Alex Neumeister

	The biopharmaceutical industry has launched numerous initiatives on how to leverage artificial intelligence (AI) to advance drug development. For example, Pfizer expressed how AI can be used in drug discovery. Emerging biopharmaceutical companies (EBPs) are getting in on the AI action by leveraging AI to discover novel applications for shelved therapies that never made it to market. In this interview, Vimal Mehta, CEO, and Vince O’Neill, CMO, at BioXcel Therapeutics will discuss how they are actively using AI to discover advanced therapies in CNS and oncology.

Moe Alsumidaie: Why is using AI and machine learning in drug development so unique, and how does it make an impact in the future of drug development?

I think information is growing at a much faster rate than in the past. And particularly in drug development, information flow is even more complex because it requires solid domain knowledge of science, the clinical side, the commercial side, the IP landscape and, the competition. It’s difficult for anybody to keep up with 5,000 publications that are coming out on a daily basis and integrate and assimilate that information in their decision process. So, machine learning technology and AI is at a point where these technologies are matured, and they can be applied. That's precisely what BioXcel Therapeutics is doing.

	We use AI across the development spectrum. First, in the identification of novel drugs. And once we identify them, we use it to design our preclinical and translational work. If all of that has gone well, then in the clinic, we continue to use these technologies for the identification of the patient. So, it's across the spectrum and in the future we believe that we will be able to utilize AI in real-world data. In addition, we use AI in combination with wearable technologies  with our therapy, BXCL501; It’s our intention that the wearable will alert the patient to the onset of an agitated episode, and potentially avoid it. 

Alex Neumeister: Do you have any suggestions if certain diseases or disease entities are more suitable for this type of approach or you think you can apply this across the entire spectrum of medical illness?

These approaches can be beneficial especially in oncology; it's not that long ago, the oncology treatment we used to use was sequential monotherapy, or in other words, we would give one drug, it fails, we switched to another drug, it fails, and then we try a third one. These days we've learned a lot from infectious disease and other therapeutic areas, and we know that combinations of drugs and cocktails are really the way to go. I believe AI has a lot to offer there, allowing us to combine drugs in ways that match the known targets. 

MA: How is your approach improving the chances of success in CNS disorders? 

At BioXcel Therapeutics, we decided that we're going to focus on treating neuro symptoms rather than doing the disease-modifying agents. If we identify new targets for a disease-modifying agent, we park it, and we put it into our partnering bucket because we don't have the required capabilities to develop that drug. We develop therapeutics focused on drugs that have unexploited potential that have gone to the clinic with positive phase I data; however, never made it to market. We believe that 3,000 drugs exist in that state, and if we can even succeed with only 1% of them in identification through AI, that could lead to 30 NDAs for us. And BXCL501 is a typical example of that. 

	BXCL501 is used as a sedative anesthetic in a surgical unit, and we are using our technology that identified the target of agitation. This is where AI support has helped us in an area we would not have been able to achieve on our own. We expect to complete our schizophrenia/bipolar phase III trial in the first half of 2020 and file our first NDA in the second half of 2020. We did a lot of preclinical translational and human proof of concept work using the current IV form of the drug before we started testing it in schizophrenia patients. We saw significant responses with multiple doses up to a 90% response rate. 

Other companies have tried to find meaningful treatments for pancreatic cancer. Yet only less than 10 drugs have been approved. How are your approaches with AI changing the realm of hard-to-treat indications?

We have now a better and more in-depth understanding of cancer at the biology level. I think that we can really leverage the AI approach to rationally seek targets and combine them with drugs and also combine different cocktails of drugs. I think that's where AI really is beginning to prove itself. Pancreatic cancer is challenging to treat. From my point of view, I think that justifies a three-drug combination. And again, trying to move away from the nonspecific chemotherapies because they're limited in their efficacy. This really is the poster child for what AI can do within drug development in oncology, not only for pancreatic cancer but, also for different pathways that are unique for other types of cancer, such as lung and colon cancers.

is Head of Medical Affairs at CliniBiz and specializes in protocol design, drug safety and clinical trial management. 

