PyGGi (Python for Glass Genomics) is a tool that uses trained Machine Learning algorithms to predict/optimize composition-property relationships in inorganic glasses.
PyGGi will be constantly updated and upgraded to meet the industrial & academic challenges in the field of glass science. In particular, some of the two capabilities that we are working on are:
We are also open to developing raw modules based on user requirements. These modules can be exclusively given to users who support the research in PyGGi.
For further details and queries, mail us at email@example.com
How many oxide components are available in PyGGi?
In PyGGi: Eight oxide components are available.
In PyGGipro: Thirty four oxide components are available.
How many oxide components can be added for a glasss composition?
In PyGGi (free version): Out of the eight available options, a maximum of three components can be added simultaneously for entering a glass composition. Once the components are entered, the preferable range of values for each of these compoenents need to be provided. Note that the range should be within 10%. For example, sodium silicate glass, SiO2 can range from 80 to 90 mol% and Na2O can range from 10 to 20 mol%. PyGGi will compute all the glass compositions possible within the range and provide the values for the chosen properties.
In PyGGipro (paid version): There is no limitation on the number of oxide components per glass composition. However, a maximum of six oxide components only can be chosen for input in the form of a range. For glasses with more than six oxides components, the user need to input the specific composition of interest. Alternatively, user can select the relevant oxide components and download the excel/csv template. The user can then manually input as many glass compositions as required. This excel/csv file can then be imported to compute the properties of the specific glass compositions entered.
Should the compositions be in wt% or mol%?
All the compositions should be entered in mol%. There is no provision to enter the compositions in wt%.
What is the allowed values in mol% for each of the oxide components while inputting the data in the form of range?
The maximum difference is 10%, i.e (maximum mol% - minimum mol%) for each oxide should be ≤ 10%.
Can the proportion of oxides for multiple glass compositions be uploaded through an excel file?
Yes, the mol% of oxide components for multiple glass compositions can be imported from an excel or a csv file. The user can download a template by choosing the required oxides using the ‘Import’ option available on the top-left corner of the software window. The same file can then be uploaded back after filling in the required compositions. For detailed description, have a look at the documentation here.
Is it possible to download the predicted results?
The results of the computation are downloadable in the form of an excel or a csv file. Additionally, the user can also download all the graphs in the form of image files.
Is the software compatible with Linux?
Presently, PyGGi and PyGGipro is available for Windows and MacOS only. Linux version may be provided in future based on user requests.For the dtailed hardware and software requirements, see ...
Which models are used for predicting the properties of glass?
Glass properties are predicted using models trained by machine learning. Two different types of models, one trained by neural network and other trained by Gaussian process regression, are used for prediction. Further details of each model is listed in the documentation.
Number of oxides available
All components available for a glass formation
Input as range for individual components
Screens at the same time
Limited to 3
Limited to 3
*an additional 18% GST is applicable to all the above prices
To purchase the above softwares, get in touch with us at firstname.lastname@example.org
N M Anoop KrishnanSupervisor
Coming together is a beginning. Keeping together is progress. Working together is success. Here is to the team that helped to build PyGGi.
Hargun SinghSoftware Developer
Pratik BhaskarWeb Developer
Suresh BishnoiMachine Learning
Sourabh Kumar SinghMachine Learning
Nishank GoyalMachine Learning
Divyarth SaxenaMachine Learning
Jyamiti MaheswariMachine Learning
Ashish GuptaMachine Learning
Arvind NairMachine Learning
Karthikeya HSMachine Learning
Block- IV 315, Civil Engineering Department, Indian Institute of Technology Delhi, 110016
Phone Number: +91-11-2659-1223