"<label style=\"text-align: center; color: #20335d; font-weight: 900; font-size: 18pt;\">Tutorial example on Crystal prediction II:</label> <label style=\"color: #20335d;font-weight: 900; font-size: 15pt;\"> Visualizing material-similarity for the case of octet-binary zincblende-vs.-rocksalt semiconductors</label>",
" </p>",
" <p style=\"font-size: 15px;\"> developed by Angelo Ziletti, Ankit Kariryaa, Fawzi Mohamed, Luca Ghiringhelli, and Matthias Scheffler. [Last update September 13, 2016]</p>"
" <h4 class=\"modal-title\" id=\"lasso-motivation-modal-label\">Introduction and motivation</h4>",
" </div>",
" <div class=\"modal-body lasso_instructions\">",
" <p> In this tutorial, we present a tool that produces two-dimensional structure maps for octet binary compounds, by starting from a high-dimensional set of <i>features</i> (coordinates) that identify each data point (material), based on free-atom data of the atomic species constituting the binary material. </p>",
" ",
" <p> The low-dimensional embedding methods (here, two-dimensional for the sake of visualization) are <i>unsupervised</i> machine-learning algorithms; so, in our example, the algorithm processes only the spatial arrangement of the points in the high-dimensional representation that is determined by the user. </p>",
" ",
" <p> In the linear method, <b>principal component analysis (<a href=\"https://en.wikipedia.org/wiki/Feature_scaling\" target=\"_blank\">PCA</a>)</b>, the direction (linear combination of the input coordinates) with the maximum variance is identified as the first principal component (PC). The direction perpendicular to the first PC with the largest variance is the second PC.",
" The process can be iterated up to as many dimensions as the initial dimensionality of the data, but here we stop at the second dimension and give the amount of total variance recovered by the first two principal components. </p>",
" <p> In the two popular non-linear method we chose, <b>multidimensional scaling (<a href=\"https://en.wikipedia.org/wiki/Multidimensional_scaling\" target=\"_blank\">MDS</a>) </b> tries to preserve the distances from the given high-dimensional to the two-dimensional representation, ",
" and the <b>t-Distributed Stochastic Neighbor Embedding (<a href=\"https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding\" target=\"_blank\">t-SNE</a>) </b> tries to preserve the local shape of groups of neighboring points. Both methods use a notion of distance that in our example is the Euclidean norm, even if in principle it could be any proper norm. </p>",
"",
" <p> In the results, we show the data points colored according to the difference in energy between the Rocksalt (RS) and Zincblende (ZB) crystal structures (both relaxed to their local minima) of the material they represent. The labeling and consequent coloring is independent of the embedding method used, therefore the labeling is an <i>a posteriori</i>",
" check that the high-dimensional representation could contain information about the labeling itself. In practice, if the coloring identifies clearly distinct areas, then the two dimensional representation is a map for the prediction of the labels, so that a new data point of unknown labeling, that lands in the 2D map in a area of points with known labeling, is expected to belong to that same labeling. </p>",
" ",
"<p>The merit of the embedding methods is to provide relatively inexpensive tools to visually test whether a given set of features contains information about an investigated property (label). For this reason, they are widely used as preliminary tools for discovering structures in the data. </p>",
"<p> The prediction of RS vs ZB structure from a simple descriptor has a notable history in materials science [1-7], where descriptors were designed by chemically/physically-inspired intuition. </p>",
"",
" <p>References:</p>",
" <ol>",
" <li>J. A. van Vechten, Phys. Rev. 182, 891 (1969).</li>",
" <li>J. C. Phillips, Rev. Mod. Phys. 42, 317 (1970).</li>",
