pith. machine review for the scientific record. sign in

arxiv: 2604.16586 · v1 · submitted 2026-04-17 · 💻 cs.LG · cs.AI· q-bio.QM

Recognition: unknown

A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era

Zongru Li , Xingsheng Chen , Honggang Wen , Regina Qianru Zhang , Ming Li , Xiaojin Zhang , Hongzhi Yin , Qiang Yang , Kwok-Yan Lam , Pietro Lio , Siu-Ming Yiu

Authors on Pith no claims yet

Pith reviewed 2026-05-10 08:39 UTC · model grok-4.3

classification 💻 cs.LG cs.AIq-bio.QM
keywords learningbenchmarkmolecularquantumdeepfoundationsurveydata
0
0 comments X

The pith

A systematic survey and benchmark of four deep learning paradigms for molecular property prediction that organizes the field, critiques current data practices, and outlines three future directions.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

Molecules have properties like how they dissolve, react, or affect biology that scientists want to predict without running every experiment. The paper groups existing computer methods into four families: direct quantum calculations, machine learning on hand-crafted molecule descriptions, geometric deep learning that uses 3D atom positions, and large foundation models trained on vast molecular data. It builds one shared classification that links how molecules are represented, which model architectures are used, and what real-world tasks they target. Benchmarks pull together standard academic datasets plus industry-style ones covering quantum energies, physical measurements, and biological activities. The authors flag recurring problems such as missing or inconsistent information about molecule handedness, data coming from different lab sources, and evaluation splits that let models cheat by seeing similar molecules in both training and test sets. These issues make it hard to know which method is truly better. The paper ends by suggesting three next steps: models that stay consistent with known physics rules, foundation models that report how confident they are in each prediction, and new benchmark collections that mix computer simulations with real lab measurements in realistic ways.

Core claim

Current benchmark practices suffer from inconsistent stereochemistry handling, heterogeneous assay sources, and reproducibility limitations under random or poorly defined splits, motivating modernization toward transparent, time- and scaffold-aware methodologies.

Load-bearing premise

That the surveyed datasets and identified challenges sufficiently represent the full range of real-world molecular prediction tasks and that the three proposed directions (physics-aware learning, uncertainty calibration, multimodal benchmarks) will measurably improve model reliability without introducing new unaddressed biases.

Figures

Figures reproduced from arXiv: 2604.16586 by Honggang Wen, Hongzhi Yin, Kwok-Yan Lam, Ming Li, Pietro Lio, Qiang Yang, Regina Qianru Zhang, Siu-Ming Yiu, Xiaojin Zhang, Xingsheng Chen, Zongru Li.

Figure 1
Figure 1. Figure 1: Overview of this survey. The framework organizes more than 100 deep learning methods for molecular property prediction along four axes: Evolution, Taxonomy, Capability, and Roadmap. From left to right: (i) Evolution traces the cumulative methodological trajectory from quantum mechanics and descriptor-based learning to geometric and foundation models; (ii) Taxonomy categorizes methods by representation moda… view at source ↗
Figure 2
Figure 2. Figure 2: Taxonomy of existing studies for molecular property prediction [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: The pipeline of deep learning-driven MPP [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Overview of molecular representation modalities: 1D sequences, 2D graphs, 3D geometric conformations, and multimodal combinations. 4.1 1D Representations One-dimensional representations describe a molecule as a linear sequence of symbols. The most prevalent format is the SMILES string, with newer alternatives like SELFIES addressing some of SMILES’ validity shortcomings. These encodings allow molecular str… view at source ↗
Figure 5
Figure 5. Figure 5: Geometric GNN in MPP extends this to torsion angles, incorporating dihedral interactions to capture finer geometric detail. Collectively, these architectures (92, 94) have reported near-chemical-accuracy performance on established benchmarks such as QM9 and MD17, while offering much lower inference cost than repeated quantum-chemical calculations once trained. Challenges include the computational cost of c… view at source ↗
Figure 6
Figure 6. Figure 6: Transformer in MPP other molecular properties. Gasteiger et al. (92) reported that DimeNet outperforms previous GNNs on average by 76% on MD17 and by 31% on QM9. The field progressed toward more sophisticated symmetry-aware models with the introduction of Tensor Field Networks (97) that first implemented spherical irreducible representations. This foundation enabled the SE(3)- Transformer (17), which estab… view at source ↗
read the original abstract

