DeepSEA model
In this blog, we will analyze the deep learning model which predict chromatin features using DNA sequence. Using this chromatin features, we can predict the disease.
Learning the regulatory code of the genome using Basset
Convolutional neural networks are widely used to understand the DNA sequence of data. In this blog, we will be discussing about one such model (Basset model) along with its implementation.
Sequence-based ab initio prediction of variant effects on expression and disease risk using ExPecto
Understading disease from the DNA mutations is one of the major problem researchers are trying to solve. In this blog, we will analyze about a machine learning model which can predict disease risk from the sequence variation.
Objective Reinforced Generative Adversarial Network(Part II)
In this blog we discuss the technicalities of the ORGAN model used to generate molecules with desired properties.
Generating Molecules using CharRNN
In this blog we are going to discuss about RNN’s and How the character RNN algorithms can be used in Molecular Structure Generation.
Objective Reinforced Generative Adversarial Network (Part I)
Finding the Lead Molecule in a Drug Discovery pipeline is one of the most challenging processes. Thousands of molecules are screened and tested. This process is time-consuming and very important and so this blog discusses a deep generative model that tries to overcome these challenges.
Non Coding Variant Effect Prediction using Basenji
Predicting the causal variants is of one of the challenging problems. This blog discusses the model, Basenji which can prioritize the causal variants.
Molecular Generation using Junction Tree VAE using PyTorch
Representation of Molecules can be done in the form of graphs. To existing generative models on graph data structures, we need better algorithms. Junction Tree VAE helps to address this issue and creates better molecular graphs.
Hypergradient Optimization
A brief introduction about the Hypergradient optimization for Hyperparameter optimization. It is considered as the relation between parameters and hyperparameters of the model for the better selection of hyperparameters.
Adversarial Autoencoders for Molecular generation
This blog states about dome pros and cons of Variational Autoencoder. It also consequently introduces a new method called Adverserial Autoencoders for better generation of molecules.
Molecular Structure Generation using VAE
This post gives a detailed explanation about using Variational Autoencoders for Molecular structure Generation. By the end of this post, you will be able to create your VAE or molecular generation.
All you need to know about Variational AutoEncoder
Variational AutoEncoders are being widely used in generative models since the day they came into existence. This blog is just a synopsis of understanding Variational AutoEncoders.