Machines first, humans second: on the importance of algorithmic interpretation of open chemistry data
Open accessAbstract
The current rise in the use of open lab notebook techniques means that there are an increasing number of scientists who make chemical information freely and openly available to the entire community as a series of micropublications that are released shortly after the conclusion of each experiment. We propose that this trend be accompanied by a thorough examination of data sharing priorities. We argue that the most significant immediate benefactor of open data is in fact chemical algorithms, which are capable of absorbing vast quantities of data, and using it to present concise insights to working chemists, on a scale that could not be achieved by traditional publication methods. Making this goal practically achievable will require a paradigm shift in the way individual scientists translate their data into digital form, since most contemporary methods of data entry are designed for presentation to humans rather than consumption by machine learning algorithms. We discuss some of the complex issues involved in fixing current methods, as well as some of the immediate benefits that can be gained when open data is published correctly using unambiguous machine readable formats. Graphical AbstractLab notebook entries must target both visualisation by scientists and use by machine learning algorithms.
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?
A considerable limitation of many databases is that the data are not 'model-ready' or machine-readable, which is needed to successfully use any machine learning methodology.
“A considerable limitation of many databases is the data are not ‘model-ready’ or machine-readable19 which is needed to successfully use any machine learning methodology.”
From Exploiting machine learning for end-to-end drug discovery and development (2019) · cites this paper as [19]
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
ZINC: A Free Tool to Discover Chemistry for Biology
Irwin, J. J., Sterling, T., Mysinger, M. M., Bolstad, E. S. D., & Coleman, R. G. (2012) · Journal of Chemical Information and Modeling · doi:10.1021/ci3001277 · Cited by 2,533 · cited 1× · see citing works
“The multitude of public databases [1-6], freely distributed vendor compound libraries a and directly shared lab notebooks [7] make it possible for scientists to prospectively gather together a large knowledgebase.”
BackgroundCotton, F. A., Wilkinson, G., & Gaus, P. L. (1978) · Journal of Molecular Structure · doi:10.1016/0022-2860(78)87123-3 · Cited by 2,018 · cited 1× · see citing works
“carboranes [51]), which raises an important point that is sometimes lost in software: the originating”
BackgroundChemSpider: An Online Chemical Information Resource
Pence, H. E., & Williams, A. J. (2010) · Journal of Chemical Education · doi:10.1021/ed100697w · Cited by 1,277 · cited 1× · see citing works
“The multitude of public databases [1-6], freely distributed vendor compound libraries a and directly shared lab notebooks [7] make it possible for scientists to prospectively gather together a large knowledgebase.”
BackgroundSelf-citationLinstrom, P. J. (2005) · Medical Entomology and Zoology · Cited by 985 · see citing works
A survey of current work in biomedical text mining
Cohen, A. M. (2005) · Briefings in Bioinformatics · doi:10.1093/bib/6.1.57 · Cited by 767 · cited 1× · see citing works
“Noble efforts to extract this information by text mining of chemical names [12-15] or optical structure recognition [16-18] have resulted in an error rate that is so high that it is arguably making the data scarcity problem worse.”
BackgroundDalby, A., Nourse, J. G., Hounshell, W. D., Gushurst, A. K. I., Grier, D., Leland, B., & Laufer, J. (1992) · Journal of chemical information and computer sciences · doi:10.1021/ci00007a012 · Cited by 600 · cited 1× · see citing works
“For example, MDL Molfiles provide a number of capabilities for specifying chemical queries [55] as atom and bond annotations.”
Background(2000) · Choice Reviews Online · doi:10.5860/choice.37sup-288 · Cited by 532 · see citing works
PubChem as a public resource for drug discovery
Li, Q., Cheng, T., Wang, Y., & Bryant, S. H. (2010) · Drug Discovery Today · doi:10.1016/j.drudis.2010.10.003 · Cited by 366 · cited 1× · see citing works
“The multitude of public databases [1-6], freely distributed vendor compound libraries and directly shared lab notebooks [7] make it possible for scientists to prospectively gather together a large knowledgebase.”
BackgroundOpen PHACTS: semantic interoperability for drug discovery
Williams, A. J., Harland, L., Groth, P., Pettifer, S., Chichester, C., Willighagen, E. L., Evelo, C. T., Blomberg, N., Ecker, G., Goble, C., et al. (2012) · Drug Discovery Today · doi:10.1016/j.drudis.2012.05.016 · Cited by 321 · cited 1× · see citing works
“These challenges have directly influenced some of the approaches associated with the Open PHACTS semantic web project [48] where a “ chemical lenses ” approach has been utilised to focus the user in on various forms of the chemical [49].”
