Start here — in plain words
Affinix uses a computer to find a chemical that can kill fruit flies. You do not run the science yourself — the computer picks, a lab tests, the result comes back here. Everything on this page is pulled live from the Affinix backend.
1
Look at the top chemicalThe strongest one is ranked #1 under Binding energy. Lower number = sticks stronger. Right now that is flufenoxuron. It is a candidate to test — not a proven killer.
2
Ask the chatTap the blue button, bottom right. Ask normal questions like “Is it safe for bees?” It answers only from Affinix backend data — if it does not know, it says so.
3
Send the plan to a labPick a chemical in Lab protocol below. That is the 7-step test plan a lab runs for you. Their result goes back into the backend and the ranking learns.
U
BdCHS2
S4TK66 • UniProt • loading…
Ch
ChEMBL
Diflubenzuron • CHEMBL6329
PDB
ESMFold structure
Residues 524–905 • loading…
Binding energy
Live from /dockOne docking run into the real BdCHS2 structure — not a time series. ESMFold pLDDT 90.1, residues 524–905.
−11.09
Best docking — Flufenoxuron (kcal/mol)
Docking PASS • Mean positive −10.336 vs negative −6.273 • Gap 4.063 • PLAPT still FAILS — no molecule is TRUSTWORTHY yet
Top candidates
Flufenoxuron
−11.093 kcal/mol
#1 • No lab test yet
Ch
Bistrifluron
−10.881 kcal/mol
PDB
Fluazuron
−10.842 kcal/mol
Ranked by docking into real BdCHS2
1. Flufenoxuron — −11.093
2. Bistrifluron — −10.881
3. Fluazuron — −10.842
2. Bistrifluron — −10.881
3. Fluazuron — −10.842
Structure: residues 524–905 • ESMFold pLDDT 90.1 • Library: 64 molecules from PubChem
Top 10 — full ranking
Live from /rank| # | Molecule | Docking | Status |
|---|---|---|---|
| 1 | Flufenoxuron | −11.093 | CANDIDATE |
| 2 | Bistrifluron | −10.881 | CANDIDATE |
| 3 | Fluazuron | −10.842 | CANDIDATE |
Docking and bee docking in kcal/mol (lower = sticks stronger). PLAPT is −log10 affinity — PLAPT FAILED validation, so its scores do not pick winners. Every molecule here is a candidate for a lab test, none is proven.
Screening frequency
Last 28 daysMonTueWedThuFriSatSun
No tests × More tests
0
Affinix lab tests run
No Affinix lab test has been run yet. The rows under Lab results are literature, not our tests. Next: use the protocol below.
Test these first — most to learn
Live from /learn1.00
Glucose
Uncertainty 1.00 — PLAPT says positive, docking says negative. Testing it teaches the most.
0.80
Benzoylureas (all 10)
Uncertainty 0.80 — PLAPT failed globally and disagrees with docking on each one.
Uncertainty 0–1. The most uncertain molecules teach the most — one lab result on them updates the whole ranking.
Top binding pockets
i Pocket is from BdCHS2 itself — EDR, QRRRW and DGD motifs. Full pocket data is only available once a lab test is run.
i Docking pocket: centroid of BdCHS2 catalytic motifs EDR 804, QRRRW 841, DGD 700, 24 Å box — from /dock.
Bee safety & lab protocol
i Bee safety is UNKNOWN for all candidates. Bees have chitin synthase too (A0A7M7IIL6, 210 aa fragment folded, pLDDT 89.7). A bee test must run alongside the fly test.
Lab protocol — live insect test
Pick a molecule and load its real 7-step plan from /protocol. This is a plan for a lab to run — nothing here has been tested on live insects yet.
- 30 flies per group, 5 doses, plus control
- Count dead every 24 hours for 7 days
- Pass if mortality is 50% higher than control and dose response is clear
- Run the same doses on honeybees in parallel
- Post the result to /results so the ranking learns
Bee safety for the selected molecule loads with the protocol.
Lab results
Live from /resultsLoading…
Reading the results table from the backend.
Literature rows are labelled — they are NOT Affinix lab tests. No Affinix lab test has been run yet.
Safety ranges
0.115
Pest PLAPT gap — BdCHS2
FAIL
FAIL
0.187
Bee PLAPT gap — A0A7M7IIL6
FAIL
FAIL
0.015
Human PLAPT gap — HAS2
FAIL
FAIL
Pest — BdCHS2
Bee
Human
PLAPT gaps — Pest 0.115 FAIL • Bee 0.187 FAIL • Human 0.015 FAIL • Backend: affinix-labs-api.chideraezeudu2.workers.dev • v1.3.0
Got ideas?
We're listening! Share feedback