, MBA, MSF, is a thought leader and expert in the application of business analytics toward clinical trials, and Editorial Advisory Board member for and regular contributor to Applied Clinical Trials

Articles

BioXcel Therapeutics Executives, Vimal Mehta and Vince O’Neill, discuss how they are actively using artificial intelligence to discover advanced therapies in CNS and oncology.

Pharma Companies Use AI to Advance Drug Development

	Neurodegenerative diseases are complex, and many, such as amyotrophic lateral sclerosis (ALS), Parkinson’s and Alzheimer’s, to name a few, are incurable. Developing therapies for those indications are extremely challenging and risky, especially when introducing novel mechanisms of action, such as regenerative medicine. Brainstorm Cell Therapeutics, however, is implementing advanced methodologies to mitigate study complexity and therapeutic area risk. In this interview, Ralph Kern, COO and CMO of BrainStorm, will discuss how they are overcoming these challenges and advancing science in neurodegenerative disease.

Alexander Neumeister:  Why did BrainStorm focus first on the area of ALS?

 Currently, there is an enormous unmet medical need in ALS. It is estimated that at least 30,000 
	individuals in the U.S. currently have ALS, and an additional 6,000 new patients are diagnosed each year. At the same time, there are only two approved treatments, both of which have limited effect on the natural history of this relentlessly progressive and fatal disease.  Brainstorm initiated early Phase I/II, IIa and Phase II trials of our innovative cell therapy in ALS and continued to evaluate NurOwn through the current Phase III pivotal trial after the initial studies showed great promise.

AN: How are the protocol and operational design of BrainStorm’s Phase III study uniquely adapted for ALS?

From a protocol standpoint, our ALS clinical trial includes a three-month run-in period, which is the time between initial screening and patient’s first treatment from their own cells. This time is also used to harvest the patient’s bone marrow cells and manufacture the final, autologous cell product. During that time, we also evaluate the patient’s rate of functional decline, which is one of our inclusion criteria. We know that the rate of decline in ALS can vary widely from patient to patient, and we learned from our Phase II trial that individuals who progress more rapidly might experience a better result from this treatment. These rapid progressors, who compose about half of the total ALS patient population, may have higher levels of brain and spinal cord inflammation compared to other patients.

	From an operations standpoint, we’ve simplified the healthcare system workload dramatically compared to what is common in many stem cell studies. In our study, once the bone marrow is harvested, it is sent directly to the manufacturing site. All the steps necessary to manufacture the treatment occur at our manufacturing site before being sent back in a pre-labeled, ready-to-use syringe for injection. Typically, stem cell studies are highly complex and require extensive, hours-long, on-site preparation in the cell and biology labs.  As you can see, we have simplified this greatly.

AN: Can you explain the process in more detail?

Once a patient’s bone marrow is harvested, it is shipped to the manufacturing site in a temperature-controlled shipping container, where all the steps needed to manufacture the finished product occur. The treatment is then packaged into a pre-labeled ready-to-use syringe containing 4MLs of fluid hosting 125 million patient autologous differentiated mesenchymal stem cells that secrete high levels of neurotrophic factors and dampen inflammation. That syringe is shipped to the study site, and treatment is administered to the patient with a simple lumbar puncture once the manufacturing site has informed the Investigator that the product has passed all release tests.

	To decrease the patient burden, we have introduced cryopreservation into our technology platform, which allows us to take a single bone marrow aspirate. By freezing the expanded mesenchymal stem cells prior to differentiation, we can produce repeated dosing from a single bone marrow aspiration. The patient experience, therefore, involves a one-time 30-minute bone marrow aspiration (BMA) procedure and pre-scheduled 30-minute treatments when the cells are re-introduced back as the therapeutic agent into the cerebrospinal fluid by lumbar puncture, every two months.  This means the patients do not need to undergo repeated bone marrow aspirations for every dose.