BackgroundSelf-citationOSCAR4: a flexible architecture for chemical text-mining
Jessop, D. M., Adams, S., Willighagen, E., Hawizy, L., & Murray‐Rust, P. (2011) · Journal of Cheminformatics · doi:10.1186/1758-2946-3-41 · Cited by 214 · cited 1× · see citing works
“Noble efforts to extract this information by text mining of chemical names [12-15] or optical structure recognition [16-18] have resulted in an error rate that is so high that it is arguably making the data scarcity problem worse.”
BackgroundChemicalTagger: A tool for semantic text-mining in chemistry
Hawizy, L., Jessop, D. M., Adams, N., & Murray‐Rust, P. (2011) · Journal of Cheminformatics · doi:10.1186/1758-2946-3-17 · Cited by 192 · cited 1× · see citing works
“Noble efforts to extract this information by text mining of chemical names [12-15] or optical structure recognition [16-18] have resulted in an error rate that is so high that it is arguably making the data scarcity problem worse.”
BackgroundFilippov, I. V., & Nicklaus, M. C. (2009) · Journal of Chemical Information and Modeling · doi:10.1021/ci800067r · Cited by 189 · cited 1× · see citing works
“Noble efforts to extract this information by text mining of chemical names [12-15] or optical structure recognition [16-18] have resulted in an error rate that is so high that it is arguably making the data scarcity problem worse.”
BackgroundHastings, J., Chepelev, L. L., Willighagen, E., Adams, N., Steinbeck, C., & Dumontier, M. (2011) · PLoS ONE · doi:10.1371/journal.pone.0025513 · Cited by 130 · cited 1× · see citing works
“The multitude of public databases [1-6], freely distributed vendor compound libraries and directly shared lab notebooks [7] make it possible for scientists to prospectively gather together a large knowledgebase.”
BackgroundWilliams, A. J., Ekins, S., & Tkachenko, V. (2012) · Drug Discovery Today · doi:10.1016/j.drudis.2012.02.013 · Cited by 126 · cited 1× · see citing works
“This is, in a nutshell, why most chemical data is inaccurate [19-23].”
BackgroundSelf-citationA quality alert and call for improved curation of public chemistry databases
Williams, A. J., & Ekins, S. (2011) · Drug Discovery Today · doi:10.1016/j.drudis.2011.07.007 · Cited by 104 · cited 1× · see citing works
“This is, in a nutshell, why most chemical data is inaccurate [19-23].”
BackgroundSelf-citationHigh-Throughput Identification of Chemistry in Life Science Texts
Corbett, P. T., & Murray‐Rust, P. (2006) · Lecture notes in computer science · doi:10.1007/11875741_11 · Cited by 99 · cited 1× · see citing works
“Noble efforts to extract this information by text mining of chemical names [12-15] or optical structure recognition [16-18] have resulted in an error rate that is so high that it is arguably making the data scarcity problem worse.”
BackgroundBerthold, M. R., Glen, R. C., Diederichs, K., Kohlbacher, O., & Fischer, I. (2005) · Lecture notes in computer science · doi:10.1007/11560500 · Cited by 86 · see citing works
CLiDE Pro: The Latest Generation of CLiDE, a Tool for Optical Chemical Structure Recognition
Valko, A. T., & Johnson, A. P. (2009) · Journal of Chemical Information and Modeling · doi:10.1021/ci800449t · Cited by 86 · cited 1× · see citing works
“Noble efforts to extract this information by text mining of chemical names [12-15] or optical structure recognition [16-18] have resulted in an error rate that is so high that it is arguably making the data scarcity problem worse.”
BackgroundUtopia documents: linking scholarly literature with research data
Attwood, T. K., Kell, D. B., McDermott, P., Marsh, J., Pettifer, S. R., & Thorne, D. J. (2010) · Bioinformatics · doi:10.1093/bioinformatics/btq383 · Cited by 78 · cited 1× · see citing works
“…seldom being done by the scientists who were responsible for the experiment: for the most part, machine readable data from the published literature is created by paid curators or algorithms designed to extract information from the intractable formats used by the primary literature and patents [10].”
