Papers › Analyzing Learned Molecular Representations for Property Prediction

Analyzing Learned Molecular Representations for Property Prediction

2 Apr 2019arXiv:1904.01561archive 2025-07-28

Kevin Yang, Kyle Swanson, Wengong Jin, Connor Coley, Philipp Eiden, Hua Gao, Angel Guzman-Perez, Timothy Hopper, Brian Kelley, Miriam Mathea, Andrew Palmer, Volker Settels, Tommi Jaakkola, Klavs Jensen, Regina Barzilay

Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that construct a learned molecular representation by operating on the graph structure of the molecule. However, recent literature has yet to clearly determine which of these two methods is superior when generalizing to new chemical space. Furthermore, prior research has rarely examined these new models in industry research settings in comparison to existing employed models. In this paper, we benchmark models extensively on 19 public and 16 proprietary industrial datasets spanning a wide variety of chemical endpoints. In addition, we introduce a graph convolutional model that consistently matches or outperforms models using fixed molecular descriptors as well as previous graph neural architectures on both public and proprietary datasets. Our empirical findings indicate that while approaches based on these representations have yet to reach the level of experimental reproducibility, our proposed model nevertheless offers significant improvements over models currently used in industrial workflows.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (swansonk14/chemprop) was not harvested; the 15 samples below come from 2 community repositories.

Syntology 15 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 15 samples from 2 repositories, 14 ran (14 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

swansonk14/chemprop officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
anonymous20201002/chemprop mentioned on GitHubpytorchMITSyntology: 6 samples, 6 ran (0 instrument-failed) · 0 unverified report
jbr-ai-labs/lipophilicity-prediction mentioned on GitHubpytorchSyntology: not harvested report
tingweidaniel/chemprop_atomicfp_save_depth_final mentioned on GitHubpytorchMITSyntology: 9 samples, 8 ran (0 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

14ran
1unverified

Licence: 3 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

anonymous20201002/chemprop community (archive-listed) 6 samples, 6 ran (0 instrument-failed) · 0 unverified
compute_gnorm chemprop/nn_utils.py ran MIT (permissive) here; the stored copy is pointer only · 8efee7d886650920 · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-24
compute_pnorm chemprop/nn_utils.py ran MIT (permissive) here; the stored copy is pointer only · c4eed975523e1ed4 · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-24
get_checkpoint_paths chemprop/args.py ran MIT (permissive) · 8fb802f2499b4ccb · report fixture: signature checkpoint_path:NoneType/0/?, checkpoint_paths:NoneType/0/?, checkpoint_dir:str/0/str, ext:str/0/str · returned list · level recorded 2026-09-24
onek_encoding_unk in 11 papers chemprop/features/featurization.py ran fingerprinted MIT (permissive) · 49ebe299656c7302 · report fixture: signature value:int/0/int, choices:list/1/int · returned list · level recorded 2026-09-24
param_count in 7 papers chemprop/nn_utils.py ran MIT (permissive) here; the stored copy is pointer only · f1cc5264ce058bab · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
predict in 126 papers chemprop/sklearn_train.py ran MIT (permissive) · c9a8d90e903cc480 · report fixture: signature model:RandomForestRegressor/0/?, model_type:str/0/str, dataset_type:str/0/str, features:ndarray/2/float · returned list · level recorded 2026-09-24
tingweidaniel/chemprop_atomicfp_save_depth_final community (archive-listed) 9 samples, 8 ran (0 instrument-failed) · 1 unverified
compute_gnorm chemprop/nn_utils.py ran MIT (permissive) · ca7675a6350f0967 · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-25
compute_pnorm chemprop/nn_utils.py ran MIT (permissive) · e415ae10bb5a4e3b · report fixture: signature model:callable/0/? · returned float · level recorded 2026-09-25
evaluate_predictions in 9 papers chemprop/train/evaluate.py ran MIT (permissive) · 37db24e9e0f38c01 · report fixture: signature preds:list/1/list, targets:list/1/list, num_tasks:int/0/int, metric_func:callable/0/?, dataset_type:str/0/str, logger:Logger/0/? · returned list · level recorded 2026-09-24
get_atom_fdim chemprop/features/featurization.py ran MIT (permissive) · 513750ee5fcea171 · report fixture: signature args:Namespace/0/? · returned int · level recorded 2026-09-24
get_bond_fdim chemprop/features/featurization.py ran MIT (permissive) · 963d26c20eb3e4da · report fixture: signature args:Namespace/0/? · returned int · level recorded 2026-09-24
load_features in 14 papers chemprop/features/utils.py ran MIT (permissive) · 5045ed0a87b443be · report fixture: signature path:str/0/str · returned ndarray · level recorded 2026-09-24
onek_encoding_unk in 11 papers chemprop/features/featurization.py ran fingerprinted MIT (permissive) · 3e07b9e0170215ca · report fixture: signature value:int/0/int, choices:list/1/int · returned list · level recorded 2026-09-26
param_count in 7 papers chemprop/nn_utils.py ran MIT (permissive) · d68ff6a82a950b49 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-25
load_args in 25 papers chemprop/utils.py unverified MIT (permissive) · 76e27ba5baa89e9f · report

Tasks

Molecular Property PredictionPredictionProperty Predictionmolecular representation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Molecular Property Prediction BACE D-MPNN ROC-AUC 80.9 #11 of 20 Archive leaderboard report
Molecular Property Prediction BBBP D-MPNN ROC-AUC 71.0 #19 of 29 Archive leaderboard report
Molecular Property Prediction ESOL D-MPNN RMSE 1.050 #20 of 20 Archive leaderboard report
Molecular Property Prediction FreeSolv D-MPNN RMSE 2.082 #17 of 22 Archive leaderboard report
Molecular Property Prediction Lipophilicity D-MPNN RMSE 0.683 #4 of 13 Archive leaderboard report
Molecular Property Prediction QM7 D-MPNN MAE 103.5 #7 of 8 Archive leaderboard report
Molecular Property Prediction QM8 D-MPNN MAE 0.0190 #3 of 8 Archive leaderboard report
Molecular Property Prediction QM9 D-MPNN MAE 0.00814 #3 of 8 Archive leaderboard report
Molecular Property Prediction SIDER D-MPNN ROC-AUC 57.0 #16 of 19 Archive leaderboard report
Molecular Property Prediction Tox21 D-MPNN ROC-AUC 75.9 #11 of 20 Archive leaderboard report
Molecular Property Prediction ToxCast D-MPNN ROC-AUC 65.5 #6 of 8 Archive leaderboard report
Molecular Property Prediction clintox D-MPNN ROC-AUC 90.6 #7 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections