Published in Towards Data Science·Jan 10Molecular Visualization in Streamlit Using RDKit and Py3DMol (Part 2)Py3DMol and stmol component — Follow this link for the first part: https://towardsdatascience.com/molecular-visualization-in-streamlit-using-rdkit-and-py3dmol-4e8e63488eb8 1. Introduction When I asked Adrien Treuille how to deploy 3D structures on Streamlit, I was soon contacted by TC Ricks, and he proposed me to develop a Streamlit Component, when components were not yet released to the public. I worked on that and…Streamlit5 min read
Published in Towards Data Science·Dec 7, 2021Molecular visualization in Streamlit using RDKit and Py3DMolPart 1: RDKit — 1. Introduction Soon after I knew about Streamlit [1], my first question [2] was, how it could be possible to deploy molecular structures? In this post AND the next, I will contribute what I have learned, hoping that this could be of help to others. In this two-part series, I will concentrate…Streamlit4 min read
Published in Towards Data Science·Aug 21, 2021Learn to Smell (Molecules) with Graph Convolutional Neural NetworksAn end to end project combining Chemistry and Deep Learning on Graphs — Here what we are going to accomplish are the following tasks: Build a custom graph dataset formatted to work in DGL (Main subject in this post 😎) Prepare Train and Test datasets randomly (Good to know 👍) Define the Graph Conv Network (Piece of cake 🍰) Train and evaluate Accuracy…Graph5 min read
Published in Towards Data Science·Jul 27, 2021Start with Graph Convolutional Neural Networks using DGLA Painless Introduction — I have reviewed some of the existing libraries to do Graph Convolutional Neural Networks (GCNN’s) and, although in general they are very good, I always return to DGL because it has excellent documentation and many examples, among other things [1]. Here, I want to share my review of a classic…Graph4 min read
Published in Towards Data Science·Jul 8, 2021How to build a super easy handwritten numbers identifierA beginner friendly use of cosine similarity — Whenever you start with machine learning, there are several well known datasets ( Iris dataset for example 🥀 ). Among them there is one for images that is simple, popular and interesting, namely the MNIST dataset which consist of a large number of handwritten digits 📝 [1]. Here we are…Mnist4 min read
Published in Towards Data Science·Jan 5, 2021Making network graphs interactive with Python and Pyvis.The easy way to plot superb graphs. — For a while, I and others in the Streamlit community [1] have been seeking a tool to render interactive graphs, but until now this has been something only a few can achieve. This can be due to the fact that a level of expertise with javascript is required, something that…Python5 min read
Published in Towards Data Science·May 3, 2020Identifying Protein-Ligand Interactions with ColabSetting up Autodock Vina “There is an urgent need to share our methods, models, and results openly and quickly to test findings, ensure reproducibility, test significance, eliminate dead-ends, and accelerate discovery. …Covid 197 min read
Published in Towards Data Science·Apr 18, 2020Graph convolutional nets for classifying COVID-19 incidence on statesHow to map a map into graph convolutional networks. — Note from the editors: Towards Data Science is a Medium publication primarily based on the study of data science and machine learning. We are not health professionals or epidemiologists, and the opinions of this article should not be interpreted as professional advice. …Covid 197 min read
Mar 29, 2020Tracking Covid-19 with Pandas and Plotly Open Source Graphing Library Maps.Mexico is still in the second phase of the spread of the SARS-Cov-2 virus and has had a very valuable opportunity when observing what has happened in other countries where today the situation is critical. In this exercise, I will show how the cases reported by 1) The Center for Systems…Covid 193 min read