BackgroundGraphical representation standards for chemical structure diagrams (IUPAC Recommendations 2008)
Brecher, J. (2008) · Pure and Applied Chemistry · doi:10.1351/pac200880020277 · Cited by 73 · cited 1× · see citing works
“There are documented standards for visual representation [33,34], but there has been little effort to implement these for the purpose of lossless interconversion between presentation and informatics.”
BackgroundChemical literature data extraction: The CLiDE Project
Ibison, P., Jacquot, M., Kam, F., Neville, A. G., Simpson, R. W., Tonnelier, C., Venczel, T., & Johnson, A. P. (1993) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci00013a010 · Cited by 71 · cited 1× · see citing works
“Noble efforts to extract this information by text mining of chemical names [12-15] or optical structure recognition [16-18] have resulted in an error rate that is so high that it is arguably making the data scarcity problem worse.”
BackgroundDetection and Assignment of Common Scaffolds in Project Databases of Lead Molecules
Clark, A. M., & Labute, P. (2008) · Journal of Medicinal Chemistry · doi:10.1021/jm801098a · Cited by 56 · cited 1× · see citing works
“avoid destroying the information in the first place [37-39].”
BackgroundSelf-citationTen simple rules of live tweeting at scientific conferences.
Ekins, S., & Perlstein, E. O. (2014) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1003789 · Cited by 55 · cited 1× · see citing works
“Twitter is also a valuable tool for real-time microblogging from scientific conferences [63]: there are an increasing number of scientists who routinely “ live tweet ” what they learn during conferences, and there is no reason why digitally accessible data cannot be incorporated into this stream.”
BackgroundSelf-citationClark, A., Labute, P., & Santavy, M. (2006) · Journal of Chemical Information and Modeling · doi:10.1021/ci050550m · Cited by 55 · see citing works
Self-citationRecent chemistry of the η5-cyclopentadienyl dicarbonyl iron anion
Theys, R. D., Dudley, M. E., & Hossain, M. M. (2008) · Coordination Chemistry Reviews · doi:10.1016/j.ccr.2007.12.022 · Cited by 49 · cited 1× · see citing works
“The drawing in 11(a) shows a chemist-friendly graphical representation, which is suitable for publication in manuscripts [52].”
BackgroundGraphical representation of stereochemical configuration (IUPAC Recommendations 2006)
Brecher, J. (2006) · Pure and Applied Chemistry · doi:10.1351/pac200678101897 · Cited by 49 · cited 1× · see citing works
“There are documented standards for visual representation [33,34], but there has been little effort to implement these for the purpose of lossless interconversion between presentation and informatics.”
BackgroundOpen Drug Discovery Teams: A Chemistry Mobile App for Collaboration
Ekins, S., Clark, A. M., & Williams, A. J. (2012) · Molecular Informatics · doi:10.1002/minf.201200034 · Cited by 38 · cited 1× · see citing works
“For example, the Open Drug Discovery Teams (ODDT) project [58] continuously scours Twitter feeds looking for specific hashtags that relate to its collection of topics, which mostly pertain to rare and neglected diseases, and other precompetitive scientific topics (e.g. green chemistry and drug…”
BackgroundSelf-citationAutomated structure verification based on a combination of 1D 1H NMR and 2D 1H13C HSQC spectra
Golotvin, S. S., Vodopianov, E., Pol, R., Lefebvre, B. A., Williams, A. J., Rutkowske, R. D., & Spitzer, T. D. (2007) · Magnetic Resonance in Chemistry · doi:10.1002/mrc.2034 · Cited by 37 · cited 1× · see citing works
“This approach can be extended to analytical data including, where feasible, validation checking between spectra and their associated compounds [24,25], or CIF checking [26].”
MethodSelf-citationRzepa, H. S., Murray‐Rust, P., & Whitaker, B. J. (1998) · Journal of Chemical Information and Computer Sciences · doi:10.1021/ci9803233 · Cited by 35 · cited 1× · see citing works
“On the other hand, if a user posts chemical data using molsync.com , or links to a verified entry in a database like ChemSpider or PubChem, or any other link that can be resolved to a download that advertises a chemical MIME type [57] it may well be crawled by information extraction services.”
BackgroundAutomated structure verification based on 1H NMR prediction
Golotvin, S. S., Vodopianov, E., Lefebvre, B. A., Williams, A. J., & Spitzer, T. D. (2006) · Magnetic Resonance in Chemistry · doi:10.1002/mrc.1781 · Cited by 34 · cited 1× · see citing works
“where feasible, validation checking between spectra and their associated compounds [24,25], or CIF checking [26].”
