the region's placement relative to the rest of the protein is entirely unresolved: PAE between residues 1-23 and residues 24-185 averages 25.1 Å, near the ceiling of the scale. The shared-core RMSD of 22.4 Å is not usable as evidence of refolding — global pTM is only 0.32/0.39 and shared-region isoform pLDDT is 0.63, both failing the confidence gates, so this large RMSD reflects placement uncertainty in a poorly-resolved model rather than a genuine conformational change.

pLDDT Differential Region: 0.739

Metric	Canonical	Isoform
pLDDT (whole protein)	0.822	0.634

Metric	Differential	Shared	Enrichment
pLDDT	0.739	0.938	0.79

Shared-Region RMSD: 22.39 Å

Property	Canonical	Isoform
Shared-region pLDDT	0.834	0.635

No helix or strand in diff region

Metric	Differential	Shared
Alpha helices	0	3
Beta strands	0	2
Longest element (aa)	0	15
Mean pLDDT	—	0.88

Removed (canonical)	Shared core
—	alpha helix 61–75 15 aa · pLDDT 0.82
—	beta strand 86–92 7 aa · pLDDT 0.79
—	beta strand 143–148 6 aa · pLDDT 0.90
—	alpha helix 149–154 6 aa · pLDDT 0.93
—	alpha helix 157–166 10 aa · pLDDT 0.94

Removed (canonical)	Shared core
—	beta strand 35–39 5 aa · pLDDT 0.92
—	beta strand 50–53 4 aa · pLDDT 0.92
—	beta strand 96–100 5 aa · pLDDT 0.74
—	beta strand 168–172 5 aa · pLDDT 0.83

S Structural Characteristics Not interesting

LLM reasoning

None of the structural-characteristics signals argue for functional consequence from losing this N-terminal 23-aa segment. No real InterPro domain overlaps the removed region (all chromo/chromo-shadow domain hits sit downstream in the shared core, unaffected). Whole-protein hydropathy, fraction-charged and disorder deltas between isoform and canonical are all tiny (0.046, -0.018, -0.018), well below a shift threshold, despite the removed segment itself having elevated local disorder and charge fractions that don't translate into a whole-protein-level change. The ESM-C sparse-autoencoder magnitude check also comes up short: the strongest shared-feature activation shift is 4.91, under the 10.0 threshold, so the gained (20) and lost (96) feature counts are just a byproduct of the length difference rather than a meaningful signal. Together this points to a dispensable, low-complexity N-terminal tail whose removal doesn't perturb the folded domain architecture or overall biophysical character of the protein.

No diverging domains

Feature	Canonical	Isoform
InterPro domains	15	15
Short linear motifs	1	1

less hydrophobic (-0.23) · more charged (+0.12) · more disordered (+0.12)

Property	Differential	Shared	Enrichment
Isoelectric point (pI)	4.3	4.6	0.935
Hydropathy (GRAVY)	-1.47	-1.23	1.19
Fraction charged	0.565	0.442	1.28
Disorder fraction	0.33	0.214	1.54
Disorder-promoting	0.652	0.681	0.958
Low-complexity fraction	0.783	0.117	6.71
Prion-like fraction	0.174	0.203	0.859
LLPS score	0.27	0.176	1.53
π–π propensity	0.13	0.178	0.733
Aromaticity	0.0435	0.0736	0.591
Instability index	108	45	2.4
Shannon entropy	2.63	3.96	0.664
Normalized complexity	0.608	0.915	0.664

116 SAE features differ

Feature	Label	Description	Activation	Prevalence
#15915	C2B and RabBD loop signal	Signal for loops within C2 domains, particularly the second C2 domain (C2B) of Rab3-interacting and synaptotagmin-like proteins, with additional firing in the N-terminal Rab-binding domain (RabBD) region of these same proteins. Activation patches contain Ser/Thr, acidic residues (E/D), and frequent Pro/Gly, consistent with C2-domain inter-strand loops.	3.76	2
#7903	Arginine-rich polybasic patches	Basic polycationic patches enriched in arginine (often with lysine) within low-complexity/disordered regions, frequently N-terminal. These include classical monopartite NLSs, nucleic acid–binding basic tails, signal peptide n-regions and cytosolic juxtamembrane segments (positive-inside rule), and basic clusters in secreted precursors; typically depleted of acidic residues.	3.04	2
#11943	Active-site proximal loops	Active-site–proximal flexible loops/turns (beta-strand turns and coil-to-helix junctions) that flank catalytic residues or cofactor/metal-binding pockets across diverse enzyme folds; these segments often contain or neighbor acidic (Asp/Glu) and glycine residues (with occasional Lys/Arg and aromatics) that position substrates, metals, or nucleotides for catalysis. In secreted peptide precursors, the feature also marks short acidic/Gly-rich turns at proteolytic processing sites that enable maturation.	2.91	2
#13152	Active-site pocket-lining turns	Short, ordered coil/turn segments lining or gating enzyme active/ligand-binding pockets, typically sparing the catalytic residue itself.	2.87	2
#1846	Glycine-rich active-site loops	Glycine-containing, flexible loop/turn motifs (often with adjacent polar/charged residues) that form catalytic and cofactor/substrate-binding loops in enzymes—covering classic glycine-rich binding loops (e.g., NAD(P)-, ATP/CoA-binding loops), oxyanion/metal-binding loops, and electrostatic substrate-guidance loops—across diverse taxa and cellular locales.	2.40	2
#8665	Conserved domain-edge hydrophobic loop	Short hydrophobic/polar sequence patches located at domain edges, recurring N-terminal to catalytic Rab-GAP TBC domains and in cytoplasmic regions of small membrane-associated subunits, likely marking a conserved structural segment adjacent to ordered β-strand or short helix	2.33	2
#16372	Lysine-rich electrostatic/PTM hotspots	A general lysine-centric signal: the feature fires on lysine residues in basic patches and K‑rich stretches that mediate electrostatic interactions with nucleic acids or acidic partners, and on functionally reactive lysines that undergo lysine-specific chemistry (acetyl/methyl/ubiquitin/SUMO in regulators; hydroxylation/oxidative crosslinking in ECM), yielding broad activation across transcriptional regulators and extracellular matrix proteins	2.20	2
#16283	Short His/Gly-rich active-site loops	Short polar catalytic/cofactor-binding loops, most characteristically the RHG motif of the histidine phosphatase superfamily (RHGXRXP), but broadly recognizing analogous His/Gly–rich segments (HxG, HGG, HxH/HxE, HGTGT) and related short glycine-/acidic-/cysteine-enriched motifs that form active-site or cofactor/metal-binding loops across diverse enzyme classes (phosphoryl transfer, porphyrin chelation, redox oxygenases/monooxygenases, electron transfer, and carbohydrate hydrolases).	2.17	2
#5045	N-terminal IDR and signal-peptide activation	N-terminal pre-domain segments used for targeting or regulation: either intrinsically disordered, low‑complexity, Ser/Thr/Pro/Gly- and acidic‑rich regulatory tails with clustered phosphosites, or short hydrophobic signal peptides; activation consistently fades before downstream structured domains.	2.15	2
#10487	Nuclear regulatory low-complexity IDRs	Intrinsically disordered, low‑complexity regulatory regions of large metazoan regulatory and scaffolding proteins—enriched in nuclear gene‑regulatory factors—especially transactivation domains, flexible linkers, and long regulatory tails that are S/P/Q/G/T- and acidic‑rich, harbor SP/TP phospho‑motifs and short homorepeats; the feature preferentially avoids compact folded DNA-/ligand-/zinc‑binding domains.	1.99	2
#14887	Start of mature domain	Start-of-mature-domain segments, often the post‑signal‑peptide stretch or the first folded subdomain following an N‑terminal region: windows that frequently form the first helix or β‑strand of the mature domain, sometimes preceded by disordered low‑complexity tails enriched in small/polar residues (P/G/S/T/A). These regions mark the onset of a structured domain rather than catalytic cores, and often carry localization/export or assembly cues (e.g., secretion signals, transit/NLS motifs).	1.95	2
#6836	N-terminus and beta-strand boundary peaks	Residue-level feature whose strongest peaks fall near N-terminal/chain-start positions of bacterial and mitochondrial proteins, with weaker secondary peaks at beta-strand starts/ends and adjacent coils in beta-rich and alpha/beta domains, generally away from catalytic centers.	1.91	2
#10290	Disordered phospho-rich regulatory tails	Eukaryotic intrinsically disordered, low‑complexity regulatory linkers and tails — often enriched in polar and acidic residues, with embedded phospho‑Ser/Thr/Tyr clusters — in scaffold/adaptor and signaling proteins; well‑folded domains such as PTB are de‑emphasized.	1.91	2
#4673	NA-binding SLiMs and cystine-knots	Short conserved interaction motifs and broader disordered/low-complexity binding segments in nucleic-acid/chromatin-associated proteins, with peaks in disordered acidic/basic and Pro/polar-rich tails of retroelement Pol proteins, key DNA/RNA-contacting loops/β-strands (OB-folds, polymerase loops), and disordered acidic/trafficking SLiMs (e.g., AHA, NES/NLS) that mediate regulatory binding; also includes disulfide-bonded cystine-knot cores in secreted TGF-beta/BMP/GDF growth factors.	1.91	2
#3660	Low-complexity basic IDRs and micro-TMs	Generic low-complexity segments that are intrinsically disordered, proline‑rich and/or Lys/Arg‑biased (often also enriched in Ser/Thr) with intermittent hydrophobic residues, together with short hydrophobic helices in small membrane proteins; these include propeptide/processing regions of secreted precursors, basic disordered segments in viral proteins, mucin‑like S/T‑rich patches in glycoproteins, surface loops in enzymes, and single‑pass transmembrane microproteins (e.g., organellar gene products) rather than a specific folded domain.	1.82	2
#4850	RRM-disordered linker activation	RRM-containing eukaryotic RNA-binding proteins, with broad activation spanning both the RRM domains and adjacent/inter-RRM disordered regions; covers splicing factors, hnRNP family, SR-type shuttling mRNA-binding proteins, cyclophilin-type RRM proteins, and plant glycine-rich RBPs.	1.76	3
#9537	N-terminal low-hydrophobic presequence detector	N-terminal low-hydrophobic presequence detector: preferentially marks low-complexity, small/polar-rich leaders (e.g., chloroplast transit peptides and some mitochondrial transit peptides), but generally not classical hydrophobic signal peptides or strongly Arg-rich amphipathic leaders	1.75	2
#2588	Exposed beta-loop interfaces	A cross-kingdom feature marking solvent-exposed beta-strand/loop segments within repeated, beta-rich binding/scaffold domains and processivity modules, recurring in nucleic-acid–binding S1/OB-fold proteins (rRNA biogenesis), DNA-binding plant factors (AP2/ERF, B3), replication clamps, extracellular adhesion modules (Ig/FN3/Laminin-G) and Ly6/uPAR three-finger proteins, as well as cupredoxin/cupin enzyme scaffolds; also present in nuclear transcriptional regulators.	1.69	2
#437	Short linear helical motifs	Short alpha-helical linear motifs (∼8-20 aa) used for assembly/targeting and interface formation—often amphipathic, mixed charged/hydrophobic (E/D/K/R with hydrophobics) and frequently proline-flanked in flexible regions, but also including short hydrophobic helices such as brief transmembrane segments.	1.59	2
#15733	Eukaryotic signal peptides and IDRs	Eukaryotic compositionally biased low‑complexity/IDR segments—including N‑terminal signal peptides and long Ser/Thr/Pro/Lys/Glu‑rich tracts—that serve as regulatory and scaffolding regions (phospho‑regulated, proline‑rich) in cell‑cycle/mitotic and microtubule/ciliary proteins, and as targeting/propeptide regions in secreted peptide precursors; also present as basic/acidic tails in RNA/translation factors and organellar ribosomal proteins.	1.52	2