Molecular property prediction integrates quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and biological behavior. This survey traces four complementary paradigms, including Quantum, Descriptor Machine Learning, Geometric Deep Learning, and Foundation Models, and outlines a unified taxonomy linking molecular representations, model architectures, and interdisciplinary applications. Benchmark analyses integrate evidence from both widely used datasets and datasets reflecting industry perspectives, encompassing quantum, physicochemical, physiological, and biophysical domains. The survey examines current standards in data curation, splitting strategies, and evaluation protocols, highlighting challenges including inconsistent stereochemistry, heterogeneous assay sources, and reproducibility limitations under random or poorly defined splits. These observations motivate the modernization of benchmark design toward more transparent, time- and scaffold-aware methodologies. We further propose three forward-looking directions: (i) physics-aware learning embedding quantum consistency, (ii) uncertainty-calibrated foundation models for trustworthy inference, and (iii) realistic multimodal benchmark ecosystems integrating computational and experimental data. Repository: https://github.com/Zongru-Li/Survey-and-Benchmarks-of-DL-for-Molecular-Property-Prediction-in-the-Foundation-Model-Era.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

As a survey paper the work introduces no new free parameters, axioms, or invented entities. It reviews existing paradigms, datasets, and evaluation practices without postulating additional constructs.

pith-pipeline@v0.9.0 · 5544 in / 1211 out tokens · 40461 ms · 2026-05-10T08:39:57.995244+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

152 extracted references · 14 canonical work pages · 1 internal anchor

  1. [1]

    K. T. Schütt, P.-J. Kindermans, H. E. Sauceda, S. Chmiela, A. Tkatchenko, and K.-R. Müller. Schnet: a continuous-filter convolutional neural network for modeling quantum interactions. InProceedings of the 31st International Conference on Neural Information Processing Systems, NIPS’17, page 992–1002, Red Hook, NY , USA, 2017. Curran Associates Inc

    2017

  2. [2]

    Schoenholz, Patrick F

    Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, and George E. Dahl. Neural message passing for quantum chemistry. InProceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, page 1263–1272. JMLR.org, 2017

    2017

  3. [3]

    Anatole von Lilienfeld, Klaus-Robert Müller, and Alexandre Tkatchenko

    O. Anatole von Lilienfeld, Klaus-Robert Müller, and Alexandre Tkatchenko. Exploring chemical compound space with quantum-based machine learning.Nature Reviews Chemistry, 4(7):347–358, 2020

    2020

  4. [4]

    Applications of machine learning in drug discovery and development.Nature Reviews Drug Discovery, 18(6):463–477, 2019

    Jessica Vamathevan, Dominic Clark, Paul Czodrowski, Ian Dunham, Edgardo Ferran, George Lee, Bin Li, Anant Madabhushi, Parantu Shah, Michaela Spitzer, and Shanrong Zhao. Applications of machine learning in drug discovery and development.Nature Reviews Drug Discovery, 18(6):463–477, 2019

    2019

  5. [5]

    A compact review of molecular property prediction with graph neural networks.Drug Discovery Today: Technologies, 37:1–12, 2020

    Oliver Wieder, Stefan Kohlbacher, Mélaine Kuenemann, Arthur Garon, Pierre Ducrot, Thomas Seidel, and Thierry Langer. A compact review of molecular property prediction with graph neural networks.Drug Discovery Today: Technologies, 37:1–12, 2020

    2020

  6. [6]

    A perspective on foundation models in chemistry.JACS Au, 5(4):1499–1518, 2025

    Junyoung Choi, Gunwook Nam, Jaesik Choi, and Yousung Jung. A perspective on foundation models in chemistry.JACS Au, 5(4):1499–1518, 2025

    2025

  7. [7]

    Advancements in molecular property prediction: A survey of single and multimodal approaches.Archives of Computational Methods in Engineering, pages 1–31, 2025

    Tanya Liyaqat, Tanvir Ahmad, and Chandni Saxena. Advancements in molecular property prediction: A survey of single and multimodal approaches.Archives of Computational Methods in Engineering, pages 1–31, 2025

    2025

  8. [8]

    Calculation of local excitations in large systems by embedding wave-function theory in density-functional theory.Physical Chemistry Chemical Physics, 10(35):5353–5362, 2008

    André Severo Pereira Gomes, Christoph R Jacob, and Lucas Visscher. Calculation of local excitations in large systems by embedding wave-function theory in density-functional theory.Physical Chemistry Chemical Physics, 10(35):5353–5362, 2008

    2008

  9. [9]

    Physnet: A neural network for predicting energies, forces, dipole moments, and partial charges.Journal of Chemical Theory and Computation, 15(6):3678–3693, 2019

