The year was 2022. Chris Norn, PhD, was wrapping up his time as a postdoctoral researcher at the Institute for Protein Design (IPD) at University of Washington (UW). AlphaFold was taking the field by storm, while a new generation of deep learning tools was rapidly advancing de novo, or from-scratch, protein design with unprecedented success rates validated at atomic resolution. Within just a few years, these AI breakthroughs, widespread applications across pharmaceuticals, nanomaterials, biosensors, and more, would help earn Norn’s mentor, David Baker, PhD, the Nobel Prize in Chemistry.
“There’s so much dark space in biology. The precision of protein design was becoming incredible.” said Norn in an interview GEN.“Designing function from scratch is going to be incredibly impactful for treating diseases.”
Norn’s research investigated the subtle structural differences that caused G-protein-coupled receptors (GPCRs) to change conformation from a healthy state to disease driver. These integral membrane proteins are the largest protein family encoded by the human genome and represent approximately one-third of drug targets, across cancer, metabolic disease, and neurological disorders. Yet, they are traditionally difficult to hit because their accessible regions barely protrude from the cell membrane.
Today, Norn is co-founder and CEO of Skape Bio, a Copenhagen-based AI protein design company building a generalizable platform to target underexplored GPCRs and treat diseases once deemed undruggable. The team has published a new study in Nature demonstrating the design of functional miniproteins that target 11 GPCRs across a diversity of receptor families implicated in itch and pain, cancer, metabolic disorders, and migraine, with examples that penetrate deeply into hard-to-reach GPCR pockets. Notably, agonists were validated against three targets.
In a key example, the study designed a chemokine receptor antagonist that mobilizes hematopoietic stem and progenitor cells in a mouse modelat a level comparable to a clinically used drug, with fewer side effects.
At the core of Skape Bio’s technology stack is a proprietary high-throughput platform that screens GPCRs directly within their native membrane environment, enabling accurate measurement of how conformational changes influence cell signaling and function. The approach represents a significant advance over traditional screening methods, which remove GPCRs from their membrane-embedded context and can fail to capture native structural dynamics. Over 100,000 miniprotein designs can be screened per target on a single-platform campaign.
Edin Muratspahić, PhD, postdoctoral research scholar at UW and co-corresponding author of the Nature study, highlights that the rise of de novo models, such as Baker lab’s RFdiffusion, has fueled the growing momentum for protein-based GPCR drugs. Compared to small molecules, protein therapeutics offer high selectivity, protease stability, and extended half-life. Notably, the small size of miniproteins allows better tissue penetration compared to antibodies.
“Many GPCRs remain underexplored because we didn’t have the tools to look at their pharmacology,” Muratspahić told GEN. “We’re excited to illuminate new biology beneficial to developing better and safer protein-based therapeutics.”
Sponsors: Rigshospitalet, Denmark; Department of Computer Science, University of Copenhagen, Denmark; Technical University of Denmark; Sundhedsdonationer
<strong>Background:</strong> Postpartum depression (PPD) is a major public health concern. Despite advancements in treatment, many barriers to accessing care remain. There has been a growing interest in digital interventions for the prevention and treatment of PPD. However, for mothers with mild and moderate symptoms of depression, there is a limited offer of self-guided internet-based interventions developed with user input and with considerations on how to integrate the intervention into stepped care models for PPD. <strong>Objective:</strong> The aim of this study was (1) to describe the process of the design and development of iCARE, a self-guided digital psychological intervention for mothers with mild and moderate symptoms of PPD in Denmark, (2) present the program’s theory illustrated by a logic model, and (3) explore its initial usability and prospective acceptability. <strong>Methods:</strong> Applying user-centered design methods, the intervention development followed six steps: (1) a literature review to identify evidence‑based therapeutic components of self‑guided interventions for PPD, (2) interviews with women with lived experience of PPD and group discussions with mental health experts and home‑visiting providers to identify user needs, (3) iterative design and content development with stakeholder feedback in collaboration with the Department of Digital Psychiatry, (4) prototype testing using think‑aloud usability sessions and interviews with 5 mothers, (5) a group cognitive walkthrough with mental health experts, and (6) final