	Over the past 10 years that our technology has been in development, we’ve built a strong track record of quality control and have consistently met the highest cell therapy product manufacturing standards. Each step of our process is fully validated, from manufacturing to cryopreservation, to the shipping parameters we have put in place so that the cells are viable for up to 72 hours. We are confident we have laid the groundwork for highly successful commercialization of this innovative cell therapy technology.

Moe Alsumidaie: What are the inclusion criteria, and how is enrollment progressing?

 We are recruiting 200 patients at six sites and currently are 85% enrolled. Inclusion criteria include:

		Early ALS patients, whose disease duration is less than two years;

		A score of 25 or more on the ALS Functional Rating Scale;

		Breathing capacity of 65 percent or higher on the predicted slow vital capacity.

	Additionally, during the run-in period, we select for rapid progressors, or patients with a minimum level of functional decline, so that we have a higher probability to demonstrate a treatment effect. Enrolled patients typically are mobile and able to travel.

	Our clinical trial sites are Mayo Clinic in Rochester, MN; University of Massachusetts in Worchester; Mass General in Boston; CPMC in San Francisco; UCI in Irvine, CA; and Cedars Sinai in Los Angeles, CA.

MA: How does your treatment approach compare to that of your competitors and to currently available treatments?

BrainStorm’s approach is clearly different for several reasons. First, we have the potential for disease modification rather than symptomatic treatment. Second, our treatment is delivered directly to the central nervous system through the cerebrospinal fluid and is not dependent on crossing the blood-brain barrier, which enables free access to the spinal cord and brain through the spinal fluid transport system. Third, our treatment works by supplementing or replacing a deficiency of neurotrophic factors thought to play a critical role in ALS progression. This provides a significant stimulus to help with survival and functioning of the surviving motor neurons and other brain tissue.

MA: How is BrainStorm using biomarkers to differentiate its approach to treatment?

 Our Phase III study assesses three types of cerebrospinal fluid biomarkers in evaluating patient response to treatment. First are the cell-secreted neurotrophic factors, which serve to confirm that the biological molecules have been delivered to the target. Second are neuroinflammatory factors, which imply target engagement and the direct effects of treatment. Third are measures of neuronal damage, which can include neurofilaments, measures of cell death, and support the action of our therapy on the survival and viability of motor neurons and other brain cells. We feel very confident in these three types of biomarkers based upon our experience in our Phase II study.  We are also open to exploring the potential of new evolving ALS biomarkers, and we will incorporate these new advances in our Phase III study analyses as the science evolves.

MA: What outcomes do you anticipate from this Phase III trial?

 The best outcome we can hope for is drug approval so that ALS patients have an innovative and effective treatment option. Our primary study endpoint is to demonstrate the proportion of treated patients who achieve meaningful change in the rate of decline in the ALS Functional Rating Scale. The study design is quite rigorous and has a 90% power to demonstrate efficacy in our primary outcome measure. Once enrollment is completed in Q4 2019, the study will be completed approximately one year later, in the fall of 2020.

MA: Have you experienced any operational challenges that are particularly unique for this study? How did you overcome those challenges?

 Our study includes many assessments and patient visits. Our sites did experience some challenges related to the complexities of bringing in new patients, administering the second and third intrathecal transplants. Additionally, there is tremendous co-ordination needed among different hospital departments, from the hematologist who performs the initial bone marrow aspirate, to the unblinded injection teams who aren't involved in the clinical care, to the clinical care teams who manage patients and perform the blinded assessments. As you can imagine, clinical trials have complexities that are much greater than routine clinical care. 

	From the manufacturing side, we needed to expand our manufacturing capabilities to accelerate enrollment early in the trial. Doing so required a technology transfer, which is a complicated procedure involving many people and has been a challenge for other cell therapy developers. Our manufacturing team did an excellent job, and we had outstanding support and guidance from the FDA. As we transition to a commercial treatment after our study, our success with technology transfers and our ability to successfully scale up manufacturing capabilities is very encouraging.

