Pablo Yarza, Founder & CEO att Bioinfile

Jesus Moreno (00:01.996)
Welcome back to global trials accelerators, the podcast. Sorry, I'm going to do that again.

Welcome back to Global Trial Accelerators, the podcast where we dismantle the barriers to clinical innovation and explore the strategies driving the next generation of life-saving therapies. I am your host, Jesus Moreno, and today we're looking at the invisible foundation of our entire industry, data. We live in an age of AI and big data. Every biotech company claims to be data-driven.

But the dirty little secret of the industry is that most of the data is unstructured, siloed, or simply unusable. We spend millions on algorithms, but we often starve them. Sorry, I'm going to do that again.

We spend millions on algorithms, but we often starve them with poor quality inputs. My guest today is Paolo Gierza, the founder of BioInfile. With over 15 years of experience specializing in advanced databases for bioinformatics, Paolo has seen firsthand how data curation issues are not just a technical annoyance, they are a massive strategic liability.

that delays R &D projects by months and even years. He is now on a mission to make quality data accessible to R &D professionals across the industry. Pablo, welcome to the show. It's a pleasure to have you with us.

Pablo Yarza (BIOINFILE) (01:42.742)
Hi, Jesus. Nice for being here. So thanks for the invite. It's fun. It's very cool. Let's go on.

Jesus Moreno (01:52.152)
Pablo, I want to start with your background because you have saddled two very different worlds, the academic and the industry. spent 15 years developing databases for bioinformatics. often in academic, sorry, often academics focuses on publishing data, whereas the industry focuses on using it.

Please tell us a bit about your origin story and how did moving between those two environments shape your understanding of what good data actually is?

Pablo Yarza (BIOINFILE) (02:34.158)
Okay, I think let's start at my PhD thesis already. So this was a joint collaboration between the Max Planck Society and the CSIC Institute in Spain. And the thesis was conducted in the Balearic Islands in the very Mediterranean area. the task was to create a sequence database.

a reference sequence database for microbial identification. And why was it so needed? This was because the primary repositories of DNA sequences were growing already very fast. At that time, it was exactly 15 years ago, more or less. We were seeing the exponential growth of the databases at the primary level, NCBI, I mean. And it was complicated to find the right sequences to actually represent the species.

So that piece was missing. It was a big curation effort to select one best sequence per species. So this piece of data selected, curated, know, something that we could prescribe to the scientific community. Hey, you can use this data because it's reliable. We have curated it so much. We have quality control it. And you don't have to go to the primary repos to find it out.

With this database, the users can do micro-viral identification safely. So you got a piece of DNA and you want to know which microorganism this belongs to, right? And then you can use this database with confidence to actually do the inference. It's bioinformatics. Okay. So there you already see that curation really focuses, saves time because otherwise you have to go to the primary repositories.

But I want to tell you something is that when we created a database, it took us about one year to release it because primary repositories are constantly growing, science is evolving. You have to update the databases. It's not that you created once, you have to maintain it. By the way, maintenance is not paid by research. We talk about this later. So we created the database and then we got to maintain it.

Pablo Yarza (BIOINFILE) (05:00.308)
And it took us about a year, but I knew every time we released it, I knew that it was already obsolete because we have started the curation process like maybe six months ago or eight months before, you know? So the primary data that we had included was already old. So this was the real bottleneck. Data curation, which is so valuable, is the bottleneck.

It was the best we could have at the time, but everybody knew that this was not the latest status of the thing. And we are talking about one single database resource, very specific for something very specific, so kind of small, know, very curated. So imagine for the larger databases out there, the difficulty to keep them up to date. So that I think is the second.

The second stage of my story on the postdoc level. So what happened then is that, well, that, that database was quite popular, very cited. And then there was a company in Germany, a Tribalcon that took me to develop farther this database and, and make it ready for industry. So what industry needs this kind of databases? It's biotech, it's pharma.

in this case, microbiological quality control, which is down in every pharma setting, you know, because these white labs, all this quality control at the microbiological level needs to be carefully done. So the reference data to be used in those settings needs to be super quality control and that. And therefore the academic data was not ready for that purpose. So at the company, we curated it further.

And then kind of sold it to these customers. Okay. So that was the story where I learned how valuable is academic data, but at the same time, it's not ready for industry as simple as that. And if, yeah. And what happens basically is that when companies need data for the R and D processes and they have, they face the challenge to look for the data and then curate the data.