refinement and implementation of the iCARE program with developers and designers. <strong>Results:</strong> Initial interviews with mothers and maternal health care providers emphasized the importance of a digital intervention offering timely psychoeducation, coping strategies, and pathways to in-person care while addressing the diversity of expressions of PPD symptoms. Stakeholders recommended a flexible program, multimodal content, and integration into maternal care systems with community health nurses supporting engagement and participation. The prototype was designed to be user-centered, engaging, and with multiple interactive features. It included components on psychoeducation, cognitive exercises grounded in cognitive behavioral therapy, acceptance and commitment principles, and mood-monitoring. The prototype was designed to be user-centered and engaging, with interactive features and components on psychoeducation, cognitive exercises grounded in cognitive behavioral and acceptance and commitment principles, and mood-monitoring. Prototype testing indicated high prospective acceptability and led to refinements across 6 themes: appropriateness of content; motivation and engagement; inclusivity and gender representation; clarity of instructions and data use; understanding of therapeutic method; and usability, layout, and navigation. <strong>Conclusions:</strong> iCARE is a self-guided internet-based psychological intervention for mothers with mild and moderate symptoms of PPD in Denmark. It was developed with user input by using qualitative methods, user-centered design, and psychological theory. Further research is needed to evaluate the feasibility and effectiveness of the program in a randomized controlled trial and its integration into maternal health care models such as universal PPD screening and home-visiting.
Conditions: Preterm Birth; Cervical Insufficiency; Bed Rest; Pregnancy Complications; Immobilization; Depression, Postpartum; Pregnancy Outcome; Infant, Premature; Uterine Cervical Incompetence; Premature Birth; Obstetric Labor, Premature; Physical Activity; Bone Density
Interventions: Behavioral: Activity Restriction; Behavioral: No Activity Restriction
Sponsors: Julie Glavind; Aarhus University Hospital; University of Aberdeen; Rigshospitalet, Denmark; Odense University Hospital; Aalborg University Hospital; Zealand University Hospital
enGene (NASDAQ: ENGN) stock suffered an 83% plunge this past week that reflects just how competitive the field is among drug candidates for nonmuscle invasive bladder cancer (NMIBC)—and how questions over clinical data are enough to send investors scurrying to sell their shares.
enGene shares cratered 81% Thursday from $8.85 to $1.72, then fell another 13% Friday, reaching a 52-week low as it finished the week at $1.50.
The sharp falloff followed enGene reporting updated data from its Phase II LEGEND trial (NCT04752722) assessing its nonviral gene therapy candidate detalimogene voraplasmid in high-risk, Bacillus Calmette-Guérin (BCG)-unresponsive NMIBC patients with carcinoma in situ (CIS) with or without concomitant papillary disease (CIS±papillary). The data showed a drop in response rates from a November 2025 readout, falling short of company and Wall Street expectations.
As of the April 21 data cutoff, 67 of 124 evaluable patients treated with detalimogene (formerly EG-70) achieved a 54% complete response (CR) at any time, a rate that fell to 43% (52 of 121 evaluable patients) CR rate at six months. That compares with the 63% CR at any time and 62% CR rate at six months shown for the first 62 patients assessed, as announced by enGene in November 2025.
Also, detalimogene showed a nine-month CR rate of 32.7%, which fell to 13.3% at 12 months after treatment. Engene said it will present its data at the American Urological Association Annual Meeting (AUA 2026), set for May 15–18 in Washington, DC.
“While durability outcomes to date are not what we hoped, these data are preliminary,” enGene president and CEO Ron Cooper stressed in a statement. “We are focused on evaluating the totality of the data as it evolves and plan to continue to engage with the FDA and the medical community.”
Speaking to analysts, Cooper added: “The data are not yet fully mature, and the durability picture is incomplete. We plan to await longer-term durability data for all of Cohort 1 in the second half of the year and continue our ongoing discussion with the FDA regarding both our statistical analysis plans and plans for potential BLA filing.”
“Below key benchmarks”
At least two analysts warned that the updated data will make it harder for enGene to compete with other developers of NMIBC treatments now in the clinic.
“Durability now screens below key benchmarks in the setting, which makes it hard for us to underwrite meaningful commercial upside for detalimogene in what will be a crowded mkt, where ~40% 12‑mo CR is the bar to clear,” cautioned Maury Raycroft, PhD, equity analyst with Jefferies, in a research note.