Feature	Label	Description	Activation	Prevalence
#9666	Alpha-helix caps and anchors	Residue-level recognition of alpha-helix termini/interfacial anchor residues: polar/aromatic sites (e.g., Asn/His/Tyr/Gly and nearby Y/F/W often following Lys/Arg) that cap or stabilize helices, including membrane–interface aromatic anchors and soluble helix caps, occurring broadly across proteins	10.72	2
#15815	Basic N-terminal targeting patch	Short, basic/polar N‑terminal leader/transit segment immediately after the initiator methionine (positions ~3–6) — i.e., the positively charged/polar start of signal peptides and organelle transit peptides, and more generally low‑acidic, disordered N‑terminal patches (including occasional cysteine‑rich starts) used for targeting, export, rRNA binding, or membrane topology cues	9.70	4
#10704	N-terminal PEST-like IDRs	Low-complexity, often acidic/proline-rich intrinsically disordered N-terminal tails of intracellular eukaryotic proteins, frequently overlapping annotated PEST-like segments.	8.87	10
#7996	Generic extreme N-terminus detector	Generic extreme N-terminus detector: marks residues around position 5 (occasionally 6–7) at the very start of the polypeptide, most often within the N-region of signal/transit peptides of secreted or organelle-targeted precursors, but also in generally disordered N-termini of cytosolic/nuclear proteins; not motif- or residue-specific	8.62	2
#10977	Early N-terminal disordered patch	Short N-terminal patch at the extreme N-terminus (around residues 5–10), capturing the first distinctive segment of preproteins/precursors and N-terminal disordered tails; residue composition is heterogeneous but frequently polar (Ser/Thr) and/or charged.	6.83	3
#8021	Extracellular exposed-loop activations	Extracytoplasmic/secreted proteins and extracellular or luminal domains (secretory pathway, periplasm, outer membrane, virion surface), with enrichment for carbohydrate-active enzymes and Ca2+-dependent recognition modules; the feature highlights solvent-exposed loop/turn residues across these regions rather than a specific catalytic motif. A minority of cytosolic glycosidases with similar loop features can also activate.	6.22	2
#8063	Disordered N-terminal activation window	Short N-terminal disordered segment found in a variety of proteins, including plant chloroplast transit peptides, bacterial prokaryotic ubiquitin-like protein Pup N-termini, anti-sigma factor N-tails, and some small RiPP precursor leaders. The activating region is Ser/Thr/Ala/Pro/Gly/Gln-rich, low in acidic residues, and typically lies in a disordered N-terminal stretch; the feature does not generally mark all transit peptides or all RiPP leaders.	5.34	7
#5506	Cysteine-rich extracellular repeat modules	Cysteine-rich, disulfide‑stabilized extracellular repeat modules—principally EGF‑like repeats and closely related small domains (CCP/Sushi, WAP/TIL, disintegrin, LDLR class‑A, and von Willebrand–type modules)—found across secreted proteins, extracellular matrix components, proteases/inhibitors, and receptor ectodomains.	5.00	2
#11990	Paired hydrophobic anchor motif	A broad, structural micro‑motif: a pair of hydrophobic “anchor” residues that sit on short β‑strand or adjacent core positions stabilizing compact helix‑based modules (winged‑helix/HTH, histone‑fold handshakes, EF‑hand pairs, HhH/base‑flipping elements). These anchors lie next to, but not at, the primary functional sites (DNA‑ or Ca2+‑binding loops), and recur early in proteins across diverse taxa.	4.80	2
#3505	Extreme N-terminus recognition	Recognition of the extreme N-terminus of proteins, especially the signal/transit-peptide cleavage junction and the first residues of the mature chain; more generally, short disordered, polar/charged N‑terminal segments (often including the initiator Met) across diverse enzymes and taxa.	4.24	4
#8262	Charged coil-to-beta cap motif	A short, polar/charged loop/turn motif at coil→β‑strand junctions and β‑hairpin connectors—typically capping or initiating β‑strands at domain boundaries or adjacent to catalytic/binding sites. The sequence signal is a 3–10 residue patch enriched in K/R, D/E, S/T, and small residues (G/P), and recurs across many folds rather than a family‑specific consensus.	4.21	3
#9145	Helix–loop boundary/linker signal	A generic helix–loop boundary/linker signal: the feature prefers short coil segments and helix-capping/hinge positions that connect or terminate alpha-helices, especially interhelical loops in multi-pass membrane proteins and structured active-site/cofactor-binding loops in soluble enzymes; it tolerates diverse amino acids but often includes small helix-modulating or interfacial aromatic residues.	4.16	2
#9632	Disordered acidic/mixed-charge interaction modules	Intrinsically disordered segments in diverse phosphoproteins and chromatin-associated factors—often with mixed basic/acidic or acidic-leaning composition—that act as flexible interaction modules; widely used in chromatin/transcription factors and also present in diverse acidic phosphoproteins across taxa.	4.12	6
#9980	Phosphate-binding loop-adjacent coils	Short coil/loop residues immediately preceding or within conserved phosphate-binding loops of NTP-utilizing enzyme domains, primarily the Walker A/G1 P-loop of P-loop NTPases (AAA+ ATPases, SF1/SF2 helicases, translational GTPases), and also analogous ATP-binding loops in related kinase folds (e.g., APS kinase P-loop kinases, Bergerat-fold histidine kinases); occasional secondary activation on gly/lys-enriched loops adjacent to functional sites in non-NTP enzymes and small translation factors (e.g., glyoxalase I, IF-1).	4.11	2
#3860	GH5 TIM-barrel stabilizing residues	A signal that fires at conserved residue positions within the catalytic (GH5) domain of fungal endo-β-1,4-mannanases, marking stabilizing positions in the well-ordered TIM-barrel scaffold rather than catalytic or substrate-binding residues.	4.08	2
#693	Helix-capping repeat boundary motifs	Short helix-capping and inter-helix turn/linker motifs at the boundaries of alpha-helical repeat units and alpha‑solenoid scaffolds (e.g., HEAT/ARM/ANK/CATCHR); the feature also fires at similar helix–loop junctions in other helical domains and in small helical RNA‑binding proteins.	3.89	2
#792	Short solvent exposed loops	Short, solvent‑exposed coil/turn segments (ordered loops) that connect secondary‑structure elements, most prominently in extracellular/periplasmic/lumenal ectodomains but also in soluble enzymes and nucleic‑acid–binding proteins; compositionally enriched in Gly and polar/acidic residues with frequent Ser/Thr and Lys/Arg; not tied to specific catalytic motifs but marking surface loops/turns (e.g., turns between beta strands) commonly used for flexibility and binding interface shaping	3.86	3
#13538	Pocket-lining strand-edge loops	Structured loop/turn residues at beta-strand edges in well-structured enzyme cores (including Rossmann-like, TIM-barrel, alpha/beta hydrolase, beta-propeller, and P-loop NTPase folds) that line cofactor/substrate-binding pockets, typically enriched in Gly and polar/charged residues, and flanking rather than constituting the catalytic residues	3.76	2
#14778	FBPA N-terminal helix motif	Short N-terminal alpha-helical patch enriched in small hydrophobics (A/V/I) with frequent Ser/Thr, corresponding to the start of the first alpha-helix of Class II fructose-1,6-bisphosphate aldolases (FBPA).	3.59	2
#10556	Helix termini and linkers	Structural motif: alpha-helical segments with a strong preference for helix termini and adjacent coil/turns (helix-capping positions and short helix–loop linkers), largely independent of protein function	3.57	2
#15526	Polar low-complexity disordered regions	Intrinsically disordered, low‑complexity regions enriched in polar/acidic and amide residues—especially Q/E/S/T/P/G—often including proline‑rich tracts and S/T clusters; these segments are flexible, cysteine‑poor, and typically lie outside structured catalytic cores (e.g., disordered tails, propeptides, and regulatory regions).	3.56	2
#8396	Amphipathic TPR helix starts	Amphipathic alpha‑helical repeat elements characteristic of tetratricopeptide repeat (TPR) and related alpha‑solenoid scaffolds, with a bias toward the N‑terminal boundary of individual TPR helices used for protein–protein docking; the feature also weakly generalizes to analogous helices in other coiled‑coil/alpha‑helical complex subunits.	3.49	2
#1370	Short low-complexity N-terminal segment	Short, low‑complexity, intrinsically disordered N‑terminal segments (~10–20 aa) that frequently correspond to leader/transit/propeptide presequences (e.g., chloroplast transit peptides, RiPP/bacteriocin leaders) or generic unstructured N‑tails; typically non‑hydrophobic and enriched in Ser/Thr/Pro but tolerant of basic (poly‑Arg/Lys) or Cys‑rich compositions	3.42	8
#7372	Helix capping transition sites	Alpha-helix termination/capping residues and helix–transition junctions (particularly C-caps and the immediately following turn/loop or helix–β connectors), which often stabilize helix ends and frequently flank catalytic or ligand-binding pockets across diverse proteins	3.23	2
#11393	Small-residue coil/turn micro-motifs	Short, flexible coil/turn micro‑motifs enriched in small/turn‑prone residues (G, A, S, T, P and small hydrophobics) that demarcate functional segment boundaries—e.g., cores of processed small peptides and structured loops flanking catalytic or metal‑binding sites—often near N‑termini but also occurring mid‑sequence; catalytic residues themselves are typically not the peaks.	3.16	2
#10406	β-strand hydrophobic anchor detector	Structural detector for hydrophobic anchor residues on β‑strands—most often the earliest (N‑terminal) strand—of β‑sheet/β‑barrel domains, especially OB/cold‑shock folds, but also other β‑rich domains across diverse proteins; it highlights packing positions rather than catalytic or basic loop/helix sites.	3.09	2
#3103	SPT/LCB2 DFY motif detector	Residue-level detector that fires predominantly on a small set of conserved positions within the PLP-dependent aminotransferase fold of serine palmitoyltransferase / LCB2-family enzymes, with a single dominant peak on a conserved aromatic (Phe) in a "D/E-F-Y" motif upstream of the catalytic core.	3.05	2
#127	Proline-rich Ser/Thr-biased IDRs	Intrinsically disordered, low‑complexity proline‑rich segments enriched in Ser/Thr (polyproline, PxxP, and SP/TP motifs) that form eukaryotic regulatory tails/linkers/activation domains; the feature marks these S/T/P‑biased IDRs rather than folded domains.	3.02	2
#14927	Structural and domain boundary residues	Residues at structural and domain junctions: starts/ends of secondary-structure elements (especially helix starts and transmembrane-helix termini) and positions immediately preceding or following annotated domains, often adjacent to ligand/cofactor-binding regions	3.01	2
#6626	Catalytic-adjacent helix–strand loops	Short loop/turn motifs at secondary-structure junctions—especially helix–strand (alpha–beta or beta–alpha) connectors and occasional strand–strand loops—often centered on glycine or other small/polar residues, typically within catalytic domains. These positions commonly flank (but rarely coincide with) catalytic or substrate-binding sites, making them particularly prominent in glycoside hydrolases and other carbohydrate-active enzymes, yet they also appear in unrelated enzymes.	2.98	2

