references.bib

@Report{RegressionTransformer,
	author        = {Jannis Born and Matteo Manica},
	date          = {2022-02},
	title         = {Regression Transformer: Concurrent sequence regression and generation for molecular language modeling},
	eprint        = {2202.01338},
	url           = {https://github.com/IBM/regression-transformer},
	archiveprefix = {arxiv},
	month         = feb,
	year          = {2022},
}

@Article{MolDreaming,
	author       = {Shen, Cynthia and Krenn, Mario and Eppel, Sagi and Aspuru-Guzik, Alán},
	date         = {2021-07},
	year         = {2021},
	journaltitle = {Machine Learning: Science and Technology},
	journal      = {Machine Learning: Science and Technology},
	title        = {Deep molecular dreaming: inverse machine learning for de-novo molecular design and interpretability with surjective representations},
	doi          = {10.1088/2632-2153/ac09d6},
	issn         = {2632-2153},
	language     = {en},
	number       = {3},
	url          = {https://dx.doi.org/10.1088/2632-2153/ac09d6},
	urldate      = {2023-05-08},
	volume       = {2},
	pages        = {03LT02},
	publisher    = {IOP Publishing},
	shorttitle   = {Deep molecular dreaming},
}

@Report{AttnRolloutFlow,
	author     = {Samira Abnar and Willem Zuidema},
	date       = {2020-05},
	title      = {Quantifying Attention Flow in Transformers},
	doi        = {10.18653/v1/2020.acl-main.385},
	journal    = {Association for Computational Linguistics},
	eprint     = {2005.00928},
	eprinttype = {arxiv},
	month      = {5},
	year       = {2020},
	note       = {arXiv:2005.00928},
	url        = {https://arxiv.org/abs/2005.00928},
}

@Article{MolGPT,
	author       = {Viraj Bagal and Rishal Aggarwal and P. K. Vinod and U. Deva Priyakumar},
	date         = {2021},
	journaltitle = {Journal of Chemical Information and Modeling},
	journal      = {Journal of Chemical Information and Modeling},
	title        = {MolGPT: Molecular Generation Using a Transformer-Decoder Model},
	doi          = {10.1021/acs.jcim.1c00600},
	issn         = {1520-5142},
	volume       = {62},
	number       = {9},
	pages        = {2064--2076},
	year         = {2021},
	journal      = {Journal of Chemical Information and Modeling},
	pmid         = {34694798},
	publisher    = {American Chemical Society},
	year         = {2021},
}

@Article{CrippenLogP,
	author    = {Scott A. Wildman and Gordon M. Crippen},
	title     = {Prediction of physicochemical parameters by atomic contributions},
	doi       = {10.1021/ci990307l},
	issn      = {0095-2338},
	issue     = {5},
	pages     = {868-873},
	volume    = {39},
	journal   = {Journal of Chemical Information and Computer Sciences},
	publisher = {American Chemical Society},
	year      = {1999},
}

@Article{ZINC15,
	author       = {Teague Sterling and John J. Irwin},
	date         = {2015-11},
	journaltitle = {Journal of Chemical Information and Modeling},
	journal      = {Journal of Chemical Information and Modeling},
	title        = {ZINC 15 - Ligand Discovery for Everyone},
	doi          = {10.1021/acs.jcim.5b00559},
	issn         = {1549-960X},
	issue        = {11},
	pages        = {2324-2337},
	volume       = {55},
	journal      = {Journal of Chemical Information and Modeling},
	month        = {11},
	pmid         = {26479676},
	publisher    = {American Chemical Society},
	year         = {2015},
}

@Article{ECFP,
	author       = {David Rogers and Mathew Hahn},
	date         = {2010-05},
	journaltitle = {Journal of Chemical Information and Modeling},
	title        = {Extended-connectivity fingerprints},
	doi          = {10.1021/ci100050t},
	issn         = {1549-960X},
	issue        = {5},
	pages        = {742-754},
	volume       = {50},
	journal      = {Journal of Chemical Information and Modeling},
	month        = {5},
	pmid         = {20426451},
	publisher    = {American Chemical Society},
	year         = {2010},
}

@Article{Bach_LRP,
	author       = {Sebastian Bach and Alexander Binder and Grégoire Montavon and Frederick Klauschen and Klaus Robert Müller and Wojciech Samek},
	year         = {2015},
	date         = {2015-07},
	journaltitle = {PLoS ONE},
	journal      = {PLoS ONE},
	title        = {On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation},
	doi          = {10.1371/journal.pone.0130140},
	issn         = {1932-6203},
	issue        = {7},
	volume       = {10},
	pages        = {7},
	journal      = {Journal of Chemical Information and Computer Sciences},
	month        = {5},
	pmid         = {15154768},
	year         = {2004},
}