" <li>J. St. John and A.N. Bloch, Phys. Rev. Lett. 33, 1095 (1974).</li>",
" <li>J. R. Chelikowsky and J. C. Phillips, Phys. Rev. B 17, 2453 (1978).</li>",
" <li>A. Zunger, Phys. Rev. B 22, 5839 (1980).</li>",
" <li>D. G. Pettifor, Solid State Commun. 51, 31 (1984).</li>",
" <li>Y. Saad, D. Gao, T. Ngo, S. Bobbitt, J. R. Chelikowsky, and W. Andreoni, Phys. Rev. B 85, 104104 (2012).</li>",
"object": "<script>\nvar beaker = bkHelper.getBeakerObject().beakerObj;\n</script>\n<style type=\"text/css\">\n .lasso_instructions{\n font-size: 15px;\n } \n</style>\n<!-- Button trigger modal -->\n<button type=\"button\" class=\"btn btn-default\" data-toggle=\"modal\" data-target=\"#lasso-motivation-modal\">\n Introduction and motivation\n</button>\n\n<!-- Modal -->\n<div style=\"display: none;\" class=\"modal fade\" id=\"lasso-motivation-modal\" tabindex=\"-1\" role=\"dialog\" aria-labelledby=\"lasso-motivation-modal-label\">\n <div class=\"modal-dialog modal-lg\" role=\"document\">\n <div class=\"modal-content\">\n <div class=\"modal-header\">\n <button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">×</span></button>\n <h4 class=\"modal-title\" id=\"lasso-motivation-modal-label\">Introduction and motivation</h4>\n </div>\n <div class=\"modal-body lasso_instructions\">\n <p> In this tutorial, we present a tool that produces two-dimensional structure maps for octet binary compounds, by starting from a high-dimensional set of <i>features</i> (coordinates) that identify each data point (material), based on free-atom data of the atomic species constituting the binary material. </p>\n \n <p> The low-dimensional embedding methods (here, two-dimensional for the sake of visualization) are <i>unsupervised</i> machine-learning algorithms; so, in our example, the algorithm processes only the spatial arrangement of the points in the high-dimensional representation that is determined by the user. </p>\n \n <p> In the linear method, <b>principal component analysis (<a href=\"https://en.wikipedia.org/wiki/Feature_scaling\" target=\"_blank\">PCA</a>)</b>, the direction (linear combination of the input coordinates) with the maximum variance is identified as the first principal component (PC). The direction perpendicular to the first PC with the largest variance is the second PC.\n The process can be iterated up to as many dimensions as the initial dimensionality of the data, but here we stop at the second dimension and give the amount of total variance recovered by the first two principal components. </p>\n <p> In the two popular non-linear method we chose, <b>multidimensional scaling (<a href=\"https://en.wikipedia.org/wiki/Multidimensional_scaling\" target=\"_blank\">MDS</a>) </b> tries to preserve the distances from the given high-dimensional to the two-dimensional representation, \n and the <b>t-Distributed Stochastic Neighbor Embedding (<a href=\"https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding\" target=\"_blank\">t-SNE</a>) </b> tries to preserve the local shape of groups of neighboring points. Both methods use a notion of distance that in our example is the Euclidean norm, even if in principle it could be any proper norm. </p>\n\n <p> In the results, we show the data points colored according to the difference in energy between the Rocksalt (RS) and Zincblende (ZB) crystal structures (both relaxed to their local minima) of the material they represent. The labeling and consequent coloring is independent of the embedding method used, therefore the labeling is an <i>a posteriori</i>\n check that the high-dimensional representation could contain information about the labeling itself. In practice, if the coloring identifies clearly distinct areas, then the two dimensional representation is a map for the prediction of the labels, so that a new data point of unknown labeling, that lands in the 2D map in a area of points with known labeling, is expected to belong to that same labeling. </p>\n \n<p>The merit of the embedding methods is to provide relatively inexpensive tools to visually test whether a given set of features contains information about an investigated property (label). For this reason, they are widely used as preliminary tools for discovering structures in the data. </p>\n<p> The prediction of RS vs ZB structure from a simple descriptor has a notable history in materials science [1-7], where descriptors were designed by chemically/physically-inspired intuition. </p>\n\n <p>References:</p>\n <ol>\n <li>J. A. van Vechten, Phys. Rev. 182, 891 (1969).