Filters








47 Hits in 4.9 sec

Dataset's chemical diversity limits the generalizability of machine learning predictions

Marta Glavatskikh, Jules Leguy, Gilles Hunault, Thomas Cauchy, Benoit Da Mota
<span title="2019-11-12">2019</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5aubiwi6v5beng6iqzj577kiaa" style="color: black;">Journal of Cheminformatics</a> </i> &nbsp;
The QM9 dataset has become the golden standard for Machine Learning (ML) predictions of various chemical properties.  ...  A statistical study of bonding distances and chemical functions shows that this new dataset encompasses more chemical diversity.  ...  Acknowledgements The calculation resources were provided by the LERIA laboratory. The authors would also like to thanks Jean-Mathieu Chantrein for his technical help.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s13321-019-0391-2">doi:10.1186/s13321-019-0391-2</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33430991">pmid:33430991</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/igmo2bpjdbdflee5qseetcgks4">fatcat:igmo2bpjdbdflee5qseetcgks4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200214133655/https://jcheminf.biomedcentral.com/track/pdf/10.1186/s13321-019-0391-2" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/79/71/797129a259b4eab420cc2d4307d2043fec6603b2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s13321-019-0391-2"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

MOESM3 of Dataset's chemical diversity limits the generalizability of machine learning predictions

Marta Glavatskikh, Jules Leguy, Gilles Hunault, Thomas Cauchy, Benoit Da Mota
<span title="2019-11-13">2019</span> <i title="figshare"> Figshare </i> &nbsp;
Details on the SOM affinity analysis.  ...  In summary, the formula accounts equally for similarity in density distribution and in chemical diversity and could be easily analyze by these terms.  ...  Fewer diversity of functional groups of QM9 leads to less universal SOM, upon which the PC9 molecules of uncommon classes would be projected mixed with the known classes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.6084/m9.figshare.10297151.v1">doi:10.6084/m9.figshare.10297151.v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mbemg2mw4vdspgm3j5sqxqe35u">fatcat:mbemg2mw4vdspgm3j5sqxqe35u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200221141902/https://s3-eu-west-1.amazonaws.com/pstorage-npg-968563215/18713513/13321_2019_391_MOESM3_ESM.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/15/76/1576ac9b1fa8c8baa7a25962300d3333bbe6dc4b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.6084/m9.figshare.10297151.v1"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> figshare.com </button> </a>

Electronic band structure screening for Dirac points in Heuslers [article]

Paul J. Meza-Morales, Alessandro Fumarola, Volha Taliaronak, Afrid Shirsekar, Jonathan Kidner, Zaheer Ali, Mazhar Ali
<span title="2022-05-05">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We then used machine learning to develop a model correlating the composition vs. number of Dirac points in the EBS for Heuslers and also other Cubic compounds by identifying said Dirac points using an  ...  The Heusler compounds have provided a playground of material candidates for various technological applications based on their highly diverse and tunable properties, controlled by chemical composition and  ...  These machine learning methods center around the core idea of learning against the hidden correlations of the material's structures with the physical property of relevance for a subgroup of materials,  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.02547v1">arXiv:2205.02547v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ozxrgizy5bhw5ggchupoyvta2i">fatcat:ozxrgizy5bhw5ggchupoyvta2i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220511070137/https://arxiv.org/pdf/2205.02547v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cd/85/cd8586c9b5dd04788c895ee4bfdc1de608617941.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2205.02547v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

How Do Graph Networks Generalize to Large and Diverse Molecular Systems? [article]

Johannes Gasteiger, Muhammed Shuaibi, Anuroop Sriram, Stephan Günnemann, Zachary Ulissi, C. Lawrence Zitnick, Abhishek Das
<span title="2022-04-06">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Chemical diversity (number of different elements), 2. system size (number of atoms per sample), 3. dataset size (number of data samples), and 4. domain shift (similarity of the training and test set).  ...  The predominant method of demonstrating progress of atomic graph neural networks are benchmarks on small and limited datasets.  ...  Acknowledgements We thank Brandon Wood for helpful discussions on performance and scaling aspects and the Open Catalyst team for their support, feedback, and discussions and for providing the foundational  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02782v1">arXiv:2204.02782v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3d5hi6rt7nbhfc7upwz2k5t44a">fatcat:3d5hi6rt7nbhfc7upwz2k5t44a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220530055114/https://arxiv.org/pdf/2204.02782v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cf/c8/cfc8d4e44e5250e8544c1ac744766787300e530e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2204.02782v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Quantifying Overfitting Potential in Drug Binding Datasets [chapter]

