SCScore: Synthetic Complexity Learned from a Reaction Corpus
Abstract
Several definitions of molecular complexity exist to facilitate prioritization of lead compounds, to identify diversity-inducing and complexifying reactions, and to guide retrosynthetic searches. In this work, we focus on synthetic complexity and reformalize its definition to correlate with the expected number of reaction steps required to produce a target molecule, with implicit knowledge about what compounds are reasonable starting materials. We train a neural network model on 12 million reactions from the Reaxys database to impose a pairwise inequality constraint enforcing the premise of this definition: that on average, the products of published chemical reactions should be more synthetically complex than their corresponding reactants. The learned metric (SCScore) exhibits highly desirable nonlinear behavior, particularly in recognizing increases in synthetic complexity throughout a number of linear synthetic routes.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Coley et al. suggested the Synthetic Complexity Score (SCS) which relies on a neural network trained on 22 million reaction pairs from the Reaxys database.
“Recently, Coley et al.157 suggested the Synthetic Complexity Score (SCS) which relies on a neural network trained on 22 million reaction pairs from the Reaxys database.”
From QSAR without borders (2020) · cites this paper as [157]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The many roles of molecular complexity in drug discovery
Méndez-Lucio, O., & Medina-Franco, J. L. (2017) · Drug Discovery Today · doi:10.1016/j.drudis.2016.08.009 · Cited by 180 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Muratov, E. N., Bajorath, J., Sheridan, R. P., Tetko, I. V., Filimonov, D., Poroikov, V., Oprea, T. I., Baskin, I. I., Varnek, A., Roitberg, A., et al. (2020) · Chemical Society Reviews · doi:10.1039/d0cs00098a · Cited by 913 · see citing works
Machine Learning in Computer-Aided Synthesis Planning
Coley, C. W., Green, W. H., & Jensen, K. F. (2018) · Accounts of Chemical Research · doi:10.1021/acs.accounts.8b00087 · Cited by 704 · see citing works
Self-citationIdentifying molecules as biosignatures with assembly theory and mass spectrometry
Marshall, S. M., Mathis, C., Carrick, E., Keenan, G., Cooper, G. J. T., Graham, H., Craven, M., Gromski, P. S., Moore, D. G., Walker, S. I., et al. (2021) · Nature Communications · doi:10.1038/s41467-021-23258-x · Cited by 168 · see citing works
Niazi, S. K. (2025) · Pharmaceuticals · doi:10.3390/ph18091271 · Cited by 61 · see citing works
An in-depth review of AI-powered advancements in cancer drug discovery
Le, M. H. N., Nguyen, P. K., Nguyen, T. P. T., Nguyen, H. Q., Tam, D. N. H., Huynh, H. H., Huynh, P. K., & Le, N. Q. K. (2025) · Biochimica et Biophysica Acta (BBA) - Molecular Basis of Disease · doi:10.1016/j.bbadis.2025.167680 · Cited by 15 · see citing works
Evaluating Large Language Models in Scientific Discovery
Song, Z., Lu, J., Du, Y., Yu, B., Pruyn, T. M., Huang, Y., Guo, K., Luo, X., Qu, Y., Qu, Y., et al. (2025) · arXiv · Cited by 3 · see citing works
- Authors
- Coley, C. W., Rogers, L., Green, W. H., & Jensen, K. F.
- Affiliations
- Massachusetts Institute of Technology (US)
- Corresponding author
- Green, William H.
- Jensen, Klavs F.
- Venue
- Journal of Chemical Information and Modeling
- Publisher
- American Chemical Society (ACS)
- Published
- 2018-01-26
- Volume
- 58
- Issue
- 2
- Pages
- 252-261
- ISSN
- 1549-9596 (ISSN-L)
- 1549-960X
- OpenAlex
- W2783658781
- Cited by
- 381
- References
- 1
- Citations by year
- 2026: 71 · 2025: 74 · 2024: 58 · 2023: 51 · 2022: 41 · 2021: 39 · 2020: 26 · 2019: 19 · 2018: 2
- FWCI
- 16.27
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Journal of Chemical Information and Modeling (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Defense Advanced Research Projects Agency (ARO W911NF-16-2-0023)
- Division of Graduate Education (1122374)
- Topics
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Physical Sciences › Chemistry › Physical and Theoretical Chemistry › History and advancements in chemistry
- Keywords
- synthetic complexity, molecular complexity, Reaxys, retrosynthesis
- MeSH terms
- Models, Molecular, Neural Networks, Computer, Combinatorial Chemistry Techniques, Drug Discovery, Databases, Chemical
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