Pablo Yarza (BIOINFILE) (07:26.763)
because you can't use it as it comes. So to put it a bit more in context, in parallel to my work in the company during my postdoc, I was working in a Max Planck Institute in Bremen in North Germany in a big project called Silva. Silva is the largest European RNA database. It's a big academic project. Now it doesn't belong to the Max Planck as moved to the...

German culture collection of microorganisms, the DSM said. But Silva project is a big database spanning all domains of life, right? So it's not like my PhD database. So it's something way larger, thousand times larger. And the team of curators, when I was there, we were two or even less. So for sure we couldn't maintain it. I mean, it was...

I mean, it seemed big and the thousands of usages of these database that we could see as database curators. Then we often got like user requests and we see, and we saw, um, how much use was this database. So that made me think, okay, all these people is using this big database, like, like the truth, like the reference, but for sure it's not up to date. So then I was thinking, okay,

these guys are for sure curating the data downstream because maybe there are companies doing that and that started to blow my mind and say okay there's a big opportunity here for entrepreneur in a project that solves the data curation this amazing bottleneck and yeah I think that was the the starting point for bio and file so yeah

Jesus Moreno (09:25.376)
Wonderful. That's a fantastic story and outreaching. mean, different countries, different datasets, different research questions being asked and answered through this trial you went through. And what you're describing is a frustration many scientists go through and most

just grind through it and build their temporary patches. But it's interesting to see how in that intersection between industry and research, you discovered there was a scalable market opportunity. Correct me if I'm misrepresenting anything of what you said, but it sounds that that was the case.

Pablo Yarza (BIOINFILE) (10:17.536)
It is exactly. So what happened at that case of RNA sequences, it's actually the same for nearly every use case. And I'm going to put you a graphical example for the audience that is watching this video. What I'm showing here, look, this is a pot of loose legal pieces, right? So when researchers discover something,

This knowledge is communicated out there to the community, but there is no organization that keeps the data organized. And then comes a company needing a piece of data, very concrete piece of data. They just need the 20 samples that are missing for the observational cohort because they are running a clinical trial and it's so expensive. And they ask, OK, is this data already existing?

But how can you find it inside this amazing pool of loose information? So that's basically where we are at. So we are helping companies find the data they need, the exact data they need, and then helping them to acquire it, to use it, to actually use it. We are facilitating access to high quality biomedical data. So this is for sure transversal.

to all biomedicine. And this is the big challenge. So to make like a platform, this is what we're creating, a platform where you can search the data you are looking for. scientific data is very specific. Everybody needs some sort of specific information because all the ontologies, all the diseases, all the conditions.

If you move out from humans, then you get a lot of animals, plants, microbes. It's really, really, really large. And so the data request can be super specific, but then it can be structured. And then we can look at among a catalog of providers of knowledge. Right. So yeah, but to make that connection good, you have to put curation inside. So there are no.

Pablo Yarza (BIOINFILE) (12:41.464)
There are no straightforward LLM or technique, you know, that can actually give it to you. So you have to put a lot of data curation inside as well. So taking the idea of the, of the, of my PhD work, you know, where we prescribed the right data for, for, for the, for the, for these users. Now we want to prescribe the best data for your use case. So it's not that we creating an open data market is that we are.

going to prescribe you what's the best data that you can have for what you need.

Jesus Moreno (13:17.336)
That's so interesting. we'll get a little bit more into the weeds of how that works in a little bit. But I want to step back and talk about data curation. To my understanding, data curation is, it sounds technical, but it's really about communicating and translating biology into something a computer can understand.

to be worked and to bring insights out of that information. But as a founder, looking at it from that perspective of a founder, are you now selling a solution to a problem that many people don't want to admit they have? How hard has it been to get research and development leaders to acknowledge that their data foundation is the source of their delays?

Pablo Yarza (BIOINFILE) (14:15.47)
Wow, that's an amazing question. So one of the tricky things here is to actually tell this truth to the customer without getting too harsh or too scary. So I met a diagnostic lab, genetic testing laboratory, that they were using a commercial solution by Informatics Platform.

Jesus Moreno (14:33.816)
Mm-hmm.

Pablo Yarza (BIOINFILE) (14:45.196)
But the reference databases within this platform were 10 years old, Jesus. And they were using it because the brand is accepted. The processes are accepted. The machines, the personal, everything is in good place. But actually, the reference data behind is old. So even though you get a pathogen in your sample, you might not get it in the final report.

Jesus Moreno (14:53.901)
Wow.