Self-citationDigital Data Repositories in Chemistry and Their Integration with Journals and Electronic Notebooks
Harvey, M. J., Mason, N. J., & Rzepa, H. S. (2014) · Journal of Chemical Information and Modeling · doi:10.1021/ci500302p · Cited by 33 · cited 1× · see citing works
“Traditionally this process involved scouring the peer reviewed literature, either online through paywalls or physically within the walls of a library, and in some cases perusing privately collected data on the subject [8].”
BackgroundClark, A. M. (2011) · Journal of Chemical Information and Modeling · doi:10.1021/ci200488k · Cited by 31 · cited 3× · see citing works
“…and works well in simple cases, but poorly defined valence rules for unusual bond types, and the absence of a common method for overriding the default formula, means that many nontrivial molecules cannot be drawn using the most popular cheminformatics file formats, such as MDL Molfile [40].”
BackgroundMethodInfluentialSelf-citationWhy Open Drug Discovery Needs Four Simple Rules for Licensing Data and Models
Williams, A. J., WILBANKS, J. T., & Ekins, S. (2012) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1002706 · Cited by 30 · cited 1× · see citing works
“The reuse of such data may require data licensing and we have suggested some rules that could be helpful [9].”
BackgroundSelf-citationFirst steps towards semantic descriptions of electronic laboratory notebook records
Coles, S. J., Frey, J. G., Bird, C., Whitby, R. J., & Day, A. (2013) · Journal of Cheminformatics · doi:10.1186/1758-2946-5-52 · Cited by 29 · cited 1× · see citing works
“Much attention of late has been given to modern on-line collaborative tools, such as using Google Docs to coauthor and share content, and for using electronic lab notebooks (ELNs) with a blog-like interface [35].”
MethodScientific Lenses to Support Multiple Views over Linked Chemistry Data
Batchelor, C. R., Brenninkmeijer, C. Y. A., Chichester, C. H., Davies, M., Digles, D., Dunlop, I., Evelo, C. T., Gaulton, A., Goble, C., Gray, A. J. G., et al. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-11964-9_7 · Cited by 28 · cited 1× · see citing works
“These challenges have directly influenced some of the approaches associated with the Open PHACTS semantic web project [48] where a “ chemical lenses ” approach has been utilised to focus the user in on various forms of the chemical [49].”
BackgroundSelf-citationClark, A. M., Bunin, B. A., Litterman, N. K., Schürer, S. C., & Visser, U. (2014) · PeerJ · doi:10.7717/peerj.524 · Cited by 21 · cited 1× · see citing works
“The emergence of standards for capturing this kind of high level metadata in a semantic form [66] is an essential step toward enabling the construction of algorithms that can mine the Internet for available knowledge, and create robust models that are based on something other than noise.”
BackgroundSelf-citation2D Depiction of Fragment Hierarchies
Clark, A. M. (2009) · Journal of Chemical Information and Modeling · doi:10.1021/ci900350h · Cited by 17 · cited 1× · see citing works
“Re-derivation of scaffolds and orientation can be attempted after the fact, but it is far more advisable to avoid destroying the information in the first place [37-39].”
BackgroundSelf-citationChemSpider: Integrating Structure-Based Resources Distributed across the Internet
Williams, A. J. (2010) · ACS symposium series · doi:10.1021/bk-2010-1060.ch002 · Cited by 16 · cited 1× · see citing works
“The multitude of public databases [1-6], freely distributed vendor compound libraries and directly shared lab notebooks [7] make it possible for scientists to prospectively gather together a large knowledgebase.”
BackgroundSelf-citationEnhancing Learning with Online Resources, Social Networking, and Digital Libraries
Belford, R. E., Moore, J. W., & Pence, H. E. (2010) · ACS symposium series · doi:10.1021/bk-2010-1060 · Cited by 12 · see citing works
Day, A., Coles, S. J., Bird, C., Frey, J. G., Whitby, R. J., Tkachenko, V., & Williams, A. J. (2015) · Journal of Chemical Information and Modeling · doi:10.1021/ci5005948 · Cited by 12 · cited 1× · see citing works
“Some progress in terms of checking data formats is being made by the utilisation of chemistry specific components into the Labtrove platform [36].”