Raycroft slashed enGene’s 12-month price target 82% from $28 to $5. More ominously, Raycroft chopped Jefferies’ peak sales forecasts for detalimogene by 79%—from the $1.7 billion forecasted for the gene therapy across CIS±papillary, papillary‑only, and BCG‑naïve NMIBC, to $350 million for CIS±papillary alone.
The NMIBC treatment space has expanded in recent years as established drugs like the cancer immunotherapy blockbuster Keytruda® (pembrolizumab), marketed by Merck & Co. (NYSE: MRK), have been joined on the market by newer therapies.
One is Johnson & Johnson (NYSE: JNJ)’s Inlexzo (gemcitabine), an intravesical drug releasing system (iDRS) designed to provide sustained local delivery of a cancer treatment into the bladder. Two other newer therapies are Adstiladrin® (nadofaragene firadenovec-vncg), a nonreplicating adenoviral vector-based gene therapy indicated for high-risk BCG-unresponsive NMIBC with CIS±papillary and marketed by privately held Ferring Pharmaceuticals (which licensed the drug from another private company, FKD Therapies, in 2018); and ImmunityBio (NASDAQ: IBRX)’s interleukin-15 (IL-15) receptor agonist Anktiva® (nogapendekin alfa inbakicept-pmln), indicated with BCG. ImmunityBio is part of the privately held NantWorks portfolio of companies.
Those marketed drugs are expected to be joined over the next couple of years by candidates being developed by:
CG Oncology (NASDAQ: CGON), which is expected to report topline data from the Phase III PIVOT-006 trial (NCT06111235) of cretostimogene grenadenorepvec, also called CG0070, as an adjuvant therapy in intermediate-risk NMIBC. First results on the combo of cretostimogene with gemcitabine from the Phase II CORE-008 trial (NCT06567743) are to be presented at AUA 2026.
Relmada Therapeutics (NASDAQ: RLMD), which will present two abstracts focused on its NDV-01, a sustained-release intravesical formulation of gemcitabine and docetaxel being developed to treat NMIBC at AUA 2026. Relmada plans to present nine-month complete response data from its open-label Phase II trial (NCT06663137) assessing NDV-01 in high-risk NMIBC, as well as discuss its open-label Phase III BOOST trial (NCT07313891), which is evaluating NDV-01 vs. surveillance following transurethral resection of bladder tumor (TURBT).
Mani Foroohar, MD, senior managing director, genetic medicines, and a senior research analyst with Leerink Partners, noted that enGene’s 54% any time and 43% six-month updated CR rates lagged behind those of three competitors: Anktiva (71% and 56%), cretostimogene (75.5% and 64%), and Inlexzo (82% and 59%). However, he added that Adstiladrin was more comparable to detalimogene, which showed rates of 51% and 41%.
Competitive position concern
“Weaker data in recent patient cohorts and lower-than-expected durability trends undermine our confidence in [detalimogene]’s competitive position and essentially foreclose the possibility of closing the efficacy gap with CGON, JNJ, etc., in a later LEGEND update,” Foroohar wrote in a research note.
“With shares trading at a level pricing in program failure, investor focus will center on cohort consistency, data evolution with longer follow-up, and FDA interpretation of the totality of the dataset (questions that will take time to address and will not be resolved prior to full LEGEND data/subsequent regulatory engagement,” Foroohar added.
Like Raycroft, Foroohar also now projects $350 million in unadjusted peak year sales for detalimogene, shredding his firm’s projection by 65% from $1 billion.
“From here, investor discussion will center on whether longer follow-up and additional cohort maturation can stabilize efficacy trends ahead of further FDA engagement in 2H26.”
enGene and Cooper insist that detalimogene is more than up to the challenge of competing with other NMIBC treatments. Of the 52 patients who responded at six months, 37 of 44 patients who had a nine-month assessment were in CR (an additional eight patients are pending evaluation), while 13 of 22 patients who had a 12-month assessment were in CR (an additional 11 patients are pending evaluation).
Among patients who showed the 43% six-month CR rate, 14% (6 of 43) successfully converted from non-CR to CR post re-induction.