Pablo Yarza (BIOINFILE) (15:13.57)
So when I told these people this thing, we didn't make a deal that time, you know, but after some months we did it. It was a bit shocking, but yeah. So honestly, data obsolescence is a truth. We have to take care of that. know, primary data, primary data.

Jesus Moreno (15:26.062)
You

Pablo Yarza (BIOINFILE) (15:40.879)
when you sequence something, when you get an image of someone. So that primary data is there, but the secondary data, so the datasets that represent something, they are really subject to obsolescence because state of the art is rapidly changing and you need more labels, you need to change the labels, you need to replace some stuff, you need to add more references and this happens at least once a year.

This should happen once a year at least to review all this thing. So what I try to communicate to our users and customers is don't, so save time on the public data acquisition and structuring and focus more on your private data. The faster you go to market with your solution, the faster you start getting your private data. So.

If you do this public data or scientific reference data acquisition, if you outsource this part and you start doing the curation by yourself, you're going to save a lot of time and money and you're going to get faster to the market. And this is the level of speech time that I'm using now. So showing the ROI of doing so, you know, and

It has a lot of benefits to outsource that part to providers like IonInfile, but can be others, you know, and focus more on the private data.

Jesus Moreno (17:17.314)
That's wonderful. And I understand that there's a challenge there to strike that right balance between letting your clients see the issue and not being too rough or aggressive in the way you communicate that. And you've touched a little bit about on the industry and how the industry should be moving forward.

is a good segue to the next segment that I would like to cover, is industry trends that you've seen. And when we speak about trends, one of the most used terms when describing trends is the AI boom. If we look at the macro trend, we're seeing a frenzy

of investment in generative AI and machine learning for drug discovery, for example. And everybody wants to buy that Ferrari engine of AI, but they are fueling it with low grade gasoline, low grade data. And I'm interested to learn, do you believe the current hype around AI?

in biotech is going to hit a wall because of our underlying data infrastructure isn't ready for it?

Pablo Yarza (BIOINFILE) (18:53.975)
Yes, data comparison with fuel is correct in the sense of the refinement of the material. If you add kerosene to your R &D, then you're going faster to market, that's clear. Okay, what I see is synthetic data, something interesting, but that's another R &D process by itself. So,

What is more important here is to check the quality of the input and the quality of the output. OK? And if in the middle, there is all the technology that you want that makes it faster, then that's perfect. But the data outcome that emerges that needs to be validated, you can't replace that with any AI or whatever technique. So that needs validation and then needs comparison with the state of the art.

that and for the input data the same you need qualified data validation is very important here so yeah so what we see is that the data is upstream the AI right so we need to put very good data we need to focus on rapidly updating the data acquisition

in order to just have good data for your processes and that's it. We use AI and LLMs and stuff for our own processes because LLMs are helping a lot to make summaries, make classifications. You've got also the knowledge graphs which add semantic compatibility between the datasets.

But everything needs curation inside. So every technique that you include needs to be curated, fine tuned and all that. So yeah, I think AI is boosting all this and I highly appreciate it. But what is boosting really is the R &D. So R &D is getting more and more common, faster, and that's amazing. So it only means we're going to have more present services for the society faster.

Pablo Yarza (BIOINFILE) (21:21.603)
Yeah, but only you can do it safely if it is quality controlled and if you have the proper validations and so on. yeah, so new methodologies are very nice. They are speeding up things and this is very cool, but they need good data behind. If not, you're going to fail.

Jesus Moreno (21:47.435)
Absolutely. It's like building a house on a solid foundation versus on sand. You need that underlying structure to support the weight of what you're putting on top.

Pablo Yarza (BIOINFILE) (22:00.364)
Exactly. And time, the state of the art is changing. the data foundations are getting, they are not strong anymore. So you have to review, you have to maintain the data foundations every time, every year. So otherwise, the building is going to fail. It's going to fall down.

Jesus Moreno (22:25.27)
Of course. And I want to touch on something you mentioned previously. I want to approach this next part of the conversation from an economic perspective. We talk a lot about the cost of clinical trials and how research and development costs are ballooning. How much of that is actually hidden waste?

of a scientist spending hours on and cleaning spreadsheets and harmonizing data instead of actually doing the research. And is this perhaps the silent budget killer that CFOs are missing? You mentioned previously that research doesn't pay for the maintenance aspect of data sets. What does?

Pablo Yarza (BIOINFILE) (23:11.983)
Hmm?