@Article{ALOGPS_VCCLab,
	author       = {Igor V. Tetko and Johann Gasteiger and Roberto Todeschini and Andrea Mauri and David Livingstone and Peter Ertl and Vladimir A. Palyulin and Eugene V. Radchenko and Nikolay S. Zefirov and Alexander S. Makarenko and Vsevolod Yu Tanchuk and Volodymyr V. Prokopenko},
	date         = {2005},
	journaltitle = {Journal of Computer-Aided Molecular Design},
	title        = {Virtual computational chemistry laboratory - Design and description},
	doi          = {10.1007/s10822-005-8694-y},
	issn         = {1573-4951},
	issue        = {6},
	pages        = {453-463},
	volume       = {19},
	journal      = {Journal of Computer-Aided Molecular Design},
	keywords     = {Drug design,Indices calculation,Model generation and validation,On-line analysis,Physico-chemical property predictions},
	pmid         = {16231203},
	publisher    = {Springer Netherlands},
	year         = {2005},
}

@Article{DeepTaylorDecomp,
	author       = {Grégoire Montavon and Sebastian Lapuschkin and Alexander Binder and Wojciech Samek and Klaus Robert Müller},
	date         = {2017-05},
	journaltitle = {Pattern Recognition},
	journal= {Pattern Recognition},
	title        = {Explaining nonlinear classification decisions with deep Taylor decomposition},
	doi          = {10.1016/j.patcog.2016.11.008},
	issn         = {0031-3203},
	pages        = {211-222},
	volume       = {65},
	journal      = {Pattern Recognition},
	keywords     = {Deep neural networks,Heatmapping,Image recognition,Relevance propagation,Taylor decomposition},
	month        = {5},
	publisher    = {Elsevier Ltd},
	year         = {2017},
}

@Article{AlphaFold2,
	author       = {John Jumper and Richard Evans and Alexander Pritzel and Tim Green and Michael Figurnov and Olaf Ronneberger and Kathryn Tunyasuvunakool and Russ Bates and Augustin Žídek and Anna Potapenko and Alex Bridgland and Clemens Meyer and Simon A.A. Kohl and Andrew J. Ballard and Andrew Cowie and Bernardino Romera-Paredes and Stanislav Nikolov and Rishub Jain and Jonas Adler and Trevor Back and Stig Petersen and David Reiman and Ellen Clancy and Michal Zielinski and Martin Steinegger and Michalina Pacholska and Tamas Berghammer and Sebastian Bodenstein and David Silver and Oriol Vinyals and Andrew W. Senior and Koray Kavukcuoglu and Pushmeet Kohli and Demis Hassabis},
	date         = {2021-08},
	journaltitle = {Nature},
	journal= {Nature},
	title        = {Highly accurate protein structure prediction with AlphaFold},
	doi          = {10.1038/s41586-021-03819-2},
	issn         = {1476-4687},
	issue        = {7873},
	pages        = {583-589},
	volume       = {596},
	journal      = {Nature},
	month        = {8},
	pmid         = {34265844},
	publisher    = {Nature Research},
	year         = {2021},
}

'
@InProceedings{AIAYN,
	author    = {Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, \Lukasz and Polosukhin, Illia},
	booktitle = {Advances in Neural Information Processing Systems},
	title     = {Attention is All you Need},
	editor    = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
	publisher = {Curran Associates, Inc.},
	url       = {https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf},
	volume    = {30},
	year      = {2017},
}

'
@Article{Chemformer,
	author       = {Irwin, Ross and Dimitriadis, Spyridon and He, Jiazhen and Bjerrum, Esben Jannik},
	date         = {2022-01},
	journaltitle = {Machine Learning: Science and Technology},
	journal      = {Machine Learning: Science and Technology},
	title        = {Chemformer: a pre-trained transformer for computational chemistry},
	doi          = {10.1088/2632-2153/ac3ffb},
	issn         = {2632-2153},
	language     = {en},
	number       = {1},
	pages        = {015022},
	url          = {https://dx.doi.org/10.1088/2632-2153/ac3ffb},
	urldate      = {2023-05-08},
	volume       = {3},
	publisher    = {IOP Publishing},
	shorttitle   = {Chemformer},
	year         = {2022},
}