</li>\n <li>J. C. Phillips, Rev. Mod. Phys. 42, 317 (1970).</li>\n <li>J. St. John and A.N. Bloch, Phys. Rev. Lett. 33, 1095 (1974).</li>\n <li>J. R. Chelikowsky and J. C. Phillips, Phys. Rev. B 17, 2453 (1978).</li>\n <li>A. Zunger, Phys. Rev. B 22, 5839 (1980).</li>\n <li>D. G. Pettifor, Solid State Commun. 51, 31 (1984).</li>\n <li>Y. Saad, D. Gao, T. Ngo, S. Bobbitt, J. R. Chelikowsky, and W. Andreoni, Phys. Rev. B 85, 104104 (2012).</li>\n </ol>\n </div>\n <div class=\"modal-footer\">\n <button type=\"button\" class=\"btn btn-default\" data-dismiss=\"modal\">Close</button>\n<!-- <button type=\"button\" class=\"btn btn-primary\">Save changes</button> -->\n </div>\n </div>\n </div>\n</div>"
"<p> In this example, you can run the linear low-dimensional embedding method, <b>principal component analysis (<a href=\"https://en.wikipedia.org/wiki/Feature_scaling\" target=\"_blank\">PCA</a>)</b> and two selected non-linear methods, <b>multidimensional scaling (<a href=\"https://en.wikipedia.org/wiki/Multidimensional_scaling\" target=\"_blank\">MDS</a>) </b>",
"<p> The input features, that can be selected in the checklist below (any number of features larger than 2 is allowed), represent chemical elements constituting binary octet materials, that crystallize typically into rocksalt or zincblende crystal structure. </p>",
"<p> The next step is to select the embedding method (exclusive selection) and whether each feature is pre-processed by dividing it by the standard deviation of the whole population (all data points). Note that the feature are anyhow centered around their mean value as pre-processing.</p> ",
" ",
"<p> After selecting the list of features, the method, and the normalization criterion, click <b>“Run two-dimensional embedding”</b> to apply the selected method. </p>",
" ",
"<p> During and at the end of the run, a brief summary is printed out below the <b>“Run two-dimensional embedding”</b> button. After the end of the run, click on <b>“View interactive 2D scatter plot”</b> (it is unlocked at the end of the run) to open a new tab where the two-dimensional map is shown as an interactive scatter plot. </p>",
"<p> Note1: the plot stays active also after another run is performed, so that the output of several sets of input parameters can be compared in the viewer tabs.</p>",
" <p> Note2: with the following selection of features:<br> ",
" and PCA method, one obtains a result similar to Fig. 4 in Y. Saad, D. Gao, T. Ngo, S. Bobbitt, J. R. Chelikowsky, and W. Andreoni, Phys. Rev. B 85, 104104 (2012).",
" The plot may appear mirrored because the sign of the principal component is immaterial. Besides, the input data are slightly different (here, everything is calculated at the converged LDA level).",
"object": "<script>\nvar beaker = bkHelper.getBeakerObject().beakerObj;\n</script>\n<style type=\"text/css\">\n .lasso_instructions{\n font-size: 15px;\n } \n</style>\n<!-- Button trigger modal -->\n<button type=\"button\" class=\"btn btn-default\" data-toggle=\"modal\" data-target=\"#lasso-instructions-modal\">\n Instructions\n</button>\n\n<!