hours  minutes  seconds


Prediktr Infrastructure Launch

Prediktr is a healthcare application (in alpha) and is also being developed as a plug and play infrastructure for life science based machine learning applications.

As a software, Prediktr uses composite reference genomes to compare genomes of bacteria in metagenomic samples to give a pathogen covergare to estimate presence of disease causing bacteria in air, water, soil or human metagenome samples.

Every day, millions of nucleotides are being sequenced by high throughput, next-generation sequencing (NGS) machines. With increased speed and accuracy of the sequencers coupled with the decreasing costs to perform DNA sequencing, many novel applications of DNA sequencing are being considered. These range from cancer studies to the detection of pathogens from body fluids or environmental samples. We have created a new composite reference genome representation and the associated programs that enable us to utilize the large amounts of high throughput sequencing data from metagenomics samples and rapidly analyze the presence of pathogenic bacterial strains. 

If you want to contribute to this project, please reach out to us using this form. This is an opportunity for bioinformatics students interested in this field. If you are a company looking to invest in a new life science/ healthcare product, please reach out to us to understand how this can align wit your needs.

To find out more about this, refer to the excerpt here and please contact us if you want to know more about it. (This is part of my thesis in Bioinformatics. To learn more about me, please follow this link.)

As a platform/ infrastructure, we support applications like Jupyter notebook, Galaxy and RStudio server although we have the capability of launching custom applications as well.

We use Django/python based Infrastructure and Code, coupled with Docker, Kubernetes (on GCP) or virtual instances on AWS. For data storage we are currently creating a GCP-FUSE mounted infrastructure for Kubernetes.

Please schedule get in touch with us if you need professional support fro your company, lab or project.

Here is a small glimpse of the infrastructural backend using GCP, Kubernetes and Docker Containers.

The Prediktr infrastructure is scheduled to go into production in February 2020 and will be fully operational by June 2020. If you are a research lab or a small company without infrastructural support, and are looking for a pre-built pipeline or need help building out a pipeline infrastructure complete with file access and authentication/authorisation, please consider using the contact form below to reach out with your requirements.

Want to try out something today? Contact us to try out a feature for free.

If you are a new student or researcher interested in bioinformatics or healthcare informatics, check out our free coding resources here.

1 Comment

  1. Anonymous says:



Leave a Comment

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

This site uses Akismet to reduce spam. Learn how your comment data is processed.