Pablo Yarza (BIOINFILE) (23:22.227)
Correct. Okay, I've calculated that about 15, no 50,000 euros. Okay, more or less is what it costs per project, the data curation part. So which is basically an employee costs. So the operational costs are basically employees, know, curating data, looking for that data and getting the data.

So, and I'm talking only about public data, data from the public domain, you know, because that's the reference scientific data. Other thing would be to get private data from others because you're missing some part of the data for your clinical trial and then you need the data. That's another part. But for the scientific reference, that's the cost. So I think this is a waste of effort, of time.

because modern companies should focus more on the getting the data as fast as possible to develop the tool or the device or the molecule faster and pass to the next stage faster and go to market faster because that's going to give you the private data as we said before. So yeah, I think the actual, the ROI for that is

easily above 300 % in three years, three, four years, because the data curation has the personal behind and that has the tangible cause for sure, but the intangible cause because you have to choose the right people to do it. You have to supervise the people. There are mistakes happening and all the time that you spend, you know, maybe eight months of a project for data acquisition.

Jesus Moreno (24:55.874)
Wow.

Pablo Yarza (BIOINFILE) (25:19.341)
data curation, this is what I've calculated, you know, and I've been in this field for a long time. And I know this, this is really costly. So you could, if you get all that and you outsource that part to a consultant, then you start getting better, right? Because there are specialized people or, or technologies companies who can do it. And then you get very good data quality controlled super fast.

In less than two months, you can get that way cheaper. So that's the point, I think. Yes.

Jesus Moreno (25:56.431)
And I think that that paves the way to one other trend that we're seeing and that's open science, the sharing of data across consortia. And one of the biggest challenges in global trials is standardization. When we have data coming from different labs, different countries, different formats, it becomes a mess to fit it all together.

Pablo Yarza (BIOINFILE) (26:09.028)
Mm-hmm.

Jesus Moreno (26:26.034)
Is it actually possible to create a universal standard for biological data? Or will we always be fighting the entropy of it all?

Pablo Yarza (BIOINFILE) (26:40.845)
Yeah, yeah, that's a problem. So for instance, in Europe, there is an emerging trend. Well, it's a regulation actually called the European Health Data Space, and it's aimed to solve exactly that thing. So one of the drivers is giving to the citizen the rights over their biomedical data. With that regulation, mean. And then at the...

institutional level being able to share primary data with same formats, with the same standards to actually get faster to that data so you don't have to repeat the data because you can share it at that level. So all that is happening in Europe for sharing primary data.

sharing primary data for secondary usages of that data, right? So that's a big trend that is apparently going to solve that problem. yeah, but finally, we go back again to the maintenance problem. Primary data is cool. It should be cheaper and it's going to be cheaper and cheaper, a commodity maybe.

But then who is going to maintain the data sets that represent something? So these pieces of knowledge, the secondary data pieces, they need maintenance. And this is not solved by this European health data space. is something else.

So here I want to add something about the microbiome field, for example. So look at what happens when you get these gut microbiome testing using one technique or the other, using one reference database in the backbone or the other, you might get different results. And this is one of the concerns about the microbiome market at the moment. Unifying those standards.

Pablo Yarza (BIOINFILE) (28:49.323)
is a necessity and who is going to do that. So my thinking is that the solution is at the academic level because academics have the wisdom, continuously upgrade their wisdom to make new research. So they are constantly up to date with science, with the state of the art. And this is what

should happen. I think knowledge transfer from academia to industry should get way faster, way more efficient. And if we do that, we help that we're going to get what we want. These standards better, this harmonization and so on. So what I'm saying is that there is a problem behind all the problems that we have mentioned, that is the knowledge transference is not working. It's not working.

Jesus Moreno (29:45.263)
And maybe that's where BioInfile can step in and that brings us to this solution, the solution you brought to market, the quality data accessibility solution. Can you walk us through the platform? If let's say I am a research and developer director at a med tech or biotech company, what specific problems does BioInfile take off my plate?

Pablo Yarza (BIOINFILE) (29:47.161)
So.

Pablo Yarza (BIOINFILE) (29:58.489)
Right.

Jesus Moreno (30:13.386)
Are you a marketplace database or are you a creation engine?

Pablo Yarza (BIOINFILE) (30:13.551)
cool.

