Startups and corporations turn to AI-driven technologies to make the drug discovery process faster and cheaper.
- AI-developed flu shots enter the clinical trials phase
- Exscientia and GSK team up to find a cure for COPD
- Healx takes on rare diseases ignored by pharma giants
- LabGenius focuses on protein drug development
- Atomwise and Enamine work on therapies for childhood cancer
- BenevolentAI builds an AI-driven drug discovery database
- Future pharma scientists will be trained in computer science
- Helping people enjoy their lives without diseases
Over the last few decades, life expectancy has increased significantly across the world. Most people today can expect to live past 70, twice as long as their ancestors just 100 years ago. Due to advances in medicine, human longevity is likely to increase even further. In 2018, for instance, the US Food and Drug Administration (FDA), approved 61 new drugs, an all-time record for new drug approvals in a single year. But despite this progress, drug development remains an inefficient process.
According to research by the Tufts Center for the Study of Drug Development, developing and testing a single drug can take years and cost up to $3 billion, and only 12 per cent of drugs entering clinical development eventually hit the market. This forces pharmaceutical firms to focus on finding cures only for diseases that affect a large number of patients. Devising a more efficient way of discovering drugs would save more lives and make treatments cheaper. Fortunately, advanced technologies might offer a solution.
Startups and corporations are increasingly turning to artificial intelligence (AI) to create better medicine at a fraction of the time and cost. Algorithms can analyse vast amounts of health data and simulate chemical interactions. Scientists are already reporting the first breakthroughs, such as inventing more effective flu shots and cures for rare diseases. However, AI-based drug discovery will also lead to some new challenges. Educational requirements for the future workforce in the pharma industry are bound to change, with software playing a critical role and pushing all actors to adjust to the new reality.
AI-developed flu shots enter the clinical trials phase
Influenza, commonly called the flu, is a viral infection that usually strikes during the winter season. Elderly people and young children are particularly at risk of contracting the flu, which is why they’re advised to get the annual influenza vaccine regularly. However, although vaccination is an effective prevention strategy, some people might still catch the disease. This fact prompted researchers at Flinders University in South Australia to come up with a better solution.
They used an AI program called SAM (Search Algorithm for Ligands) to analyse trillions of different chemical compounds to “find candidates that it thought might be good human immune drugs”, says professor Nikolai Petrovsky. The top candidates were then tested on animals. In the next phase, the AI-developed drugs will be deployed in 12-month clinical trials across the US.
Confirming the effectiveness of this drug in humans would enable the team to not only commercialise the product, but also use the same technology to develop many other vaccines. AI-powered drug discovery could save hundreds of millions of dollars and shorten the process by decades. Getting to that point, however, will require more money. After being rejected in Australia and almost halting the research, Petrovsky managed to secure funding for his current work from the US National Institute of Allergy and Infectious Diseases.
Exscientia and GSK team up to find a cure for COPD
Chronic obstructive pulmonary disease (COPD) is a health problem affecting around 384 million people worldwide. Its main symptoms, such as shortness of breath and coughing, usually worsen over time, making it difficult for patients to even walk or get dressed. In a bid to find an effective treatment for this disease, the tech startup Exscientia joined forces with the pharma giant GlaxoSmithKline (GSK). The British duo is using an AI-driven platform called Centaur Chemist to accelerate medical research. The software uses AI algorithms to automatically design and prioritise novel compounds for synthesis, decreasing the amount of time needed to develop new drug candidates. In 2019, the startup reported the discovery of a molecule that might treat COPD and has passed the findings to its corporate partner. Exscientia claims that it can deliver pre-clinical drug candidate molecules in 25 per cent of the time and at 25 per cent of the cost of traditional methods.
Healx takes on rare diseases ignored by pharma giants
Around 350 million people worldwide battle 7,000 different types of rare diseases. Finding treatments for these conditions using traditional drug discovery procedures would take thousands of years of research and over $13 trillion. Because of this, pharma companies rarely tackle these diseases, and patients suffer and die with no help in sight. The UK-based biotech firm Healx, however, is challenging the status quo. It developed a system called HealNet that relies on AI, pharmacology expertise, and patient group insights to predict treatments for rare conditions more accurately than traditional approaches. To that end, the algorithms use more than 20 data sources and a knowledge base to make their recommendations.