The company cited other data from the LEGEND trial showing that the progression rate to muscle-invasive or advanced disease was 3.2%, a figure enGene calls low. Detalimogene was generally well tolerated, the company added, with 55% of patients having experienced a treatment-related adverse event (TRAE), mostly mild (Grade 1 and 2), though six patients (4.8%) reported a Grade 3 TRAE.
“These updated data continue to reinforce the favorable safety and tolerability profile of detalimogene and its clinical activity in a heavily pretreated, high-risk NMIBC patient population with limited therapeutic options,” enGene’s Cooper stated. “Importantly, the low rate of progression to muscle-invasive disease leaves patients eligible for other bladder-sparing therapies.”
Detalimogene’s favorable safety profile was also acknowledged by Jefferies’ Raycroft: “We continue to view this administrability/safety profile as a core differentiator vs other intravesical gene/immune constructs (and a key adoption lever), even as durability to date is tracking below expectations.”
IPO roundup: Odyssey raises $304M, drops 9%
Odyssey Therapeutics (NASDAQ: ODTX) raised $304 million in gross proceeds through an upsized initial public offering (IPO) by selling 15.5 million shares priced Thursday at $18 a share, the top of its $16–$18 range, and well above the 13.2 million shares it disclosed in its prospectus just before the offering. Concurrently, an affiliate of TPG Life Sciences Innovations purchased 1.39 million shares at the IPO price, raising another $25 million for Odyssey.
But on their first full day of trading on Friday, Odyssey’s shares fell 9%, closing at $16.42, as investors deemed the upsizing to be aggressive.
Odyssey, a developer of targeted therapies for autoimmune and inflammatory diseases, said it would use approximately $135 million in IPO proceeds to advance its lead candidate, the oral small molecule RIPK2 scaffolding inhibitor OD-001, through 12-week induction readouts from its planned Phase IIa combination trial and Phase IIb monotherapy trial in ulcerative colitis.
Plans also call for using approximately $50.0 million of proceeds to advance Odyssey’s oral small molecule SLC15A4 inhibitor OD-002 through IND-enabling activities and a planned Phase I/IIa trial; and the rest for additional discovery, preclinical, and clinical activities for disclosed or future programs, enabling capabilities, as well as general corporate purposes, working capital, and other capital expenditures.
An option to purchase up to an additional 2.325 million shares at the IPO price is held by Odyssey’s IPO underwriters: J.P. Morgan, TD Cowen, and Cantor are joint book-running managers, while Wedbush PacGrow and Oppenheimer are co-lead managers.
The Odyssey IPO is one of four biotech IPOs emerging in recent weeks:
Hemab Therapeutics Holdings (NASDAQ: COAG), based in Cambridge, MA, and Copenhagen, closed its IPO on May 4, having raised $346.7 million by selling 19,262,500 shares at $18 a share—the original offering of 16.75 million shares, plus all 2,512,500 shares for which underwriters held purchase options. Goldman Sachs, Jefferies, and Evercore ISI were joint book-running managers; Wedbush PacGrow was the lead manager. Shares have since jumped 40%, closing Friday at $25.12.
Seaport Therapeutics (NASDAQ: SPTX) of Boston garnered $254.88 million on April 30 by selling 14.16 million shares at $18 a share. Seaport’s underwriters have a 30-day option to buy an additional 2.124 million shares at the IPO price less underwriting discounts and commissions. Goldman Sachs, J.P. Morgan, Leerink Partners, Citigroup, and Stifel are joint book-running managers. Shares have since slipped 11%, closing Friday at $16.05.
A day earlier, Avalyn Pharma (NASDAQ: AVLN), also of Boston, launched an IPO that garnered $300 million by selling 16,666,667 shares at $18 a share—and revived the market of biotech initial offerings after a lull during March and early April. Avalyn ultimately racked up $345 million in gross proceeds after its underwriters exercised in full their option to buy 2.5 million more shares at the IPO price. Morgan Stanley, Jefferies, Evercore ISI, and Guggenheim Securities were joint book-running managers. Shares have since vaulted 52%, closing Friday at $27.33.