Feature	Label	Description	Δ activation	Iso act.	Canon act.	Iso prev.	Canon prev.
#1135	Homopolymeric low-complexity tracts	Compositionally biased, low-complexity sequence segments characterized by homopolymeric residue runs; the feature detects local stretches of repeated single amino acids regardless of chemistry (polar, basic, or hydrophobic), most often within disordered or unstructured contexts but also occasionally within folded domains where such runs occur.	-2.62	2.34	4.96	8	18
#6360	N-terminal low-complexity IDRs	Eukaryotic intrinsically disordered, low‑complexity N‑terminal tails enriched in Lys/Arg/Ser/Asp/Glu that precede structured domains of RNA biogenesis/translation and chromatin‑remodeling factors (nucleolar/ssu‑processome, spliceosome/DEAD‑box helicases, H2A.Z chaperones); these flexible segments are typical interaction/assembly regions.	-2.55	2.21	4.77	7	23
#4977	Strand-edge turn motifs	Short coil-to-β-strand transition motifs—beta-turns/strand-edge loops (often the N-termini of β-strands)—recurring across diverse folds and functions.	-2.33	6.12	8.45	11	19
#13334	N-terminal IDR boundary	Recognition of short, low-complexity, intrinsically disordered N-terminal tails immediately upstream of the first folded domain; these segments are often Ser/Thr/Pro/Gly/Ala-biased and sometimes extend a few residues into the initial helix or the very beginning of the first domain (domain boundary/disorder-to-order transition), especially in transcription regulators and co-regulators.	-2.31	2.68	5.00	6	25
#6484	Prion-like low-complexity IDRs	Polar low-complexity intrinsically disordered regions (IDRs)—especially Q/N-rich (prion-like) segments and S/T- and glycine-rich tracts with simple SG/TG/PG repeats—typically located in inter-domain linkers and terminal tails of eukaryotic proteins and often harboring Ser/Thr phosphorylation sites.	-1.81	2.32	4.13	9	6
#6016	Helix-biased internal methionine detector	Detector for methionine residues, firing on internal Met across diverse proteins with somewhat enhanced response when Met occurs in helical or low-complexity contexts; occasional hits at the initiator Met when embedded in a locally Met- or hydrophobic-rich N-terminus; weak cross-reactivity to other bulky hydrophobics (notably tryptophan).	+1.78	7.61	5.83	3	3
#14712	SPS N-terminal regulatory motif	A conserved N-terminal regulatory motif in plant sucrose-phosphate synthases (SPS), centered on a short ATR(N/S/P)xRERS / SPQERN-type sequence upstream of the catalytic glycosyltransferase core.	-1.68	4.98	6.66	9	11
#9332	Hydrophobic aliphatic core packing	Hydrophobic aliphatic residue packing: the feature marks individual Val/Ile (with Ala/Leu/Thr) at nonpolar, well-ordered positions in secondary structure (alpha-helices and beta-strands), frequently forming the hydrophobic core or lining/co-supporting ligand/nucleotide pockets across diverse folds and taxa.	-1.66	3.20	4.86	4	4
#512	Short functional domain segments	Short sequence segments distributed across diverse proteins, with peaks that often fall within structured catalytic, transporter, or fold-defining domains as well as occasional acidic/charged stretches and flexible linkers.	+1.61	3.43	1.82	10	5
#5022	Disordered zinc-finger linkers	Short, intrinsically disordered linker segments that flank or connect zinc‑binding domains—especially tandem zinc‑finger repeats (C2H2, RanBP2/CCCH, matrin‑type)—with selectivity for the immediate N‑terminal side or inter‑finger spacers, rather than the folded zinc‑binding cores or other structured domains; most common in eukaryotic chromatin/nuclear regulatory proteins.	-1.58	3.27	4.85	7	16
#13016	Acidic low-complexity IDRs	Acidic intrinsically disordered low-complexity regions (IDRs)—often terminal tails or linkers—i.e., long D/E-rich acidic tracts commonly found in nuclear/chromatin proteins, viral tegument/IE phosphoproteins, and cytoskeletal regulators	-1.57	4.74	6.31	13	21
#9627	Short Pro/Gly-rich strand-turn patches	Short, compositionally biased strand/turn segments that nucleate or flank brief secondary‑structure elements (typically beta‑strands with adjacent loops/turns, occasionally short helices), enriched in Pro and Gly together with aliphatic residues (Leu/Ile/Val) and frequent Ser/Thr; these patches occur both within folded beta‑sheet domains and in intrinsically disordered regions (often at coil↔secondary‑structure transitions), and can host linear motifs such as leucine‑rich nuclear export signals or mark the first structured residues after signal‑peptide cleavage.	-1.55	2.10	3.65	7	15
#13080	Phospho-acidic disordered tails	Acidic, serine-rich low-complexity intrinsically disordered regions (IDRs)—typically long N- or C-terminal tails enriched in Asp/Glu and Ser/Thr-Pro motifs and phosphoserine sites—i.e., phospho-acidic regulatory stretches rather than structured domains.	-1.42	4.12	5.54	5	15
#5076	N-terminal disordered pre-sequences	Intrinsic N-terminal pre-sequences and regulatory tails: extended, low-complexity, intrinsically disordered segments at protein termini—especially cleavable signal/transit peptides and propeptides, as well as noncleavable acidic/PST-rich regulatory tails that harbor PTM sites and linear binding motifs—marking the boundary before structured mature domains.	-1.39	2.38	3.78	43	64
#1501	Acidic phosphosite-rich IDRs	Low-complexity intrinsically disordered segments enriched in polar residues with embedded acidic/phospho-regulatory clusters, serving as interaction modules across diverse proteins (nuclear/chromatin/RNA-associated and also secreted)	-1.37	5.18	6.55	10	21
#1584	Acidic serine-rich disordered tails	Long acidic, serine-enriched intrinsically disordered low‑complexity regions (DE/S‑rich IDRs), typically found as internal or C‑terminal tails of chromatin- and transcription-associated eukaryotic proteins (and mimicked by large DNA viruses), often densely phosphorylated and depleted of bulky hydrophobics.	-1.36	2.59	3.95	12	25
#6205	Broad domain-level activation	A broad, low-amplitude sensor that activates across most of the sequence in folded proteins, with particular prominence in DEAD-box / SF1-SF2 RNA helicase ATP-binding domains. Activation is broadly distributed rather than localized to specific catalytic residues, and tends to be weaker on N-terminal targeting/transit peptides and cleavable leaders than on the mature chain.	-1.33	2.40	3.72	8	17
#13982	Bromodomain and HTH core signature	A eukaryotic nuclear recognition-module signature that targets compact all-alpha binding cores—most strongly bromodomains (acetyl-lysine reader pocket and adjoining helices) but also helix-turn-helix/winged-helix nucleic-acid-binding cores (e.g., La/ARID/ETS/IRF/HSF). The shared signal is a conserved hydrophobic/basic recognition element within these reader cores.	-1.24	2.11	3.36	4	7
#13122	Charged polar low-hydrophobicity segments	Compositionally biased, low-hydrophobicity segments enriched in charged and small polar residues (E, D, K, R, S, T; often with P/G), most often found as intrinsically disordered N‑terminal stretches or propeptides but also occurring as surface-exposed polar helices/β-strands within folded domains	-1.24	2.44	3.68	5	19
#10941	Amphipathic alpha-helical interaction motifs	Generic preference for well-ordered alpha-helical elements, with strongest response to amphipathic, interaction-mediating helices used across eukaryotic regulatory proteins (chromatin/transcription factors and signaling/scaffold proteins), including both short binding motifs (e.g., IQ and AKAP RII-binding helices) and multi-helix domains (e.g., SEC7, bromodomains, coiled-coils, EF-hand helices).	-1.24	3.58	4.82	12	14
#3970	TAFA conserved residue motifs	Residues at conserved positions within small secreted cysteine-containing proteins, particularly the TAFA/chemokine-like family, with additional sparse activations in folded enzymatic domains away from annotated catalytic residues.	-1.22	3.71	4.93	3	4
#14076	GARIN central LxLTR motif	A conserved central segment in Golgi-associated RAB2 interactor (GARIN) family proteins, characterized by a short "(L/V)xLTR"-like motif (e.g., LELTR, LVLTR) preceded by a basic/polar stretch (often K/R/S-rich).	-1.19	4.88	6.07	14	31
#8115	GNAT beta-strand core hydrophobics	Hydrophobic residues on conserved beta-strands that form the core of α/β folds, most characteristically the central beta-sheet of GNAT/NAT acetyltransferases lining the acetyl‑CoA/substrate-binding groove; the same signal appears at structurally analogous beta‑strand positions adjacent to catalytic or other functionally critical sites in diverse proteins, including non-enzymes such as ribosomal protein uL22.	-1.16	2.42	3.58	2	2
#5310	Catalytic Asp N-terminal strand	Short beta-strand or tight-loop elements that sit immediately N-terminal to catalytic metal-binding acidic residues (Asp/Glu) in nuclease active sites—especially RecB/RecB-like and VRR-NUC folds—and, more broadly, analogous beta-edge segments lining nucleotide/metal-binding pockets in other DNA-processing enzymes; peaks frequently center on glycine at a coil-to-beta transition.	-1.16	6.18	7.34	7	10
#10142	Transsulfuration N-terminal P[IVL][Y/F] motif	Family-specific sequence detector that fires on a conserved N-terminal "P-[IVL]-[Y/F]" stretch characteristic of PLP-dependent transsulfuration enzymes, with a secondary site near a C-terminal D/E-L-[IV]-R-[IL] segment.	-1.14	2.96	4.10	3	5
#13204	SRA/YDG DNA methylation reader	YDG/SRA domain of UHRF1-family and related RING-type E3 ubiquitin ligases involved in DNA methylation reading, with activation concentrated on the structured base-flipping/5-methylcytosine-binding region.	-1.06	2.67	3.73	13	23
#8939	N-terminal regulatory tail	N-terminal sequence tracts (often disordered or low-complexity, sometimes acidic/polar) within the first ~20-60 residues of diverse eukaryotic and viral proteins; a generic "regulatory/tethering" N-terminal tail feature.	-1.04	1.80	2.84	2	4
#10973	PDZ beta-sandwich GLGF loop	PDZ domains—specifically the β‑sandwich core and the conserved carboxylate‑binding loop (GLGF/GFGF/GGx) that engages C‑terminal PDZ‑binding motifs	-1.00	2.48	3.49	10	13
#14534	Unknown generic feature	Unknown generic feature	-4.91	9.70	14.60	160	181
#1803	Unknown generic feature	Unknown generic feature	-2.43	14.87	17.30	161	182

