Antibiotic resistance isn’t just a looming problem. It’s a global crisis. Every year, more than one million people die directly from resistant infections, and another 5 million die indirectly. Routine infections are becoming life-threatening, and healthcare systems worldwide are under pressure.

Despite decades of warnings, pharmaceutical solutions are falling behind, while “superbugs” continue to outpace new drug development. If trends continue, by 2050, antibiotic resistance could claim 10 million lives annually and cost the world $1 trillion.

In this episode from the Smart Biotech Scientist Podcast, David Brühlmann meets José Luis Bila, CEO of Precise Health, a company dedicated to making phage therapy faster, smarter, and more accessible through AI-driven innovation.

Key Topics Discussed

• José Bila’s personal experience with antibiotic resistance and its influence on his career in personalized medicine.
• Human, economic, and healthcare burdens; comparisons to other global health crises.
• Barriers to innovation, bioprocess inefficiencies, and the withdrawal of big pharma.
• Biological adaptation of bacteria, misuse of antibiotics, and systemic disincentives.
• Overview of phages, their specificity, safety, and sourcing.
• Slow matching processes, limited physician adoption, and the urgency of timely treatment.
• Leveraging data to interconnect global phage banks and accelerate personalized treatment.
• Building scalable, region-specific therapy networks and fostering innovation through partnerships.

Episode Highlights

• José's personal story: Losing both parents to antibiotic resistance and its impact on his career path [00:00]
• Scope of the antibiotic resistance crisis: Global deaths, indirect impacts, and economic cost projections [06:29]
• Why antibiotic resistance persists: Static nature of antibiotics versus adaptable bacteria, and misuse of antibiotics [09:45]
• Why big pharma is pulling out of antibiotic development and why innovation may come from smaller startups [11:39]
• Introduction to bacteriophage therapy and its specificity challenges [11:46]
• The current slow, manual process for matching phages to infections and its limitations in urgent clinical settings [13:08]
• How machine learning is being used at Precise Health to rapidly identify and source the right phages using genetic information [13:08]
• The potential to reduce phage matching and delivery time from months to just days, and how smart batching and regional surveillance improve economics [17:23]

In Their Words

Throughout my studies, of course, I've been passionate about life sciences in general. But when I was doing my bachelor’s, a very unfortunate event happened. Two events happened where I lost both my parents to antibiotic resistance due to co-infections and because they were immunocompromised at the time. In one case, it was that the doctors did not have time to react with the right antibiotic, but in another case, which was more extended, more chronic, they just couldn't find anything else off the shelf that they could try.

Unfortunately, I lost both my parents in one year after the other, 2010 and 2011. Since then, I've been really quite motivated to use my knowledge to go into personalized medicine because I believe that in their cases, it's just that they couldn't find something specific to them, most importantly.

Episode Transcript: Fighting Antimicrobial Resistance: How AI Cuts Phage Therapy Access from 6 Months to 5 Days with José Luis Bila - Part 1

David Brühlmann [00:00:48]:
Antibiotic resistance kills 1.3 million people annually and could cost $1 trillion by 2050. Traditional antibiotics are failing against superbugs, leaving patients with few options. What if artificial intelligence could revolutionize how we fight these deadly infections? Today's guest, José Bila, lost both parents to antibiotic-resistant infections, a tragedy that sparked his mission to develop AI-powered phage therapy solutions. His personal journey from chemistry PhD to biotech entrepreneur and now CEO of Precise Health reveals how cutting-edge science meets deeply personal purpose in the fight against antibiotic resistance. Welcome to the Smart Biotech Scientist. I'm David Brühlmann, your host. Join me today as José shares his journey from personal tragedy to pioneering AI
solutions that could save millions from deadly bacterial infections.

Welcome, José, to the Smart Biotech Scientist. It's a pleasure to have you on today.

José Luis Bila [00:03:09]:
Thank you so much. It's a pleasure to be here.

David Brühlmann [00:03:11]:
José, share something that you believe about bioprocess development that most people disagree with.

José Luis Bila [00:03:18]:
I wouldn't say it's directly the bioprocess itself. It's more on the economics of the bioprocess. Especially when you start thinking of more kind of personalized medicine, usually people think it's a problem with scale-up more than anything. But in reality, when it comes to the field in which we are specifically, it's more about the economics regarding batch utilization. This is something that is a little bit controversial, depending on who you speak to, of course. For instance, in the case of personalized medicine, you can have a thousand liters of the product, but if you're only using it for one patient, it doesn't change anything. You need to be able to have a high-scale batch utilization. These are things that can also be solved with different approaches like machine learning and so on. So it's not really a bioprocess per se. Like I say, it's more of a general thing regarding the economics of bioprocessing.