Leaders and laggards
Atara Biotherapeutics (NASDAQ: ATRA) shares nearly doubled, leaping 92% from $5.15 to $9.93 Thursday after saying its partner Pierre Fabre Pharmaceuticals (PFP) had a productive Type A meeting with FDA officials to discuss an approval path for tabelecleucel (tab-cel). PFP’s Biologics License Application (BLA) has been rejected twice by the agency through Complete Response Letters, the most recent one in January. The FDA, Atara said, agreed that a single-arm study with an “appropriate” historical control, conducted in a pre-specified manner, “could serve as an adequate and well-controlled study and provide safety and efficacy data in support of a future marketing application.” Atara said PFP intends to submit updated data with longer follow-up from the pivotal Phase III ALLELE trial (NCT03394365) assessing tabelecleucel in adults and children ages 2+ with relapsed/refractory Epstein-Barr virus plus post-transplant lymphoproliferative disease (PTLD) following solid organ transplant or hematopoietic cell transplant.
Entrada Therapeutics (NASDAQ: TRDA) shares nosedived 57% Thursday from $16.03 to $6.85 after the genetic medicine developer reported topline data from Cohort 1 of the multiple ascending dose (MAD) portion of the Phase I/II ELEVATE-44-201 trial (NCT07037862) that the company called positive, but which disappointed investors. Entrada said its Duchenne muscular dystrophy (DMD) candidate ENTR-601-44 met the trial’s primary objective by showing favorable safety and tolerability, no discontinuations, and no serious adverse events. But data showed an increase of 2.36% in dystrophin from a baseline of 4.00%—compared to the 10% increase sought by analysts such as Myles R. Minter, PhD, of William Blair. “Management is attributing the miss on biomarker data to lower-than-expected drug exposure,” Minter wrote, “likely due to the transition from dosing adults to juvenile patients.” Entrada cited other positive data, such as lower plasma exposure in Cohort 1 participants ages 6–17 vs. healthy adult volunteers; and markers of kidney function via eGFR, Cystatin C, and magnesium all falling within normal ranges and comparable to placebo.
Moderna (NASDAQ: MRNA) shares rose 12% Friday from $48.54 to $54.35 after a news report that the messenger RNA (mRNA)-based vaccine developer was researching vaccines designed to protect against hantaviruses. In a statement, Moderna disclosed that it has carried out early-stage vaccine research on hantaviruses with the U.S. Army Medical Research Institute of Infectious Diseases and is also partnering with the Vaccine Innovation Center at Korea University College of Medicine on a potential jab. “These efforts are early-stage and ongoing and reflect Moderna’s broader responsibility to develop countermeasures against emerging infectious diseases,” Moderna told Bloomberg News. As of Friday, the World Health Organization (WHO) has reported eight cases of hantavirus, including three deaths, among passengers aboard the MV Hondius cruise ship, traveling between Argentina and the Canary Islands in the Atlantic Ocean.
Viridian Therapeutics (NASDAQ: VRDN) shares jumped 33% from $14.06 to $18.75 Tuesday after the autoimmune and rare disease drug developer announced positive topline data from the Phase III REVEAL‑2 trial (NCT06625398) assessing elegrobart in chronic thyroid eye disease (TED). Doses of elegrobart given every 4 and 8 weeks achieved what Viridian called “highly statistically significant” 50% and 54% proptosis responder rates (PRR) at week 24, respectively, vs. 15% for placebo. Elegrobart is a subcutaneously delivered, half‑life‑extended monoclonal antibody targeting the insulin‑like growth factor‑1 receptor (IGF‑1R). Viridian said it remains on track to submit a Biologics License Application (BLA) to the FDA for elegrobart in Q1 2027. Viridian cashed in on the news by launching underwritten public offerings of $150 million in convertible senior notes due 2032 and $100 million in Series B nonvoting convertible preferred stock.
Korea-based Novelty Nobility expanded its agreement with CDMO AGC Biologics to advance their bispecific antibody drug candidate through process development and GMP manufacturing at AGC Biologics’ facility in Chiba, Japan. The project leverages AGC Biologics’ global network, having completed cell line development in Copenhagen, Denmark, to be followed by tech transfer to the Chiba site for the next manufacturing stages.