Pablo Yarza (BIOINFILE) (30:18.871)
Okay, cool. So we are creating the platform now. So behind the scenes, we are creating the platform, but it's not visible yet. So we are connecting these pieces kind of consultive way at the moment. But we say, tell us what data you need, what you're looking for. And maybe the customer say, but we need an NDA. Okay, we sign an NDA today, no problem. But you tell us.

specific data you want, the type of data, and we are specifically focused on omics data at the moment, from genomics, transcriptomics, all kinds of omics data, okay. Tell us the biological origin of the data you want, so it can be human tissue, but maybe not, you know, because if you are working with microbiome, for instance, you might want both human genetics, but also

microbial genetics, and also tell us about the type of sample you are working with. And we go deeper and specify all that. And with that, then we pass and use our technology and our providers to generate those datasets according to your needs. And we're going to produce those datasets with a quality control process.

following pharma principles, know, representativity, traceability, very, very clear structure with a quality report. And we're going to sell you that data with a report. So this is how it works, okay? So behind the scenes, what we're doing is AI processes to consume the public repositories and

papers and all those unstructured resources to get a sense of the current state of the art of that topic. For instance, if we are talking about vaginal and endometrial microbiome, for instance, so we are monitoring what's going on on that level. And then when a request comes from a customer, then we engage that knowledge

Pablo Yarza (BIOINFILE) (32:45.901)
with the public DNA repositories and generate this data set. We can also use academic providers as a support for the knowledge that we don't have. And this is how BioInfile scales. So as a platform, we are giving the opportunity to academics to contribute with the knowledge together with the public repositories to contribute data curated.

that we can aggregate and generate a new piece and sell it to the customer. Sometimes the data needs several resources or yeah, sources of expertise that are in different universities, in different places. So having BioInfo as a platform, aggregating that, adding the quality control on top and selling a piece of data that meets those requirements is what really solves the time.

for the customer that do not have to go to all those resources and make the agreements and the contracts and so on. So compared to other solutions, BioInfile is focusing more on the academic level. That's why we are helping to solve the knowledge transfer problem.

Universities typically love this thing when we talk to them because they are looking for tech transfer. They are having, at least in Spain, can tell you 60 % of the professors, 60 % of the professors do not have, do not engage into knowledge transfer, tech transfer services outside of the university. So the TTOs here in Spain are really looking forward these kind of collaborations. And as I say, the experts.

the wise people are the professors at the university. So hospitals can get the primary data, Devices can get it as well. But the ones who can curate the data, maintain the quality of the data sets are the researchers, are the professors. So we are going there for the left side of the platform. And then

Pablo Yarza (BIOINFILE) (35:03.555)
At the beginning, are selling these two companies that are doing R &D and need good data for those processes. But later on, this can be used by everyone who is doing research and needs good data to begin with the processes.

Jesus Moreno (35:18.452)
Excellent, that sounds like a very intricate web of collaboration between industry and research and academics. It's definitely a value add to bring to market those desperately needed breakthroughs. Pablo, in closing, for the innovators listening,

Pablo Yarza (BIOINFILE) (35:20.537)
you

Jesus Moreno (35:46.585)
who are looking to speed up their discovery phase. What is the low-hanging fruit for them? Are there specific therapeutic areas or types of biological data, for example, microbiome or genomics, where bio-infile currently has the strongest impact? And are there other biological data topics, areas where

you will be able to provide valuable insights in the near future.

Pablo Yarza (BIOINFILE) (36:20.751)
Okay, so BioInn file is helping to get access to curated biomedical data in the genomics field, genomics and transcriptomics field. Say for example, you have already looked for some data and you are then spending too much time and you're not getting what you want. We can help you find that because we're...

we are specialized on connecting with the genomic providers at the academic level, that are the experts on that. So we are multiplying that capacity of getting the data that is hidden in the scientific repositories sparse distributed. But sometimes, this data can actually be still private and not in the public domain.

So for instance, if you are doing a clinical trial and you need data for the observational cohort, because we are working with all the providers and the universities, we can easily find if the data exists or not. And that's already helping you at least saving time on the search function because that data is usually not known that exists. So for that part, think...

can be really valuable this functionality. Yeah, basically that. So omics data for sure and then especially in microbiome yes because our expertise as researchers comes from the microbiology sector we can offer immediate value in that field but finally bioinfo is transversal so it's not focused on microbiology

But okay, we started in all mixed data, but later on it's not, it's not going to be all mixed, but it's going to be all biomedicine because basically we're going to connect all universities and data providers because the search functionality is what we are solving first, you know, and this is one of the main bottlenecks. So to understand is this data existing and where is it?