    Oliver T Unke and Markus Meuwly. Physnet: A neural network for predicting energies, forces, dipole moments, and partial charges.Journal of Chemical Theory and Computation, 15(6):3678–3693, 2019

    2019

  10. [10]

    The performance of density functional and wavefunction- based methods for 2d and 3d structures of au10.Journal of Computational Chemistry, 34(23):1975–1981, 2013

    Daniel A Götz, Rolf Schäfer, and Peter Schwerdtfeger. The performance of density functional and wavefunction- based methods for 2d and 3d structures of au10.Journal of Computational Chemistry, 34(23):1975–1981, 2013

    1975

  11. [11]

    Linear-scaling quantum mechanical calculations of biological molecules: The divide-and-conquer approach.Computational Materials Science, 12(3):259–277, 1998

    Tai-Sung Lee, James P Lewis, and Weitao Yang. Linear-scaling quantum mechanical calculations of biological molecules: The divide-and-conquer approach.Computational Materials Science, 12(3):259–277, 1998

    1998

  12. [12]

    Large-scale molecular simulations of hypervelocity impact of materials.Procedia Engineering, 58:167–176, 2013

    Andres Jaramillo-Botero, Qi An, Patrick L Theofanis, and William A Goddard III. Large-scale molecular simulations of hypervelocity impact of materials.Procedia Engineering, 58:167–176, 2013

    2013

  13. [13]

    Extended-connectivity fingerprints.Journal of chemical information and modeling, 50(5):742–754, 2010

    David Rogers and Mathew Hahn. Extended-connectivity fingerprints.Journal of chemical information and modeling, 50(5):742–754, 2010

    2010

  14. [14]

    Ling Xue, Jeffrey W Godden, Florence L Stahura, and Jürgen Bajorath. Design and evaluation of a molecular fingerprint involving the transformation of property descriptor values into a binary classification scheme.Journal of chemical information and computer sciences, 43(4):1151–1157, 2003

    2003

  15. [15]

    Reconstruction of lossless molecular representations from fingerprints.Journal of cheminformatics, 15(1):26, 2023

    Umit V Ucak, Islambek Ashyrmamatov, and Juyong Lee. Reconstruction of lossless molecular representations from fingerprints.Journal of cheminformatics, 15(1):26, 2023. 21

    2023

  16. [16]

    Geometry-enhanced molecular representation learning for property prediction.Nature Machine Intelligence, 4(2):127–134, 2022

    Xiaomin Fang, Lihang Liu, Jieqiong Lei, Donglong He, Shanzhuo Zhang, Jingbo Zhou, Fan Wang, Hua Wu, and Haifeng Wang. Geometry-enhanced molecular representation learning for property prediction.Nature Machine Intelligence, 4(2):127–134, 2022

    2022

  17. [17]

    Se (3)-transformers: 3d roto-translation equivariant attention networks.Advances in neural information processing systems, 33:1970–1981, 2020

    Fabian Fuchs, Daniel Worrall, V olker Fischer, and Max Welling. Se (3)-transformers: 3d roto-translation equivariant attention networks.Advances in neural information processing systems, 33:1970–1981, 2020

    1970

  18. [18]

    Directed message passing based on attention for prediction of molecular properties

    Gong Chen and Yvon Maday. Directed message passing based on attention for prediction of molecular properties. Computational Materials Science, 229:112443, 2023

    2023

  19. [19]

    Generalizing from a few examples: A survey on few-shot learning.ACM computing surveys (csur), 53(3):1–34, 2020

    Yaqing Wang, Quanming Yao, James T Kwok, and Lionel M Ni. Generalizing from a few examples: A survey on few-shot learning.ACM computing surveys (csur), 53(3):1–34, 2020

    2020

  20. [20]

    Fs-mol: A few-shot learning dataset of molecules

    Megan Stanley, John F Bronskill, Krzysztof Maziarz, Hubert Misztela, Jessica Lanini, Marwin Segler, Nadine Schneider, and Marc Brockschmidt. Fs-mol: A few-shot learning dataset of molecules. InThirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2), 2021

    2021

  21. [21]

    Nawaf Alampara, Mara Schilling-Wilhelmi, Martiño Ríos-García, Indrajeet Mandal, Pranav Khetarpal, Har- gun Singh Grover, N. M. Anoop Krishnan, and Kevin Maik Jablonka. Probing the limitations of multimodal language models for chemistry and materials research.Nature Computational Science, 5(10):952–961, Oct 2025

    2025

  22. [22]