Healx has already achieved some notable successes. The company is working with the FRAXA Foundation on finding a cure for Fragile X syndrome, a genetic condition that affects one in 4,000 males and one in 8,000 females. It leads to learning disabilities, autistic behaviours, and other issues. Thanks to Healx’s technology, it took only 18 months for scientists to discover a chemical compound that might tackle the disease. The research is now moving to the second phase of clinical trials.
Healx’s co-founder Dr Tim Guilliams is even more ambitious. He wants to scale the company’s technologies and find medicine for 100 rare diseases by 2025. Also, Guilliams envisions a future in which AI will be able to analyse medical data and “discover putative therapeutic interventions even before the disease is affecting the individual. The future of medicine is set to be faster, cheaper and far more efficient.”
LabGenius focuses on protein drug development
LabGenius, a London-based startup, wants to make protein drug development better and faster. The company is building a platform called EVA that uses machine learning, robotic automation, and gene synthesis technologies to discover new therapeutic proteins. Apart from this research, LabGenius is also undertaking commercial projects. It’s currently working with Tillotts Pharma AG, a Swiss pharmaceutical company, to develop molecules that could potentially treat inflammatory bowel disease. The British firm operates by taking the project from concept to the preclinical stage, after which clients can commence clinical trials.
Atomwise and Enamine work on therapies for childhood cancer
Faster drug discovery could also save the lives of hundreds of thousands of children. Each year, around 300,000 new cases of childhood cancer are reported, and many of them lack effective treatments. The California-based chemistry startup Atomwise and the New Jersey-based chemical building blocks supplier Enamine have partnered to offer a solution. The duo will use AI software to simulate up to 10 billion interactions between small molecules and target cancer proteins. Algorithms will analyse the ensuing chemical reactions to find molecules that may be used to slow cancer growth or halt metastasis.
Abraham Heifets, the CEO and co-founder of Atomwise, explains that the company’s clients discovered early drug candidates by screening only 10 million compounds. “Imagine what will be found when we screen a chemical library that is a thousand times larger,” says Heifets. Also, the preclinical success rates of Atomwise’s partners was twice the industry average. These improvements, combined with the fast screening of millions of molecules, could reduce the amount of time and money pharma companies need to develop effective treatments.
BenevolentAI builds an AI-driven drug discovery database
BenevolentAI, a UK-based tech startup, has developed an AI platform that analyses data from an array of sources, such as research papers, patents, and clinical trials. The software operates a database that maps the relationships of specific drugs with genes, diseases, species, tissues, and other biological factors. Users can query the system to, for instance, find genes associated with a medical condition or the compounds that affect it. Jackie Hunter, the chief executive of BenevolentAI, says that “AI can put all this data in context and surface the most salient information for drug-discovery scientists.”
Future pharma scientists will be trained in computer science
Despite the promising applications of smart algorithms in drug discovery, more than 40 per cent of pharmaceutical researchers are unfamiliar with AI. But this attitude is bound to change soon. AI will become ever more critical in drug discovery jobs, and the skills needed to thrive in this industry will increasingly revolve around computer science and machine learning. The way PhDs and other graduate courses are run will change as well. “The years of students focusing solely on — and learning more than anyone else about — a particular gene mutation, say, are over,” says Thomas Chittenden, who leads a team at Wuxi NextCODE, a US-based biopharma startup.
To succeed in the tech-driven drug discovery market, professionals will have to become flexible learners. Monitoring leading journals and news sources will be crucial. Also, universities won’t be able to provide all the skills students need, forcing them to rely on self-learning. The next five years will be crucial as engineers gather more data to demonstrate the full potential of AI in drug discovery. “If by then we are creating better drugs, and doing it faster and cheaper, then AI will really take off,” says Niven Narain, the CEO of Berg, a Boston-based biotech firm.
Helping people enjoy their lives without diseases
Understanding what went wrong in the human body is a challenging endeavour. It involves analysing complex biological reactions and huge amounts of medical data, a task more suited to smart algorithms than humans. That’s why AI is becoming more popular in pharmaceutical research. It enables scientists to comprehend diseases more thoroughly and invent better and cheaper drugs. Although we’re just beginning to grasp the full potential of algorithms, they’re likely to change the way health problems are managed and treated. The therapies of the future will help even those suffering from rare diseases, ensuring that millions of people get to enjoy their lives without being hampered by medical conditions.