Compugen Ltd. (CGEN) Earnings Call Transcript & Summary

Welcome to Jones fireside chat with Dr. Eran Ophir, President and CEO of Compugen. I am Danya Ben Hail, an analyst at Jones Research. Compugen is doing computational target discovery long before AI and biotech became a buzzword. So they will explore what it really takes to turn predictive biology into first-in-class immuno-oncology drugs. Eran. Thank you for joining us.

Thank you Danya for inviting me.

Let's start with the foundation. Compugen repeatedly and covers first-in-class targets where traditionally the discovery methods stall. Every AI company today claims a data advantage. Getting started, can you give a brief overview on Compugen's platform, and what makes it unique?

So first, as you mentioned, we are not just a recent AI story that's saying that we're doing AI, just to have the buzzword in the name of the company. We're doing it a long time ago. We have built a best the system. We have this engine called Unigen. So this is one. I think the second part is that stage of the riches and development that we are focused on, which is relatively unique. I mean you gathered a really nice group of companies in this set of fireside chatter with AI companies, -- most of them are doing, for example, AI to identify the drug targets to identify easier, maybe better antibodies, small molecules, but we are focusing on the very first stage of the research and development on the drug target itself, which target, which molecule, which protein in the human body, we should target to really modify it to have eventually affecting cancer patients. And there are not many companies that are focusing on this relatively challenging first part of bringing mobile targets -- and there are definitely not many companies that have shown again and again that they can bring novel targets and that they're generating clinical data and further validation by pharma companies collaborating on the targets, so I think this is another differentiation that the platform is validated. And finally, it's not only the AI and the machine learning and the algorithms and the database that we have that we built a long years -- it's really the end-to-end capabilities. In one company, we have this know-how, again, developed a long years of using the right algorithm right at assets, asking the right questions to identify the drug targets but then also how to validate how to eliminate target that should not proceed, how to choose the most promising one to take into the clinic And then in the clinic, we're exactly to take them I think also this end-to-end approach is relatively unique for Compugen.

Yes. Well, that completely makes sense. So I mean, your thermal propriety algorithms, our decades of accumulated VetLab and you have the specific letumab, immune evasion mechanisms. So all of that together brings it gives you this advantage? Or is there anything very specific and unique that you'd like to say this is what -- this is the point of uniqueness or.

So it's absolutely that. It's the combination of how these pieces reinforce each other. We have great algorithms. We are mapping the tumor macro environment for years from every different angle you can imagine, Traxyptomics, photonics to try to learn about the human tumor macroenvironment. But then also the convergence of disciplines, having data scientists, beverages and clinicians, sitting together in the same table asking the self what clinical problem we can solve but asking a specific biological question and how we can use the algorithms and data science to help us identify the targets to solve that problem. So this is one. And second is that this is a flexible approach. So the database continue and fits itself. We continue to generate data all the time from the preclinical data from clinical studies we are doing. We're sequencing patients whatever sample we can put our hands on were sequencing, and this feeds back into the database to enable us to choose even better targets for the next round.

Yes. Given the high failure rate of novel biology, so why is finding new targets still the most valuable application of your platform? And how do you protect against the existential risk of novel target failing in Phase I.

So first, I don't think this is only a problem of a novel target, which fails in the clinic. This is -- the biggest challenge is how to really predict clinical success in the preclinical package. For example, if you want to generate a better molecule for a known target, then you need sometimes to be better than the existing one and you need to be differentiated. So you could even if your molecule is working because the target is validated clinically, you are not better than the existing drug. So there are many challenges also for developing better drugs for known targets. Especially, I think these days, when China competition rising up, I think that's really bringing the target itself and not just trying to develop better drugs or loan targets is something which is still a challenge, something that we have a know-how and advantage in how to do it. And again, given the recent competition for China, I think this is still something which is unique and still is -- have less competition and less competitive pressure from others.

Yes. I mean, you're right. And the industry has seen like high-profile failures. But I will point that especially in targets that took great in silico, but failed in humans. So how does Compugen ensure its models are capturing real drug responsive human biology rather than just finding statistical noise and massive multi-omics benefits.