    Evaluating large language models on multimodal chemistry olympiad exams.Communications Chemistry, 8(1):402, Dec 2025

    Yiming Cui, Xin Yao, Yuxuan Qin, Xin Li, Shijin Wang, and Guoping Hu. Evaluating large language models on multimodal chemistry olympiad exams.Communications Chemistry, 8(1):402, Dec 2025

    2025

  23. [23]

    Ash, Cas Wognum, Raquel Rodríguez-Pérez, Matteo Aldeghi, Alan C

    Jeremy R. Ash, Cas Wognum, Raquel Rodríguez-Pérez, Matteo Aldeghi, Alan C. Cheng, Djork-Arné Clevert, Ola Engkvist, Cheng Fang, Daniel J. Price, Jacqueline M. Hughes-Oliver, and W. Patrick Walters. Practically significant method comparison protocols for machine learning in small molecule drug discovery.Journal of Chemical Information and Modeling, 65(18):...

    2025

  24. [24]

    DeepTox: Toxicity Prediction using Deep Learning.Frontiers in Environmental Science, 3, 2016

    Andreas Mayr, Günter Klambauer, Thomas Unterthiner, and Sepp Hochreiter. DeepTox: Toxicity Prediction using Deep Learning.Frontiers in Environmental Science, 3, 2016

    2016

  25. [25]

    Fate-tox: fragment attention transformer for E(3)-equivariant multi-organ toxicity prediction.Journal of Cheminformatics, 17(1):74, May 2025

    Sumin Ha, Dongmin Bang, and Sun Kim. Fate-tox: fragment attention transformer for E(3)-equivariant multi-organ toxicity prediction.Journal of Cheminformatics, 17(1):74, May 2025

    2025

  26. [26]

    DeepDTA: deep drug–target binding affinity prediction

    Hakime Öztürk, Arzucan Özgür, and Elif Ozkirimli. DeepDTA: deep drug–target binding affinity prediction. Bioinformatics, 34(17):i821–i829, September 2018

    2018

  27. [27]

    Seyone Chithrananda, Gabriel Grand, Bharath Ramsun- dar, et al

    Walid Ahmad, Elana Simon, Seyone Chithrananda, Gabriel Grand, and Bharath Ramsundar. Chemberta-2: Towards chemical foundation models.arXiv preprint arXiv:2209.01712, 2022

    work page arXiv 2022

  28. [28]

    Molecular representation learning with language models and domain-relevant auxiliary tasks, 2020

    Benedek Fabian, Thomas Edlich, Héléna Gaspar, Marwin Segler, Joshua Meyers, Marco Fiscato, and Mohamed Ahmed. Molecular representation learning with language models and domain-relevant auxiliary tasks, 2020

    2020

  29. [29]

    Rouyi Wang, Shujun Yi, Guoqiang Shan, and Lingyan Zhu. Integration of transfer learning and multitask learning to predict the potential of per/polyfluoroalkyl substances in activating multiple nuclear receptors associated with hepatic lipotoxicity.Environmental Science & Technology, 59(44):23727–23738, 2025

    2025

  30. [30]

    Mole: a foundation model for molecular graphs using disentangled attention.Nature Communications, 15(1):9431, 2024

    Oscar Méndez-Lucio, Christos A Nicolaou, and Berton Earnshaw. Mole: a foundation model for molecular graphs using disentangled attention.Nature Communications, 15(1):9431, 2024

    2024

  31. [31]

    Uni-mol: A universal 3d molecular representation learning framework

    Gengmo Zhou, Zhifeng Gao, Qiankun Ding, Hang Zheng, Hongteng Xu, Zhewei Wei, Linfeng Zhang, and Guolin Ke. Uni-mol: A universal 3d molecular representation learning framework. InThe Eleventh International Conference on Learning Representations, 2023

    2023

  32. [32]

    Hoffman, C

    Vijil Chenthamarakshan, Samuel C. Hoffman, C. David Owen, Petra Lukacik, Claire Strain-Damerell, Daren Fearon, Tika R. Malla, Anthony Tumber, Christopher J. Schofield, Helen M.E. Duyvesteyn, Wanwisa Dejnirattisai, Loic Carrique, Thomas S. Walter, Gavin R. Screaton, Tetiana Matviiuk, Aleksandra Mojsilovic, Jason Crain, Martin A. Walsh, David I. Stuart, and...