Brian Davis, Kevin Mcloughlin, Jonathan Allen, Sally R. Ellingson
<span title="">2020</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
In this paper, we investigate potential biases in datasets used to make drug binding predictions using machine learning.  ...  We find that the new metrics allow to quantify overfitting while not overly limiting training data and produce models with greater predictive value.  ...  Drug discovery programs need accurate computational methods to predict protein-drug binding, and advances in machine learning have improved the accuracy of these predictions used in early stages of drug  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-50420-5_44">doi:10.1007/978-3-030-50420-5_44</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6tgiccbesvaadbs64acrooxdqi">fatcat:6tgiccbesvaadbs64acrooxdqi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108132514/https://link.springer.com/content/pdf/10.1007%2F978-3-030-50420-5_44.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/b3/c7/b3c79c8f74b381ec55fe38c51ed3f846873d18b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-50420-5_44"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Fear in a Handful of Dust: The Epidemiological, Environmental and Economic Drivers of Death by PM2.5 Pollution

James Chen, Mira Zovko, Nika Šimurina, Vatroslav Zovko
<span title="2021-08-17">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vyslcn4ljzdq3jes5w7fln3qyu" style="color: black;">International Journal of Environmental Research and Public Health</a> </i> &nbsp;
The first step consists of conventional linear models and supervised machine learning alternatives.  ...  Linear regression and its machine learning equivalents also inform unsupervised machine learning methods such as clustering and manifold learning.  ...  Table 3 reports these measures of diversity and concentration with respect to the six machine learning models.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/ijerph18168688">doi:10.3390/ijerph18168688</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/34444435">pmid:34444435</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8393768/">pmcid:PMC8393768</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2mqckehjdvfddmg2nfjw6v2the">fatcat:2mqckehjdvfddmg2nfjw6v2the</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210903213159/https://mdpi-res.com/d_attachment/ijerph/ijerph-18-08688/article_deploy/ijerph-18-08688-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/f6/d3/f6d3d4143e3b36e7e9e76fa069aa204b6ae82c4b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/ijerph18168688"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8393768" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Enabling robust offline active learning for machine learning potentials using simple physics-based priors [article]

Muhammed Shuaibi, Saurabh Sivakumar, Rui Qi Chen, Zachary W. Ulissi
<span title="2020-08-25">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Developed models typically rely on a substantial amount of data to make reliable predictions of the potential energy landscape or careful active learning and uncertainty estimates.  ...  When starting with small datasets, convergence of active learning approaches is a major outstanding challenge which limited most demonstrations to online active learning.  ...  ACKNOWLEDGEMENTS We acknowledge the support from the U.S. Department of Energy, Office of Science, Basic Energy Sciences Award #DE-FOA-0001912.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.10773v1">arXiv:2008.10773v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ri6jwkbd2bdgvlqxw3zxqapkbi">fatcat:ri6jwkbd2bdgvlqxw3zxqapkbi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901031101/https://arxiv.org/pdf/2008.10773v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.10773v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Ten quick tips for deep learning in biology

Benjamin D. Lee, Anthony Gitter, Casey S. Greene, Sebastian Raschka, Finlay Maguire, Alexander J. Titus, Michael D. Kessler, Alexandra J. Lee, Marc G. Chevrette, Paul Allen Stewart, Thiago Britto-Borges, Evan M. Cofer (+9 others)
<span title="2022-03-24">2022</span> <i title="Public Library of Science (PLoS)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ch57atmlprauhhbqdf7x4ytejm" style="color: black;">PLoS Computational Biology</a> </i> &nbsp;
In particular, machine learning is concerned with the development and applications of algorithms that PLOS COMPUTATIONAL BIOLOGY  ...  Machine learning is a modern approach to problem-solving and task automation.  ...  Acknowledgments The authors would like the thank Daniel Himmelstein and the developers of Manubot for creating the software that enabled the collaborative composition of this manuscript.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1371/journal.pcbi.1009803">doi:10.1371/journal.pcbi.1009803</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/35324884">pmid:35324884</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC8946751/">pmcid:PMC8946751</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w4dc6qupsbecjlkcaroq7r2t3e">fatcat:w4dc6qupsbecjlkcaroq7r2t3e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220518054416/https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009803&amp;type=printable" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/45/4e/454e43f34835751bfa4209a1f13650cf1867d12e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1371/journal.pcbi.1009803"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> plos.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8946751" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