So this is a very important question. It has another multiple layers of the way we ensure it. First of all, we are not looking into statistical noise in data sets. We are starting with a unique clinical question. And we always, always, always make our analysis in the most relevant human samples. We never use proxies. We make sure that we have the right data set of human tumors from patients to answer the clinical questions that you have. But then the targets that we are working on are never remains in silicon. Then come and discussed before, the end-to-end capabilities, how to build a biological package to really convince us, first of all, that these targets is a valid target that can succeed in clinical settings. So we put huge efforts into doing all direct experiments, and maybe they can take an example. The COFI that we licensed to Gilead, it haven't yet proven clinical or least we didn't disclose any clinical data but at least the package is convincing enough for a few pharma companies to chase it. And eventually, we got this $90 million -- $850 million deal, $60 million plus $30 million and all of that. So the package was convincing also to others, let's say, is that -- so the [indiscernible], we started with a very unique clinical question about resistant mechanism to PD-1. And then we looked into patient samples in UNIGEN -- for some of the samples, we actually for that specific question, we collected more samples. We have a very good collaboration with hospitals in Israel, and we get every day samples from hospitals, from surgeries. And then we met discover itself. So a disease-relevant and that source for the data in which we found the discovery. But then also the validation stage. We try to rely as much as we can on human samples directly ever from patients showing the activity of the drug in the most relevant system. Yes, sometimes mice could be relevant. But definitely, the focus should be on the human systems. -- on a very rigorous validation and high bar for targets to move forward. And then at the end of the day, also in the clinical settings to really use the computational tools to identify the patients that could benefit, giving all the data that we have. So I think this whole package going from discovery in human samples, all the way to the clinical settings with a very strong biological package around it, experimental package is key to what we do. And this is, in a way, taking this initial in silico prediction into a target with full biology around it that is sufficient for us to move forward with.

Yes. And that gets into -- so you're one of the first companies to bring computationally discovered targets into human trials. What have regulators thought to you about how they evaluate for clinical packages that were rooted predictive algorithms.

So from our experience, we didn't have any issues because eventually, we are not bringing them the silica package. We're bringing them the experimental package, the preclinical package lots of focus on safety. So the packages that we generated for our computational discovery targets had never any issues with the regulators. We always had a nice path into Phase 1, INDs, acceptance, and all of that. So if you generate the right package, the fact that the target initially was discovered in silico doesn't really matter much.

And Okay. So with AI being implemented across the entire R&D path, what is the hardest biological constraint in drug discover, whether it's tumor microenvironment complexity or immune pathway redundancy that no algorithm can simply optimize away?

So it's exactly that. I think that eventually, the ability to model the complexity of the human in our case immune system, but in general, the immune system is extremely challenging. So what we are doing to address that, as mentioned before, we are really modeling and mapping the 2 macro environment from every angle, you can imagine, we definitely use the recent AI tools, which allows us to do things that we couldn't have done before. Absolutely. We could navigate now in this complex, huge complexity of data in a way that we couldn't have navigated before, definitely. And still -- we're not in the place we can say, okay, we can push on the button and we get a target. This is a very complex system, a very complex trial and error approach. But definitely, those are improving every day, and we definitely can do today things we couldn't have done in the past.

All right. So there is the biological redundancy, and something that AI can't fully predict today, hopefully, we'll get better at. So does that explain your shift into looking at combination therapies like during your either inhibitors with TIGIT or BD1 inhibitors? How does the platform account for these complex interactions?

So first of all, I think that in general, oncology is going into combinations. We know that a single drug can achieve, in some cases, significant effects. But in many cases, you need to combine different mechanisms. And this is, again, where Compugen fits in. We are bringing new mechanisms that could work as monotherapy, but could definitely also work in combination, for example, the biologic PPA, which we think is very relevant for ovarian cancer. The focus now in the MAIA study, and we'll discuss it in a second is on the monotherapy activity of COM701, the blocker of PVRIG that we identified computationally, but the next steps could definitely also be combinations. But this really depends on the patient population, what they can tolerate, the ability to combine, again, PG, for example, COM701, the block of Berg has a very good safety profile. So it's relatively easy to combine. So I think combination is definitely something that is relevant. It is not necessarily for AI discovered or non-AI discover targets.

Yes. And or PBG, what gave you the confidence to take it into preclinical and then clinical studies? What's in celial signals convince you to continue with that.