“We believe this bispecific antibody has the potential to offer a truly differentiated treatment option for patients with neovascular retinal diseases,” said Sang Gyu Park, CEO of Novelty Nobility.
The product candidate, NN4101, a first-in-class, connects a fully human anti-c-Kit monoclonal antibody with a vascular endothelial growth factor (VEGF) trap.
“Our mammalian expression teams are adept at handling complex proteins, and we are a world leader in applying flexible, single-use bioreactor technology,” commented said Tadashi Murano, president of the AGC Life Science Company. “We are proud to support Novelty Nobility as they advance this innovative candidate toward the clinic.”
To further support growing demand in the region and globally, AGC is also expanding its facility in Yokohama, Japan, which is designed to utilize single-use bioreactor technology to offer large-scale GMP manufacturing.
Background: Evidence-based psychological interventions are usually not accessed by marginalized groups such as refugees. Culturally adapted psychological interventions have reported larger effect sizes than nonadapted psychological interventions. However, the cultural adaptation of interventions is a lengthy process, entailing a challenge. One potential solution to overcome this challenge is the use of artificial intelligence (AI). Objective: The aim of this study was to investigate and compare the perceived cultural relevance and acceptability of 2 common cognitive behavioral therapy (CBT) techniques when translated and culturally adapted by AI versus a human psychologist. Methods: In a 2×2 factorial design, the text generator type (AI vs human psychologist) and the CBT technique (cognitive restructuring vs behavior modification) were compared. CBT technique texts translated and culturally adapted either by AI or by a human psychologist were blindly rated using the Cultural Relevance Questionnaire and the Theoretical Framework of Acceptability. Raters were Arabic-speaking refugees and immigrants, aged between 18 and 69 years, residing in Sweden, Denmark, and Germany. Raters were randomly allocated to 1 of 4 conditions. Each condition consisted of 2 stimuli. Two-factor between-subject design analyses were used to analyze the data. Results: A significant main effect of the text generator domain type (=.02; η²=0.045) was found in the first rating, with texts adapted by the AI domain perceived as more culturally relevant than those adapted by the human domain. No significant main effect of the CBT technique was found in the first rating (=.10; η²=0.022). There were no differences in the second rating. Regarding acceptability, no significant main effects of text generator domain type (=.09; η²=0.024) or the CBT technique (=.88; η²=0.001) were found in either of the ratings. Conclusions: CBT technique materials adapted by AI may be perceived as similarly culturally relevant as those adapted by a human psychologist. This finding implies the potential to accelerate the cultural adaptation of psychological interventions. However, AI still needs to be used with caution and in accordance with rigorous safety standards and robust frameworks.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/717971a3020c51a80c4b35fb1e059041" />
Agentic AI goes beyond predictive and generative AI and, in biomanufacturing, has the potential to enhance efficiency by integrating with existing manufacturing infrastructure such as IoT sensors, process information management systems, management execution systems, and even enterprise resource planning software. The challenge, however, is that industrial biomanufacturing processes are complex, demand resilience, and are tightly regulated.
The Adaptive Agent-Oriented System Control (AAOSC) framework developed by a team from the Technical University of Denmark (DTU) and SiC Systems addresses that challenge through a decentralized control layer. In it, “specialized autonomous agent ‘hives’ [are] coordinating digital twin enabled manufacturing infrastructure and real-time communications protocols.” The latter lets biomanufacturers integrate models, make learning-based inferences, and control process systems.
Four AAOSC case studies were discussed in a recent paper by Seyed Soheil Mansouri, PhD, professor at DTU and co-founder and CSO of SiC Systems and Christopher J. Savoie, PhD, co-founder and CEO of SiC Systems, and inventor of the agentic AI technology behind Siri. Those case studies “demonstrate AAOSO’s prowess [in] reducing deviating durations, averting shutdowns in severe fault scenarios, and boosting efficiency through virtual quantum and classical sensing and decentralized reasoning, all while aligning with regulatory imperatives…”
Despite its capabilities in monitoring process, identifying discrepancies, and recommending solutions, agentic AI “is not yet fully ready for complete, independent control in biopharmaceutical manufacturing,” Mansouri tells GEN. “Any AI that directly affects medicine quality still needs strong human oversight and full approval. We are getting closer, but full integration requires official [regulatory] clearance.”
