Biotech Innovator Leen Kawas On How Biomarkers Integrate with AI and Machine Learning to Solve Complex Healthcare Problems
By Contributing Writer
Hannah Madison
Dr. Leen Kawas, managing general partner at Propel Bio Partners, illustrates how biomarkers work alongside AI and machine learning to alleviate healthcare limitations and issues
Artificial intelligence (or AI) and machine learning (ML) (a form of AI) are becoming relevant and significant in the biotech and life science industry. AI capabilities are integral to more accurate diagnostics, personalized patient treatment, and chronic disease prediction, among other applications. AI and ML are anticipated to have the most transformative effect on pharmaceutical research and development (R&D).
According to Propel Bio Partners’ Dr. Leen Kawas, this is driven by the advancement in computational power, and advancement in data sciences increasing the ability to capture and process large and diverse data sets. AI/ML have been used in drug discovery in the last two decades. What is even more exciting is that now we are seeing an increased focus on the utilization of AI/ML in clinical trials and conduct. This is possible due to the increased reliance on digital technologies and a better understanding of molecular and physiological biomarkers.
AI Accelerates drug discovery and development
Biotech companies are increasingly using AI to help achieve their product development objectives. On a macro scale, AI can facilitate the acceleration of the development of drug candidates, which enables cost savings for end users.
For perspective, traditional target and drug discovery-led optimization, including animal testing, takes three to five years. After this, human trials can begin, which could take another 3–5 years and sometimes longer. AI-based start-ups have the promise of identifying and designing new drug candidates in a more efficient and effective way. AI holds the potential to reduce timelines for drug discovery, improve predictions on clinical efficacy and safety, and can diversify drug pipelines without any bias from individual experience. Artificial intelligence has also proven itself in clinical trials. AI technology uses biomarker monitoring platforms, plus millions of individual patient data points. The AI technology can analyze a blood sample, obtained by a clinical trial participant, capture a large volume of information, and potentially correlate it to efficacy or safety endpoints.
Biomarkers May Enable Rare Disease Drug Advances
Rare disease drug development attracts an increasingly large share of investor dollars. This influx of funds is likely driven by potential cures for single-gene mutation-caused diseases. However, drug developers have found it difficult to identify patients for drug research and treatment activities.
Biomarkers may be an ideal solution, as they can identify the patient population that can benefit most from specific therapies, model response, and effects that can increase the success of potential therapies. As personalized medicine gradually comes into focus, each individual’s biomarker panel can help with patient selection and stratification. In the most innovative companies, the use of adaptive trial design and data analysis can drive to detect a treatment effect.
Propel Bio Partners LLC Supports Innovative Bioscience Companies
Los Angeles-based Propel Bio Partners LLC is a rapidly growing private equity firm focused on investments in the healthcare and life sciences sector. The firm is distinctly different from other venture capital firms, as Propel Bio Partners offers recognized experts’ guidance along with a financial investment.
Leen Kawas, Ph.D. is Propel’s Managing General Partner, and she is deeply involved in evaluating potential investments. Formerly Athira Pharma, Inc.’s co-founder, she invented several drug candidates and was key to the firm’s growth. Dr. Kawas was the first female in twenty years to take a company public in Washington state, at the time when she took Athira public.
In early 2023, Dr. Leen Kawas noted that more companies have integrated AI into their drug development programs. “We see a big surge in the number of companies that are trying to use AI and predictive modeling to accelerate drug development and discovery,” she remarked.
Persephone Biosciences
Persephone Biosciences, Inc. is one of Propel Bio Partners’ most recent investments. In July 2022, Persephone Biosciences closed its $15 million seed funding round. Propel Bio Partners co-led this pivotal funding vehicle.
San Diego-based Persephone Biosciences is focused on developing microbiome-based drugs for infant health, oncology, and other applications.
Persephone Biosciences’ Argonaut trial, the United States’ largest-ever study, involves the use of the gut-immune conjunction to find biomarkers for cancer prevention and treatment.
Dr. Kawas Spotlights Persephone Biosciences’ Work
Dr. Leen Kawas noted that Persephone Biosciences uses AI and machine learning to discover patient datasets’ biomarkers. Persephone Biosciences utilizes these biomarkers “to inform the development of our therapeutic and consumer products. Persephone’s technology platform is based on diverse and inclusive, population-scale, observational clinical trials in conjunction with advanced multi-omics analyses and machine learning.
“[Persephone’s aim is] to probe the complex interaction between microbes and the immune system. Discovered biomarkers are used to develop precision immunotherapies utilizing synthetic biology for unmet needs and more equitable treatment outcomes,” Dr. Kawas concluded.
Inherent Biosciences
Inherent Biosciences is a biotechnology firm headquartered in Salt Lake City, UT. Propel Bio Partners has invested in this epigenetics-based venture, which uses AI to devise innovative clinical solutions for complex healthcare problems.