-- Modal -->\n<div class=\"modal fade\" id=\"lasso-instructions-modal\" tabindex=\"-1\" role=\"dialog\" aria-labelledby=\"lasso-instructions-modal-label\" style=\"display: none;\">\n <div class=\"modal-dialog\" role=\"document\">\n <div class=\"modal-content\">\n <div class=\"modal-header\">\n <button type=\"button\" class=\"close\" data-dismiss=\"modal\" aria-label=\"Close\"><span aria-hidden=\"true\">×</span></button>\n <h4 class=\"modal-title\" id=\"lasso-instructions-modal-label\">Instructions</h4>\n </div>\n <div class=\"modal-body lasso_instructions\">\n<p> In this example, you can run the linear low-dimensional embedding method, <b>principal component analysis (<a href=\"https://en.wikipedia.org/wiki/Feature_scaling\" target=\"_blank\">PCA</a>)</b> and two selected non-linear methods, <b>multidimensional scaling (<a href=\"https://en.wikipedia.org/wiki/Multidimensional_scaling\" target=\"_blank\">MDS</a>) </b>\n and <b>t-Distributed Stochastic Neighbor Embedding (<a href=\"https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding\" target=\"_blank\">t-SNE</a>) </b>. </p>\n \n<p> The input features, that can be selected in the checklist below (any number of features larger than 2 is allowed), represent chemical elements constituting binary octet materials, that crystallize typically into rocksalt or zincblende crystal structure. </p>\n<p> The next step is to select the embedding method (exclusive selection) and whether each feature is pre-processed by dividing it by the standard deviation of the whole population (all data points). Note that the feature are anyhow centered around their mean value as pre-processing.</p> \n \n<p> After selecting the list of features, the method, and the normalization criterion, click <b>“Run two-dimensional embedding”</b> to apply the selected method. </p>\n \n<p> During and at the end of the run, a brief summary is printed out below the <b>“Run two-dimensional embedding”</b> button. After the end of the run, click on <b>“View interactive 2D scatter plot”</b> (it is unlocked at the end of the run) to open a new tab where the two-dimensional map is shown as an interactive scatter plot. </p>\n<p> Note1: the plot stays active also after another run is performed, so that the output of several sets of input parameters can be compared in the viewer tabs.</p>\n <p> Note2: with the following selection of features:<br> \n ['rs(A)', 'rs(B)', 'rp(A)', 'rp(B)', 'Es(A)/sqrt(Zval(A))', 'Es(B)/sqrt(Zval(B))', 'Ep(A)/sqrt(Zval(A))', 'Ep(B)/sqrt(Zval(B))']<br>\n and PCA method, one obtains a result similar to Fig. 4 in Y. Saad, D. Gao, T. Ngo, S. Bobbitt, J. R. Chelikowsky, and W. Andreoni, Phys. Rev. B 85, 104104 (2012).\n The plot may appear mirrored because the sign of the principal component is immaterial. Besides, the input data are slightly different (here, everything is calculated at the converged LDA level).\n </p>\n </div>\n <div class=\"modal-footer\">\n <button type=\"button\" class=\"btn btn-default\" data-dismiss=\"modal\">Close</button>\n<!-- <button type=\"button\" class=\"btn btn-primary\">Save changes</button> -->\n </div>\n </div>\n </div>\n</div>"
" <p class=\"lasso_selection_description\"><b>Primary features </b>",
" (all energies are in eV and all distances in Å, hover the mouse pointer over the feature names to see a full description):</p>",
" <form id=\"lasso_features_select\">",
" <div class=\"lasso_form_group\">",
" <label class =\"col-xs-4 col-md-4 col-lg-2\" title=\"Ionization potential of atom A\"> <input type=\"checkbox\" value=\"IP(A)\" > <i>IP</i> <sup>A</sup></label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"IP(B)\" > <span title=\"Ionization potential of atom B\"><i>IP</i> <sup>B</sup></span></label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"EA(A)\" > <span title=\"Electron affinity of atom A\"> <i>EA</i> <sup>A</sup></span></label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"EA(B)\" > <span title=\"Electron affinity of atom B\"> <i>EA</i> <sup>B</sup></span></label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HOMO(A)\" > <span title=\"Energy of highest occupied molecular orbital for atom A\"><i>E</i> <sup>A</sup><sub>HOMO</sub></span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HOMO(B)\" > <span title=\"Energy of highest occupied molecular orbital for