    2023

  33. [33]

    ADMET-AI: a machine learning ADMET platform for evaluation of large-scale chemical libraries

    Kyle Swanson, Parker Walther, Jeremy Leitz, Souhrid Mukherjee, Joseph C Wu, Rabindra V Shivnaraine, and James Zou. ADMET-AI: a machine learning ADMET platform for evaluation of large-scale chemical libraries. Bioinformatics, 40(7):btae416, July 2024

    2024

  34. [34]

    Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S

    Zhenqin Wu, Bharath Ramsundar, Evan N. Feinberg, Joseph Gomes, Caleb Geniesse, Aneesh S. Pappu, Karl Leswing, and Vijay Pande. Moleculenet: a benchmark for molecular machine learning.Chem. Sci., 9:513–530, 2018

    2018

  35. [35]

    Schoenholz, Muratahan Aykol, Gowoon Cheon, and Ekin Dogus Cubuk

    Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, Gowoon Cheon, and Ekin Dogus Cubuk. Scaling deep learning for materials discovery.Nature, 624(7990):80–85, December 2023

    2023

  36. [36]

    A predictive machine learning force-field framework for liquid electrolyte development.Nature Machine Intelligence, 7(4):543–552, April 2025

    Sheng Gong, Yumin Zhang, Zhenliang Mu, Zhichen Pu, Hongyi Wang, Xu Han, Zhiao Yu, Mengyi Chen, Tianze Zheng, Zhi Wang, Lifei Chen, Zhenze Yang, Xiaojie Wu, Shaochen Shi, Weihao Gao, Wen Yan, and Liang Xiang. A predictive machine learning force-field framework for liquid electrolyte development.Nature Machine Intelligence, 7(4):543–552, April 2025

    2025

  37. [37]

    Uni-electrolyte: An artificial intelligence platform for designing electrolyte molecules for rechargeable batteries.Angewandte Chemie International Edition, 64(30):e202503105, 2025

    Xiang Chen, Mingkang Liu, Shiqiu Yin, Yu-Chen Gao, Nan Yao, and Qiang Zhang. Uni-electrolyte: An artificial intelligence platform for designing electrolyte molecules for rechargeable batteries.Angewandte Chemie International Edition, 64(30):e202503105, 2025

    2025

  38. [38]

    Do transformers really perform badly for graph representation? InThirty-Fifth Conference on Neural Information Processing Systems, 2021

    Chengxuan Ying, Tianle Cai, Shengjie Luo, Shuxin Zheng, Guolin Ke, Di He, Yanming Shen, and Tie-Yan Liu. Do transformers really perform badly for graph representation? InThirty-Fifth Conference on Neural Information Processing Systems, 2021

    2021

  39. [39]

    Graphmae: Self- supervised masked graph autoencoders

    Zhenyu Hou, Xiao Liu, Yukuo Cen, Yuxiao Dong, Hongxia Yang, Chunjie Wang, and Jie Tang. Graphmae: Self- supervised masked graph autoencoders. InProceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 594–604, 2022

    2022

  40. [40]

    Chemberta: Large-scale self-supervised pretrain- ing for molecular property prediction, 2020

    Seyone Chithrananda, Gabriel Grand, and Bharath Ramsundar. Chemberta: Large-scale self-supervised pretrain- ing for molecular property prediction, 2020

    2020

  41. [41]

    Molecular contrastive learning of representations via graph neural networks.Nature Machine Intelligence, 4(3):279–287, 2022

    Yuyang Wang, Jianren Wang, Zhonglin Cao, and Amir Barati Farimani. Molecular contrastive learning of representations via graph neural networks.Nature Machine Intelligence, 4(3):279–287, 2022

    2022

  42. [42]

    Nadkarni, Benjamin S

    Kexin Huang, Payal Chandak, Qianwen Wang, Shreyas Havaldar, Akhil Vaid, Jure Leskovec, Girish N. Nadkarni, Benjamin S. Glicksberg, Nils Gehlenborg, and Marinka Zitnik. A foundation model for clinician-centered drug repurposing.Nature Medicine, 30(12):3601–3613, December 2024

    2024

  43. [43]

    Allegro-fm: Toward an equivariant foundation model for exascale molecular dynamics simulations.The Journal of Physical Chemistry Letters, 16:6637–6644, 2025

    Ken-ichi Nomura, Shinnosuke Hattori, Satoshi Ohmura, Ikumi Kanemasu, Kohei Shimamura, Nabankur Das- gupta, Aiichiro Nakano, Rajiv K Kalia, and Priya Vashishta. Allegro-fm: Toward an equivariant foundation model for exascale molecular dynamics simulations.The Journal of Physical Chemistry Letters, 16:6637–6644, 2025