Feature	Label	Description	Activation	Prevalence
#2114	Chromodomain and integrase-proximal activation	A feature that activates broadly across chromodomain-containing proteins and other chromatin-associated factors, as well as on retrotransposon Gag-Pol polyproteins (in integrase-proximal regions). Activation is distributed widely along the chain with peaks tending to fall within or adjacent to chromodomain folds rather than on catalytic enzyme cores.	13.35	23
#5780	Conserved N-terminal beta-strand cores	Conserved β‑strand residues within β‑sheet cores—especially in OB/Cold‑shock–like β‑barrels and analogous β‑rich domains—most often at the first β‑strands near domain N‑termini; captures the structured strand face used widely in nucleic‑acid–binding modules and in diverse β‑sheet proteins	11.30	3
#13702	Regulatory low-complexity IDRs	Eukaryotic intrinsically disordered, low‑complexity regulatory segments (terminal tails and inter‑domain linkers) enriched in Pro/Ser/Thr/acidic composition and short linear motifs for modular protein–protein interactions—frequently including WW‑domain–binding PY/PPxY segments and PTM hotspots—with reduced but not absent activation within folded recognition/catalytic domains (WW, PTB/PID, chromo/chromoshadow, SET).	10.05	23
#15815	Basic N-terminal targeting patch	Short, basic/polar N‑terminal leader/transit segment immediately after the initiator methionine (positions ~3–6) — i.e., the positively charged/polar start of signal peptides and organelle transit peptides, and more generally low‑acidic, disordered N‑terminal patches (including occasional cysteine‑rich starts) used for targeting, export, rRNA binding, or membrane topology cues	9.70	4
#10704	N-terminal PEST-like IDRs	Low-complexity, often acidic/proline-rich intrinsically disordered N-terminal tails of intracellular eukaryotic proteins, frequently overlapping annotated PEST-like segments.	8.87	10
#4977	Strand-edge turn motifs	Short coil-to-β-strand transition motifs—beta-turns/strand-edge loops (often the N-termini of β-strands)—recurring across diverse folds and functions.	8.45	9
#5895	PDZ and chromatin readers	Eukaryote-biased feature marking scaffold/signaling PDZ-domain proteins and nuclear chromatin regulators (readers/writers/remodelers), with additional coverage of ubiquitin/SUMO-pathway E3s, polarity/Rho-pathway components, PP1 glycogen-targeting CBM21 proteins, and ATAT1 acetyltransferases; broad functional/subcellular coverage and low specificity in SwissProt.	7.82	2
#300	AT-hook-like basic IDRs	Arg/Lys-rich, glycine/proline-spaced intrinsically disordered segments in nuclear chromatin/transcription regulators—especially AT-hook–like RGR cores and RGG/GRG tracts—that provide nonspecific DNA minor-groove/chromatin association and targeting, typically in tails and linkers flanking structured domains.	7.36	7
#5310	Catalytic Asp N-terminal strand	Short beta-strand or tight-loop elements that sit immediately N-terminal to catalytic metal-binding acidic residues (Asp/Glu) in nuclease active sites—especially RecB/RecB-like and VRR-NUC folds—and, more broadly, analogous beta-edge segments lining nucleotide/metal-binding pockets in other DNA-processing enzymes; peaks frequently center on glycine at a coil-to-beta transition.	7.34	4
#8462	Acidic phospho-regulated IDR SLiMs	Short linear motifs embedded in intrinsically disordered, acidic Ser/Thr‑rich regions of nuclear proteins—often phospho‑regulated and frequently including SUMO‑interaction motifs—captured as hydrophobic cores (I/V/L/M) within low‑complexity acidic tracts that mediate transient interactions in DNA/RNA metabolism.	6.91	9
#3541	Flexible solvent-exposed loops/linkers	Generic structural signal for short, flexible, solvent‑exposed coil/loop and linker residues—especially at secondary‑structure transitions and inter‑domain boundaries—and for disordered signal/propeptide segments; not tied to a specific sequence motif or function, explaining its ubiquity across taxa and protein families	6.84	6
#10977	Early N-terminal disordered patch	Short N-terminal patch at the extreme N-terminus (around residues 5–10), capturing the first distinctive segment of preproteins/precursors and N-terminal disordered tails; residue composition is heterogeneous but frequently polar (Ser/Thr) and/or charged.	6.83	3
#8412	Valine-centered residue detector	Detector that fires on valine residues across diverse sequence contexts, including hydrophobic transmembrane helices and signal peptides as well as Val-containing tandem repeats (elastomeric Gly-rich lamprin-like repeats, Pro/Arg-rich disordered repeats) and isolated Val positions in soluble globular proteins.	6.82	4
#14712	SPS N-terminal regulatory motif	A conserved N-terminal regulatory motif in plant sucrose-phosphate synthases (SPS), centered on a short ATR(N/S/P)xRERS / SPQERN-type sequence upstream of the catalytic glycosyltransferase core.	6.66	2
#1501	Acidic phosphosite-rich IDRs	Low-complexity intrinsically disordered segments enriched in polar residues with embedded acidic/phospho-regulatory clusters, serving as interaction modules across diverse proteins (nuclear/chromatin/RNA-associated and also secreted)	6.55	11
#13016	Acidic low-complexity IDRs	Acidic intrinsically disordered low-complexity regions (IDRs)—often terminal tails or linkers—i.e., long D/E-rich acidic tracts commonly found in nuclear/chromatin proteins, viral tegument/IE phosphoproteins, and cytoskeletal regulators	6.31	9
#8237	Conserved structured domain peaks	A feature that activates within structured partner-recognition/DNA-binding domains and adjacent ordered segments of eukaryotic regulatory proteins, with peaks falling on conserved residues inside these domains rather than on flanking low-complexity stretches.	6.25	3
#13745	Hydrophobic secondary structure signal	Generic hydrophobic secondary-structure signal: activates on hydrophobic/aromatic side chains that form stable α-helices and β-strands—covering transmembrane helices, coiled-coils, and the hydrophobic cores of globular domains—while avoiding catalytic/metal-binding residues and disordered segments	6.21	3
#14076	GARIN central LxLTR motif	A conserved central segment in Golgi-associated RAB2 interactor (GARIN) family proteins, characterized by a short "(L/V)xLTR"-like motif (e.g., LELTR, LVLTR) preceded by a basic/polar stretch (often K/R/S-rich).	6.07	16
#14234	Ordered cores and transmembrane helices	Generic preference for ordered chain regions of folded proteins, with particularly strong responses in hydrophobic α-helices that span membranes; avoids signal peptides and low-confidence N-terminal precursor regions.	5.93	2
#10856	Short domain-boundary linkers	Short, flexible coil/linker segments at or flanking structured domains—especially domain boundaries, inter‑domain linkers, and proteolytic processing junctions (signal peptides/propeptides)—with occasional peaks in loops within the domains themselves; not broadly marking long intrinsically disordered regions.	5.84	3
#8139	Structured cores of genome regulators	Core residues of folded domains in eukaryotic genome-function proteins (chromatin-, DNA-, and RNA-associated factors, including transcriptional regulators, RNA-binding proteins, replication and repair factors), emphasizing beta-strand/loop elements of nucleic-acid–associated folds (e.g., B3 DNA-binding and RRM RNA-binding) and the PB1 oligomerization module; the feature marks conserved, well-structured domain cores and avoids long low-complexity/disordered regions.	5.74	3
#6178	Nuclear basic/polar low-complexity IDRs	Intrinsically disordered, low‑complexity regulatory segments of nuclear proteins—especially transcription factors/cofactors, chromatin regulators, RNA/splicing factors, and nuclear RING‑type E3 ligases—enriched in basic (Lys/Arg) and polar (Ser/Pro/Gln/Glu/Gly/Thr) tracts that serve as activation/repression, partner‑binding, or localization (NLS‑like) regions; typically outside folded DNA‑binding/catalytic domains and often overlapping phosphorylation sites or simple helices within IDRs.	5.70	7
#9000	Glutamate-biased acidic tract detector	Detector of glutamate identity and glutamate-enriched acidic tracts: strong activation on E residues, especially within acidic, low‑complexity/disordered regions; weaker, sporadic responses on D; largely domain-, function-, and taxonomy-agnostic.	5.66	8
#14895	Unknown generic feature	Unknown generic feature	20.17	23
#9214	Unknown generic feature	Unknown generic feature	17.88	23
#1803	Unknown generic feature	Unknown generic feature	17.30	23
#14534	Unknown generic feature	Unknown generic feature	14.60	21
#9194	Unknown generic feature	Unknown generic feature	13.19	21
#9005	Unknown generic feature	Unknown generic feature	9.39	23