Dr. Kawas Highlights Inherent Biosciences’ Work
Dr. Leen Kawas detailed Inherent Biosciences’ overarching goal. “Inherent uses machine learning to identify epigenetic biomarkers (epimutations) for use in diagnostics and potential therapeutic targets. An example, and the first application pursued, was employing machine learning to develop a sperm vitality calculator that integrates sperm DNA methylation signatures and is highly predictive of an individual’s biological age.
“Importantly, the Inherent team has found that specific lifestyle factors (including smoking) shift the predicted biological age upwards. Our preliminary data also show that increased BMI is another factor affecting biological age.
“Additionally, inherent academic collaborators found that in a mouse model, many smoking-associated differentially methylated regions (DMRs) in sperm are corrected following the removal of the smoke exposure. These data suggest that sperm epigenetic changes are both modifiable, and to some degree, correctable,” Dr. Kawas summarized.
AI Empowers More Effective Decision Making
Dr. Leen Kawas also noted that AI enables a new biological perspective that drives higher-level decision-making. “AI enables us to bring a number of different data (like omics, metabolomics, proteomics, epigenetics, and clinical presentation) to empower more accurate and comprehensive decision-making,” she noted.
For perspective, omics is a multidisciplinary field that includes the other listed modalities. AI’s high-level processing capabilities drive rapid depiction of multiple-level cellular processes, interactions, and reactions. In turn, this enables a better understanding of the relationship between expansive datasets and faster health-related discoveries.
AI Enables Improved Diagnostic Performance
Accurate diagnosis of medical problems is key to resolving them. However, every year, close to 12 million Americans who seek outpatient medical care are misdiagnosed. Some diagnostic errors have resulted in life-threatening outcomes.
Most often, the misdiagnoses result from a general radiologist analyzing scans when a subspecialist is more appropriate. In other cases, the physician does not order a mandatory follow-up test or misinterprets the test results.
Fortunately, increasingly advanced digital imaging solutions, and biological samples analysis enhanced by AI capabilities, can provide accurate medical analysis. AI can often analyze medical data more quickly and accurately than a clinician. However, AI technology is currently not capable of completely replacing skilled radiologists.
AI Brings Personalized Patient Treatment Into Focus
Recent decades’ medical advances have led to the introduction of new medical treatments. In many cases, physicians have assumed every patient would respond the same way to a specific medication. Certain patients have had sometimes-serious medication reactions. In other cases, over-prescribing of a broad-spectrum antibiotic has caused its ineffectiveness when given to a patient who has built up a strong resistance to the drug. Here, the physician may be left with few tools in their therapeutic toolkit.
Fortunately, patient-specific treatments and medications are increasingly becoming an option. To set the stage for their use, healthcare providers are now monitoring certain treatments’ results via wearable sensors and trackers.
Next, AI-enhanced software can analyze treatment outcome patterns and recommend the most effective treatments according to each patient’s profile data. This personalized care approach should drive measurable outcome improvements. In turn, post-treatment complications costs should be considerably reduced.
AI Interprets Patient Data for Chronic Disease Identification and Treatment
Early chronic disease detection enables timely treatment and often a more positive outcome. For each patient, obtaining lifestyle as well as clinical data helps to paint a picture of that patient’s health and risk factors. On a macro scale, health experts can gather multiple patients’ data to predict a population’s emerging health problems.
However, because much of this useful information appears in each patient’s electronic health record’s notes section, it has probably not been analyzed. More information about this patient may be found in other digital forms, including social media and online surveys. Manually reviewing each patient’s records is not a feasible or cost-effective proposition. Combining multiple datasets is also an unwieldy and time-consuming task.
That’s where AI and machine learning can be a game-changer. These and other similar technologies can provide researchers and healthcare providers with a range of useful insights. As a bonus, the technologies can produce this valuable information in a fraction of the time required for existing data-gathering and analysis methods.
Dr. Leen Kawas Brings Technology and AI to the Forefront
Dr. Leen Kawas’ biotechnology expertise has led her to strongly advocate for the technology’s integration into healthcare applications. She also recognizes the key role of personalized medicine. “Technology can lead to better tools for individualized and precision medicine. It allows us to make sense of the different factors that can make each individual or patient unique.”
Dr. Kawas also believes that targeted AI use can drive new treatments that can help patients live healthier lives. “Using AI to have a holistic view of patients and individuals can lead to the discovery of new therapies or technologies that can help humans live healthier and better,” she summarized. In Dr. Kawas’ Propel Bio Partners role, she is well-positioned to help bring this ambitious goal to fruition.
This story originally appeared on: https://www.tmcnet.com/topics/articles/2023/03/21/455347-biotech-innovator-leen-kawas-how-biomarkers-integrate-with.htm