The AAOSC framework that Mansouri and colleagues built may be unique in the industry. It isn’t all-knowing and “God-like,” he points out. Instead, “our methods are grounded in physics, chemistry, and biology within an agent ‘hive’—an orchestration of rule-based, mathematically informed agents. So, AAOSC is, foundationally, a different philosophy of building AI [in which] humans are in control.”
First, run in shadow mode
To introduce agentic AI, Mansouri advises starting gradually. “Run the AI alongside your current control systems in shadow mode—it watches everything and gives recommendations, but doesn’t make any actual changes without human oversight. This lets the teams learn how it works without any risks to production. Once confident, you can slowly expand its role while always keeping humans in final control.”
Both the FDA and EMA require systems that are fixed rather than continuously learning, he points out, and that can complicate adoption. To minimize the potential for regulatory issues that may arise by integrating AI into manufacturing processes, “work closely with your quality and regulatory teams from the beginning.
“Always maintain clear human responsibility, so no one is left wondering who is accountable if something goes wrong. Strong cybersecurity is essential,” Mansouri adds, “because these AI agents connect and talk to each other.” Therefore, “Start small, test thoroughly, and talk to regulators early.”
Last December, news broke that the Centers for Disease Control and Prevention had awarded $1.6 million to a Danish vaccine research group to study the effects of the hepatitis B vaccine on infants in the West African nation of Guinea-Bissau. The proposed five-year study compared outcomes between infants vaccinated at birth and those vaccinated at six weeks of age. As a medical student and researcher, I was shocked by the brazen inequity of the trial.
Randomized controlled trials have already demonstrated superior outcomes when the hepatitis B vaccine is administered at birth. More troubling, however, was the setting of the study. Guinea-Bissau is a highly endemic country for hepatitis B, where vaccination coverage lags behind global averages and roughly 60 percent of the population lives in poverty.
The mood at the recent 2026 AD/PD International Conference on Alzheimer’s and Parkinson’s Diseases and Related Neurological Disorders in Copenhagen was notably different from the mood that has hung over much of neurodegeneration research for the past decade.
There was still plenty of caution, and plenty of unanswered questions, and certainly no shortage of technical nuance. But there was also something more concrete than hope: a growing sense that the field now has enough tools, biological insight, and clinical momentum to start probing more deeply and stratifying pathologies of neurodegenerative diseases in patients, at varying stages of progression.
That shift was visible across the meeting. It was there in conversations about co-pathologies, the increasingly central role of inflammation and the rapid maturation of blood-based biomarkers. It also featured in the way industry and academia alike talked about therapy: not as a search for a single silver bullet, but as a move toward combination treatment strategies more familiar from the fields of oncology, cardiology, and other complex chronic diseases.
Henrik Zetterberg, PhD, Gothenburg University
Henrik Zetterberg, PhD, Gothenburg University, University College London, and a guest professor at University of Wisconsin-Madison, one of the field’s most influential biomarker researchers, put the central theme plainly: “I think disease heterogeneity will be the mantra in the coming years, to dissect the molecular underpinnings of this heterogeneity.”
Heterogeneity moves from caveat to core concept
Zetterberg described how biomarker-enabled phenotyping is exposing just how different patient trajectories can be once amyloid begins to accumulate. Some people decline quickly. Others remain resilient for a decade or longer. Some cases that appear clinically similar may in fact be driven by very different molecular constellations.
Geoff Kerchner, MD, PhD, vice president, global head of neurodegeneration at Roche
Geoff Kerchner, MD, PhD, vice president, global head of neurodegeneration at Roche, made a similar point from the therapeutic side. In Alzheimer’s disease, he said, some features remain strikingly consistent across patients.
But once one moves beyond core pathology, “the rate at which that happens varies from person to person,” and that variance is shaped in part by co-pathologies, including alpha-synuclein, TDP-43, and vascular disease.
Steve Williams, MD, PhD, chief scientific officer at Alamar Biosciences, pushed the same logic further, arguing that mixed biology is not the exception but the rule. “Everyone with neurodegeneration is carrying around some combination of other pathologies,” he said. “It’s almost inevitable because it’s a feature of aging.”
