All episodes

In some respects, 2024 has been a record year for AI in biotech, with the $1 billion founding of the antibody-centered biotech company Xaira and the awarding of the Nobel Prize in Chemistry to DeepMind researchers Demis Hassabis, John Jumper, and David Baker. However, despite years of investment and innovation, we still lack an answer to the most pressing question: Will AI revolutionize drug development, or are we in a bubble that is about to burst?

In episode 30 of the BioRevolution podcast, Andreas Horchler and Louise von Stechow explore various use cases for AI in biotech—from discovery to clinical...

2025: For millions of people, the new year starts with the self-promise to improve, to quit smoking, alcohol, to get in shape, to stay young and attractive, to basically create and become a new me. While traditionally new year vows meant to relinquish, today there seem to be many helpers in the form of biohacking.
Beginning with diets and not ending with technical devices.
While there are real shortcuts and fake abbreviations to reach some of those goals, there´s also traditional ways. In "New year old me – no biohacks needed", Louise von Stechow and Andreas Horchler try to distinguish...

Modern humans are stressed creatures: overloaded schedules, constantly “on-call,” and social media haunting us into the late night.
Part of this stress is maladaptive responses that date back to human history when stressors were about life and death and not about writing emails and making phone calls. A key player in those ancient responses is cortisol, a stress hormone that interacts with many biological functions, from heart rate to glucose metabolism, to inflammation and immune responses, as well as sleep and cognition.
But is cortisol - as the social media proponents of the so-called cortisol detox make us believe -...

Science can be complex and difficult to grasp, yet public understanding is crucial for navigating issues like disease risk, climate change, and pandemics. Clear, engaging science communication can help prevent misinformation and conspiracy theories, offering facts in place of myths. But how can we make science more digestible and appealing?
Counterintuitively, it might be less facts and more emotions that can help to make science more appealing, more impactful – both when communicating to the public and to fellow scientists. In episode 28 of We’re doomed, We’re saved, Andreas Horchler and Louise von Stechow discuss strategies for scientific storytelling, drawing...

In the expensive and failure-prone process of drug development, artificial intelligence (AI) can serve both as an efficiency tool and as a creativity tool. Increased efficiency means shorter timelines, reduced investment, and earlier insights into success or failure. This can lead to more opportunities to bring new drugs to patients. Increased creativity means exploring new areas in drug discovery and development, such as identifying new patterns in targets, drug molecules, and patient populations that may be unintelligible to the human eye. While we are witnessing the first tangible milestones of AI in drug development, the hype in the field can...

How will the medicine of the future look? Healthcare and medicine are on the verge of transformative change, driven by new technologies such as artificial intelligence, telemedicine, and wearable devices. Alongside the technologization and virtualization of medicine, there is a shift from reactive "fix the broken" approaches to preventative strategies and from one-size-fits-all treatments to personalized medicine.

In this future, human healthcare professionals and machines will work hand-in-hand to deliver the best possible care, with empowered patients acting as equal decision-makers who understand and access their own healthcare data. However, a darker scenario could see medicine becoming fully industrialized and...

Some 36 months after the release of ChatGPT, the verdict is still out on the role that large language models (LLMs) will play in biotech, pharma, and medicine. On paper, the range of tasks that LLMs can perform in biomedical research and healthcare is vast—excavating relevant information for drug discovery from mountains of scientific literature, designing novel proteins, transcribing doctors' notes, aiding diagnostic decision-making, and acting as patient-facing chatbots.
But given the models’ propensity to hallucinate, we need to define how much error we can tolerate for different LLM use cases in the biomedical fields and create evaluation frameworks that...

Rare or orphan diseases affect only a small percentage of the population and often lack effective treatments. While rare individually, in total, more than 350 million people worldwide live with rare diseases. Many of these are very hard to diagnose, let alone cure, and the rarity of patients challenges the development of novel treatments.

To make the development of drugs for rare diseases more efficient and successful, artificial intelligence could be an important ally not only for drug makers but also for patients.

In episode 24 of "We’re Doomed, We’re Saved," Andreas Horchler and Louise von Stechow discuss the benefits...

When we think about revolutions, we think of systemic changes in politics, economics, and lifestyles. Revolutions transform how we live, work, interact, and communicate. In the past, political uprisings and new technologies, from the steam engine to the smartphone, have led to such transformative changes.

Now, a revolution driven by novel biotechnologies (gene editing, neuroprosthetics, synthetic biology, and artificial intelligence in biotech) has the potential to not only change the way we live but the very foundations of our lives – our biology.

But is the so-called biorevolution a real "scientific revolution"?

In the new episode of "We're Doomed, We're...

Polygenic risk scores (PRS), put simply, look at gene variants across the human genome in order to determine an individual's risk of getting a disease, from different types of cancer to type II diabetes. PRS could complement current risk prediction models and lead to a more accurate risk prediction. However, for PRS to become a useful clinical instrument, transparent ways to assess their performance and careful communication of disease risks to individuals are key.
In episode 22 of We’re doomed we’re saved, Andreas Horchler and Louise von Stechow speak to two PRS researchers, who contributed to the international and interdisciplinary,...