'
@Report{MoleculeAttnTransformer,
	author      = {Maziarka, {\L}ukasz and Danel, Tomasz and Mucha, S{\l}awomir and Rataj, Krzysztof and Tabor, Jacek and Jastrz{\k{e}}bski, Stanis{\l}aw},
	date        = {2020-02},
	institution = {arXiv},
	title       = {Molecule {Attention} {Transformer}},
	doi         = {10.48550/arXiv.2002.08264},
	note        = {arXiv:2002.08264},
	url         = {http://arxiv.org/abs/2002.08264},
	urldate     = {2023-05-08},
	keywords    = {Computer Science - Machine Learning, Physics - Computational Physics, Statistics - Machine Learning},
	year        = {2020},
}
'
@Article{SolTranNet,
	author       = {Francoeur, Paul G. and Koes, David R.},
	date         = {2021-06},
	journaltitle = {Journal of Chemical Information and Modeling},
	journal= {Journal of Chemical Information and Modeling},
	title        = {{SolTranNet}-{A} {Machine} {Learning} {Tool} for {Fast} {Aqueous} {Solubility} {Prediction}},
	doi          = {10.1021/acs.jcim.1c00331},
	issn         = {1549-960X},
	language     = {eng},
	number       = {6},
	pages        = {2530--2536},
	volume       = {61},
	keywords     = {Machine Learning, Software, Solubility, Water},
	pmcid        = {PMC8900744},
	pmid         = {34038123},
	year         = {2021},
}
'
@Article{SaliencyMaps,
	author       = {Gevrey, Muriel and Dimopoulos, Ioannis and Lek, Sovan},
	date         = {2003-02},
	journaltitle = {Ecological Modelling},
	journal= {Ecological Modelling},
	title        = {Review and comparison of methods to study the contribution of variables in artificial neural network models},
	doi          = {10.1016/S0304-3800(02)00257-0},
	issn         = {0304-3800},
	language     = {en},
	number       = {3},
	pages        = {249--264},
	series       = {Modelling the structure of acquatic communities: concepts, methods and problems.},
	url          = {https://www.sciencedirect.com/science/article/pii/S0304380002002570},
	urldate      = {2023-05-08},
	volume       = {160},
	keywords     = {Artificial neural networks, Backpropagation, Non-linear relationships, Variables contribution, Sensitivity analysis, Perturbation, Partial derivatives, Trout, Habitat modelling},
	year         = {2003},
}

'
@Report{GradCAM,
	author     = {Ramprasaath R Selvaraju and Michael Cogswell and Abhishek Das and Ramakrishna Vedantam and Devi Parikh and Dhruv Batra},
	date       = {2017-10},
	title      = {Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization},
	doi        = {10.1109/iccv.2017.74},
	note       = {ISSN: 2380-7504},
	pages      = {618--626},
	url        = {http://gradcam.cloudcv.org},
	booktitle  = {2017 {IEEE} {International} {Conference} on {Computer} {Vision} ({ICCV})},
	issn       = {2380-7504},
	keywords   = {Visualization, Cats, Dogs, Computer architecture, Knowledge discovery},
	shorttitle = {Grad-{CAM}},
	year       = {2017},
}