So first of all, as leverage identified computationally, there are no publications around it. The academical community didn't know Piper when they identified it, which is a good start, but definitely not the important part. The important part that we started to explore it, we identified it as a very, very different biology, different from TIGIT completely from PD-1. So we don't only have a new checkpoint. It's a checkpoint that could have different consequences when you block it compared to other checkpoints. And this is what we saw preclinically, and this is exactly what we saw clinically. In patients, we have seen this unique biology translating into activity. As mentioned before, we're sequencing the patients. We looked in patients treated with COM701 before, and we take biopsy also and samples also after treatment, and we saw COM-701 can modulate the tumor convirnment in a way that we think is unique to its biology. And then also the clinical signals. We have, for example, a patient with PDL1 negative ovarian cancer that failed all the sound of care treatment is could receive she received COM701 in monotherapy and that computational prediction prolonged the light of that patient, he were made on the study for 2 years. So the goal of the current MIA study is to take the signals we have seen -- I mean so the drug is active. And PLG is not in silico prediction now. We know it's an active drug that can modulate and affect the progress of bring cancer tumors. We also have seen signals in other tumors. And now the MAIA study is a study we're doing that after seeing signals in the last line platinum-resistant to gain cancer, patient who failed everything. Some of them had 10 prior lines. We are now taking the signals we have seen and the very good safety profile into an earlier line of platinum-sensitive patients, ovarian cancer; second, third line, and the goal of the study is really to see 1071 in monotherapy, mediate significant monotherapy activity and prolong the progression-free survival of these patients who have no standard of care. These patients have a huge unmet need in the second, third line, they received the platinum and there, there is no treatment approved to maintain them from becoming platinum-resistant and this is the goal of the MAIA study.

And we expect interim data readout in first quarter 2017 correct?

Absolutely. We expect to have the interim analysis, which will include the meaningful data of progression-free survival and any other clinical signals by Q1 27, yes.

And if the data is strongly positive, does Compugen take the leap into building its all late-stage clinical infrastructure? Or does that milestone simply trigger another out-licensing event?

Yes. It's a good question. It will depend on the actual data, magnitude of effect, whether we will think that -- remember, again, there's a huge unmet need. So definitely thinking about this exact patient population. And now we can go to registration fast will be the first priority, either we can do it alone or maybe we think that the best thing will be to partner to move fast and aggressive into Phase III. In addition, we're talking here about an adaptive trial design. So we can also add additional arms to continue to explore the possibilities. For example, we can combine COM701 after showing the monotherapy with BEV between combine it with ADCs and then open also more opportunities going earlier, later in ovarian cancer also into other indications.

Yes, especially taking into account, it's a very competitive space right now.

It's a very competitive space, but there are very few nontoxic agents, which are fighting for that space. And patients after 6 cycles of platinum, some of them may want to have a bit of an easier drug than an ADC, which is eventually toxic. And the pharma companies, which are fighting between themselves with a different ADCs, also on the way to differentiate. So having a combination partner, which is combinable and ideally Again, the durability works in the last line will transit as well could also be a matter of priority for -- to differentiate in the competition for pharma companies.

Yes, makes complete sense. You've secured impressive validation with your AstraZeneca and Gilead partnerships, beginning in substantial milestone potential. Is the monetization strategy to continue offload these assets early or -- yes. So do you intend to keep full commercialization right for future discovery assets beyond what we have currently in the pipeline.

So I think it's really going to be program dependent. First of all, I think with the financial stability we have now, after the monetization of a small portion of the AstraZeneca royalty last year, -- so we now have cash in the '29. So we have financial stability. And this gives us the freedom to make our choices because we don't have to rush and out-licensed to maintain the company alive. So if we think for unspecific program, if we generate additional data in a Phase II or maybe even a Phase III study if it's small and focused one, we will bring most of the value for ourselves and for the shareholders, we'll do so. If we think that we need now a very aggressive clinical program, and we need a pharma partner to move aggressively in multiple fronts. And this will be the path that will bring most of the value to the company and our shareholders. This will be the part of eventually it's going to be program dependent.

Yes. And to summarize this part, so where does your platform create a sharp shift in return on investments? So is there financial and operational leverage found in accelerated early target discovery? Or is it a derisking downstream clinical decisions. Where is it lies?