	Other challenges we anticipated did not come to pass. For example, we were concerned that our three naïve sites which had not participated in Phase II would take longer to learn the trial procedures. That turned out not to be the case, and one of our newer clinical trial sites is a top-performer for enrollment. We also were uncertain about patient demand. However, the sites were so well connected to the ALS community through advocacy organizations that the challenge became having to efficiently manage robust patient demand.

MA: How might the BrainStorm platform be applied to other unrelated indications?

Our approach is based upon our hypothesis that in conditions such as ALS, Alzheimer's, Parkinson's and progressive MS, neurons and other brain tissue go through a period of injury prior to cell death and may be salvageable in that period by reducing the inflammatory environment and improving their viability via neurotrophic and other repair factors. We have solid pre-clinical data in Parkinson's, Huntington's Disease, autism, and other brain diseases, and we recently initiated a Phase II trial in progressive MS. We're optimistic that this technology platform can play widely across many neurodegenerative diseases.

COO and CMO of BrainStorm, Ralph Kern, discusses how his company is overcoming challenges and advancing science in neurodegenerative disease.

Overcoming the Complexities of Neurodegenerative Clinical Trials

	The opioid crisis is front and center, as The National Institute on Drug Abuse is raising alarming data on the skyrocketing increase in opioid-related deaths in the US

, the White House has launched new initiatives to reduce opioid drug prescriptions

, and the increasing number of legal settlements with Mallinckrodt

 are creating a need for non-opioid options. However, the development of such will medical products comes with many challenges, and emerging biopharmaceutical companies face an uphill battle to develop pain medical products that are safer and more or equally as effective than opioid medications. In this interview, Dr. Steven Fox, CEO of Akelos, Inc., will discuss the environment of non-opioid drug options, and challenges of developing new non-opioid medical products. 

Alexander Neumeister: Where does the field of pain stand right now, and what's the openness 

: There are two types of pain: acute and chronic. Patients, especially those who had surgery, undergo a lot of pain after surgery, and many physicians would be giving them opioids for the surgery, when that doesn't necessarily have to be done - they could be using other analgesics instead of prescribing them opioids and potentially introducing them to addiction.

	Now, what we're looking to do is to treat chronic neuropathic pain. This type of pain can be demonstrated by people with diabetes who have peripheral pain in the toes and hands, people that have shingles, or people on chemotherapy, for example. Hundreds of millions of people worldwide and an estimated 21 million people in the United States suffer from this type of pain and don’t have the right drug for relief. Physicians and dentists are giving them opioids, so patients are not getting a chance to take drugs that are non-addictive or non-opioid. As a result, we now have the worst healthcare crisis in the history of the United States. Last year, more people died in the opioid crisis than HIV at its height, the Vietnam War, and gun and auto deaths combined.

	This has led to two massive problems: The first is that there aren’t good non-opioid drugs available to treat chronic neuropathic pain, and the second is that we are now suffering from this opioid crisis because we don’t have an alternative drug available. 

AN:Are you saying that the problem really comes from the fact that there is no adequate treatment available at this point?

	That's right. Opioids don’t actually offer much in terms of treating pain. They work by crossing the blood-brain barrier and the spinal cord, which means they reduce the transmission of pain messages to the brain. But that’s actually not very effective at all, and unfortunately, if you combine the lack of efficacy with the potential to become addicted, you end up with high rates of addiction

AN: So, when you look at your development plan, what makes you believe that this will make a significant change?

Well, we have taken Propofol, which is a safe and effective anesthetic used every day in every hospital, and we've altered it. So we believe it's safe and effective. We've tested a previous pharmacophore on animals and in vitro, and we've seen good results with mechanical and thermal stimulation, so now we've altered it again, so the compounds are in vivo and in vitro, and we think we've got an excellent chance to develop a safe and effective drug.

	The key is to not cross the blood-brain barrier so that the drug isn’t addictive. And we have created a platform with a tether and anchor and a pharmacophore in conjunction with our drug to inhibit the HCN1 receptor. So with all of that combined, we're hoping that we can get this new drug developed.