'
@InProceedings{DeepLIFT_LRP,
	author    = {Shrikumar, Avanti and Greenside, Peyton and Kundaje, Anshul},
	booktitle = {Proceedings of the 34th {International} {Conference} on {Machine} {Learning} - {Volume} 70},
	date      = {2017-08},
	title     = {Learning important features through propagating activation differences},
	location  = {Sydney, NSW, Australia},
	pages     = {3145--3153},
	publisher = {JMLR.org},
	series    = {{ICML}'17},
	urldate   = {2023-05-08},
	year      = {2017},
}
'
@Report{MolBERT,
	author      = {Fabian, Benedek and Edlich, Thomas and Gaspar, Héléna and Segler, Marwin and Meyers, Joshua and Fiscato, Marco and Ahmed, Mohamed},
	date        = {2020-11},
	institution = {arXiv},
	title       = {Molecular representation learning with language models and domain-relevant auxiliary tasks},
	doi         = {10.48550/arXiv.2011.13230},
	note        = {arXiv:2011.13230},
	url         = {http://arxiv.org/abs/2011.13230},
	urldate     = {2023-05-25},
	keywords    = {Computer Science - Machine Learning, Computer Science - Artificial Intelligence},
	year        = {2020},
}
'
@Report{BART,
	author      = {Lewis, Mike and Liu, Yinhan and Goyal, Naman and Ghazvininejad, Marjan and Mohamed, Abdelrahman and Levy, Omer and Stoyanov, Ves and Zettlemoyer, Luke},
	date        = {2019-10},
	institution = {arXiv},
	title       = {{BART}: {Denoising} {Sequence}-to-{Sequence} {Pre}-training for {Natural} {Language} {Generation}, {Translation}, and {Comprehension}},
	doi         = {10.48550/arXiv.1910.13461},
	note        = {arXiv:1910.13461},
	url         = {http://arxiv.org/abs/1910.13461},
	urldate     = {2023-08-10},
	keywords    = {Computer Science - Computation and Language, Computer Science - Machine Learning, Statistics - Machine Learning},
	readstatus  = {read},
	shorttitle  = {{BART}},
	year        = {2019},
}
'
@Article{Perspective_MolViz,
	author       = {Wellawatte, Geemi P. and Gandhi, Heta A. and Seshadri, Aditi and White, Andrew D.},
	date         = {2023-04},
	journaltitle = {Journal of Chemical Theory and Computation},
	journal= {Journal of Chemical Theory and Computation},
	title        = {A {Perspective} on {Explanations} of {Molecular} {Prediction} {Models}},
	doi          = {10.1021/acs.jctc.2c01235},
	issn         = {1549-9618},
	number       = {8},
	pages        = {2149--2160},
	url          = {https://doi.org/10.1021/acs.jctc.2c01235},
	urldate      = {2023-08-18},
	volume       = {19},
	publisher    = {American Chemical Society},
	year         = {2023},
}
'
@Report{unreliablesaliency,
	author      = {Kindermans, Pieter-Jan and Hooker, Sara and Adebayo, Julius and Alber, Maximilian and Schütt, Kristof T. and Dähne, Sven and Erhan, Dumitru and Kim, Been},
	date        = {2017-11},
	institution = {arXiv},
	title       = {The ({Un})reliability of saliency methods},
	doi         = {10.48550/arXiv.1711.00867},
	note        = {arXiv:1711.00867},
	url         = {http://arxiv.org/abs/1711.00867},
	urldate     = {2023-08-21},
	keywords    = {Statistics - Machine Learning, Computer Science - Machine Learning},
	year        = {2017},
}

'
@Report{ChemBERTa,
	author      = {Chithrananda, Seyone and Grand, Gabriel and Ramsundar, Bharath},
	date        = {2020-10},
	institution = {arXiv},
	title       = {{ChemBERTa}: {Large}-{Scale} {Self}-{Supervised} {Pretraining} for {Molecular} {Property} {Prediction}},
	doi         = {10.48550/arXiv.2010.09885},
	note        = {arXiv:2010.09885},
	url         = {http://arxiv.org/abs/2010.09885},
	urldate     = {2023-08-28},
	annotation  = {Comment: Submitted to NeurIPS 2020 ML for Molecules Workshop},
	keywords    = {Computer Science - Machine Learning, Computer Science - Computation and Language, Physics - Chemical Physics, Quantitative Biology - Biomolecules, I.2.7, I.2.1, J.2, J.3},
	shorttitle  = {{ChemBERTa}},
	year        = {2020},
}

@InProceedings{BERT,
	author     = {Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
	booktitle  = {Proceedings of the 2019 {Conference} of the {North} {American} {Chapter} of the {Association} for {Computational} {Linguistics}: {Human} {Language} {Technologies}, {Volume} 1 ({Long} and {Short} {Papers})},
	date       = {2019-06},
	title      = {{BERT}: {Pre}-training of {Deep} {Bidirectional} {Transformers} for {Language} {Understanding}},
	doi        = {10.18653/v1/N19-1423},
	location   = {Minneapolis, Minnesota},
	pages      = {4171--4186},
	publisher  = {Association for Computational Linguistics},
	url        = {https://aclanthology.org/N19-1423},
	urldate    = {2023-09-06},
	shorttitle = {{BERT}},
	year       = {2019},
}

@Report{chinchilla,
	author      = {Hoffmann, Jordan and Borgeaud, Sebastian and Mensch, Arthur and Buchatskaya, Elena and Cai, Trevor and Rutherford, Eliza and Casas, Diego de Las and Hendricks, Lisa Anne and Welbl, Johannes and Clark, Aidan and Hennigan, Tom and Noland, Eric and Millican, Katie and Driessche, George van den and Damoc, Bogdan and Guy, Aurelia and Osindero, Simon and Simonyan, Karen and Elsen, Erich and Rae, Jack W. and Vinyals, Oriol and Sifre, Laurent},
	date        = {2022-03},
	institution = {arXiv},
	title       = {Training {Compute}-{Optimal} {Large} {Language} {Models}},
	doi         = {10.48550/arXiv.2203.15556},
	note        = {arXiv:2203.15556},
	url         = {http://arxiv.org/abs/2203.15556},
	urldate     = {2023-09-11},
	keywords    = {Computer Science - Computation and Language, Computer Science - Machine Learning},
	publisher   = {arxiv},
	year        = {2022},
}

