Knowledge discovery reimagined: finding new hypotheses with Causaly Cloud

It is well recognized among scientists that target selection can improve clinical trial success rates (1). Being able to stay up to date with scientific data and efficiently extracting insights is critical to drug R&D – but currently it is a manual, time-consuming process.

In this on-demand webinar, you will find out how Causaly’s AI platform empowers users to drastically reduce research time and make brand new discoveries.

You will:

Please scroll below to find a summary of the salient points mentioned throughout the webinar.

It’s no secret that better target selection is of critical importance when it comes to successfully developing drugs. According to the Center for Medicines Research (CMR), drugs have a mere 10% chance of making it past Phase 1 clinical trials to market (2). Furthermore, a study by AstraZeneca demonstrated 40% of their clinical trials failed because no clear link was made between the target and disease at the R&D stage (3).

In addition, another 29% of clinical trials failed because the compound chosen did not have the correct physical properties or did not reach the target tissue (4).

The data clearly shows that target selection is a weak link in the process. And when you consider the time and cost of getting a drug to Phase 3 clinical trials, improving the R&D stage in drug development should be a major priority.

But why are so many nonviable targets being selected for clinical trials? And crucially, what can be done to improve candidate nomination and ensure drugs entering clinical trials have the best chance of reaching the market and making an impact?

That is the problem that Causaly solves.

A key challenge pharma companies face is the exponential growth of biomedical knowledge. Today, researchers are faced with more data than they can possibly digest: 35M+ publications, 500k+ clinical trials, 3M+ patents, and 100k+ regulatory documents.

While the amount of data is growing quickly, the time researchers have to consume it remains static. And it is in the widening chasm between available time and the increasing amount of data that issues arise.

While tools like PubMed can filter information to some degree, researchers are still left with thousands upon thousands of documents and have to make decisions about which to read and which to disregard. Manually choosing which documents to filter inevitably runs the risk of selection bias, which ultimately leads to skewed conclusions. This method also has the problems that affect all humans during cumbersome, manual processes: things like fatigue, boredom, and distraction – all of which can interfere with knowledge extraction.

This problem is exacerbated as the amount of data continues to grow. The information needed to make connections, form new hypotheses, and develop transformational drugs is all out there, hiding among millions of documents. But researchers need a radical new way to join the dots and unlock these insights.

Causaly Cloud is an AI platform that can read text like a human. Using Natural Language Processing, it can comprehend the entire body of published scientific documents in just a few seconds.

Crucially though, unlike other tools, our platform doesn’t just run shallow keyword queries. Instead, it understands the complex causal relationships between biomedical entities that are embedded in natural language – whether that relationship is a treatment, side-effect, comorbidity, or anything else. With this understanding, it can extract knowledge and present evidence in the form of high-precision knowledge graphs that can be easily explored and interrogated.

This inverts the traditional research paradigm. Rather than reading documents then extracting insights, users are now presented with a complete picture of the insights already extracted from the data – free of selection bias or the constraints of time – and can then explore individual articles of interest in more detail.

Causaly Cloud of course saves time – up to 88% according to our customers. But another exciting benefit is the ability to get an objective, bird’s eye view of the evidence. This dramatically reduces scientific bias and enables researchers to spot hidden connections that conventional research would completely miss.

That’s not to mention advanced features like Multi-Hop, which allows users to discover hidden mediators that exist between biomedical concepts and generate new hypotheses.

Ultimately, Causaly Cloud is empowering researchers, enabling them to select better targets in much less time. Using the platform, drug companies can make sure only the most viable candidates go through to clinical trials – ensuring time and money are spent on the drugs that are most likely to make it to market and make an impact on society.

Founded in 2018, Causaly’s mission is to transform how humans can find, visualize and interpret biomedical knowledge, to accelerate solutions for some of the greatest challenges we face in human health. Causaly acts as an operating system for biomedical and health data that empowers researchers to effortlessly identify new research avenues and innovative drug development opportunities. Its technology mimics human reading, and digests tens of millions of documents into an Enterprise Knowledge Graph allowing researchers and decision-makers to answer questions they can’t answer anywhere else. To learn more, visit www.causaly.com