So I think, first of all, the platform is focusing on bringing new biology, bringing new targets as mentioned before, pharma companies tend to hear also biotechs to hear they are on the same target, same biology, and we're bringing new biology that could really enable more and new options for patients. But also, as discussed, the rigorous process that we are doing, and this is yet to be proven, but I think this is ongoing, shouldn't bring us on not only targets with new biology, but also targets will have more probability of success. We discussed before the COM701 data, and we have the readout by 2027. We didn't discuss, for example, digital number of targets we identified a long time ago. Definitely multiple failures for TIGIT. I think this is a case of a target that is definitely clinically active. It's clear that TIGIT is active. We've seen it in multiple trials. But some of the initial assumptions that some of the drug makers had on TIGIT, maybe overestimated activity, maybe didn't choose in this case, the right format. In this case, for example, I think that with the right format with the bispecific antibody of AstraZeneca, they will leverage also the TIGIT biology that we initially identified. We have 11 Phase III trials ongoing. It was interesting to hear AstraZeneca's management in the recent ASCO event, talking about the way they see the evolving data for rilvagostamic. They were talked about stabilization of the responses they showed an ASCO durable responses in early trials that talk about combinability. So I think that also TIGIT, which is a target that we identified that has definitely a roller coster of ups and downs. I think that that AstraZeneca with their way of developing it, the clinical strategy, the bispecific will also eventually make the most potential out of this digital computational discovery.

Can you just highlight the differences of your TIGIT asset compared to the prior failures just to clarify to people listening in?

Absolutely. It's very important. So again, this is an example in which doing the -- what we think is the wrong drug format could make a difference. So most of the initial developers develop TIGIT has an FT active. I would not go through all that biology, but that was, we think, was not the right format. It caused the safety issues. It had challenges to combine. And eventually, it was difficult to keep patients for a long time on the study because of the safety. But even maybe more importantly is the fact that AstraZeneca are the only ones who are developing TIGIT as a bispecific for PD-1 and TIGIT. This has some mechanistic advantages that we see across other bispecifics as well that could be more active than some evidences for that, could be more active than PD-1 digit combinations that others have done. And this also allows a different clinical strategy, much easier to combine less burden of showing contribution of components of the bispecific. So I think it's the format of the antibody the clinical design strategy and the combination around all these 11 is trials, most of them or many of them with ADCs that will put AstraZeneca stage antibody which is partnered from us, obviously, in a different position than the other TIGIT were.

Yes. Thank you, Eran. So as we look into the second half 2016 and beyond, what are the most important clinical and strategic milestones investors should be watching?

So first, obviously, is our own asset, COM701, the MAIA study by Q1 27. We're going to have the meaningful data to show if COM701 can really drive monotherapy activity in this population of a brand cancer. Relvagostamic the expectation from AstraZeneca for Phase III readout, which is going to be the meaningful 1 is after '27, but we see all the time accumulation of data like in the recent ASCO showing again the durability, the safety, the potential of different combinations. So I think with the accumulation of data, it will show eventually that this molecule of TIGIT is doing something else. And then obviously, the comp called now GS0321, that will access to Gilead. We were already in the clinic for more than a year now and the progress from Phase I, we don't have yet disclosures for exactly when typically when working with the pharma company, but definitely keep an eye for the Conferoand the early pipeline, the competition discovery platform, we have financial stability. We have a validated engine that will continue every day to leverage and be more assets. And along the coming year, again, we don't have specific guidelines, but definitely, we will report on the early pipeline when time will come.

Great. looking forward. So to close up, we will do a rapid fire questions section. So let's get going. Most overhyped claim in AI drug discovery today.

I think that people that say that AI is going to dramatically increase clinical success rate in any disease are still a bit early. Things are moving fast. So difficult to make predictions. But for now, human system is too complex to be installed with a push of a button.

So most underappreciated bottleneck?

The clinical development. The community must do something, especially in the U.S., but also in general, about making trials cheaper faster. We have great targets. We need to test them. We need to see in patients if it works or not. And for that, we need a better system for faster and more cost-effective clinical development process.

And hopefully, I can help with that.

Absolutely.

What is the 1 metric investors should focus on that actually captures platform value?

So eventually, looking at the totality of the assets that we have and that we will have and we'll disclose our ability to open new target space, new mechanism to bring additional bid activities to bring more clinical validation for our internal and partnered assets.

One proof point investment should demand over the next 2 to 3 years.

Eventually, the proof is in the pudding. I can sit here and tell about the processes we are doing and the rigorous validation, eventually, and assets should show success in clinical translation, this is what we work for. This is what the investors should wait for.

Great. Well, thank you for the thoughtful discussion. What you've built competence shows that computation al isn't about shortcuts. It's about uncovering biology that was invisible to additional methods, and we are looking forward to the future updates. Thank you, everyone, for joining us today. Enjoy the rest of the upcoming sessions.

Thank you, Danya.