Predicted protein targets (top 17)
| gene | UniProt | supporting neighbours | confidence | |
|---|---|---|---|---|
| ▸ | SYK | P43405 | 6/20 | 0.58 |
| ▸ | NOTUM | Q6P988 | 1/20 | 0.46 |
| ▸ | IDO1 | P14902 | 1/20 | 0.46 |
| ▸ | LOXL2 | Q9Y4K0 | 2/20 | 0.42 |
| ▸ | TP53 | P04637 | 1/20 | 0.42 |
| ▸ | BIRC5 | O15392 | 1/20 | 0.41 |
| ▸ | LOX | P28300 | 1/20 | 0.41 |
| ▸ | PTGS2 | P35354 | 2/20 | 0.40 |
| ▸ | PTGS1 | P23219 | 1/20 | 0.40 |
| ▸ | MAP4K4 | O95819 | 1/20 | 0.40 |
| ▸ | RAB9A | P51151 | 2/20 | 0.40 |
| ▸ | NPC1 | O15118 | 1/20 | 0.40 |
| ▸ | ALDH1A1 | P00352 | 1/20 | 0.39 |
| ▸ | MAPT | P10636 | 1/20 | 0.39 |
| ▸ | HPGD | P15428 | 1/20 | 0.39 |
| ▸ | HK1 | P19367 | 1/20 | 0.39 |
| ▸ | HKDC1 | Q2TB90 | 1/20 | 0.39 |
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 | |
|---|---|---|---|---|
| SCHEMBL29581126 | 0.79 | LOXL2 (0.52) | SYKNOTUMIDO1LOXL2LOX | |
| SCHEMBL484767 | 0.79 | LOXL2 (0.52) | SYKNOTUMIDO1LOXL2LOX | |
| Bromide SCHEMBL15720464 | 0.77 | LOXL2 (0.50) | SYKNOTUMIDO1LOXL2LOX | |
| Ammonia Solution, Strong SCHEMBL27910510 | 0.77 | LOXL2 (0.50) | SYKNOTUMIDO1LOXL2LOX | |
| SCHEMBL31119651 | 0.76 | KIF11 (0.54) | SYKNOTUMIDO1LOXL2LOX | |
| SCHEMBL32670670 | 0.76 | MGLL (0.51) | SYKNOTUMIDO1LOXL2LOX | |
| SCHEMBL19347487 | 0.74 | SYK (1.00) | SYK | |
| SCHEMBL22322823 | 0.74 | IDO1 (0.56) | NOTUMIDO1LOXL2LOXMAP4K4 | |
| SCHEMBL18000549 | 0.74 | RAB9A (0.51) | SYKIDO1TP53BIRC5RAB9A | |
| SCHEMBL28726693 | 0.73 | SYK (0.46) | SYKIDO1TP53RAB9AALDH1A1 |
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 1 patent. claimed = in the patent's claims; disclosed = body only.
| Patent | Title | Assignee | Published | Priority | Filing | Country | Status |
|---|---|---|---|---|---|---|---|
| US-20260034105-A1 | Generative AI-Assisted Identification of Novel PI3K-alpha Inhibitors | THE FIRST AFFILIATED HOSPITAL OF XI'AN JIAOTONG UNIVERSITY (CN) | 2026-02-05 | — | — | US | 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 (1 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-20260034105-A1 | Generative AI-Assisted Identification of Novel PI3K-alpha Inhibitors | PIK3R1, PIK3R4, PIK3R2 | SYK 695/4885NOTUM 4024/4885IDO1 1199/4885 |
“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.