MethodSelf-citationCMLLite: a design philosophy for CML
Townsend, J. A., & Murray‐Rust, P. (2011) · Journal of Cheminformatics · doi:10.1186/1758-2946-3-39 · Cited by 12 · cited 1× · see citing works
“For example, the Chemical Markup Language (CML) [56] is for all practical purposes a superset of all possible chemical formats, since additional tags can be introduced by any writer without affecting validity, which passes the interpretation problem down the line: there is no guarantee that other…”
BackgroundBachrach, S. M. (2012) · Journal of Cheminformatics · doi:10.1186/1758-2946-4-34 · Cited by 9 · cited 1× · see citing works
“There are many advocates of the use of SMILES or InChI codes for raw structure representation [41], mainly because they are convenient for storing in spreadsheets or text files, and have intrinsic canonical properties.”
BackgroundRendering Molecular Sketches for Publication Quality Output
Clark, A. M. (2013) · Molecular Informatics · doi:10.1002/minf.201200171 · Cited by 7 · cited 2× · see citing works
“…specified by aspects that are implemented by the server - such as chemical reactions - are drawn using a high grade rendering lay-out algorithm [54] and passed to the front end as vector drawing instructions, which means that the page can be rendered to any resolution, and also can be sent to…”
BackgroundSelf-citationEkins, S., Alex, C., & Wood, J. (2013) · Molecular Genetics and Metabolism · doi:10.1016/j.ymgme.2012.11.076 · Cited by 1 · see citing works
Self-citationThe Open Drug Discovery Teams (ODDT) Mobile App For Green Chemistry
Ekins, S., m clark, A., & M Clark, A. (2012) · Figshare · doi:10.6084/m9.figshare.92858 · Cited by 1 · see citing works
Self-citationMining public domain data as a basis for drug repurposing
Williams, A., Tkachenko, V., & Ekins, S. (2013) · Figshare · doi:10.6084/m9.figshare.658961 · Cited by 1 · see citing works
Self-citationEkins, S., m clark, A., & M Clark, A. (2012) · Figshare · doi:10.6084/m9.figshare.93007 · Cited by 1 · see citing works
Self-citationOn the Accuracy of Chemical Structures Found on the Internet
Williams, A., Muratov, E., Fant, A., Fourches, D., Tropsha, A., & Sharpe, D. (2013) · Figshare · doi:10.6084/m9.figshare.662308 · Cited by 1 · see citing works
Self-citationLiving Molecules App to create Ingredients lists
Ekins, S., & Clark, A. (2013) · Figshare · doi:10.6084/m9.figshare.712593 · Cited by 1 · see citing works
Self-citationSecure sharing with mobile cheminformatics apps
Ekins, S., & Clark, A. M. (2012) · Figshare · doi:10.6084/m9.figshare.95654 · Cited by 1 · see citing works
Self-citation
Flagged first, then by citations
2 of the 52 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- [27]PubChem, ChemSpider and ChEBI are regularly cited internet resources, which can be accessed via the URLs [ http://pubchem.ncbi.nlm.nih.gov], [ http://chemspider.com] and [ http://www.ebi.ac.uk/chebi] respectively (accessed October 2014).
Cited by
Sorted by citations
Southan, C., Sharman, J., Benson, H., Faccenda, E., Pawson, A. J., Alexander, S. P. H., Buneman, O., Davenport, A., McGrath, J., Peters, J., et al. (2015) · Nucleic Acids Res. · doi:10.1093/nar/gkv1037 · Cited by 1,121 · see citing works
“Recent publications continue to highlight challenges of operating in the intersection of bioinformatics and chemin-formatics (20,21,34,35).”
