17 April 2023
Image source, Natalie Lisbona
Dr Talia Cohen Solal, left, is using AI to help her and her team find the best antidepressants for patients
Dr Talia Cohen Solal sits down at a microscope to look closely at human brain cells grown in a petri dish.
"The brain is very subtle, complex and beautiful," she says.
A neuroscientist, Dr Cohen Solal is the co-founder and chief executive of Israeli health-tech firm Genetika+.
Established in 2018, the company says its technology can best match antidepressants to patients, to avoid unwanted side effects, and make sure that the prescribed drug works as well as possible.
"We can characterise the right medication for each patient the first time," adds Dr Cohen Solal.
Genetika+ does this by combining the latest in stem cell technology - the growing of specific human cells - with artificial intelligence (AI) software.
From a patient's blood sample its technicians can generate brain cells. These are then exposed to several antidepressants, and recorded for cellular changes called "biomarkers".
This information, taken with a patient's medical history and genetic data, is then processed by an AI system to determine the best drug for a doctor to prescribe and the dosage.
Although the technology is currently still in the development stage, Tel Aviv-based Genetika+ intends to launch commercially next year.
Image source, Getty Images
The global pharmaceutical sector had revenues of $1.4 trillion in 2021
An example of how AI is increasingly being used in the pharmaceutical sector, the company has secured funding from the European Union's European Research Council and European Innovation Council. Genetika+ is also working with pharmaceutical firms to develop new precision drugs.
"We are in the right time to be able to marry the latest computer technology and biological technology advances," says Dr Cohen Solal.
A senior lecturer of biomedical AI and data science at King's College London, she says that AI has so far helped with everything "from identifying a potential target gene for treating a certain disease, and discovering a new drug, to improving patient treatment by predicting the best treatment strategy, discovering biomarkers for personalised patient treatment, or even prevention of the disease through early detection of signs for its occurrence".
New Tech Economy is a series exploring how technological innovation is set to shape the new emerging economic landscape.
Yet fellow AI expert Calum Chace says that the take-up of AI across the pharmaceutical sector remains "a slow process".
"Pharma companies are huge, and any significant change in the way they do research and development will affect many people in different divisions," says Mr Chace, who is the author of a number of books about AI.
"Getting all these people to agree to a dramatically new way of doing things is hard, partly because senior people got to where they are by doing things the old way.
"They are familiar with that, and they trust it. And they may fear becoming less valuable to the firm if what they know how to do suddenly becomes less valued."
However, Dr Sailem emphasises that the pharmaceutical sector shouldn't be tempted to race ahead with AI, and should employ strict measures before relying on its predictions.
"An AI model can learn the right answer for the wrong reasons, and it is the researchers' and developers' responsibility to ensure that various measures are employed to avoid biases, especially when trained on patients' data," she says.
Hong Kong-based Insilico Medicine is using AI to accelerate drug discovery.
"Our AI platform is capable of identifying existing drugs that can be re-purposed, designing new drugs for known disease targets, or finding brand new targets and designing brand new molecules," says co-founder and chief executive Alex Zhavoronkov.
Image source, Insilico Medicine
Alex Zhavoronkov says that using AI is helping his firm to develop new drugs more quickly than would otherwise be the case
Its most developed drug, a treatment for a lung condition called idiopathic pulmonary fibrosis, is now being clinically trialled.
Mr Zhavoronkov says it typically takes four years for a new drug to get to that stage, but that thanks to AI, Insilico Medicine achieved it "in under 18 months, for a fraction of the cost".
He adds that the firm has another 31 drugs in various stages of development.
Back in Israel, Dr Cohen Solal says AI can help "solve the mystery" of which drugs work.
Continue reading here:
How artificial intelligence is matching drugs to patients - BBC
- Microsoft reportedly working on its own AI chips that may rival Nvidia's - The Verge - April 20th, 2023 [April 20th, 2023]
- Deepfake porn could be a growing problem amid AI race - The Associated Press - April 20th, 2023 [April 20th, 2023]
- AI cameras: More than 2 on two-wheelers, even if children, will invite fine - Onmanorama - April 20th, 2023 [April 20th, 2023]
- These are the tech jobs most threatened by ChatGPT and A.I. - CNBC - April 20th, 2023 [April 20th, 2023]
- Will Generative AI Supplant or Supplement Hollywoods Workforce? - Variety - April 20th, 2023 [April 20th, 2023]
- Marrying Human Interaction and AI with Navid Alipour - Healio - April 20th, 2023 [April 20th, 2023]
- Competition authorities need to move fast and break up AI - Financial Times - April 20th, 2023 [April 20th, 2023]
- 5 AI Projects to Try Right Now - IGN - April 20th, 2023 [April 20th, 2023]
- Financial Services Will Embrace Generative AI Faster Than You Think - Andreessen Horowitz - April 20th, 2023 [April 20th, 2023]
- Grandma exploit tricks Discords AI chatbot into breaking its rules - Polygon - April 20th, 2023 [April 20th, 2023]
- US FTC leaders will target AI that violates civil rights or is deceptive - Reuters - April 20th, 2023 [April 20th, 2023]
- Why open-source generative AI models are an ethical way forward ... - Nature.com - April 20th, 2023 [April 20th, 2023]
- Religion against the machine: Pope Francis takes on AI - Euronews - April 20th, 2023 [April 20th, 2023]
- Fujitsu launches AI platform Fujitsu Kozuchi, streamlining access to ... - Fujitsu - April 20th, 2023 [April 20th, 2023]
- Commonwealth joins forces with global tech organisations to ... - Commonwealth - April 20th, 2023 [April 20th, 2023]
- In this era of AI photography, I no longer believe my eyes - The Guardian - April 20th, 2023 [April 20th, 2023]
- AI is the word as Alphabet and Meta get ready for earnings - MarketWatch - April 20th, 2023 [April 20th, 2023]
- Google CEO Sundar Pichai warns society to brace for impact of A.I. acceleration, says its not for a company to decide' - CNBC - April 20th, 2023 [April 20th, 2023]
- Purdue launches nation's first Institute of Physical AI (IPAI), recruiting ... - Purdue University - April 20th, 2023 [April 20th, 2023]
- We soon wont tell the difference between AI and human music so can pop survive? - The Guardian - April 20th, 2023 [April 20th, 2023]
- Atlassian brings an AI assistant to Jira and Confluence - TechCrunch - April 20th, 2023 [April 20th, 2023]
- How DARPA wants to rethink the fundamentals of AI to include trust - The Register - April 20th, 2023 [April 20th, 2023]
- Dating an AI? Artificial Intelligence dating app founder predicts the future of AI relationships - Fox News - April 20th, 2023 [April 20th, 2023]
- Snapchat expands chatbot powered by ChatGPT to all users, creates AI-generated images - Fox Business - April 20th, 2023 [April 20th, 2023]
- ChatGPT sparks AI investment bonanza - DW (English) - April 20th, 2023 [April 20th, 2023]
- AI-generated spam may soon be flooding your inbox -- and it will be personalized to be especially persuasive - The Conversation - April 20th, 2023 [April 20th, 2023]