David Brühlmann [00:04:17]:
José, draw us into your story. Can you share what sparked your initial interest in biotechnology and how your personal experience shaped your very scientific focus and led you to fight antibiotic resistance?

José Luis Bila [00:04:32]:
So I'm a chemist. I studied chemistry my entire life. I did my bachelor's, master's, and PhD in chemistry. And throughout my studies, of course I've been passionate about life sciences in general. But when I was doing my bachelor’s, a very unfortunate event happened. Two events happened where I lost both my parents to antibiotic resistance due to co-infections and because they were immunocompromised at the time. In one case, it was that the doctors did not have time to react with the right antibiotic. But in another case, which was more extended, more chronic, they just couldn't find anything else off the shelf that they could try. Unfortunately, I lost both my parents in one year after the other, 2010 and 2011.

Since then, I've been really quite motivated to use my knowledge to go into personalized medicine because I believe that in their cases, it's just that they couldn't find something specific to them, most importantly. From there, after my master's, for instance, I worked as a chemist. Of course, I was designing molecules and synthesizing molecules for photodynamic therapy, so it’s another strategy that is used for cancer, for instance, and that was very deep personalized medicine. After my PhD, I went into management consulting, specifically in life sciences. There I learned a lot about gene therapies, personalized medicine, and so on, and all this knowledge and my personal story culminated in Precision Medicine, a startup that we have built today.

David Brühlmann [00:05:56]:
It's a very tragic story indeed. And at the same time, I love your purpose behind that — a greater purpose and not just science. Well, it comes out of a personal experience, a tragic one, and now you're using that for the greater good, which is very powerful. So I am wondering, José, to what extent is this tragic event an isolated case? Can you tell us a bit? What is the current state of antibiotic resistance? How many deaths do we have per year, and what is the cost to our healthcare system?

José Luis Bila [00:06:29]:
So estimations from the World Health Organization and all the different surveillance programs we have estimate that there are 1.2 to 1.3 million deaths globally per year caused directly by antibiotic resistance. But there are actually around 5 million which are indirectly caused by antibiotic resistance. Of course, we usually look at the direct ones, but the indirect ones also — these co-infections — lead to something else, which is reported not as a death by antibiotic resistance but by organ failure or something else that we never learn about. So the number is huge. Estimations again by 2050 indicate that there will be about 10 million deaths globally per year. This is huge if you look at it, and it's quite comparable to cancer today. The number is increasing day by day, and some newer estimates indicate even more than 10 million deaths today. This is a big problem. It's not only a question of the deaths themselves; there is also a cost burden associated with this. Because when a patient has an antibiotic-resistant infection, the tendency is that they will stay longer at the hospital, and this patient is not going to work.

You have more doctors having to focus on one specific patient, and so on. So the economics globally actually show about 1 trillion dollars in additional costs by 2050 globally for healthcare alone. This is huge, associated with the 10 million deaths that are expected. I think the bottom line is that we need to find a solution that works. The current antibiotics are failing, and this is not working as we have today. As you might know, and also your listeners might already know, a lot of the pharma companies are actually exiting the entire antibiotic space. The economics of it are not very attractive compared to cancer and many other indications. Since 1950, I think it’s been more than 50 years, and some reports show that there hasn't been a new antibiotic that has been very effective compared to what we already have today against gram-negative bacteria.

Gram-negative bacteria are causing a lot more damage than maybe gram-positive, relatively speaking. Finding new modalities is important. Finding new approaches is very important. This is why I think a lot of the innovation has to come from smaller companies because the big ones are exiting. We should have a collaborative approach from different institutions, academics, SMEs, private companies, and so on. So it's a big problem because out of these 10 million people that will be dying, it could be my parents, but it could be somebody else's parents, or it could be us — exactly. That could be the next person dying. So this is a big problem for sure.

David Brühlmann [00:09:24]:
It definitely is a big problem. And the numbers are crazy. Antibiotic resistance has been a hot topic for several decades already. So what is the current state now in 2025? Is it still the main drivers that we've talked about for the last decades, or is it something else that's causing even greater numbers of people to probably die in the future?

José Luis Bila [00:09:45]:
One of the drivers, of course, is what caused antibiotic resistance in the first place. You can think of antibiotics as these static molecules: once you synthesize a chemical molecule, it's static, it will not change. I mean, I'm a chemist, you're also a chemist, so you know that even changing one substitution on one of the positions of the molecule requires going through clinical trials again, which can take 10 to 15 years until you can actually commercialize it. So this static molecule is fighting against something that is changing; it’s adapting itself. If you are in a box fight and you keep throwing punches the same way in the same direction, if I am adaptable, of course I will know after a few punches that I need to run away and I know how to defend myself against that. That’s what bacteria is actually doing. We need an approach that is adaptable as bacteria is also adapting. So having static approaches is one of the things increasing the issue with antibiotics.