@Report{toy_models_superpos,
	author      = {Elhage, Nelson and Hume, Tristan and Olsson, Catherine and Schiefer, Nicholas and Henighan, Tom and Kravec, Shauna and Hatfield-Dodds, Zac and Lasenby, Robert and Drain, Dawn and Chen, Carol and Grosse, Roger and McCandlish, Sam and Kaplan, Jared and Amodei, Dario and Wattenberg, Martin and Olah, Christopher},
	date        = {2022-09},
	institution = {arXiv},
	title       = {Toy {Models} of {Superposition}},
	doi         = {10.48550/arXiv.2209.10652},
	note        = {arXiv:2209.10652},
	url         = {http://arxiv.org/abs/2209.10652},
	urldate     = {2023-10-11},
	annotation  = {Comment: Also available at https://transformer-circuits.pub/2022/toy\_model/index.html},
	keywords    = {Computer Science - Machine Learning},
	year        = {2022},
}


@Report{monosemantic,
	author         = {Bricken, Trenton and Templeton, Adly and Batson, Joshua and Chen, Brian and Jermyn, Adam and Conerly, Tom and Turner, Nick and Anil, Cem and Denison, Carson and Askell, Amanda and Lasenby, Robert and Wu, Yifan and Kravec, Shauna and Schiefer, Nicholas and Maxwell, Tim and Joseph, Nicholas and Hatfield-Dodds, Zac and Tamkin, Alex and Nguyen, Karina and McLean, Brayden and Burke, Josiah E and Hume, Tristan and Carter, Shan and Henighan, Tom and Olah, Christopher},
	date           = {2023},
	institution    = {arXiv},
	title          = {Towards Monosemanticity: Decomposing Language Models With Dictionary Learning},
	url            = {https://transformer-circuits.pub/2023/monosemantic-features/index.html},
	comment-stefan = {Sparse overcomplete word vector representations M. Faruqui, Y. Tsvetkov, D. Yogatama, C. Dyer, N. Smith. arXiv preprint arXiv:1506.02004. 2015. Linear algebraic structure of word senses, with applications to polysemy S. Arora, Y. Li, Y. Liang, T. Ma, A. Risteski. Transactions of the Association for Computational Linguistics, Vol 6, pp. 483--495. MIT Press. 2018. Spine: Sparse interpretable neural embeddings A. Subramanian, D. Pruthi, H. Jhamtani, T. Berg-Kirkpatrick, E. Hovy. Proceedings of the AAAI Conference on Artificial Intelligence, Vol 32(1). 2018. Word embedding visualization via dictionary learning J. Zhang, Y. Chen, B. Cheung, B.A. Olshausen. arXiv preprint arXiv:1910.03833. 2019. Word2Sense: sparse interpretable word embeddings A. Panigrahi, H.V. Simhadri, C. Bhattacharyya. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 5692--5705. 2019. Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors Z. Yun, Y. Chen, B.A. Olshausen, Y. LeCun. arXiv preprint arXiv:2103.15949. 2021. Emergent Linear Representations in World Models of Self-Supervised Sequence Models N. Nanda, A. Lee, M. Wattenberg. arXiv preprint arXiv:2309.00941. 2023. Discovering latent knowledge in language models without supervision C. Burns, H. Ye, D. Klein, J. Steinhardt. arXiv preprint arXiv:2212.03827. 2022.},
	journal        = {Transformer Circuits Thread},
	year           = {2023},
}

@Report{attributionslie,
	author     = {Sixt, Leon and Granz, Maximilian and Landgraf, Tim},
	date       = {2020-11},
	title      = {When {Explanations} {Lie}: {Why} {Many} {Modified} {BP} {Attributions} {Fail}},
	language   = {en},
	pages      = {9046--9057},
	url        = {https://proceedings.mlr.press/v119/sixt20a.html},
	urldate    = {2023-12-11},
	issn       = {2640-3498},
	publisher  = {PMLR},
	shorttitle = {When {Explanations} {Lie}},
	year       = {2020},
}