    2025

  44. [44]

    Smiles-bert: Large scale unsupervised pre-training for molecular property prediction

    Sheng Wang, Yuzhi Guo, Yuhong Wang, Hongmao Sun, and Junzhou Huang. Smiles-bert: Large scale unsupervised pre-training for molecular property prediction. InProceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, BCB ’19, page 429–436, New York, NY , USA, 2019. Association for Computing Machinery

    2019

  45. [45]

    Transformers for molecular property prediction: Domain adaptation efficiently improves performance, 2025

    Afnan Sultan, Max Rausch-Dupont, Shahrukh Khan, Olga Kalinina, Dietrich Klakow, and Andrea V olkamer. Transformers for molecular property prediction: Domain adaptation efficiently improves performance, 2025

    2025

  46. [46]

    Mol2vec: Unsupervised machine learning approach with chemical intuition.Journal of Chemical Information and Modeling, 58(1):27–35, 2018

    Sabrina Jaeger, Simone Fulle, and Samo Turk. Mol2vec: Unsupervised machine learning approach with chemical intuition.Journal of Chemical Information and Modeling, 58(1):27–35, 2018. PMID: 29268609

    2018

  47. [47]

    Bemis and Mark A

    Guy W. Bemis and Mark A. Murcko. The properties of known drugs. 1. Molecular frameworks.J. Med. Chem., 39(15):2887–2893, 1996

    1996

  48. [48]

    Unsupervised data base clustering based on Daylight’s fingerprint and Tanimoto similarity: A fast and automated way to cluster small and large data sets.J

    Darko Butina. Unsupervised data base clustering based on Daylight’s fingerprint and Tanimoto similarity: A fast and automated way to cluster small and large data sets.J. Chem. Inf. Comput. Sci., 39(4):747–750, 1999. 23

    1999

  49. [49]

    Ballester

    Qianrong Guo, Saiveth Hernandez-Hernandez, and Pedro J. Ballester. Scaffold splits overestimate virtual screening performance. InArtificial Neural Networks and Machine Learning – ICANN 2024, volume 15025 of Lecture Notes in Computer Science, pages 58–72. Springer, 2024

    2024

  50. [50]

    Ballester

    Qianrong Guo, Saiveth Hernandez-Hernandez, and Pedro J. Ballester. UMAP-based clustering split for rigorous evaluation of AI models for virtual screening on cancer cell lines.J. Cheminform., 17(1):94, 2025

    2025

  51. [51]

    Sheridan

    Robert P. Sheridan. Time-split cross-validation as a method for estimating the goodness of prospective prediction. J. Chem. Inf. Model., 53(4):783–790, 2013

    2013

  52. [52]

    Patrick Walters

    W. Patrick Walters. Some thoughts on splitting chemical datasets. Practical Cheminformatics Blog, https: //practicalcheminformatics.blogspot.com/2024/11/some-thoughts-on-splitting- chemical.html, 2024. Accessed: 2026

    2024

  53. [53]

    Uncertainty quantification and propagation in atomistic machine learning.Reviews in Chemical Engineering, 41(4):333–357, 2025

    Jin Dai, Santosh Adhikari, and Mingjian Wen. Uncertainty quantification and propagation in atomistic machine learning.Reviews in Chemical Engineering, 41(4):333–357, 2025

    2025

  54. [54]

    AkshatKumar Nigam, Robert Pollice, Matthew F. D. Hurley, Riley J. Hickman, Matteo Aldeghi, Naruki Yoshikawa, Seyone Chithrananda, Vincent A. V oelz, and Alán Aspuru-Guzik. Assigning confidence to molecular property prediction.Expert Opinion on Drug Discovery, 16(9):1009–1023, September 2021

    2021

  55. [55]

    Lior Hirschfeld, Kyle Swanson, Kevin Yang, Regina Barzilay, and Connor W. Coley. Uncertainty quantification using neural networks for molecular property prediction.Journal of Chemical Information and Modeling, 60(8):3770–3780, August 2020

    2020

  56. [56]

    Grambow, Barbara Pernici, Yi-Pei Li, and William H

    Gabriele Scalia, Colin A. Grambow, Barbara Pernici, Yi-Pei Li, and William H. Green. Evaluating scalable uncertainty estimation methods for deep learning-based molecular property prediction.Journal of Chemical Information and Modeling, 60(6):2697–2717, June 2020

    2020

  57. [57]

    Ltau-ff: Loss trajectory analysis for uncertainty in atomistic force fields.Machine Learning: Science and Technology, 6(1):015048, feb 2025