The other thing is that, over time, depending on which culture or country you come from, people, whenever they have a small symptom, their intuition is to go and get, for example, a medicine like Aristamol. But in some cases, most people just say, “Oh, just take an antibiotic.” So the misuse and overuse of antibiotics has been driving the entire issue with antimicrobial resistance (AMR).

On the adaptability aspect, on the pharma side, if you have to spend 10-15 years to develop a new drug and spend billions of dollars, then at the end the economics may not make sense. The margins are low, and this makes it less attractive to develop something adaptable to a bacteria that keeps changing. These factors all come together. We've known them for ages, but not much is being done in that space.

David Brühlmann [00:11:39]:
So how are we going to solve that problem as an industry? And more specifically, how are you solving that in your company?

José Luis Bila [00:11:46]:
So in our company, we are focusing on bacteriophages. Bacteriophages are viruses that are present where bacteria are present, and they usually exist to either control the growth or eliminate pathogenic bacteria. They infect and kill specific bacteria. They are very specific and natural. You can find them from many different sources. In our case, we isolate them from wastewater, agricultural products, or samples from people. They are very good because they are specific to the strain level or a group of bacterial strains. They are harmless to human cells, or at least that has been indicated so far. So they are quite safe compared to chemical molecules like antibiotics, which could be toxic in certain instances. These bacteriophages can be used as a weapon against pathogenic bacteria resistant to antibiotics. That’s what we focus on in our startup.

David Brühlmann [00:12:58]:
And I imagine these bacteriophages are very specific. So you have to do some analysis to know which one to pick. How do you find the needle in the haystack?

José Luis Bila [00:13:08]:
Exactly. Bacteriophages have been with us for over a hundred years and have been used in many locations. Specifically, ex-USSR geographies like Georgia have been using phages for quite some time. But the issue is that they are very specific. Antibiotics, being chemical molecules, can be given to a bunch of people, and they kill the infections in general, even if they are not perfect. Phages are too specific. Being too specific means you have to personalize to the individual, which makes the economics more difficult.

To find the right phage today, you need to take the bacterial isolate and loop within a phage library, testing manually one by one to find the right one. This uses plaque assays or liquid assays. It is laborious, which is why many doctors don’t use it. We asked doctors: bacteriophages are amazing — they can even penetrate biofilms, have less toxicity than antibiotics — so why aren't they using them? Even when you have a patient that is dying, why not resort to bacteriophages? The key issue is that finding the bacteriophage manually can take two to six months. This is insane for a patient with an acute or subacute infection, which is a good portion of the infections that we have today.

You don't have time. You need to react fast. Normally, if you isolate the bacteria and then you have to ship it to a phage bank that is somewhere, maybe you're in Switzerland and this phage bank is in Georgia and then another one in Portugal, you have to accept the fact that, even if you ship it, they might not have what you're looking for. So the entire manual process and then the production, it’s a whole nightmare.

This is where machine learning can help. Using ML, we can combine traits of bacteria and phages, learn what works and why, and train a model to identify the right phage for a bacterial strain without the manual hassle. At Precise Health, our startup, we are developing a platform interconnecting multiple phage banks. The doctor only needs DNA information and metadata of the bacteria, upload it to the platform, and within minutes we can scan multiple phage banks to find which phage is ready for use under local regulations.

David Brühlmann [00:16:58]:
So the traditional approach takes weeks or months, by which time the patient might be dead or in very bad condition. Now, with your machine learning approach, how fast can it identify and produce that bacteriophage?

José Luis Bila [00:17:23]:
The big dream for us is to have multiple phage banks holding already produced and qualified phage, let's say batches, to speak. And in that big dream, the idea would be that when doctor already decides that, Oh, my antibiogram shows that nothing on the shelf that I have is going to work, then can I use bacteriophages. And usually these can be done anywhere between 48 to 72 hours, of course, depending on the hospital capability. It really depends on which country you are. But in Switzerland we know that this can be done by hour to 72 for sure. And with that in mind, can I just search within minutes and get my phage? I don't know, even if it's somewhere in Finland, can I just, in two clicks, request the phage and that the Finnish biobank which has the ready-to-use phage already produced, send that to me next-day shipment, depending on the severity of the case that I have.