@inproceedings{SHAP,
	author = {Lundberg, Scott M and Lee, Su-In},
	booktitle = {Advances in Neural Information Processing Systems},
	editor = {I. Guyon and U. Von Luxburg and S. Bengio and H. Wallach and R. Fergus and S. Vishwanathan and R. Garnett},
	pages = {},
	publisher = {Curran Associates, Inc.},
	title = {A Unified Approach to Interpreting Model Predictions},
	url = {https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf},
	volume = {30},
	year = {2017}
}

@Article{Yang2019_scaffold,
	author    = {Yang, Kevin and Swanson, Kyle and Jin, Wengong and Coley, Connor and Eiden, Philipp and Gao, Hua and Guzman-Perez, Angel and Hopper, Timothy and Kelley, Brian and Mathea, Miriam and others},
	title     = {Analyzing learned molecular representations for property prediction},
	number    = {8},
	pages     = {3370--3388},
	volume    = {59},
	journal   = {Journal of chemical information and modeling},
	publisher = {ACS Publications},
	year      = {2019},
}

@Report{ViT,
	author      = {Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
	date        = {2021-06},
	institution = {arXiv},
	title       = {An {Image} is {Worth} 16x16 {Words}: {Transformers} for {Image} {Recognition} at {Scale}},
	doi         = {10.48550/arXiv.2010.11929},
	note        = {arXiv:2010.11929},
	url         = {http://arxiv.org/abs/2010.11929},
	urldate     = {2024-01-08},
	annotation  = {Comment: Fine-tuning code and pre-trained models are available at https://github.com/google-research/vision\_transformer. ICLR camera-ready version with 2 small modifications: 1) Added a discussion of CLS vs GAP classifier in the appendix, 2) Fixed an error in exaFLOPs computation in Figure 5 and Table 6 (relative performance of models is basically not affected)},
	keywords    = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning},
	shorttitle  = {An {Image} is {Worth} 16x16 {Words}},
	year        = {2021},
}

@Article{AqSolDB,
	author       = {Sorkun, Murat Cihan and Khetan, Abhishek and Er, Süleyman},
	date         = {2019-08},
	journaltitle = {Scientific Data},
	journal      = {Scientific Data},
	title        = {{AqSolDB}, a curated reference set of aqueous solubility and {2D} descriptors for a diverse set of compounds},
	doi          = {10.1038/s41597-019-0151-1},
	issn         = {2052-4463},
	language     = {en},
	number       = {1},
	pages        = {143},
	url          = {https://www.nature.com/articles/s41597-019-0151-1},
	urldate      = {2024-01-08},
	volume       = {6},
	keywords     = {Cheminformatics, Thermodynamics},
	publisher    = {Nature Publishing Group},
	year         = {2019},
}

@Report{MegaMolBART,
	author      = {Nvidia},
	institution = {Github},
	title       = {MegaMolBART},
	url         = {https://github.com/NVIDIA/MegaMolBART},
	year        = {2022},
}

@Report{RDKit,
	author      = {Landrum, G.},
	institution = {RDKit},
	title       = {RDKit (Version 2023.3.3)},
	url         = {https://zenodo.org/records/8254217},
	year        = {2023},
}

@InProceedings{dovsilovic2018explainable,
	author       = {Do{\v{s}}ilovi{\'c}, Filip Karlo and Br{\v{c}}i{\'c}, Mario and Hlupi{\'c}, Nikica},
	booktitle    = {2018 41st International convention on information and communication technology, electronics and microelectronics (MIPRO)},
	title        = {Explainable artificial intelligence: A survey},
	organization = {IEEE},
	pages        = {0210--0215},
	year         = {2018},
}

@Article{FlamShepherd2022,
	author       = {Flam-Shepherd, Daniel and Zhu, Kevin and Aspuru-Guzik, Alán},
	date         = {2022-06},
	journaltitle = {Nature Communications},
	journal= {Nature Communications},
	title        = {Language models can learn complex molecular distributions},
	doi          = {10.1038/s41467-022-30839-x},
	issn         = {2041-1723},
	language     = {en},
	number       = {1},
	pages        = {3293},
	url          = {https://www.nature.com/articles/s41467-022-30839-x},
	urldate      = {2024-01-08},
	volume       = {13},
	keywords     = {Cheminformatics, Computational chemistry, Machine learning, Method development},
	publisher    = {Nature Publishing Group},
	year         = {2022},
}

