Online hackathon on
Deep Learning and Bioinformatics
*By joining the competition, you agree with terms and conditions
February 25 — March 31, 2019
First prize - MacBook Pro
Second prize - RTX 2080 Ti
Third prize - RTX 2080
Deep Learning has become an essential part of research in many areas. Latest advancements in deep learning make it possible for neural networks to perform better than humans in some tasks such as identifying people in some photos, driving cars, playing games (e.g., Chess, Go, etc.), among others.
Research in drug discovery significantly affects human life.
Developing drugs against aging and diseases like cancer and Alzheimer can be accelerated with machine learning. Traditional drug discovery pipelines take years or even decades to produce new medicine, whereas Insilico Medicine aims to shorten this time using Deep Learning techniques.
About us
Insilico Medicine is a leading company in the field of Deep Learning for Drug Discovery.
NVIDIA Top5 AI companies for social impact, 2017

CBInsights Top100 most promising private AI companies, 2018
Insilico Medicine does Deep Learning and Bioinformatics research:
1. The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology.
2. druGAN: An Advanced Generative Adversarial Autoencoder Model for
de Novo Generation of New Molecules with Desired Molecular Properties in Silico.
3. Deep Learning Applications for Predicting Pharmacological Properties of Drugs and Drug Repurposing Using Transcriptomic Data.
4. Deep biomarkers of human aging: Application of deep neural networks
to biomarker development.
An important aspect of drug discovery is the capability to design new molecules that have some characteristics of interest. Such characteristics may be (approximately) encoded in the molecule's fingerprint (such as MACCS fingerprint). The capability to generate new molecules that have fingerprints of interests is therefore very important. Such a task may be achieved through a carefully designed and trained Deep Neural Network (DNN) that is conditioned on molecules fingerprints. Such a model can be said to be a Conditional Generative DNN model for generating new and unique molecules based on target MACCS fingerprints.
We seek to model the generation of small molecules that have some specific features as a Deep Learning problem. Since the characteristics of a molecule may be encoded in its MACCS fingerprint, the goal is to build and train a Conditional Generative DNN model for generating new and unique molecules based on target MACCS fingerprints.
At the minimum, the MolHack challenge will require the participants to build and train a Conditional Generative DNN model that can generate new small molecules such that the newly generated small molecules have similar MACCS fingerprints as the target MACCS fingerprint upon which the generation of the molecules is conditioned.