Clinical variants

Differential region — lost N-terminus (canonical-only)

Pos (iso)	AA change	Consequence	Source	Clin. sig.	AF (gnomAD)	Impact	AlphaMissense	ESM-C ΔLLR	Link
—	V→V	intronic	gnomAD	—	2.74e-06	—	—	0.00	chr17-48076939-C-T
—	E→E	intronic	gnomAD	—	2.05e-06	—	—	0.00	chr17-48076945-T-C
—	E→E	intronic	gnomAD	—	1.37e-06	—	—	0.00	chr17-48076951-T-C
—	E→G	intronic	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.77)	-9.56	chr17-48076952-T-C
—	E→Q	intronic	gnomAD	—	1.37e-06	damaging	likely_pathogenic (0.61)	-9.81	chr17-48076956-C-G
—	E→Q	intronic	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.62)	-9.69	chr17-48076959-C-G
—	E→K	intronic	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.83)	-11.12	chr17-48076962-C-T
—	L→L	intronic	gnomAD	—	2.05e-06	—	—	0.00	chr17-48076963-T-C
—	V→V	intronic	gnomAD	—	1.37e-06	—	—	0.00	chr17-48076966-C-T
—	V→L	intronic	gnomAD	—	2.05e-06	damaging	likely_benign (0.30)	-7.78	chr17-48076968-C-A
—	V→M	intronic	gnomAD	—	2.74e-06	damaging	likely_benign (0.24)	-8.68	chr17-48076968-C-T
—	V→V	intronic	gnomAD	—	1.37e-06	—	—	0.00	chr17-48076975-C-T
—	V→G	intronic	gnomAD	—	6.85e-07	damaging	likely_benign (0.14)	-8.75	chr17-48076976-A-C
—	V→M	intronic	gnomAD	—	7.53e-06	damaging	likely_benign (0.13)	-8.37	chr17-48076977-C-T
—	K→N	intronic	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.58)	-9.00	chr17-48076978-T-A
—	—	intronic	gnomAD	—	1.37e-06	—	—	—	chr17-48076978-TTTC-T
—	K→I	intronic	gnomAD	—	6.84e-07	damaging	ambiguous (0.56)	-11.69	chr17-48076979-T-A
—	K→R	intronic	gnomAD	—	9.58e-06	damaging	likely_benign (0.12)	-8.94	chr17-48076979-T-C
—	K→*	intronic	gnomAD	—	6.84e-07	damaging	—	—	chr17-48076980-T-A
—	K→E	intronic	gnomAD	—	6.84e-07	damaging	ambiguous (0.42)	-9.69	chr17-48076980-T-C
—	K→N	intronic	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.84)	-9.87	chr17-48076981-C-A
—	K→R	intronic	gnomAD	—	6.84e-07	damaging	likely_benign (0.12)	-9.06	chr17-48076982-T-C
—	K→N	intronic	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.73)	-9.94	chr17-48076984-C-G
—	—	intronic	gnomAD	—	6.84e-07	—	—	—	chr17-48076984-CTTG-C
—	K→Q	intronic	gnomAD	—	1.37e-06	damaging	likely_benign (0.24)	-10.25	chr17-48076986-T-G
—	N→K	intronic	gnomAD	—	1.85e-05	damaging	likely_pathogenic (0.68)	-8.87	chr17-48076987-G-C
—	Q→Q	intronic	gnomAD	—	6.84e-07	—	—	0.00	chr17-48076990-T-C
—	K→K	intronic	gnomAD	—	2.74e-06	—	—	0.00	chr17-48076993-T-C
—	G→G	intronic	gnomAD	—	6.85e-07	—	—	0.00	chr17-48076999-C-A
—	G→V	intronic	gnomAD	—	6.85e-07	damaging	likely_pathogenic (0.88)	-9.25	chr17-48077000-C-A
—	G→W	intronic	gnomAD	—	6.85e-07	damaging	likely_pathogenic (0.97)	-12.31	chr17-48077001-C-A
—	M→I	intronic	gnomAD	—	1.37e-06	damaging	—	-10.94	chr17-48077002-C-G
—	M→I	intronic	gnomAD	—	6.85e-07	damaging	—	-10.94	chr17-48077002-C-T
—	M→T	intronic	gnomAD	—	6.85e-07	damaging	—	-11.50	chr17-48077003-A-G
—	M→L	intronic	gnomAD	—	6.85e-07	damaging	—	-11.19	chr17-48077004-T-G
—	N→K	intronic	ClinVar	Uncertain significance	—	damaging	likely_pathogenic (0.68)	-8.87	ClinVar:3827926
—	V→V	intronic	COSMIC	—	—	—	—	0.00	COSV99848141
—	E→Q	intronic	COSMIC	—	—	damaging	likely_pathogenic (0.95)	-11.25	COSV99848313
—	E→K	intronic	COSMIC	—	—	damaging	likely_pathogenic (0.83)	-9.56	COSV56681509
—	V→L	intronic	COSMIC	—	—	damaging	likely_benign (0.20)	-8.06	COSV56682280
—	Q→K	intronic	COSMIC	—	—	damaging	ambiguous (0.37)	-10.00	COSV56682149
—	—	intronic	COSMIC	—	—	damaging	—	—	COSV56681712
—	—	intronic	COSMIC	—	—	damaging	—	—	COSV56681499
—	M→V	intronic	COSMIC	—	—	damaging	—	-11.44	COSV56682591