atom B\"> <i>E</i> <sup>B</sup><sub>HOMO</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"LUMO(A)\" > <span title=\"Energy of lowest unoccupied molecular orbital for atom A\"> <i>E</i> <sup>A</sup><sub>LUMO</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"LUMO(B)\" > <span title=\"Energy of lowest unoccupied molecular orbital for atom B\"> <i>E</i> <sup>B</sup><sub>LUMO</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rs(A)\" CHECKED > <span title=\"Radius at which the radial probability density of the valence s orbital is maximum for atom A\"> <i>r</i><sub>s</sub><sup>A</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rs(B)\" CHECKED > <span title=\"Radius at which the radial probability density of the valence s orbital is maximum for atom B\"> <i>r</i><sub>s</sub><sup>B</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rp(A)\" CHECKED > <span title=\"Radius at which the radial probability density of the valence p orbital is maximum for atom A\"> <i>r</i><sub>p</sub><sup>A</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rp(B)\" CHECKED > <span title=\"Radius at which the radial probability density of the valence p orbital is maximum for atom B\"> <i>r</i><sub>p</sub><sup>B</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rd(A)\" CHECKED > <span title=\"Radius at which the radial probability density of the valence d orbital is maximum for atom A\"> <i>r</i><sub>d</sub><sup>A</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rd(B)\" CHECKED > <span title=\"Radius at which the radial probability density of the valence d orbital is maximum for atom B\"> <i>r</i><sub>d</sub><sup>B</sup> </span> </label>",
" <span title=\"Energy of the valence s orbital(s) divided by the square root of the number of valence electrons of atom A. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>s</sub><sup>A</sup>/sqrt(<i>Z</i> <sup>A</sup><sub>val</sub>) </span> </label>",
" <span title=\"Energy of the valence s orbital(s) divided by the square root of the number of valence electrons of atom B. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>s</sub><sup>B</sup>/sqrt(<i>Z</i> <sup>B</sup><sub>val</sub>) </span> </label>",
" <span title=\"Energy of the valence p orbital(s) divided by the square root of the number of valence electrons of atom A. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>p</sub><sup>A</sup>/sqrt(<i>Z</i> <sup>A</sup><sub>val</sub>) </span> </label>",
" <span title=\"Energy of the valence p orbital(s) divided by the square root of the number of valence electrons of atom B. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>p</sub><sup>B</sup>/sqrt(<i>Z</i> <sup>B</sup><sub>val</sub>) </span> </label>",
" ",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"d_AA\" > <span title=\"Bond length of atomA-atomA dimer\"> <i>d</i><sup>AA</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"d_BB\"> <span title=\"Bond length of atomB-atomB dimer\"> <i>d</i><sup>BB</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HL_gap_AA\" > <span title=\"HOMO-LUMO gap of atomA-atomA dimer\"> Δ<i>E</i> <sup>AA</sup><sub>HL</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HL_gap_BB\" > <span title=\"HOMO-LUMO gap of atomB-atomB dimer\"> Δ<i>E</i> <sup>BB</sup><sub>HL</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Ebinding_AA\" > <span title=\"Binding energy of atomA-atomA dimer\"> <i>E</i> <sup>AA</sup><sub>b</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Ebinding_BB\" > <span title=\"Binding energy of atomB-atomB dimer\"> <i>E</i> <sup>BB</sup><sub>b</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Z(A)\" > <span title=\"Atomic number of atom A\"> <i>Z</i> <sup>A</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Z(B)\" > <span title=\"Atomic number of atom B\"> <i>Z</i> <sup>B</sup> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"val(A)\" > <span title=\"Number of valence electrons of atom A\"> <i>Z</i> <sup>A</sup><sub>val</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"val(B)\" > <span title=\"Number of valence electrons of atom B\"> <i>Z</i> <sup>B</sup><sub>val</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"period(A)\" > <span title=\"Period (in the periodic table) of atom A\"> <i>n</i> <sup>A</sup><sub>period</sub> </span> </label>",