    Joshua A Vita, Amit Samanta, Fei Zhou, and Vincenzo Lordi. Ltau-ff: Loss trajectory analysis for uncertainty in atomistic force fields.Machine Learning: Science and Technology, 6(1):015048, feb 2025

    2025

  58. [58]

    Fast uncertainty estimates in deep learning interatomic potentials.The Journal of Chemical Physics, 158(16), 2023

    Albert Zhu, Simon Batzner, Albert Musaelian, and Boris Kozinsky. Fast uncertainty estimates in deep learning interatomic potentials.The Journal of Chemical Physics, 158(16), 2023

    2023

  59. [59]

    Deep evidential regression.Advances in neural information processing systems, 33:14927–14937, 2020

    Alexander Amini, Wilko Schwarting, Ava Soleimany, and Daniela Rus. Deep evidential regression.Advances in neural information processing systems, 33:14927–14937, 2020

    2020

  60. [60]

    Soleimany, Alexander Amini, Samuel Goldman, Daniela Rus, Sangeeta N

    Ava P. Soleimany, Alexander Amini, Samuel Goldman, Daniela Rus, Sangeeta N. Bhatia, and Connor W. Coley. Evidential deep learning for guided molecular property prediction and discovery.ACS Central Science, 7(8):1356–1367, August 2021

    2021

  61. [61]

    Dropout as a Bayesian approximation: Representing model uncertainty in deep learning

    Yarin Gal and Zoubin Ghahramani. Dropout as a Bayesian approximation: Representing model uncertainty in deep learning. InProceedings of The 33rd International Conference on Machine Learning, volume 48 of Proceedings of Machine Learning Research, pages 1050–1059. PMLR, 2016

    2016

  62. [62]

    When gaussian process meets big data: A review of scalable gps.IEEE transactions on neural networks and learning systems, 31(11):4405–4423, 2020

    Haitao Liu, Yew-Soon Ong, Xiaobo Shen, and Jianfei Cai. When gaussian process meets big data: A review of scalable gps.IEEE transactions on neural networks and learning systems, 31(11):4405–4423, 2020

    2020

  63. [63]

    SimSon: Simple contrastive learning of SMILES for molecular property prediction.Bioinformatics, 41(5), 2025

    Chae Eun Lee, Jin Sob Kim, Jin Hong Min, and Sung Won Han. SimSon: Simple contrastive learning of SMILES for molecular property prediction.Bioinformatics, 41(5), 2025

    2025

  64. [64]

    Convolutional neural network based on SMILES representation of compounds for detecting chemical motif.BMC Bioinformatics, 19(Suppl 19):526, 2018

    Masaki Hirohara, Yutaka Saito, Yuki Koda, Koji Sato, and Yasubumi Sakakibara. Convolutional neural network based on SMILES representation of compounds for detecting chemical motif.BMC Bioinformatics, 19(Suppl 19):526, 2018

    2018

  65. [65]

    Deepsmiles: An adaptation of smiles for use in machine-learning of chemical structures.ChemRxiv, 2018(0919), 2018

    Noel O’Boyle and Andrew Dalke. Deepsmiles: An adaptation of smiles for use in machine-learning of chemical structures.ChemRxiv, 2018(0919), 2018. 24

    2018

  66. [66]

    Smiles pair encoding: A data-driven substructure tokenization algorithm for deep learning.Journal of Chemical Information and Modeling, 61(4):1560–1569, 2021

    Xinhao Li and Denis Fourches. Smiles pair encoding: A data-driven substructure tokenization algorithm for deep learning.Journal of Chemical Information and Modeling, 61(4):1560–1569, 2021. PMID: 33715361

    2021

  67. [67]

    SPVec: A Word2vec-Inspired Feature Representation Method for Drug-Target Interaction Prediction.Frontiers in Chemistry, 7, 2020

    Yu-Fang Zhang, Xiangeng Wang, Aman Chandra Kaushik, Yanyi Chu, Xiaoqi Shan, Ming-Zhu Zhao, Qin Xu, and Dong-Qing Wei. SPVec: A Word2vec-Inspired Feature Representation Method for Drug-Target Interaction Prediction.Frontiers in Chemistry, 7, 2020

    2020

  68. [68]

    AlHammadi

    Obaid Khaleifah Alhmoudi, Mahmoud Aboushanab, Muhammed Thameem, Ali Elkamel, and Ali A. AlHammadi. Domain adaptation of a smiles chemical transformer to selfies with limited computational resources.Scientific Reports, 15(1):23627, 2025