44 variants in the differential region.

Shared canonical core — sequence common to canonical and isoform; AlphaMissense applies here

Pos (iso)	AA change	Consequence	Source	Clin. sig.	AF (gnomAD)	Impact	AlphaMissense	ESM-C ΔLLR	Link
0	V→V	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48076936-C-A
0	V→V	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48076936-C-G
1	E→V	missense_variant	ClinVar	—	—	damaging	likely_pathogenic (1.00)	-11.31	ClinVar:4423332
2	K→N	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.99)	-9.37	chr17-48076930-T-A
4	L→L	synonymous_variant	gnomAD	—	6.84e-06	—	—	0.00	chr17-48076924-G-A
4	L→I	missense_variant	COSMIC	—	—	damaging	likely_benign (0.28)	-9.56	COSV56682110
5	D→H	missense_variant	gnomAD	—	1.37e-06	damaging	likely_pathogenic (0.94)	-7.89	chr17-48076923-C-G
5	D→N	missense_variant	gnomAD	—	1.85e-05	damaging	likely_pathogenic (0.56)	-4.01	chr17-48076923-C-T
6	R→H	missense_variant	gnomAD	—	2.74e-06	damaging	likely_pathogenic (0.79)	-7.03	chr17-48076919-C-T
6	R→C	missense_variant	gnomAD	—	1.23e-05	damaging	likely_pathogenic (0.87)	-7.12	chr17-48076920-G-A
7	R→Q	missense_variant	gnomAD	—	2.05e-06	damaging	likely_pathogenic (0.99)	-9.25	chr17-48076916-C-T
7	R→R	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48076917-G-T
7	R→R	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56682056
7	R→*	stop_gained	COSMIC	—	—	LoF	—	—	COSV56681749
8	V→V	synonymous_variant	gnomAD	—	2.05e-06	—	—	0.00	chr17-48076912-C-T
8	V→A	missense_variant	gnomAD	—	1.37e-06	damaging	likely_pathogenic (0.92)	-7.43	chr17-48076913-A-G
9	V→V	synonymous_variant	gnomAD	—	1.37e-06	—	—	0.00	chr17-48076909-T-C
9	V→L	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.76)	-6.96	chr17-48076911-C-A
10	K→K	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48076906-C-T
11	G→G	synonymous_variant	gnomAD	—	3.42e-06	—	—	0.00	chr17-48076903-G-A
11	G→S	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.96)	-7.97	chr17-48076905-C-T
11	G→S	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.96)	-7.97	COSV99847936
12	K→R	missense_variant	gnomAD	—	2.05e-06	—	likely_benign (0.09)	-5.18	chr17-48076901-T-C
14	E→D	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (1.00)	-7.72	chr17-48076894-C-G
14	E→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-10.19	COSV56682856
15	Y→Y	synonymous_variant	gnomAD	—	1.71e-05	—	—	0.00	chr17-48076891-G-A
16	L→L	synonymous_variant	gnomAD	—	3.43e-06	—	—	0.00	chr17-48076888-G-A
16	L→R	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (0.84)	-9.56	chr17-48076889-A-C
16	L→F	missense_variant	COSMIC	—	—	—	ambiguous (0.35)	-6.53	COSV56681814
17	L→L	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48076885-T-G
18	K→K	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48076882-C-T
18	K→E	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (1.00)	-11.19	chr17-48076884-T-C
21	G→G	synonymous_variant	gnomAD	—	4.39e-05	—	—	0.00	chr17-48076873-T-C
22	F→F	synonymous_variant	gnomAD	—	6.86e-07	—	—	0.00	chr17-48076870-G-A
22	F→L	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-10.37	COSV56682209
25	E→K	missense_variant	gnomAD	—	7.10e-07	damaging	likely_pathogenic (0.84)	-9.50	chr17-48076177-C-T
25	E→Q	missense_variant	ClinVar	—	—	damaging	likely_pathogenic (0.60)	-11.12	ClinVar:4423331
25	E→Q	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.60)	-11.12	COSV56681530
26	D→H	missense_variant	gnomAD	—	7.06e-07	damaging	likely_pathogenic (0.97)	-12.12	chr17-48076174-C-G
27	N→D	missense_variant	gnomAD	—	1.41e-06	damaging	likely_pathogenic (0.97)	-10.37	chr17-48076171-T-C
27	N→S	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.59)	-9.00	COSV56681968
30	E→D	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-10.56	COSV99848274
32	E→D	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.96)	-8.69	COSV99848151
34	N→N	synonymous_variant	gnomAD	—	1.38e-06	—	—	0.00	chr17-48076148-G-A
35	L→L	synonymous_variant	gnomAD	—	1.38e-06	—	—	0.00	chr17-48076147-G-A
38	P→P	synonymous_variant	gnomAD	—	1.51e-05	—	—	0.00	chr17-48076136-G-A
38	P→P	synonymous_variant	gnomAD	—	6.88e-07	—	—	0.00	chr17-48076136-G-C
38	P→P	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV99847948
39	D→N	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.96)	-8.31	COSV99847954
40	L→L	synonymous_variant	gnomAD	—	1.23e-05	—	—	0.00	chr17-48076130-G-A
42	A→A	synonymous_variant	gnomAD	—	5.48e-06	—	—	0.00	chr17-48076124-A-G
42	A→A	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48076124-A-T
42	A→G	missense_variant	gnomAD	—	1.37e-06	damaging	ambiguous (0.38)	-9.94	chr17-48076125-G-C
45	L→L	synonymous_variant	gnomAD	—	1.37e-06	—	—	0.00	chr17-48076115-C-T
45	L→L	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48076117-G-A
45	L→L	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV105045650
46	Q→*	stop_gained	COSMIC	—	—	LoF	—	—	COSV99848158
47	S→L	missense_variant	gnomAD	—	2.74e-06	damaging	likely_benign (0.27)	-9.37	chr17-48076110-G-A
47	S→L	missense_variant	ClinVar	Uncertain significance	—	damaging	likely_benign (0.27)	-9.37	ClinVar:4648788
48	Q→R	missense_variant	gnomAD	—	6.85e-07	—	likely_benign (0.33)	-7.47	chr17-48076107-T-C
48	Q→*	stop_gained	COSMIC	—	—	LoF	—	—	COSV99848270
49	K→R	missense_variant	gnomAD	—	6.85e-07	—	likely_benign (0.12)	-6.44	chr17-48076104-T-C
49	K→Q	missense_variant	ClinVar	Uncertain significance	—	damaging	likely_benign (0.33)	-8.75	ClinVar:4531663
50	T→A	missense_variant	gnomAD	—	6.85e-07	—	likely_benign (0.06)	-6.06	chr17-48076102-T-C
52	H→P	missense_variant	gnomAD	—	4.79e-06	—	likely_benign (0.11)	-7.21	chr17-48076095-T-G
54	T→R	missense_variant	gnomAD	—	2.74e-06	damaging	likely_benign (0.23)	-7.90	chr17-48076089-G-C
55	D→G	missense_variant	gnomAD	—	6.84e-07	—	likely_benign (0.10)	-6.27	chr17-48076086-T-C
55	D→N	missense_variant	gnomAD	—	6.84e-07	—	likely_benign (0.10)	-6.15	chr17-48076087-C-T
55	D→G	missense_variant	ClinVar	Uncertain significance	—	—	likely_benign (0.10)	-6.27	ClinVar:4220041
55	D→N	missense_variant	ClinVar	Uncertain significance	—	—	likely_benign (0.10)	-6.15	ClinVar:4220044
56	K→K	synonymous_variant	gnomAD	—	4.04e-05	—	—	0.00	chr17-48076082-T-C
56	K→I	missense_variant	gnomAD	—	6.84e-07	damaging	ambiguous (0.43)	-10.75	chr17-48076083-T-A
56	K→I	missense_variant	ClinVar	Uncertain significance	—	damaging	ambiguous (0.43)	-10.75	ClinVar:4220042
57	S→S	synonymous_variant	gnomAD	—	4.79e-06	—	—	0.00	chr17-48076079-T-G
58	E→K	missense_variant	COSMIC	—	—	damaging	likely_benign (0.26)	-8.68	COSV99848247
59	G→R	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.58)	-8.76	chr17-48076075-C-G
59	G→R	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.58)	-8.76	COSV56682528
62	R→H	missense_variant	gnomAD	—	7.53e-06	damaging	likely_pathogenic (0.89)	-9.31	chr17-48076065-C-T
62	R→C	missense_variant	gnomAD	—	6.16e-06	damaging	likely_pathogenic (0.96)	-9.31	chr17-48076066-G-A
62	R→H	missense_variant	ClinVar	Uncertain significance	—	damaging	likely_pathogenic (0.89)	-9.31	ClinVar:2290145
62	R→H	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.89)	-9.31	COSV56682901