" <label class =\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"period(B)\" > <span title=\"Period (in the periodic table) of atom B\"> <i>n</i> <sup>B</sup><sub>period</sub> </span> </label>",
" <label title=\"This button becomes active when the run is finished. By clicking it, an interactive structural-similarity plot will be opened\"> <a href=\"#\" target=\"_blank\" class=\"btn btn-primary disabled\" id=\"lasso_result_button\" >View interactive 2D scatter plot</a> </label>",
"</div> <!-- End of lasso_control -->",
""
],
"hidden": true
},
"output": {
"selectedType": "BeakerDisplay",
"outputArrived": true,
"elapsedTime": 0,
"state": {},
"result": {
"type": "BeakerDisplay",
"innertype": "Html",
"object": "<script>\nvar beaker = bkHelper.getBeakerObject().beakerObj;\n</script>\n<script>\nvar run_lasso = function() {\n $(\"#lasso_result_button\").removeClass(\"active\").addClass(\"disabled\");\n getFeatures();\n getEmbedMethod();\n getStandardize();\n beaker.evaluate(\"lasso_cell\"); // evaluate cells with tag \"lasso_cell\"\n // view_result()\n};\nvar reset_lasso = function(){\n beaker.evaluate(\"lasso_gui\");\n};\nvar getFeatures = function() {\n beaker.selected_feature_list = [];\n $('#lasso_features_select input:checkbox').each(function () {\n if(this.checked )\n beaker.selected_feature_list.push(this.value);\n });\n};\n\n \nvar getEmbedMethod = function() {\n beaker.embed_method = \"pca\";\n $('#embed_method_selector input:radio').each(function () {\n if(this.checked )\n beaker.embed_method = this.value;\n });\n};\n \nvar getStandardize = function() {\n beaker.standardize = \"yes\";\n $('#standardize input:radio').each(function () {\n if(this.checked )\n beaker.standardize = this.value;\n });\n};\n \nbeaker.view_result = function(result_link) {\n// beaker.evaluate(\"lasso_viewer_result\").then(function(x) {\n $(\"#lasso_result_button\").attr(\"href\", result_link);\n// }); \n $(\"#lasso_result_button\").removeClass(\"disabled\").addClass(\"active\");\n}\n</script>\n<style type=\"text/css\">\n label {\n font-size: 18px;\n }\n .lasso_control{\n font-size: 18px;\n } \n.lasso_form_group input {\n width: 15px;\n height: 15px;\n padding: 0;\n margin:0;\n padding-right:5px; \n vertical-align: bottom;\n top: -1px;\n} \n .lasso_selection_description{\n padding: 10px 15px;\n }\n</style>\n<div class=\"lasso_control\">\n <div class=\"row\">\n <p class=\"lasso_selection_description\"><b>Primary features </b>\n (all energies are in eV and all distances in Å, hover the mouse pointer over the feature names to see a full description):</p>\n <form id=\"lasso_features_select\">\n <div class=\"lasso_form_group\">\n <label class=\"col-xs-4 col-md-4 col-lg-2\" title=\"Ionization potential of atom A\"> <input type=\"checkbox\" value=\"IP(A)\"> <i>IP</i> <sup>A</sup></label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"IP(B)\"> <span title=\"Ionization potential of atom B\"><i>IP</i> <sup>B</sup></span></label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"EA(A)\"> <span title=\"Electron affinity of atom A\"> <i>EA</i> <sup>A</sup></span></label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"EA(B)\"> <span title=\"Electron affinity of atom B\"> <i>EA</i> <sup>B</sup></span></label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HOMO(A)\"> <span title=\"Energy of highest occupied molecular orbital for atom A\"><i>E</i> <sup>A</sup><sub>HOMO</sub></span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HOMO(B)\"> <span title=\"Energy of highest occupied molecular orbital for atom B\"> <i>E</i> <sup>B</sup><sub>HOMO</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"LUMO(A)\"> <span title=\"Energy of lowest