AN: What is your plan for designing an effective protocol for non-opioid pain? How do you plan to incorporate protocol design strategy to generate compelling data to compete with the safety and efficacy of opioid treatments? 

We will follow the guidelines provided by the regulatory agencies for all steps throughout the process. We are aware of the specific challenges related to safety and efficacy specifically in the development of a novel pain treatment. Specifically, patient-centered questionnaires often lack the sensitivity to ascertain certain domains of pain experience and pain processing, which is a factor that can contribute to missing signals of efficacy in clinical trials. Therefore, we will focus on a biomarker strategy from the beginning links together objective biomarkers and subjective assessments of the pain experience. Another critical factor that we will address in the clinical trials is the impact of chronic pain on the quality of life and psychosocial functioning. Improvement of quality of life is one key outcome measure in our development efforts because it provides insight into the real-life experience of pain patients and how an effective and safe treatment has the potential to become a life-changer for patients.

Moe Alsumidaie:Will regulatory agencies embrace a medical product like this? 

:I believe they'll embrace it, as it is direly needed, and unfortunately, they are still approving some opioid drugs. So I think that they will pay close attention to a non-opioid treatment, and hopefully support innovation in non-opioid drug development for pain.FDA’s initiatives are also driven by patient and physician needs, which is to have access to a non-addictive option for pain relief. Additionally, some states are cracking down on opioid prescriptions. In New York State, for example, I recently took a new course requirement for opioid addiction in order to get relicensed. New regulations require I search for a patient’s opioid history to ensure access to opioids is limited.  

MA: How will investigators respond to a new potential non-opioid therapy?

:I think physician investigators are likely to embrace a new pain relief option that is non-opioid. However, I do anticipate some skepticism, especially with the promise of a safe and effective non-opioid medical product, and the potential for trial failure. As an emerging biopharmaceutical company, we plan to address skepticism by partnering with thought-leaders in the area of pain and generating success stories with people who would have otherwise suffered from addiction, had they been prescribed an opioid. Additionally, the value of having a non-opioid medical product is significant, as not only are we addressing the value of reduced pain, but also the value of reducing potential addiction; I believe payers will pay attention to a novel non-opioid medical product.

https://www.drugabuse.gov/related-topics/trends-statistics/overdose-death-rates

https://www.whitehouse.gov/briefings-statements/president-donald-j-trumps-initiative-stop-opioid-abuse-reduce-drug-supply-demand-2/

https://www.washingtonpost.com/health/mallinckrodt-reaches-settlement-with-bellwether-counties-in-mammoth-opioid-lawsuit/2019/09/06/1e8a19f8-d0d9-11e9-b29b-a528dc82154a_story.html?noredirect=on

https://www.nytimes.com/2019/08/26/health/oklahoma-opioids-johnson-and-johnson.html

Dr. Steven Fox, CEO of Akelos Inc., discusses the challenges of developing new non-opioid medical products as the need intensifies as the crisis worsens. 

Emerging Biopharma Tackles the Opioid Crisis

	The field of Alzheimer’s Disease (AD), while poses a significant opportunity, has been faced with big challenges, and massive late-phase trial failures. Some argue that trial design was the culprit, however, many believe the science was to blame. Despite subsequent setbacks in the field, emerging biopharmaceutical companies are still pursuing AD therapies with new science, and different preclinical and clinical trial models. In this interview, Dr. Daniel Alkon, President & Chief Science Officer at Neurotrope will discuss novel approaches to AD therapy development.