62	R→C	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.96)	-9.31	COSV56682920
63	K→R	missense_variant	gnomAD	—	8.90e-06	damaging	likely_benign (0.11)	-7.87	chr17-48076062-T-C
64	A→T	missense_variant	gnomAD	—	1.37e-06	—	likely_benign (0.08)	-6.34	chr17-48076060-C-T
64	A→T	missense_variant	ClinVar	Uncertain significance	—	—	likely_benign (0.08)	-6.34	ClinVar:4220043
65	D→G	missense_variant	gnomAD	—	6.85e-07	damaging	likely_benign (0.15)	-8.36	chr17-48076056-T-C
66	S→A	missense_variant	gnomAD	—	6.85e-07	damaging	likely_benign (0.06)	-9.87	chr17-48076054-A-C
66	S→T	missense_variant	gnomAD	—	1.37e-06	—	likely_benign (0.05)	-7.31	chr17-48076054-A-T
70	D→V	missense_variant	gnomAD	—	1.37e-06	damaging	likely_benign (0.13)	-9.56	chr17-48076041-T-A
70	D→V	missense_variant	ClinVar	Uncertain significance	—	damaging	likely_benign (0.13)	-9.56	ClinVar:2307098
70	D→N	missense_variant	COSMIC	—	—	damaging	likely_benign (0.11)	-7.93	COSV56682563
71	K→K	synonymous_variant	gnomAD	—	1.37e-06	—	—	0.00	chr17-48076037-C-T
71	K→R	missense_variant	gnomAD	—	2.05e-06	—	likely_benign (0.09)	-4.90	chr17-48076038-T-C
71	K→E	missense_variant	gnomAD	—	6.85e-07	damaging	likely_benign (0.18)	-11.05	chr17-48076039-T-C
71	K→K	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56682520
71	K→N	missense_variant	COSMIC	—	—	damaging	likely_benign (0.29)	-9.30	COSV99848170
72	G→G	synonymous_variant	gnomAD	—	2.06e-06	—	—	0.00	chr17-48076034-T-C
72	—	frameshift_variant	gnomAD	—	1.37e-06	LoF	—	—	chr17-48076035-CCCTT-C
72	G→R	missense_variant	gnomAD	—	2.74e-06	damaging	ambiguous (0.54)	-7.55	chr17-48076036-C-T
73	E→E	synonymous_variant	gnomAD	—	6.86e-07	—	—	0.00	chr17-48076031-C-T
73	E→Q	missense_variant	COSMIC	—	—	damaging	likely_benign (0.23)	-8.62	COSV99848203
74	E→D	missense_variant	gnomAD	—	6.86e-07	—	likely_benign (0.05)	-5.84	chr17-48076028-C-G
75	S→S	synonymous_variant	gnomAD	—	4.81e-06	—	—	0.00	chr17-48076025-G-A
75	S→G	missense_variant	gnomAD	—	6.86e-07	—	likely_benign (0.06)	-5.94	chr17-48076027-T-C
75	S→S	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV99848275
77	P→P	synonymous_variant	gnomAD	—	2.07e-06	—	—	0.00	chr17-48076019-T-C
77	P→L	missense_variant	gnomAD	—	1.38e-06	—	likely_benign (0.09)	-6.30	chr17-48076020-G-A
79	K→N	missense_variant	gnomAD	—	6.90e-07	damaging	likely_pathogenic (0.93)	-10.37	chr17-48076013-C-A
79	K→K	synonymous_variant	gnomAD	—	1.38e-06	—	—	0.00	chr17-48076013-C-T
80	K→N	missense_variant	gnomAD	—	6.91e-07	damaging	likely_pathogenic (0.91)	-10.25	chr17-48076010-C-G
80	K→R	missense_variant	gnomAD	—	1.38e-06	—	likely_benign (0.09)	-5.37	chr17-48076011-T-C
80	K→N	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.91)	-10.25	COSV56681336
80	K→N	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.91)	-10.25	COSV99848297
81	—	inframe_deletion	gnomAD	—	2.77e-06	—	—	—	chr17-48076007-TTTC-T
81	K→R	missense_variant	gnomAD	—	6.92e-07	—	likely_benign (0.09)	-6.75	chr17-48076008-T-C
82	E→G	missense_variant	gnomAD	—	6.92e-07	damaging	likely_benign (0.33)	-8.81	chr17-48076005-T-C
83	E→V	missense_variant	gnomAD	—	1.39e-06	damaging	likely_benign (0.30)	-8.24	chr17-48076002-T-A
83	E→Q	missense_variant	gnomAD	—	6.94e-07	damaging	ambiguous (0.43)	-8.99	chr17-48076003-C-G
84	S→S	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48075098-T-A
84	S→L	missense_variant	gnomAD	—	6.85e-07	—	likely_benign (0.08)	-6.09	chr17-48075099-G-A
85	E→A	missense_variant	gnomAD	—	6.85e-07	damaging	ambiguous (0.50)	-9.43	chr17-48075096-T-G
87	P→S	missense_variant	gnomAD	—	6.84e-07	—	ambiguous (0.53)	-5.76	chr17-48075091-G-A
87	P→Q	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.61)	-7.20	COSV106082017
87	P→S	missense_variant	COSMIC	—	—	—	ambiguous (0.53)	-5.76	COSV56682997
88	R→Q	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.92)	-8.69	chr17-48075087-C-T
88	R→*	stop_gained	gnomAD	—	2.05e-06	LoF	—	—	chr17-48075088-G-A
88	R→*	stop_gained	COSMIC	—	—	LoF	—	—	COSV56682269
90	F→S	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (1.00)	-10.44	chr17-48075081-A-G
91	A→A	synonymous_variant	gnomAD	—	1.37e-06	—	—	0.00	chr17-48075077-A-C
91	A→A	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48075077-A-G
92	R→Q	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.99)	-8.12	chr17-48075075-C-T
92	R→*	stop_gained	gnomAD	—	6.84e-07	LoF	—	—	chr17-48075076-G-A
92	R→R	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV107309107
92	R→L	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-10.37	COSV99847942
92	R→Q	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.99)	-8.12	COSV56683114
92	R→*	stop_gained	COSMIC	—	—	LoF	—	—	COSV104387334
93	G→D	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.89)	-9.62	COSV105045685
95	E→K	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.87)	-7.54	chr17-48075067-C-T
95	E→E	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56681442
96	P→P	synonymous_variant	gnomAD	—	1.97e-04	—	—	0.00	chr17-48075062-C-T
96	P→L	missense_variant	gnomAD	—	7.52e-06	damaging	likely_pathogenic (1.00)	-10.81	chr17-48075063-G-A
96	P→P	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV99848187
96	P→Q	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-12.12	COSV56682499
96	P→S	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-9.69	COSV99848079
97	E→D	missense_variant	gnomAD	—	1.37e-06	damaging	likely_pathogenic (0.92)	-9.06	chr17-48075059-C-A
97	E→E	synonymous_variant	gnomAD	—	1.37e-06	—	—	0.00	chr17-48075059-C-T
97	E→D	missense_variant	ClinVar	Uncertain significance	—	damaging	likely_pathogenic (0.92)	-9.06	ClinVar:4648787
97	E→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-12.12	COSV56681862
98	R→R	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48075056-C-T
98	R→Q	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.98)	-7.87	COSV56682101
98	R→L	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.99)	-10.12	COSV99848174
99	I→V	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.96)	-7.69	chr17-48075055-T-C
101	G→A	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-12.44	COSV56682437
103	T→T	synonymous_variant	gnomAD	—	2.74e-06	—	—	0.00	chr17-48075041-T-C
105	S→S	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48075035-G-A
106	S→S	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56681832
108	E→Q	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.92)	-10.00	chr17-48075028-C-G
109	L→L	synonymous_variant	gnomAD	—	9.59e-06	—	—	0.00	chr17-48075023-G-A
110	M→L	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (0.91)	-10.25	chr17-48075022-T-A
110	M→V	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (0.99)	-11.50	chr17-48075022-T-C
110	—	inframe_deletion	COSMIC	—	—	—	—	—	COSV56681204
111	F→F	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48075017-G-A
112	L→P	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (1.00)	-13.06	chr17-48075015-A-G
112	L→L	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV99848148
112	L→L	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56681918
113	M→I	missense_variant	gnomAD	—	6.86e-07	damaging	likely_pathogenic (0.97)	-8.12	chr17-48075011-C-A