QMugs: Quantum Mechanical Properties of Drug-like Molecules [article]

Clemens Isert, Kenneth Atz, José Jiménez-Luna, Gisbert Schneider
<span title="2021-07-30">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Machine learning approaches in drug discovery, as well as in other areas of the chemical sciences, benefit from curated datasets of physical molecular properties.  ...  This dataset is intended to facilitate the development of models that learn from molecular data on different levels of theory while also providing insight into the corresponding relationships between molecular  ...  C.I. acknowledges support from the Scholarship Fund of the Swiss Chemical Industry.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.00367v2">arXiv:2107.00367v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nc7x2famrze5hobkvtmllnrxpa">fatcat:nc7x2famrze5hobkvtmllnrxpa</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210803224248/https://arxiv.org/pdf/2107.00367v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6d/84/6d844db1be2a7a55facfc6eb08531cb528efaaf1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2107.00367v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Structure–activity relationship-based chemical classification of highly imbalanced Tox21 datasets

Gabriel Idakwo, Sundar Thangapandian, Joseph Luttrell, Yan Li, Nan Wang, Zhaoxian Zhou, Huixiao Hong, Bei Yang, Chaoyang Zhang, Ping Gong
<span title="2020-10-27">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5aubiwi6v5beng6iqzj577kiaa" style="color: black;">Journal of Cheminformatics</a> </i> &nbsp;
In this study, in order to improve the prediction accuracy of imbalanced learning, we employed SMOTEENN, a combination of Synthetic Minority Over-sampling Technique (SMOTE) and Edited Nearest Neighbor  ...  We also found that a strong negative correlation existed between the prediction accuracy and the imbalance ratio (IR), which is defined as the number of inactive compounds divided by the number of active  ...  Acknowledgements Permission was granted by the Chief of Engineers, U.S. Army Corps of Engineers to publish this paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s13321-020-00468-x">doi:10.1186/s13321-020-00468-x</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/33372637">pmid:33372637</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j2dfmp2pavckbd2cawbjhinnra">fatcat:j2dfmp2pavckbd2cawbjhinnra</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428080927/https://aquila.usm.edu/cgi/viewcontent.cgi?article=19500&amp;context=fac_pubs" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/10/06/1006ed7e2c8827067e2708d2c40f6c6a858d64be.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1186/s13321-020-00468-x"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Split Optimization for Protein/Ligand Binding Models [article]

Brian Davis, Kevin Mcloughlin, Jonathan Allen, Sally Ellingson
<span title="2020-01-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we investigate potential biases in datasets used to make drug binding predictions using machine learning.  ...  We find that the new metrics allow to quantify overfitting while not overly limiting training data and produce models with greater predictive value.  ...  This issue of generalizability is common in machine learning applications, but is particularly relevant in settings with insufficient and non-uniformly distributed data, as is the case with drug binding  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03207v1">arXiv:2001.03207v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/tzpzw6rsdvfhzklviipe7rx2yy">fatcat:tzpzw6rsdvfhzklviipe7rx2yy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200321080835/https://arxiv.org/pdf/2001.03207v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2001.03207v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

ATOM3D: Tasks On Molecules in Three Dimensions [article]

