These are unique questions and answers not given in the podcast interview. I’m experimenting with this, and thankfully, Murat decided to give it a try. See the full episode here with all of the hyperlinked timestamped show notes to navigate the audio.
Quick Facts Before the Text Interview
Antiverse: Leveraging AI to Achieve Antibody Drug Discovery in One Day
Antiverse is building a world-first computational antibody drug discovery platform to predict antibody-antigen binding and provide antibody drug candidates in one day.
A combination of state of the art machine learning and cell-free protein synthesis is used to predict antibodies that bind to a given antigen target with high affinity. The resulting software can then take antigen taget sequence, provided by the customer, and do a high-throughput screening of all possibilities of antibody sequences to detect the sequence that will produce a high-affinity antibody for the target. The customer will be provided with the sequence in a single day, thus reducing the time typically required for antibody therapeutics discovery by 3 to 18 months.” Source
About Murat
Murat Tunaboylu has a BSc in Electrical Engineering and twelve years of experience as a software engineer. He also has extensive experience in labware automation and will be automating the lab work and creating the software that customers will use. Linkedin Profile
1) What tools, languages, and programs do you use on a daily basis to build and grow your startup?
On the business side, we use G-Suite for emails and documents, Slack for team communication, and GoToMeeting for daily stand-up calls. We have experimented with project management tools, but found most of them overkill at our stage.
To build the product we use TensorFlow and Python libraries with PyCharm. For training and hyperparameter optimisation, our choice is Google Cloud Platform.
2) How did you decide on the technology to build the service?
Tooling and technologies around machine learning are evolving everyday. We have tried to strike a balance between feature set, tech maturity, and developer productivity.
3) How could someone train themselves to program, run a startup, etc?
Once you have decided to build a start-up, it helps to be in an ecosystem where there is a plethora of accelerators, funding, and potential co-founders. I would recommend moving to an area such as London or San Francisco. Secondly, although self studies do help, I would advise to join an accelerator/incubator to speed-up your journey. Finally, you do not have to train yourself on every possible thing, but rather rely on your co-founders, advisors, network.
4) What do you both do on a typical day/week? Basically, if we cracked open your startup, what would we see you all doing?
Besides developing our product, we continuously look for additional funding and expand our customer base.
5a) What makes you hopeful for the future?
We are in a timeframe coined as “Century of Biology” by many thought leaders. I believe biology in combination with engineering will solve the problems of our time in agriculture, healthcare, and energy.
5b) Are there things going on in the science community that keep catching your attention? If so, what?
Democratization of information and tools. Freeing information by removing paywalls is happening now and will continue to do so. Freeing the tools will happen as well with open hardware initiatives and cloud labs such as Transcriptic.
5c) Any people specifically that interest you?
In addition to our advisors, I find Vijay Pande, general partner at Andreessen Horowitz, to be very interesting because of his views on AI and biology. I have been fascinated by the work of George Church (Harvard) and Tom Knight (Ginkgo) in the field of synthetic biology. When it comes to software, the first name that comes to my mind is Scott Hanselman (Microsoft) for being a well-rounded developer and a great contributor with his blog and podcast.
5d) Where do you see the future of the industry going?
H+
6) If your startup succeeds, what additional areas might you be able to expand into?
We have started with drug discovery and might move up (target discovery) and down (drug optimisation) as the next areas.
7) What are the next big mountains you want to climb in what you are working on? Why have you chosen those issues as things to work on?
Our mountain is generating a full antibody for any given target in no time. We have chosen it because of the impact it will have on the industry and patients, who eventually reach to more drugs faster.
8) What advice would you give someone starting out?
Move to a start-up hub. Bootstrap if you can. If not, get VC money. Do not stop fundraising.
9) What has been the most rewarding?
Finding the co-founders I have and the feeling you have when you work on something that you truly believe in.