@Article{lusci2013deep,
	author       = {Lusci, Alessandro and Pollastri, Gianluca and Baldi, Pierre},
	date         = {2013-07},
	journaltitle = {Journal of Chemical Information and Modeling},
	journal= {Journal of Chemical Information and Modeling},
	title        = {Deep {Architectures} and {Deep} {Learning} in {Chemoinformatics}: {The} {Prediction} of {Aqueous} {Solubility} for {Drug}-{Like} {Molecules}},
	doi          = {10.1021/ci400187y},
	issn         = {1549-9596},
	number       = {7},
	pages        = {1563--1575},
	url          = {https://doi.org/10.1021/ci400187y},
	urldate      = {2024-01-08},
	volume       = {53},
	publisher    = {American Chemical Society},
	shorttitle   = {Deep {Architectures} and {Deep} {Learning} in {Chemoinformatics}},
	year         = {2013},
}

@Article{reinvent,
	author       = {Blaschke, Thomas and Arús-Pous, Josep and Chen, Hongming and Margreitter, Christian and Tyrchan, Christian and Engkvist, Ola and Papadopoulos, Kostas and Patronov, Atanas},
	date         = {2020-12},
	journaltitle = {Journal of Chemical Information and Modeling},
	journal      = {Journal of Chemical Information and Modeling},
	title        = {{REINVENT} 2.0: {An} {AI} {Tool} for {De} {Novo} {Drug} {Design}},
	doi          = {10.1021/acs.jcim.0c00915},
	issn         = {1549-9596},
	number       = {12},
	pages        = {5918--5922},
	url          = {https://doi.org/10.1021/acs.jcim.0c00915},
	urldate      = {2024-01-19},
	volume       = {60},
	publisher    = {American Chemical Society},
	shorttitle   = {{REINVENT} 2.0},
	year         = {2020},
}

@Article{Otter2021,
	author       = {Otter, Daniel W. and Medina, Julian R. and Kalita, Jugal K.},
	date         = {2021-02},
	journaltitle = {IEEE Transactions on Neural Networks and Learning Systems},
	journal      = {IEEE Transactions on Neural Networks and Learning Systems},
	title        = {A {Survey} of the {Usages} of {Deep} {Learning} for {Natural} {Language} {Processing}},
	doi          = {10.1109/TNNLS.2020.2979670},
	issn         = {2162-2388},
	number       = {2},
	pages        = {604--624},
	url          = {https://ieeexplore.ieee.org/abstract/document/9075398},
	urldate      = {2024-01-29},
	volume       = {32},
	keywords     = {Machine learning, Natural language processing, Decoding, Neural networks, Computer architecture, Computational linguistics, Training, Computational linguistics, deep learning, machine learning, natural language processing (NLP), neural networks},
	year         = {2021},
}

@article{SMILES,
	title={SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules},
	author={Weininger, David},
	journal={Journal of chemical information and computer sciences},
	volume={28},
	number={1},
	pages={31--36},
	year={1988},
	publisher={ACS Publications}
}

@Article{MolecularTransformer18,
	author       = {Schwaller, Philippe and Laino, Teodoro and Gaudin, Théophile and Bolgar, Peter and Hunter, Christopher A. and Bekas, Costas and Lee, Alpha A.},
	date         = {2019-09},
	journaltitle = {ACS Central Science},
	journal      = {ACS Central Science},
	title        = {Molecular {Transformer}: {A} {Model} for {Uncertainty}-{Calibrated} {Chemical} {Reaction} {Prediction}},
	doi          = {10.1021/acscentsci.9b00576},
	issn         = {2374-7943},
	number       = {9},
	pages        = {1572--1583},
	url          = {https://doi.org/10.1021/acscentsci.9b00576},
	urldate      = {2024-01-30},
	volume       = {5},
	publisher    = {American Chemical Society},
	shorttitle   = {Molecular {Transformer}},
	year         = {2019},
}

@InProceedings{AttnViz_self,
	author   = {Chefer, Hila and Gur, Shir and Wolf, Lior},
	year     = {2021},
	title    = {Transformer {Interpretability} {Beyond} {Attention} {Visualization}},
	booktitle = {Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
	language = {en},
	pages    = {782--791},
	url      = {https://openaccess.thecvf.com/content/CVPR2021/html/Chefer_Transformer_Interpretability_Beyond_Attention_Visualization_CVPR_2021_paper.html},
	urldate  = {2024-01-30},
}

