Biology Atlas

Map / Open register

question · intermediate · partly written

Does a quantum-derived representation add anything to an ECFP fingerprint on a biological endpoint?

Quantum-informed atom pairs gained 0.5 to 6% over plain atom pairs, not over ECFP; no scaffold-split head-to-head against ECFP on an activity task was found.

What the sources show more

Quantum-informed atom pairs improved on plain atom pairs by 0.5 to 6% mean R-squared on 10 datasets under repeated 10-fold cross-validation, with RDKit descriptors best overall; the one hardware run in this area generates molecules and does not give a fingerprint. 12

Reported, not yet replicated

What is missing more

The same dataset, learner and scaffold split with ECFP count alone against ECFP count plus quantum descriptors, matched tuning. 1

Our inference

What would settle it (our inference) more

Add semi-empirical charges to ECFP count on one public ADMET set; baseline ECFP count alone, scaffold split. 13

Our inference

Observation

Quantum-derived inputs help most where the target is itself a computed quantum quantity. 34

Reported, not yet replicated

What is known

Quantum-informed atom pairs improved on plain atom pairs by 0.5 to 6% mean R-squared on 10 datasets under repeated 10-fold cross-validation, with RDKit descriptors best overall; the one hardware run in this area generates molecules and does not give a fingerprint. 12

Reported, not yet replicated

What is not

The same dataset, learner and scaffold split with ECFP count alone against ECFP count plus quantum descriptors, matched tuning. 1

Our inference

What would settle it

Add semi-empirical charges to ECFP count on one public ADMET set; baseline ECFP count alone, scaffold split. 13

Our inference

Still open here

Not yet written: Hypotheses, What is missing, Who works on it.

Linked from

Sources

  1. Fliszkiewicz B, Sajdak M. Toward Quantum-Informed Atom Pairs. ACS Omega (2024). paper; opened 2026-11-18 all records citing this
  2. Ghazi Vakili M, Gorgulla C, et al., Aspuru-Guzik A. Quantum-computing-enhanced algorithm unveils potential KRAS inhibitors. Nature Biotechnology (2025). paper; opened 2026-11-18 all records citing this
  3. Rupp M, Tkatchenko A, Müller KR, von Lilienfeld OA. Fast and accurate modeling of molecular atomization energies with machine learning. Physical Review Letters (2012). paper; opened 2026-11-18 all records citing this
  4. Faber FA, Hutchison L, Huang B, et al.. Machine learning prediction errors better than DFT accuracy. arXiv (2017). preprint, not peer reviewed; opened 2026-11-18 all records citing this
Where it sits on the map
History of this record (5)

This record has been changed 5 times, on the dates below. The note kept against each change is written for the people who maintain the atlas, in their own shorthand, so it is not shown here; it is in the record itself.

Kind
amit
Register
open-question
Triage
needs-research
Status
partly written
Last updated
2026-11-19
Record
content/questions/does-a-quantum-derived-representation-add-to-ecfp.json