Our target actually is by day five, you get your phages in-house to be used under whatever regulations you're following in your specific country. But there is another issue. The production itself is an issue because isolating phages is not the issue. We have more than 200 phages in our laboratory, so we can go and produce all of them. But then it comes back to my very first comment regarding the bioprocessing. If I produce all the 200 phages in whatever batches, how likely am I to use a certain percentage that is going to make the economics actually, right? That is the key question. Again, coming back to our machine learning algorithm. What we can do is, by looking at specific regional fingerprints, we can already anticipate which phages within certain phage libraries or phage banks can maximize the chance of being utilized.

Just a simple example. If I go to a hospital in Switzerland, and let's say in Zurich, we often have kind of the same bacteria patterns that are running around because the population is the same, they are eating the same thing, they are breathing the same air. The travel patterns are quite relevant. By looking historically at the different bacteria that have been deposited and isolated in the ranks of the hospitals, can we use that information to predict or develop a fingerprint for the region of Zurich in this case? And with that fingerprint, can we look into the phage libraries that we have incorporated in our machine learning platform to scan for the phages that are likely to cover 80 to 90% of the fingerprint for Zurich? And can you do this for multiple segments, cities? Maybe it's not Zurich, maybe it's entire Switzerland or the entire Europe? We don't know for sure for now. Right? But that's what we are working towards to understand. By doing so, let's say for Zurich, you need X amount of phages that are likely to cover 80 to 90%.

Can you already take those and get them pre-produced and stock? And when the doctor needs them, they are already produced because you already know that it's very likely that it's going to be one of those. And then in case you have cases where the 10% is not covered, you can come back and search again within the libraries. And if the patient still has time to cope with the infection, this would have to be taken into production again and be taken into the library.

Using the exact same system, what if you were to get a continuous bacterial surveillance program from this hospital that I'm talking about in Zurich, every, I don't know, three to six months, we collect new bacteria and we check again, are we still covering 80 to 90% or are we down to 70 or 60%? And then can we scan again and say, how do we get back to the 90% and do the production? Then you have a continuous surveillance program and a continuous update of the bacteriophages which are produced. This is the way we believe is to go, and you reduce time, you make it fast and more effective, and more targeted, and then the economics will be correct.

David Brühlmann [00:21:37]:
That's a wrap on part one. Jose's story shows how personal tragedy can fuel scientific innovation. In part two, we'll dive deeper into the economics and regulatory challenges of AI-guided phage therapy. If you have process development or manufacturing questions, book a free call at www.bruehlmann-consulting.com/call and I’m happy to help you get started. And also, please leave us a review on Apple Podcasts or whatever platform you found us on. It helps other biotech scientists discover actionable insights like these. Thank you so much for tuning in, and I'll see you next time. All right, smart scientists, that's all for today on the Smart Biotech Scientist Podcast. Thank you for tuning in and joining us on your journey to bioprocess mastery. If you enjoyed this episode, please leave a review on Apple Podcasts or your favorite podcast platform. By doing so, we can empower more scientists like you. For additional bioprocessing tips, visit us at www.bruehlmann-consulting.com. Stay tuned for more inspiring biotech insights in our next episode. Until then, let's continue to smarten up Biotech.

Disclaimer: This transcript was generated with the assistance of artificial intelligence. While efforts have been made to ensure accuracy, it may contain errors, omissions, or misinterpretations. The text has been lightly edited and optimized for readability and flow. Please do not rely on it as a verbatim record.

Next Step

Book a free consultation to help you get started on any questions you may have about bioprocess development: https://bruehlmann-consulting.com/call

🧬 De-risk CMC development and get decision-making guidance with a new AI platform that transforms CMC overwhelm into predictable development success (launching early 2026). Join the waitlist here: https://david-jkhjdoje.scoreapp.com

About José Luis Bila

Dr. José Luis Bila is the Co-founder and CEO of Precise Health, a company dedicated to making phage therapy faster, smarter, and more accessible through AI-driven innovation. He earned his PhD in Chemistry from EPFL and began his career in life sciences consulting, advising global biotech and pharmaceutical firms on strategy and innovation. He later joined a MedTech startup developing rapid STI diagnostics.

Blending scientific rigor with entrepreneurial vision, José leads Precise Health’s strategy, product development, and partnerships. His personal experience—losing both parents to antibiotic-resistant infections—fuels his mission to bring effective, precision therapies to patients where traditional antibiotics no longer work.

Connect with José Luis Bila on LinkedIn.

He is also a biotech technology innovation coach, technology transfer leader, and host of the Smart Biotech Scientist podcast—the go-to podcast for biotech scientists who want to master biopharma CMC development and biomanufacturing.  

Hear It From The Horse’s Mouth

Want to listen to the full interview? Go to Smart Biotech Scientist Podcast. 

Want to hear more? Do visit the podcast page and check out other episodes. 
Do you wish to simplify your biologics drug development project? Contact Us