@InProceedings{AttnViz_MM,
	author    = {Chefer, Hila and Gur, Shir and Wolf, Lior},
	booktitle = {2021 {IEEE}/{CVF} {International} {Conference} on {Computer} {Vision} ({ICCV})},
	date      = {2021-10},
	title     = {Generic {Attention}-model {Explainability} for {Interpreting} {Bi}-{Modal} and {Encoder}-{Decoder} {Transformers}},
	doi       = {10.1109/ICCV48922.2021.00045},
	note      = {ISSN: 2380-7504},
	pages     = {387--396},
	url       = {https://ieeexplore.ieee.org/document/9710570},
	urldate   = {2024-01-30},
	issn      = {2380-7504},
	keywords  = {Measurement, Computer vision, Visualization, Image segmentation, Computational modeling, Computer architecture, Object detection, Explainable AI, Vision + language},
	year      = {2021},
}

@Article{SolvBERT,
	author       = {Jiahui Yu and Chengwei Zhang and Yingying Cheng and Yun-Fang Yang and Yuan-Bin She and Fengfan Liu and Weike Su and An Su},
	journaltitle = {Digital Discovery},
	journal      = {Digital Discovery},
	title        = {SolvBERT for solvation free energy and solubility prediction: a demonstration of an NLP model for predicting the properties of molecular complexes},
	doi          = {10.1039/d2dd00107a},
	url          = {https://doi.org/10.1039/D2DD00107A},
	journal      = {Digital Discovery},
	volume={2},
	number={2},
	pages={409--421},
	year={2023},
	publisher={Royal Society of Chemistry}
}

@Article{Le2012,
	title = {Quantitative Structure–Property Relationship Modeling of Diverse Materials Properties},
	volume = {112},
	ISSN = {1520-6890},
	url = {http://dx.doi.org/10.1021/cr200066h},
	DOI = {10.1021/cr200066h},
	number = {5},
	journal = {Chemical Reviews},
	publisher = {American Chemical Society (ACS)},
	author = {Le,  Tu and Epa,  V. Chandana and Burden,  Frank R. and Winkler,  David A.},
	year = {2012},
	month = jan,
	pages = {2889–2919}
}

@Article{Vermeire2022,
	title = {Predicting Solubility Limits of Organic Solutes for a Wide Range of Solvents and Temperatures},
	volume = {144},
	ISSN = {1520-5126},
	url = {http://dx.doi.org/10.1021/jacs.2c01768},
	DOI = {10.1021/jacs.2c01768},
	number = {24},
	journal = {Journal of the American Chemical Society},
	publisher = {American Chemical Society (ACS)},
	author = {Vermeire,  Florence H. and Chung,  Yunsie and Green,  William H.},
	year = {2022},
	month = jun,
	pages = {10785–10797}
}

@Article{Vermeire2021,
	author       = {Vermeire, Florence H. and Green, William H.},
	date         = {2021-08},
	year = {2021},
	journaltitle = {Chemical Engineering Journal},
	journal= {Chemical Engineering Journal},
	title        = {Transfer learning for solvation free energies: {From} quantum chemistry to experiments},
	doi          = {10.1016/j.cej.2021.129307},
	issn         = {1385-8947},
	pages        = {129307},
	url          = {https://www.sciencedirect.com/science/article/pii/S1385894721008925},
	urldate      = {2024-03-07},
	volume       = {418},
	shorttitle   = {Transfer learning for solvation free energies},
}

@article{Yang2019,
	title={Analyzing learned molecular representations for property prediction},
	author={Yang, Kevin and Swanson, Kyle and Jin, Wengong and Coley, Connor and Eiden, Philipp and Gao, Hua and Guzman-Perez, Angel and Hopper, Timothy and Kelley, Brian and Mathea, Miriam and others},
	journal={Journal of chemical information and modeling},
	volume={59},
	number={8},
	pages={3370--3388},
	year={2019},
	publisher={ACS Publications}
}

@article{sklearn,
	title={Scikit-learn: Machine Learning in {P}ython},
	author={Pedregosa, F. and Varoquaux, G. and Gramfort, A. and Michel, V.
		and Thirion, B. and Grisel, O. and Blondel, M. and Prettenhofer, P.
			and Weiss, R. and Dubourg, V. and Vanderplas, J. and Passos, A. and
			Cournapeau, D. and Brucher, M. and Perrot, M. and Duchesnay, E.},
	journal={Journal of Machine Learning Research},
	volume={12},
	pages={2825--2830},
	year={2011}
}

@article{Mastropietro2023,
	title={Calculation of exact Shapley values for explaining support vector machine models using the radial basis function kernel},
	author={Mastropietro, Andrea and Feldmann, Christian and Bajorath, J{\"u}rgen},
	journal={Scientific Reports},
	volume={13},
	number={1},
	pages={19561},
	year={2023},
	publisher={Nature Publishing Group UK London}
}