unoccupied molecular orbital for atom A\"> <i>E</i> <sup>A</sup><sub>LUMO</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"LUMO(B)\"> <span title=\"Energy of lowest unoccupied molecular orbital for atom B\"> <i>E</i> <sup>B</sup><sub>LUMO</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rs(A)\" checked=\"\"> <span title=\"Radius at which the radial probability density of the valence s orbital is maximum for atom A\"> <i>r</i><sub>s</sub><sup>A</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rs(B)\" checked=\"\"> <span title=\"Radius at which the radial probability density of the valence s orbital is maximum for atom B\"> <i>r</i><sub>s</sub><sup>B</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rp(A)\" checked=\"\"> <span title=\"Radius at which the radial probability density of the valence p orbital is maximum for atom A\"> <i>r</i><sub>p</sub><sup>A</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rp(B)\" checked=\"\"> <span title=\"Radius at which the radial probability density of the valence p orbital is maximum for atom B\"> <i>r</i><sub>p</sub><sup>B</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rd(A)\" checked=\"\"> <span title=\"Radius at which the radial probability density of the valence d orbital is maximum for atom A\"> <i>r</i><sub>d</sub><sup>A</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"rd(B)\" checked=\"\"> <span title=\"Radius at which the radial probability density of the valence d orbital is maximum for atom B\"> <i>r</i><sub>d</sub><sup>B</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Es(A)/sqrt(Zval(A))\"> \n <span title=\"Energy of the valence s orbital(s) divided by the square root of the number of valence electrons of atom A. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>s</sub><sup>A</sup>/sqrt(<i>Z</i> <sup>A</sup><sub>val</sub>) </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Es(B)/sqrt(Zval(B))\"> \n <span title=\"Energy of the valence s orbital(s) divided by the square root of the number of valence electrons of atom B. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>s</sub><sup>B</sup>/sqrt(<i>Z</i> <sup>B</sup><sub>val</sub>) </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Ep(A)/sqrt(Zval(A))\"> \n <span title=\"Energy of the valence p orbital(s) divided by the square root of the number of valence electrons of atom A. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>p</sub><sup>A</sup>/sqrt(<i>Z</i> <sup>A</sup><sub>val</sub>) </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Ep(B)/sqrt(Zval(B))\"> \n <span title=\"Energy of the valence p orbital(s) divided by the square root of the number of valence electrons of atom B. [Phys. Rev. B 85, 104104 (2012)]\"> <i>E</i><sub>p</sub><sup>B</sup>/sqrt(<i>Z</i> <sup>B</sup><sub>val</sub>) </span> </label>\n \n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"d_AA\"> <span title=\"Bond length of atomA-atomA dimer\"> <i>d</i><sup>AA</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"d_BB\"> <span title=\"Bond length of atomB-atomB dimer\"> <i>d</i><sup>BB</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HL_gap_AA\"> <span title=\"HOMO-LUMO gap of atomA-atomA dimer\"> Δ<i>E</i> <sup>AA</sup><sub>HL</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HL_gap_BB\"> <span title=\"HOMO-LUMO gap of atomB-atomB dimer\"> Δ<i>E</i> <sup>BB</sup><sub>HL</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Ebinding_AA\"> <span title=\"Binding energy of atomA-atomA dimer\"> <i>E</i> <sup>AA</sup><sub>b</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Ebinding_BB\"> <span title=\"Binding energy of atomB-atomB dimer\"> <i>E</i> <sup>BB</sup><sub>b</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Z(A)\"> <span title=\"Atomic number of atom A\"> <i>Z</i> <sup>A</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Z(B)\"> <span title=\"Atomic number of atom B\"> <i>Z</i> <sup>B</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"val(A)\"> <span