Build a multi-functional app with good memory management and avoid memory leak
This is not a tutorial of how to use streamlit, you can find great tutorials in the streamlit docs and medium articles. This is the summary of my trial and error deploying an app and debugging the most frequent bugs with streamlit sharing.
For those who don’t know streamlit, it’s an open-source app framework for data scientists to deploy their data apps in a few lines of code. The use of streamlit is very easy. Here, we are talking about building the app, because deploying the app is another story. It’s as they call it: Ridiculously Easy.
Now, let’s dive…
3 Tips on how to train machine learning models efficiently when your data is noisy and mislabeled…
In this article, I would like to talk about 3 tricks that helped me to efficiently train models and win a silver medal in a kaggle competition where the dataset was mislabeled and contained a significant amount of noise.
Simple tutorial using biopython library to analyze the SARS-CoV-2’s genome in python.
In this article, we will identify the viral proteins in the novel SARS-CoV-2 genome with biopython and do a comparative analysis with the SARS and bat coronaviruses.
Materials and methods:
- Download the genome file from the kaggle dataset: SARS-CoV-2 genbank file. (NCBI accession number: NC_045512)
- SARS-CoV-2 genome analysis was carried with Biopython and DNA features viewer libraries.
- PSI-BLAST search was used to compare our SARS-CoV-2 proteins with the SARS and Bat coronavirus proteins.
1- SARS-CoV-2 genetic information:
Genome sequencing has increasingly become an important tool for studying disease outbreaks. The SARS-CoV-2 genome used in this study was sequenced from a sample of bronchoalveolar lavage fluid from a…
A summary of the Mechanisms of action (MoA) prediction competition on kaggle where we used deep learning algorithms to predict the MoA of new drugs.
Discovering a new drug has always been a long process that takes years. With the recent advances of AI and the accumulation of research data in biological databases, the drug discovery process and the research pace are getting faster than ever. Researchers in the laboratory of innovation and science at Harvard are working on the Connectivity MAP project [1] with the goal of advancing drug development through improvements to the drugs MoA prediction algorithms. This challenge was launched as a kaggle competition [2] in order to build machine learning models to predict the MoA of unknown drugs.
1- Dataset:
We start by…
