aBioBot – A robotic lab assistant that can see what it’s doing

raghu

Dr. Raghu Machiraju, Founder of aBioBot

I spoke to Dr. Raghu Machiraju who is the co-founder and CEO of aBioBot and a Professor of Bioinformatics and Computer Science and Engineering at The Ohio State University.  His primary research interest is in developing methods of integrative genomics for cancer subtyping and biomarker discovery that examine data concurrently from histology images, proteomics, and high throughput sequencing. We spoke about his startup, aBioBot and how it is helping bio-scientists in shortening the time to discovery. 

Screen Shot 2016-04-25 at 11.48.09 AM

When was your company founded and who are the Founders and team members?

Our company, aBioBot was founded in early March 2015 and was part of Indiebio’s first batch of incubatees. I am the Founder, CEO and the primary software architect of the company. The team is also comprised of a software engineer, a hardware technologist and a biologist.

What is the mission of your company?

Our mission is to help bio-scientists make breakthroughs by shortening the time for scientific discovery. We are building a flexible and friendly robotic lab assistant to help scientists be scientists.

As a Professor at Ohio State University, I do a lot of bioinformatics and work on cancer problems too. I like to dabble in technology and we conceived this idea of using/leveraging 3D printer to do bench lab stuff.  There is a lot of wet lab stuff that’s very boring and is totally encodable and can be automated.

So we do that by taking a relatively complicated protocol and then mark/analyze which part of these processes are encodable. This is similar to how industrial engineers used to work where they take a process and try to automate certain parts of it which are encodable, and then the classic computer scientists work to create an algorithm to automate it.

What is the aBioBot solution?

At aBioBot, we wish to re-create the flexibility of the familiar wet laboratory bench on a robotic platform. Our lab assistant is a robotic platform combining state-of-the-art hardware and software:

LabBench

A web browser user interface to facilitate protocol authoring, observe the layout on the bench, monitor the progress of the experiment, and log the protocol on the cloud. The user interface of LabBench is realised in HTML5 and Javascript, and leverages toolkits such as bootstrap.

Yan = Eyes

In our platform, Yan is machine vision that watches over the experiment for you. Yan’s software module learns the layout of objects including wells and provides surveillance of the bench for untoward accidents. Yan is implemented in Python and uses the OpenCV library.

The Bot

Our robotic platform is modified from a 3D printer. The Bot is derived from open source 3D printer hardware and rapid prototyping machinery. We have ported our APIs onto three different hardware platforms which will serve as the prototypes in various labs. We are also collaborating with another open-robotics company to provide much needed software.

Although aBioBot is built on open source hardware and software, both Lab Bench and Yan will be accessible through open APIs and extended as necessary.

Lab Bench has two functional components accessible to users:

  • Every lab staff member has a book of her favorite protocols, which have been refined and improved over time. LabSmith is a protocol-authoring tool with the capability to import lab procedures and notebooks from various repositories, including OpenWetWare and protocols.io. Most importantly, it will also allow for protocols to be changed and adopted as required.
  • Every log, video, and status report for your experiment will be automatically uploaded to the cloud through LabCloud.
abiobot-1434474681283

Photo credit: O’Donnell Photography Source: http://bit.ly/23TJEwm

What is the USP of your product?

There are companies which are trying to automate laboratory processes. The uniqueness of our product is that we are going to equip our robots with a sensing capability so that the sensors can identify all objects on the bench and makes robotic operations easy to plan. It also allows the robot to be safer (it can easily detect any obstructions)) and is less error-prone (i.e., it will automatically be able to sense if a well has liquid in it, whether a tip is missing from the box, or whether colonies or contamination exist on a plate). Any problem with the tips, and the operator will be informed.

Screen Shot 2016-04-25 at 4.33.56 AM

Source: aBioBot

What are the future plans for your company?

I have identified some early adopters with whom I am trying to develop some protein assays, medicinal chemistry assays for automation.

Any advice for biotech/healthcare entrepreneurs?

1) You need to have a pretty good idea about what you want to do. That’s very important.

2) You need to have a good idea about your market.

 

4 replies

Leave a Reply

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

WordPress.com Logo

You are commenting using your WordPress.com 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 )

Google+ photo

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

Connecting to %s