Raphael J.L. Townshend, Martin Vögele, Patricia Suriana, Alexander Derry, Alexander Powers, Yianni Laloudakis, Sidhika Balachandar, Bowen Jing, Brandon Anderson, Stephan Eismann, Risi Kondor, Russ B. Altman (+1 others)
<span title="2022-01-15">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In particular, deep neural networks have gained significant attention, but their widespread adoption in the biomolecular domain has been limited by a lack of either systematic performance benchmarks or  ...  We implement several classes of three-dimensional molecular learning methods for each of these tasks and show that they consistently improve performance relative to methods based on one- and two-dimensional  ...  in the SPS representation directly from the protein 3D structure, rather than the predicted ones by the SSpro/ACCpro software [Magnan and Baldi, 2014, Cheng et al., 2005] as done in the DeepAffinity  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.04035v4">arXiv:2012.04035v4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5uvarnqwpjaxdei4hxa3d6gxku">fatcat:5uvarnqwpjaxdei4hxa3d6gxku</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220122151551/https://arxiv.org/pdf/2012.04035v4.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2a/47/2a47973215c6b860181e3b5950746e05fb92761b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2012.04035v4" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel

Chunguang Shen, Chenchong Wang, Xiaolu Wei, Yong Li, Sybrand van der Zwaag, Wei Xu
<span title="">2019</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ecglm3g5nvfvxm5i7f73czhmx4" style="color: black;">Acta Materialia</a> </i> &nbsp;
Furthermore, various important factors influencing the generalizability of the ML model are discussed in detail.  ...  Physical metallurgy-guided machine learning and artificial intelligent design of ultrahigh-strength stainless steel. Acta Materialia, 179, 201-214. https://doi. 'You share, we take care!'  ...  The other datasets were used to study the generalizability of the model.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.actamat.2019.08.033">doi:10.1016/j.actamat.2019.08.033</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qgyh3v6tqrgvvp3iywo34ymkwi">fatcat:qgyh3v6tqrgvvp3iywo34ymkwi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210427081153/https://repository.tudelft.nl/islandora/object/uuid%3Af1254cd4-f218-49a9-a854-115742be8de0/datastream/OBJ/download" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/60/ef/60efbce53adb9769abf101cf679cd842d1cfc80b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/j.actamat.2019.08.033"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Machine Learning-based Virtual Screening and Its Applications to Alzheimer's Drug Discovery: A Review

Kristy A Carpenter, Xudong Huang
<span title="2018-06-07">2018</span> <i title="Bentham Science"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/xtiwjcbzsbd35jtqmz56mrpmb4" style="color: black;">Current pharmaceutical design</a> </i> &nbsp;
As a subset of Artificial Intelligence (AI), Machine Learning (ML) is a powerful way of conducting VS for drug leads.  ...  Machines (SVM), Random Forests (RF), and Artificial Neural Networks (ANN).  ...  The authors would like to thank the MIT externship program for allowing KAC to be a student intern at MGH.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2174/1381612824666180607124038">doi:10.2174/1381612824666180607124038</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/29879881">pmid:29879881</a> <a target="_blank" rel="external noopener" href="https://pubmed.ncbi.nlm.nih.gov/PMC6327115/">pmcid:PMC6327115</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kvowpmifvjhpblsqbgkquamwmi">fatcat:kvowpmifvjhpblsqbgkquamwmi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200513132853/http://europepmc.org/backend/ptpmcrender.fcgi?accid=PMC6327115&amp;blobtype=pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fd/2f/fd2fa2b57511069e05573be448cd93af256656e2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2174/1381612824666180607124038"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6327115" title="pubmed link"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> pubmed.gov </button> </a>

Temporal convolutional networks predict dynamic oxygen uptake response from wearable sensors across exercise intensities [article]

Robert Amelard, Eric T Hedge, Richard L Hughson
<span title="2021-10-13">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A TCN model was developed using causal convolutions across an effective history length to model the time-dependent nature of VO_2.  ...  The best performing model encoded 218 s history length (TCN-VO_2 A), with 187 s, 97 s, and 76 s yielding less than 3 prediction accuracy (mean, 95 ml.min^-1, [-262, 218]), spanning transitions from low-moderate  ...  The primary limitations impacting the widespread generalizability of these results stem from the dataset's constrained demographic (young healthy adults) and structured exercise protocol.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.09987v2">arXiv:2105.09987v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ose3lifyrje73lkjmwmfss7gvu">fatcat:ose3lifyrje73lkjmwmfss7gvu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211015070323/https://arxiv.org/pdf/2105.09987v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/12/49/124981a908bab8c3e5537a8c381507029e4007c5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2105.09987v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 47 results