title=\"Number of valence electrons of atom A\"> <i>Z</i> <sup>A</sup><sub>val</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"val(B)\"> <span title=\"Number of valence electrons of atom B\"> <i>Z</i> <sup>B</sup><sub>val</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"period(A)\"> <span title=\"Period (in the periodic table) of atom A\"> <i>n</i> <sup>A</sup><sub>period</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"period(B)\"> <span title=\"Period (in the periodic table) of atom B\"> <i>n</i> <sup>B</sup><sub>period</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"r_sigma\"> <span title=\"John-Bloch's indicator1: |rp(A) + rs(A) - rp(B) -rs(B)| \n [Phys. Rev. Lett. 33. 1095 (1974)]\"> r<sub>σ</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"r_pi\"> <span title=\"John-Bloch's indicator2: |rp(A) - rs(A)| +| rp(B) -rs(B)| \n [Phys. Rev. Lett. 33. 1095 (1974)]\"> r<sub>π</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"d_AB\"> <span title=\"Bond length of atomA-atomB dimer\"> <i>d</i><sup>AB</sup> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"HL_gap_AB\"> <span title=\"HOMO-LUMO gap of atomA-atomB dimer\"> Δ<i>E</i> <sup>AB</sup><sub>HL</sub> </span> </label>\n <label class=\"col-xs-4 col-md-4 col-lg-2\"> <input type=\"checkbox\" value=\"Ebinding_AB\"> <span title=\"Binding energy of atomA-atomB dimer\"> <i>E</i> <sup>AB</sup><sub>b</sub> </span> </label>\n </div>\n </form>\n </div> <!-- End of row-->\n <br>\n <div class=\"row\"> <!-- Start of second row-->\n <div class=\"lasso_form_group\">\n <p class=\"lasso_selection_description\"><b>Embedding methods:</b> </p>\n <div id=\"embed_method_selector\">\n <label class=\"col-xs-4 col-md-4 col-lg-4\"><input type=\"radio\" name=\"inlineRadioOptions\" id=\"inlineRadio1\" value=\"pca\" checked=\"\"> Principal Compenent Analysis (PCA) [<a href=\"https://en.wikipedia.org/wiki/Principal_component_analysis\" target=\"_blank\">more info</a>]</label>\n <label class=\"col-xs-4 col-md-4 col-lg-4\"><input type=\"radio\" name=\"inlineRadioOptions\" id=\"inlineRadio2\" value=\"mds\"> Multidimensional scaling (MDS) [<a href=\"https://en.wikipedia.org/wiki/Multidimensional_scaling\" target=\"_blank\">more info</a>]</label>\n <label class=\"col-xs-4 col-md-4 col-lg-4\"><input type=\"radio\" name=\"inlineRadioOptions\" id=\"inlineRadio3\" value=\"tsne_pca\"> t-Distributed Stochastic Neighbor Embedding (t-SNE) [<a href=\"https://en.wikipedia.org/wiki/T-distributed_stochastic_neighbor_embedding\" target=\"_blank\">more info</a>]</label>\n </div> \n </div>\n </div><!-- End of row--> \n <div class=\"row\"> <!-- Start of second row-->\n <div class=\"lasso_form_group\">\n <p class=\"lasso_selection_description\"><b>Scale data to unit-variance:</b>\n (data are centered around the mean in any case) [<a href=\"https://en.wikipedia.org/wiki/Feature_scaling\" target=\"_blank\">more info</a>]</p>\n <div id=\"standardize\">\n <label class=\"col-xs-4 col-md-4 col-lg-4\"><input type=\"radio\" name=\"inlineRadioOptionsStandardize\" id=\"inlineRadio4\" value=\"True\" checked=\"\"> yes </label>\n <label class=\"col-xs-4 col-md-4 col-lg-4\"><input type=\"radio\" name=\"inlineRadioOptionsStandardize\" id=\"inlineRadio5\" value=\"False\"> no </label>\n </div> \n </div>\n </div><!-- End of row--> \n <br>\n\n<!-- <span title=''> <img src=\"http://images.clipartpanda.com/question-purzen_Icon_with_question_mark_Vector_Clipart.png\" style=\"height: 30px; width: 30px;\"> </span> -->\n <button class=\"btn btn-default\" onclick=\"run_lasso()\">RUN TWO-DIMENSIONAL EMBEDDING</button>\n <button class=\"btn btn-default\" onclick=\"reset_lasso()\">RESET</button>\n <label title=\"This button becomes active when the run is finished. By clicking it, an interactive structural-similarity plot will be opened\"> <a href=\"#\" target=\"_blank\" class=\"btn btn-primary disabled\" id=\"lasso_result_button\">View interactive 2D scatter plot</a> </label>\n</div> <!-- End of lasso_control -->\n"