When Alois Alzheimer discovered the disease around 1906, it didn’t have any traction. In 1984, two scientists identified a protein called amyloid beta. When that happened,everyone thought,"Oh this will be a real breakthrough because we now know what key protein is involved. And it was involved in what are called amyloid plaques and tau tangles, neurofibrillary tangles,which are the pathologichall marks. The main approach, neuro-pharmacologic approach, is where researchers tried to develop drugs to address other deficits that people had thought attended those pathologic deposits, such as the loss of cholinergic neurons, which contribute to memory and attention deficits. This worked to the point where we developed drugs that provided mild symptomatic relief, but, did not treat the disease. So, the industry started to focus on getting rid of amyloid beta buildup, as they believed the disease was caused by that protein. There have been many approaches to try to reduce amyloid-beta. One is to use animal antibodies to combine with and eliminate amyloid-beta; another involves activating enzymes in the brain to degrade amyloid-beta, another is to inhibit enzymes in the brain that help form A-Beta such as inhibitors of Beta Secretase; none of these approaches worked.  Many scientists had thought that amyloid plaque and tau tangles were destroying brain neurons and synapses; this theory was also disproven.

MA: What have you discovered is the main contributor to AD?

  I worked on memory at the NIH and then at the Rockefeller Neuroscience Institutefor 15 years, and we implicated certain key molecular pathways that were responsible for memory formation. In memory formation, we found that we could demonstrate with electron microscopy the formation of new synapses and once we understood that and the pathology that had been acquired with human brain samples,we hypothesized that we could facilitate not only memory formation but also the formation of synapses, which might be a regenerative or restorative approach to AD. That motivated us to work on clinical trials, first with a compassionate use trial with patients suffering from advanced AD. We generated successful results, hence, we went to a Phase II trial, and we published the results recently in the Journal of Alzheimer's Disease.

Alexander Neumeister: What is your hypothesis?

Our hypothesis is that since wesaw an improvement in patients who underwent the compassionate use trial,we pursued a larger number of patients to see if we could achieve similar results. Results from that study demonstrate clear signals including not only a reduction in degradation, but, also a reversal in memory loss and an improvement in their conventional psychometric measurements. Even one month post study completion, and after all treatment had been stopped, results were consistent with a new and constructed wiring. These findings have encouraged us to continue development with this hypothesis. 
	
	

What did other researchers miss in their animal models?

 I think a lot of the industry was misled by some of the animal models that they used. For example, there was one double transgenic amyloid precursor protein(APP) model that the industry used. The APP model makes a huge amount of amyloid, so much amyloid that it acts like a tumor occupying space in the animal’s brain. So, if there is a reduction in that amyloid and it's not so huge anymore, the animal tends to get better. But that's not what happens in AD, we tend to observe a gradual build-up of much less amyloid.

MA: Why did you target patients with advanced AD?

While we have every reason to believe that we can treat much milder cases and even prevention, we chose patients with advanced AD because we saw benefits in the compassionate use patients, which were very advanced. And it's because the industry basically has abandoned that niche and we wanted to see whether we could undertake that challenge.

MA: What challenges did you experience with recruiting and retaining patients with advanced AD?

: Patients with advanced AD are a challenge to recruit. But fortunately we had 27 sites with principa linvestigators at each site and a dedicated team of researchers. We were pleasantly surprised that we could recruit the patients even though they were advanced based on their caregivers making the decision, and we believe that we saw such good recruitment figures because of our relationship with our investigators and their relationship with their patients and caregivers. We also believe what contributed to this success was the hope of reversing AD with these patients; we saw very few dropouts, and we think that was fueled by the hope that our medical product could improve those patients’ lives. For instance, in the compassionate use trial, one patient who has a familial gene for early onset AD(by the time she was 31 or so), and couldn’t speak, swallow or move at the beginning of the trial, saw a significant improvement in speech, movement, and her livelihood. That story got around, and the story fueled recruitment and retention.
	 

, MBA, MSF, is a thought leader and expert in the application of business analytics toward clinical trials, and Editorial Advisory Board member for and regular contributor to Applied Clinical Trials

Dr. Daniel Alkon, President & Chief Science Officer at Neurotrope, discusses novel approaches to AD therapy development and why his company chose to target patients with advanced AD for their own. 

Alex Neumeister

Articles

Pharma Companies Use AI to Advance Drug Development

Overcoming the Complexities of Neurodegenerative Clinical Trials

Emerging Biopharma Tackles the Opioid Crisis

Alzheimer’s Disease Research Finds New Beginnings