BackgroundExploiting machine learning for end-to-end drug discovery and development
Ekins, S., Puhl, A. C., Zorn, K. M., Lane, T. R., Russo, D. P., Klein, J. J., Hickey, A. J., & Clark, A. M. (2019) · Nature Materials · doi:10.1038/s41563-019-0338-z · Cited by 578 · see citing works
Self-citationA review of molecular representation in the age of machine learning
Wigh, D. S., Goodman, J. M., & Lapkin, A. A. (2022) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1603 · Cited by 398 · see citing works
“nontrivial valency could lead to the wrong number of implied hydrogen atoms; an important issue not easily solved (simply requiring the number of H-atoms to be specified might compromise back-compatibility).(50)”
BackgroundData-driven materials research enabled by natural language processing and information extraction
Olivetti, E. A., Cole, J. M., Kim, E., Kononova, O., Ceder, G., Han, T. Y.-J., & Hiszpanski, A. M. (2020) · Applied Physics Reviews · doi:10.1063/5.0021106 · Cited by 302 · see citing works
Opportunities and challenges using artificial intelligence in ADME/Tox
Bhhatarai, B., Walters, W. P., Hop, C. E. C. A., Lanza, G., & Ekins, S. (2019) · Nature Materials · doi:10.1038/s41563-019-0332-5 · Cited by 118 · see citing works
Self-citationMulti-scale Modeling in Clinical Oncology: Opportunities and Barriers to Success
Yankeelov, T. E., An, G. C., Saut, O., Luebeck, E. G., Popel, A. S., Ribba, B., Vicini, P., Zhou, X., Weis, J. A., Ye, K., et al. (2016) · Annals of Biomedical Engineering · doi:10.1007/s10439-016-1691-6 · Cited by 80 · see citing works
Multiple Machine Learning Comparisons of HIV Cell-based and Reverse Transcriptase Data Sets
Zorn, K. M., Lane, T. R., Russo, D. P., Clark, A. M., Makarov, V., & Ekins, S. (2019) · Molecular Pharmaceutics · doi:10.1021/acs.molpharmaceut.8b01297 · Cited by 62 · see citing works
Self-citationGuerrero, J. P., Nguewa, P., & García‐Sosa, A. T. (2021) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1513 · Cited by 61 · see citing works
“176 Ekins et al. (2015) analyzed and identified more than 500 molecules with associated target information 176 to create the Collaborative Drug Discovery database.”
BackgroundEvolution of game-play in the Australian Football League from 2001 to 2015
Woods, C. T., Robertson, S. J., & Collier, N. F. (2016) · Journal of Sports Sciences · doi:10.1080/02640414.2016.1240879 · Cited by 59 · see citing works
Entity recognition in the biomedical domain using a hybrid approach
Basaldella, M., Furrer, L., Tasso, C., & Rinaldi, F. (2017) · Journal of Biomedical Semantics · doi:10.1186/s13326-017-0157-6 · Cited by 48 · see citing works
OGER++: hybrid multi-type entity recognition
Furrer, L., Jancso, A., Colic, N., & Rinaldi, F. (2019) · Journal of Cheminformatics · doi:10.1186/s13321-018-0326-3 · Cited by 39 · see citing works
Towards automation of chemical process route selection based on data mining
Jacob, P., Yamin, P., Perez-Storey, C., Hopgood, M., & Lapkin, A. A. (2016) · Green Chemistry · doi:10.1039/c6gc02482c · Cited by 35 · see citing works
Complex mixtures by NMR and complex NMR for mixtures: experimental and publication challenges
Wist, J. (2016) · Magnetic Resonance in Chemistry · doi:10.1002/mrc.4533 · Cited by 22 · see citing works
A Survey on the Problems Affecting the Development of Open Government Data Initiatives
Roa, H. N., Loza-Aguirre, E., & Flores, P. (2019) · International Conference on eDemocracy & eGovernment · doi:10.1109/icedeg.2019.8734452 · Cited by 21 · see citing works
“Finally, data scarcity refers to that data is difficult to collect or to produce, and on most occasions is not enough to be useful [49].”
BackgroundDesigning drugs optimized for both blood–brain barrier permeation and intra-cerebral partition
Dichiara, M., Cosentino, G., Giordano, G., Pasquinucci, L., Marrazzo, A., Costanzo, G., & Amata, E. (2023) · Expert Opinion on Drug Discovery · doi:10.1080/17460441.2023.2294118 · Cited by 17 · see citing works
“Overall, while AI-driven strategies collectively enhance the efficiency of drug discovery processes, a significant limitation still arises from the heterogeneity of data sets due to varied and non-comparable experimental conditions [60,61].”
BackgroundJeannerat, D. (2016) · Magnetic Resonance in Chemistry · doi:10.1002/mrc.4527 · Cited by 15 · see citing works
Müller, S. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-01064-7 · Cited by 9 · see citing works
“1, errors in structures can originate from a variety of sources, including human errors [1].”