113	M→T	missense_variant	gnomAD	—	6.86e-07	damaging	likely_pathogenic (1.00)	-11.81	chr17-48075012-A-G
114	K→K	synonymous_variant	gnomAD	—	6.86e-07	—	—	0.00	chr17-48075008-T-C
114	K→T	missense_variant	gnomAD	—	6.86e-07	damaging	likely_pathogenic (1.00)	-11.87	chr17-48075009-T-G
116	K→R	missense_variant	gnomAD	—	8.28e-06	—	likely_benign (0.14)	-6.94	chr17-48071577-T-C
117	N→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.89)	-8.94	COSV99848229
118	S→F	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.99)	-10.37	COSV56681364
121	A→A	synonymous_variant	gnomAD	—	6.87e-07	—	—	0.00	chr17-48071561-A-G
122	D→D	synonymous_variant	gnomAD	—	6.87e-07	—	—	0.00	chr17-48071558-G-A
124	V→L	missense_variant	gnomAD	—	6.86e-07	damaging	likely_pathogenic (1.00)	-11.25	chr17-48071554-C-G
126	A→A	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48071546-G-A
126	A→D	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (1.00)	-12.00	chr17-48071547-G-T
126	A→V	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-10.62	COSV99848117
128	E→*	stop_gained	gnomAD	—	6.85e-07	LoF	—	—	chr17-48071542-C-A
128	E→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.99)	-10.94	COSV56681808
130	N→S	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.91)	-12.44	chr17-48071535-T-C
131	V→F	missense_variant	gnomAD	—	2.74e-06	damaging	likely_pathogenic (0.57)	-8.73	chr17-48071533-C-A
131	V→V	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56681933
132	K→K	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56682664
133	C→C	synonymous_variant	gnomAD	—	1.37e-06	—	—	0.00	chr17-48071525-G-A
133	C→S	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (1.00)	-5.97	chr17-48071526-C-G
134	P→L	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (1.00)	-10.62	chr17-48071523-G-A
135	Q→Q	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48071519-C-T
135	Q→*	stop_gained	gnomAD	—	6.84e-07	LoF	—	—	chr17-48071521-G-A
136	V→F	missense_variant	gnomAD	—	2.05e-06	damaging	likely_pathogenic (0.99)	-12.05	chr17-48071518-C-A
138	I→I	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56681722
138	I→T	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (1.00)	-11.06	COSV56682067
139	S→S	synonymous_variant	gnomAD	—	2.05e-06	—	—	0.00	chr17-48071507-G-T
140	F→F	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48071504-G-A
141	Y→Y	synonymous_variant	gnomAD	—	1.37e-06	—	—	0.00	chr17-48071501-A-G
141	Y→C	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (1.00)	-11.94	chr17-48071502-T-C
144	R→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.99)	-11.06	COSV56682552
146	T→T	synonymous_variant	gnomAD	—	4.11e-06	—	—	0.00	chr17-48071486-C-T
146	T→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.99)	-13.94	COSV56681836
148	H→H	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48071480-A-G
149	S→S	synonymous_variant	gnomAD	—	6.84e-07	—	—	0.00	chr17-48071477-G-A
149	S→F	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.97)	-11.12	chr17-48071478-G-A
149	S→A	missense_variant	gnomAD	—	6.84e-07	damaging	likely_benign (0.27)	-9.06	chr17-48071479-A-C
149	S→P	missense_variant	gnomAD	—	6.84e-07	damaging	likely_pathogenic (0.98)	-11.81	chr17-48071479-A-G
149	S→T	missense_variant	gnomAD	—	6.84e-07	damaging	ambiguous (0.44)	-10.19	chr17-48071479-A-T
150	Y→Y	synonymous_variant	gnomAD	—	2.94e-05	—	—	0.00	chr17-48071474-G-A
150	Y→*	stop_gained	gnomAD	—	6.85e-07	LoF	—	—	chr17-48071474-G-T
151	P→S	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (0.58)	-8.75	chr17-48071473-G-A
151	P→S	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.58)	-8.75	COSV108798400
152	S→S	synonymous_variant	gnomAD	—	4.11e-06	—	—	0.00	chr17-48071468-C-T
152	S→L	missense_variant	gnomAD	—	2.05e-06	damaging	likely_benign (0.21)	-8.42	chr17-48071469-G-A
152	S→L	missense_variant	ClinVar	Uncertain significance	—	damaging	likely_benign (0.21)	-8.42	ClinVar:3138046
152	S→S	synonymous_variant	COSMIC	—	—	—	—	0.00	COSV56681272
152	S→*	stop_gained	COSMIC	—	—	LoF	—	—	COSV99848014
153	E→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.75)	-12.00	COSV104555665
154	D→E	missense_variant	gnomAD	—	4.80e-06	—	likely_benign (0.09)	-5.24	chr17-48071462-A-C
154	D→D	synonymous_variant	gnomAD	—	6.85e-07	—	—	0.00	chr17-48071462-A-G
154	D→Y	missense_variant	gnomAD	—	6.85e-07	damaging	likely_pathogenic (0.71)	-11.56	chr17-48071464-C-A
154	D→N	missense_variant	gnomAD	—	1.37e-06	damaging	likely_benign (0.31)	-10.18	chr17-48071464-C-T
154	D→E	missense_variant	ClinVar	Uncertain significance	—	—	likely_benign (0.09)	-5.24	ClinVar:2517719
156	—	inframe_deletion	gnomAD	—	2.06e-06	—	—	—	chr17-48071456-GTCA-G
156	D→N	missense_variant	COSMIC	—	—	damaging	likely_benign (0.19)	-8.62	COSV99848218
157	K→N	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.72)	-9.62	COSV99848111
157	—	frameshift_variant	COSMIC	—	—	LoF	—	—	COSV56682928
158	K→*	stop_gained	gnomAD	—	6.85e-07	LoF	—	—	chr17-48071452-T-A
159	D→V	missense_variant	gnomAD	—	6.86e-07	damaging	ambiguous (0.45)	-9.47	chr17-48071448-T-A
159	—	frameshift_variant	gnomAD	—	6.86e-07	LoF	—	—	chr17-48071449-C-CT
159	—	frameshift_variant	gnomAD	—	6.86e-07	LoF	—	—	chr17-48071449-CTTTT-C
159	D→H	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.73)	-10.72	COSV56682228
159	D→Y	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.65)	-9.97	COSV56681987
160	—	frameshift_variant	gnomAD	—	6.86e-07	LoF	—	—	chr17-48071445-TC-T
160	D→Y	missense_variant	gnomAD	—	1.37e-06	damaging	likely_pathogenic (0.68)	-10.43	chr17-48071446-C-A
160	D→N	missense_variant	gnomAD	—	6.86e-07	—	likely_benign (0.27)	-7.43	chr17-48071446-C-T
160	—	frameshift_variant	gnomAD	—	6.86e-07	LoF	—	—	chr17-48071446-CA-C
162	N→K	missense_variant	gnomAD	—	6.87e-07	damaging	likely_pathogenic (0.68)	-7.21	chr17-48071438-G-C
162	—	frameshift_variant	gnomAD	—	1.37e-06	LoF	—	—	chr17-48071439-TTCTTG-T
162	N→K	missense_variant	COSMIC	—	—	damaging	likely_pathogenic (0.68)	-7.21	COSV56682095

237 variants in the shared canonical core.

LoF = frameshift / stop-gain / splice-disrupting — inherently loss-of-function, flagged by consequence (AlphaMissense and ESM-C score only missense/substitutions, so they are blank here by design, not by absence of impact). AlphaMissense is computed in the canonical reading frame, so it scores the shared core but reads N/A across an isoform-unique extension — use ESM-C ΔLLR there.

CBX1 · ENST00000225603.9

Folding

Evidence — click any tile for the differential-region detail

Comparison

Comparison

Comparison

Comparison

Comparison

Comparison

Details

Comparison

Comparison

Comparison

Comparison

Comparison

Comparison

Comparison

Elements and coordinates

Below threshold

Comparison

Comparison

Part 1 · Global feature comparison

Isoform-only features — 20 total (prevalence ≥ 2)

Canonical-only features — 96 total (prevalence ≥ 2)

Shared features by |Δ| activation — 859 total (prevalence ≥ 2)

Part 2 · Differential coordinates

Unique-region features — 203 distinct (prevalence ≥ 2)

Clinical variants

Differential region — lost N-terminus (canonical-only)

Shared canonical core — sequence common to canonical and isoform; AlphaMissense applies here