Jesus Moreno (38:40.94)
Wonderful, thank you so much for that. Excuse me, I'm gonna pause here for a second. I wanna ask you, do you hear that motor sound on the background?

Pablo Yarza (BIOINFILE) (38:42.239)
Yeah. Helper, yeah.

Pablo Yarza (BIOINFILE) (38:53.784)
Now yes.

Jesus Moreno (38:55.81)
You do, okay. There's someone cleaning up outside. I don't want that to get into the interview. Honestly, those were the questions I had for you. think we've covered, we've had the discussion I was hoping to have with you. We're only missing the outro.

I would like you to ask I would like to ask you if you can give me a couple of minutes for whoever is doing that to stop So I can record that outro and and and that would be it's on my end Is that okay with you? Do you have a hard stop?

Pablo Yarza (BIOINFILE) (39:25.548)
Vale.

Pablo Yarza (BIOINFILE) (39:35.149)
Yeah, no, no, it's okay with me. Now I am thinking that maybe one of the parts I was a bit not very sharp on responding, but I think overall it was good. Or what's your opinion about the quality of the interview?

Jesus Moreno (39:50.511)
I agree. I think it was fast paced, it covered considerable ground. We went from your background to the problem to how it's affecting not only the research side of things, but also

Pablo Yarza (BIOINFILE) (40:03.394)
Okay.

Jesus Moreno (40:15.414)
convincing those stakeholders of the importance of this. And finally, what's the solution, which is integrating academic and industry through a structured and curated platform, is BioInfo. Those are my takeaways from the conversation. Hopefully that covers it. Yeah.

Pablo Yarza (BIOINFILE) (40:19.289)
Bye.

Pablo Yarza (BIOINFILE) (40:33.389)
Okay, cool. Yes, yes.

Yeah, exactly. So, well, I think we didn't mention, but we are collaborating with CROs actually to get to our customers because this is our channel, you know, maybe to get to the end customers because we are solving the same problem, know, facilitate or speeding up the R &D processes. And the other thing that I missed to maybe say is that we are on an investment round at the moment, but...

I'm not sure if this fits or not with the interview, you maybe it's a bit out of the...

Jesus Moreno (41:12.269)
Okay.

Pablo Yarza (BIOINFILE) (41:16.333)
What?

Jesus Moreno (41:16.366)
Maybe we can, you can mention it during the closing. You can make mention of that, like, thank you for having me. And by the way, we're doing this. I think that would be a good place to make that plug.

Pablo Yarza (BIOINFILE) (41:36.207)
Okay, cool, cool.

Jesus Moreno (41:36.718)
So let me let me step away for a second I'll hopefully I'll be able to ask whoever is doing this to to stop at least for you know a couple of minutes and and we can finish up the interview I'll keep recording so that you know my my team can edit it afterwards just a second, please

Pablo Yarza (BIOINFILE) (41:41.357)
I wait.

Pablo Yarza (BIOINFILE) (41:48.173)
I wait, I wait for you here. No problem.

Jesus Moreno (43:15.552)
Okay, I think that that works. So in closing, Pablo, you're taking, excuse me, Pablo, you're tackling the under, excuse me, Pablo, you are tackling the unglamorous, but absolutely vital work of building the foundation for science. If we don't get the right data, the rest doesn't really matter.

Thank you for sharing your insights with us today.

Pablo Yarza (BIOINFILE) (43:48.825)
That's right, Jesus. It's a very interesting conversation. I'm so happy to contribute to this topic. We are doing this from BioInfile and wanted to say that at this very moment, we are having an open investment round. It's our first proceed investment round. So if there is anyone interested, please contact us at bioinfile.com or here you have my email contact data. So we're open to talk.

So thanks Jesus. You're having a great podcast series. So go on with this. It's amazing.

Jesus Moreno (44:23.854)
Thank you so much for your words and for listening. Thank you so much for your words and for our listeners. If you're in, excuse me, I got disconnected. Thank you so much for your words and for our listeners. If you are trying to, excuse me, give me just a second. Let me send you.

Pablo Yarza (BIOINFILE) (44:47.447)
Yeah, yeah, sure.

Jesus Moreno (44:57.465)
Thank you so much for your words. And for our listeners, if you're tired of your data scientists spending all their time cleaning spreadsheets instead of making discoveries, I highly suggest you to look at what Pablo and the team at BioInfoil are building. Until next time, keep accelerating.