Developing bespoke algorithms to reveal the true value of data

9 Dec 2020

Deva Senevirathne. Image: © Nick Callaghan/Luminex Photography

Women in AI finalist Deva Senevirathne talks about the creation of Sonraí Analytics and how AI and data science can help the world of healthcare.

Sonraí Analytics is a Belfast-based software company that provides pharmaceutical, bioscience and other medical research organisations with a remotely accessible and highly secure online platform where they can store, analyse and share large amounts of healthcare data.

The company recently received a special award of €10,000 at this year’s InterTradeIreland Seedcorn competition and became the winner of the 2020 Startup of the Year Digital DNA Awards.

The woman at the helm, co-founder Deva Senevirathne, was also named a finalist in the Women in AI Awards 2020. “I am a full-stack software engineer who has been specialising in designing and developing software frameworks for big data analytics using both traditional and artificial intelligence based analytical techniques,” she told Siliconrepublic.com.

‘Buried in datasets are the patterns that are crucial to unlocking new treatments’
– DEVA SENEVIRATHNE

Prior to founding Sonraí Analytics, Senevirathne’s experience in tech had primarily been within the academic research sphere.

“I completed my primary education in Sri Lanka. Then, as I was interested in technology and programming from an early age, I decided to obtain a professional qualification in the field by pursuing a degree in computer science.”

Once she had her degree from University College Dublin, Senevirathne was keen to find to translate her knowledge into the domain of healthcare research. This led her to a master’s degree in bioinformatics and computational genomics at Queen’s University Belfast.

She then began a PhD in bioinformatics within the field of colorectal cancer research where she explored possible architectures in designing an integrative analytical environment for pan-cancer studies. Her research here led to the creation of Sonraí Analytics.

Senevirathne said it was “pure curiosity” that attracted her to tech and AI. From a very early age I was fascinated by the concepts of artificial intelligence and smart robotics. Growing up I remember reading the sci-fi works by Isaac Asimov and Arthur C Clarke and wanting to one day create the first blueprints of a functional positronic brain,” she said.

“Of course, my nine-year-old-self had a very long, and not often an easy road to travel ahead before she got the chance to actually work on any sort of AI-based algorithms.”

However, she said with more time and experience, she began to see how AI could be used to enhance people’s lives across multiple domains. “Of course, I realise now that I am still a good way behind building that positronic brain, but I hope that my nine-year-old-self would be happy with how far we’ve come.”

Making data accessible

Senevirathne said Sonraí Analytics was created to help its clients realise the true value of their data.

“Buried in datasets are the patterns that are crucial to unlocking new treatments. Yet, identifying these can be slow and expensive. Many businesses today are simply overwhelmed by the scale and complexity of the data being generated,” she said.

“Our core product, InDRA, is a cloud-native self-service data science platform that has a suite of traditional and AI-powered applications, which enable researchers to identify novel and complex patterns.

“InDRA is capable of addressing many of the data-related challenges that are posed by the diverse and untidy multiomic data types generated by laboratories driving preclinical and clinical research in the precision medicine sector. Our platform solves this problem by providing a remotely accessible and highly secure online environment where businesses can store, analyse and share large amounts of data.”

Senevirathne said a lot of the excitement surrounding AI is based on the advancements made in the deep learning space. “However, I also think it’s important that we maintain a degree of realism in terms of our goals, expectations and target timelines within this domain,” she said.

“Also, I believe we must be aware, and be prepared to tackle and learn from the unintended consequences of AI such as misuse, algorithmic bias and the general black-box nature of the modern AI algorithms.”

Women in AI

Having come second in the Women in AI awards this year, Senevirathne is an important role model for other women in the industry. “We have a considerable gender gap in the tech industry in general,” she said.

“I think important for those who are already part of the industry to help and support the upcoming talent. While I am sure it is not impossible to make it in the industry on your own, by experience, I know it is a much more positive experience when you have good mentors and a strong support network around you, especially as a beginner.”

She said because everyone has different circumstances, it’s often hard to give specific advice for those who want to pursue a career in AI. “I myself am only still at the start of my career path and have a long way to travel before I get to the point I would like to be at,” she said.

“But what has worked for me so far is to remember that when it comes to dreams, it’s OK if you must take a few detours to get there, because the only way to fail is to abandon them. Also, as one of my mentors taught me, don’t be afraid to ask for help when you need it.”

Want stories like this and more direct to your inbox? Sign up for Tech Trends, Silicon Republic’s weekly digest of need-to-know tech news.

Jenny Darmody is the deputy editor of Silicon Republic

editorial@siliconrepublic.com