BioAssay Templates for the semantic web
Clark, A. M., Litterman, N. K., Kranz, J. E., Gund, P., Gregory, K., & Bunin, B. A. (2016) · PeerJ Computer Science · doi:10.7717/peerj-cs.61 · Cited by 9 · see citing works
Self-citationGad, A., Manuel, A., Jinuraj, K. R., John, L., Sajeev, R., Priya, V. G. S., & Jaleel.U.C, A. (2017) · Computational Biology and Chemistry · doi:10.1016/j.compbiolchem.2017.07.005 · Cited by 5 · see citing works
Choosing an appropriate model chemistry in a big data context: Application to dative bonding
Almas, Q. L., Keefe, B. L., Profitt, T. A., & Pearson, J. K. (2016) · Computational and Theoretical Chemistry · doi:10.1016/j.comptc.2016.04.005 · Cited by 4 · see citing works
Southan, C., Sharman, J. L., Faccenda, E., Pawson, A. J., Harding, S. D., & Davies, J. A. (2018) · ACS Omega · doi:10.1021/acsomega.8b00884 · Cited by 4 · see citing works
Learning adaptive representations for entity recognition in the biomedical domain
Lauriola, I., Aiolli, F., Lavelli, A., & Rinaldi, F. (2021) · Journal of Biomedical Semantics · doi:10.1186/s13326-021-00238-0 · Cited by 3 · see citing works
Developing Next Generation Tools for Computational Toxicology
Clark, A. M., Zorn, K. M., Lingerfelt, M. A., & Ekins, S. (2018) · Computational Toxicology · doi:10.1002/9781119282594.ch14 · Cited by 3 · see citing works
Self-citationPreparing Your Data for Publication
McEwen, L. (2020) · American Chemical Society eBooks · doi:10.1021/acsguide.30105 · Cited by 1 · see citing works
Mobile Apps for Green Chemistry
Clark, A. M., Williams, A. J., & Ekins, S. (2016) · Encyclopedia of Inorganic and Bioinorganic Chemistry · doi:10.1002/9781119951438.eibc2413 · Cited by 1 · see citing works
Self-citationPeer Review #3 of "BioAssay templates for the semantic web (v0.1)"
(2016) · PeerJ Computer Science · doi:10.7287/peerj-cs.61v0.1/reviews/3
Reporting Data in the Digital Environment
McEwen, L. (2020) · American Chemical Society eBooks · doi:10.1021/acsguide.30102
Peer Review #2 of "BioAssay templates for the semantic web (v0.1)"
(2016) · PeerJ Computer Science · doi:10.7287/peerj-cs.61v0.1/reviews/2
Peer Review #1 of "BioAssay templates for the semantic web (v0.1)"
(2016) · PeerJ Computer Science · doi:10.7287/peerj-cs.61v0.1/reviews/1
McEwen, L. (2020) · American Chemical Society eBooks · doi:10.1021/acsguide.30107
Additional Machine Interpretation Problems
Banik, G. M. (2020) · American Chemical Society eBooks · doi:10.1021/acsguide.30204
McEwen, L. (2020) · American Chemical Society eBooks · doi:10.1021/acsguide.30103
NOCTIS: open-source toolkit that turns reaction data into actionable graph networks
Lopanitsyna, N., Pasquini, M., & Stenta, M. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-01118-w
“These numbers highlight the necessity of effective data management aligned with FAIR principles (Findable, Accessible, Interoperable, and Reusable) [21–24].”
- Authors
- Clark, A. M., Williams, A. J., & Ekins, S.
- Affiliations
- Royal Society of Chemistry (GB)
- Collaborative Drug Discovery (United States) (US)
- Corresponding author
- Clark, Alex M
- Venue
- Journal of Cheminformatics
- Published
- 2015-03-22
- Volume
- 7
- Issue
- 1
- Pages
- 9-9
- ISSN
- 1758-2946 (ISSN-L)
- PMC
- PMC4369291
- OpenAlex
- W2138095945
- Cited by
- 33
- References
- 52
- Citations by year
- 2025: 2 · 2023: 1 · 2022: 1 · 2021: 2 · 2020: 6 · 2019: 5 · 2018: 2 · 2017: 2 · 2016: 11 · 2015: 1
- FWCI
- 14.39
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Journal of Cheminformatics (publishedVersion, cc-by)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › Research Data Management Practices
- Social Sciences › Decision Sciences › Information Systems and Management › Scientific Computing and Data Management
- Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
- Keywords
- open lab notebooks, open data, machine-readable data formats, data sharing, machine learning, chemical information, data curation
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