    2025

  69. [69]

    Mol-bert: An effective molecular representation with bert for molecular property prediction.Wireless Communications and Mobile Computing, 2021(1):7181815, 2021

    Juncai Li and Xiaofei Jiang. Mol-bert: An effective molecular representation with bert for molecular property prediction.Wireless Communications and Mobile Computing, 2021(1):7181815, 2021

    2021

  70. [70]

    Chemformer: a pre-trained transformer for computational chemistry.Machine Learning: Science and Technology, 3(1):015022, jan 2022

    Ross Irwin, Spyridon Dimitriadis, Jiazhen He, and Esben Jannik Bjerrum. Chemformer: a pre-trained transformer for computational chemistry.Machine Learning: Science and Technology, 3(1):015022, jan 2022

    2022

  71. [71]

    Bonggun Shin, Sungsoo Park, Keunsoo Kang, and Joyce C. Ho. Self-Attention Based Molecule Representation for Predicting Drug-Target Interaction. In Finale Doshi-Velez, Jim Fackler, Ken Jung, David Kale, Rajesh Ranganath, Byron Wallace, and Jenna Wiens, editors,Proceedings of the 4th Machine Learning for Healthcare Conference, volume 106 ofProceedings of Ma...

    2019

  72. [72]

    Goh, Nathan O

    Garrett B. Goh, Nathan O. Hodas, Charles Siegel, and Abhinav Vishnu. Smiles2vec: An interpretable general- purpose deep neural network for predicting chemical properties, 2018

    2018

  73. [73]

    ReactionT5: a pre-trained transformer model for accurate chemical reaction prediction with limited data.Journal of Cheminformatics, 17(1):126, August 2025

    Tatsuya Sagawa and Ryosuke Kojima. ReactionT5: a pre-trained transformer model for accurate chemical reaction prediction with limited data.Journal of Cheminformatics, 17(1):126, August 2025

    2025

  74. [74]

    Chemical representation learning for toxicity prediction.Digital Discovery, 2(3):674–691, 2023

    Jannis Born, Greta Markert, Nikita Janakarajan, Talia B Kimber, Andrea V olkamer, María Rodríguez Martínez, and Matteo Manica. Chemical representation learning for toxicity prediction.Digital Discovery, 2(3):674–691, 2023

    2023

  75. [75]

    MolTrans: Molecular Interaction Transformer for drug–target interaction prediction.Bioinformatics, 37(6):830–836, March 2021

    Kexin Huang, Cao Xiao, Lucas M Glass, and Jimeng Sun. MolTrans: Molecular Interaction Transformer for drug–target interaction prediction.Bioinformatics, 37(6):830–836, March 2021

    2021

  76. [76]

    Group selfies: a robust fragment-based molecular string representation.Digital Discovery, 2, 03 2023

    Austin Cheng, Andy Cai, Santiago Miret, Gustavo Malkomes, Mariano Phielipp, and Alán Aspuru-Guzik. Group selfies: a robust fragment-based molecular string representation.Digital Discovery, 2, 03 2023

    2023

  77. [77]

    SELFormer: Molecular representation learning via SELFIES language models.Machine Learning: Science and Technology, 4(2):025035, 2023

    Atakan Yüksel, Erva Ulusoy, Atabey Ünlü, and Tunca Do˘gan. SELFormer: Molecular representation learning via SELFIES language models.Machine Learning: Science and Technology, 4(2):025035, 2023

    2023

  78. [78]

    Self-referencing embedded strings (selfies): A 100% robust molecular string representation.Machine Learning: Science and Technology, 1(4):045024, 2020

    Mario Krenn, Florian Häse, AkshatKumar Nigam, Pascal Friederich, and Alan Aspuru-Guzik. Self-referencing embedded strings (selfies): A 100% robust molecular string representation.Machine Learning: Science and Technology, 1(4):045024, 2020

    2020

  79. [79]

    Distributed representations of words and phrases and their compositionality

    Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. Distributed representations of words and phrases and their compositionality. In C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger, editors,Advances in Neural Information Processing Systems, volume 26. Curran Associates, Inc., 2013

    2013

  80. [80]

    Heller, Alan McNaught, Igor Pletnev, Stephen Stein, and Dmitrii Tchekhovskoi

    Stephen R. Heller, Alan McNaught, Igor Pletnev, Stephen Stein, and Dmitrii Tchekhovskoi. Inchi, the IUPAC international chemical identifier.Journal of Cheminformatics, 7(1):23, 2015

    2015

Showing first 80 references.