Predicted protein targets (top 20)
| gene | UniProt | supporting neighbours | confidence | |
|---|---|---|---|---|
| ▸ | GRM5 | P41594 | 7/20 | 0.53 |
| ▸ | RAB9A | P51151 | 4/20 | 0.52 |
| ▸ | SMN1; SMN2 | Q16637 | 4/20 | 0.52 |
| ▸ | MAPT | P10636 | 4/20 | 0.52 |
| ▸ | NPC1 | O15118 | 3/20 | 0.52 |
| ▸ | AHR | P35869 | 1/20 | 0.52 |
| ▸ | JAK2 | O60674 | 4/20 | 0.51 |
| ▸ | JAK1 | P23458 | 2/20 | 0.51 |
| ▸ | TYK2 | P29597 | 2/20 | 0.51 |
| ▸ | JAK3 | P52333 | 2/20 | 0.51 |
| ▸ | MAP4K4 | O95819 | 1/20 | 0.51 |
| ▸ | GSK3B | P49841 | 1/20 | 0.51 |
| ▸ | ALDH1A1 | P00352 | 4/20 | 0.49 |
| ▸ | HPGD | P15428 | 2/20 | 0.49 |
| ▸ | LMNA | P02545 | 1/20 | 0.49 |
| ▸ | ASIC3 | Q9UHC3 | 1/20 | 0.49 |
| ▸ | KMT2A | Q03164 | 2/20 | 0.46 |
| ▸ | MEN1 | O00255 | 1/20 | 0.46 |
| ▸ | KCNH2 | Q12809 | 1/20 | 0.46 |
| ▸ | HTT | P42858 | 1/20 | 0.45 |
Click a target to see other patent compounds predicted against it — the reverse direction, in place.
Similar compounds — the chemically nearest patent molecules
Nearest neighbours by Morgan-fingerprint cosine across the patent-compound collection, with each neighbour's top predicted target and the predicted targets it shares with this molecule.
| Compound | similarity | top predicted | shared targets | |
|---|---|---|---|---|
| SCHEMBL31247663 | 0.82 | JAK2 (0.52) | GRM5JAK2JAK1TYK2JAK3 | |
| SCHEMBL31247520 | 0.80 | GRM5 (0.54) | GRM5MAPTJAK1TYK2ALDH1A1 | |
| SCHEMBL31247541 | 0.80 | JAK2 (0.57) | JAK2JAK1TYK2JAK3MAP4K4 | |
| SCHEMBL31247714 | 0.80 | JAK2 (0.54) | JAK2JAK1TYK2JAK3MAP4K4 | |
| SCHEMBL31247774 | 0.79 | GRM5 (0.84) | GRM5ASIC3KMT2AHTT | |
| SCHEMBL31247576 | 0.76 | GRM5 (0.55) | GRM5RAB9ASMN1; SMN2NPC1ALDH1A1 | |
| SCHEMBL31247639 | 0.75 | GRM5 (0.62) | GRM5ASIC3HTT | |
| SCHEMBL31247511 | 0.75 | TYK2 (0.53) | RAB9ASMN1; SMN2MAPTNPC1AHR | |
| SCHEMBL29421243 | 0.74 | MAPT (0.62) | GRM5RAB9ASMN1; SMN2MAPTNPC1 | |
| SCHEMBL25289695 | 0.73 | MAPT (0.56) | RAB9ASMN1; SMN2MAPTNPC1AHR |
Similarity is cosine over the 2,048-bit Morgan fingerprint (≈ Tanimoto). Identical fingerprints score 1.00.
Patent provenance — the patents this molecule appears in, and who filed them
Claimed or disclosed in 6 patents. claimed = in the patent's claims; disclosed = body only.
| Patent | Title | Assignee | Published | Priority | Filing | Country | Status |
|---|---|---|---|---|---|---|---|
| EP-4719394-A2 | INHIBITORS OF TYK2 | Atomwise Inc. (US) | 2026-04-08 | — | — | EP | disclosed |
| US-20260048051-A1 | TREATMENT OF INFLAMMATORY BOWEL DISEASE | ATOMWISE INC (US) | 2026-02-19 | — | — | US | disclosed |
| US-12358904-B2 | Inhibitors of TYK2 | Atomwise Inc. (US) | 2025-07-15 | — | — | US | disclosed |
| US-20240425484-A1 | INHIBITORS OF TYK2 | Atomwise Inc. | 2024-12-26 | — | — | US | disclosed |
| US-20240417396-A1 | INHIBITORS OF TYK2 | Atomwise Inc. | 2024-12-19 | — | — | US | disclosed |
| WO-2024250010-A2 | INHIBITORS OF TYK2 | Atomwise Inc. (US) | 2024-12-05 | — | — | WO | disclosed |
Patent text — is the patent's own abstract consistent with the prediction?
For each of this compound's patents that has machine-readable text (4 of them — usually the abstract, not the full specification), we ask MedCPT which protein the text reads most about, and where the chemistry-predicted target lands among 4885 human targets. A high rank means the patent's own wording is consistent with the prediction — a weak, independent signal, not proof of activity.
| Patent | Title | Text reads most about | Predicted target · text-rank |
|---|---|---|---|
| US-20240417396-A1 | INHIBITORS OF TYK2 | TYK2, LCK, JAK2 | GRM5 2396/4885RAB9A 3603/4885SMN1; SMN2 733/4885 |
| US-20260048051-A1 | TREATMENT OF INFLAMMATORY BOWEL DISEASE | TYK2, FRK, DYRK2 | GRM5 1437/4885RAB9A 1986/4885SMN1; SMN2 1866/4885 |
| US-12358904-B2 | Inhibitors of TYK2 | TYK2, LCK, JAK2 | GRM5 2396/4885RAB9A 3603/4885SMN1; SMN2 733/4885 |
| US-20240425484-A1 | INHIBITORS OF TYK2 | TYK2, LCK, JAK2 | GRM5 2396/4885RAB9A 3603/4885SMN1; SMN2 733/4885 |
“Text reads most about” is the patent abstract's nearest protein in MedCPT space (background-debiased). Only ~1.4% of patents have machine-readable text, so most compounds won't have this panel.