Steve Williams, MD, PhD, chief scientific officer at Alamar Biosciences
That view has major consequences. It means the field is increasingly moving away from asking whether a patient is amyloid-positive or tau-positive in a binary sense and toward asking what additional pathological burden may be present, what that burden means for progression, and how it should influence treatment choice.
Betty M. Tijms, PhD, head of science Alzheimer Center Amsterdam
Betty M. Tijms, PhD, head of science Alzheimer Center Amsterdam at Amsterdam UMC, offered a useful example from discovery research. In her work integrating CSF proteomics and lipidomics, she described signals that shift depending on tau status and amyloid background. At one point, she noted that these patterns “will inform which type of patients may require their own, personalized therapies.” It captures the direction of travel: from broad molecular mapping to biologically meaningful subtyping.
Inflammation is no longer a side story
Andréa Lessa Benedet, PhD, University of Gothenburg
Andréa Lessa Benedet, PhD, University of Gothenburg, discussed findings showing that people with faster progression in tau-related pathology had “higher expression of many inflammatory markers in plasma and in CSF.” That observation alone is not enough to settle the longstanding question of whether inflammation is driving disease, responding to it, or doing both. But it adds to a growing body of work suggesting that immune biology is closely tied to the pace of progression.
What made Benedet’s description especially interesting was that the signal was not identical across biofluids. The proteins elevated in CSF were not the same as those elevated in plasma. Yet when her group mapped those proteins to cell types and pathways, the two compartments converged on similar biology. In other words, the field may not always be looking for one-to-one molecular matches between brain-adjacent and peripheral compartments. It may instead be learning to recognize pathway-level concordance.
Benedet pointed to evidence suggesting that amyloid pathology together with inflammation may influence how tau spreads through the brain. That “bit of both” view—driver and response, cause and consequence—may be unsatisfying if one wants a simple mechanism. It may also be closer to biological reality.
The therapeutic implication is obvious. If inflammatory processes help define faster-progressing biology, then they are not merely descriptive. They become candidates for stratification and, eventually, intervention.
Blood-based biomarkers as research infrastructure
Jacob Vogel, PhD, Lund University and SciLifeLab
Few topics drew more sustained attention in Copenhagen than blood-based biomarkers. Kerchner called blood-based biomarkers one of the biggest themes of the meeting saying they could “really democratize the diagnosis of Alzheimer’s disease.”
Democratization here is about health equity—geography, trial access, earlier identification, and the possibility of shifting neurodegeneration research beyond the relatively narrow populations that have historically been easiest to recruit and deeply phenotype. That broader perspective surfaced in a session on sex differences in neurodegeneration, where Jacob Vogel, PhD, assistant professor at Lund University and SciLifeLab, presented findings suggesting that brain cells responding to Alzheimer’s pathology have different expression patterns in men and women. Seen that way, the field needs tools that are sophisticated enough to capture the true biological complexity of disease across different patients.
However, one excellent blood-based biomarker, such as brain-derived p-tau217, does not solve the co-pathology problem. As Niranjan Bose, PhD, managing director at Gates Ventures put it, there is a growing “need to do better when it comes to co-pathologies so we can stratify participants better.” A strong single analyte may be enough to identify one core process very well; it is not enough to capture the layered biology of aging brains. That is why the discussion is shifting from singleplex to multiplex, from favorite markers to models.
Zetterberg spoke about the new NULISA Neuro 220 panel from Alamar Biosciences, as a research tool that can help the field probe lysosomal and synaptic biology, alpha-synuclein-related processes, and other pathways relevant to co-pathology. He also highlighted the importance of brain-derived tau readouts, arguing that they may reduce confounding from peripheral tau expression and make blood results easier to interpret in diseases where peripheral neuropathy or other non-CNS biology could muddy the picture.
Zetterberg said, “Those broader panels will be the engines for discovery.” In other words, the value of broad biomarker panels is not that every protein measured will someday be run routinely in a clinical lab. It is that broad panels can reveal reproducible patterns, identify hub biology, and narrow the search toward robust clinical assays.
Combination treatment is becoming the default future
The conference’s other major shift was therapeutically focused. Even where amyloid remained central, the discussion increasingly assumed that amyloid-directed therapy alone will not be the endpoint.
Michael Irizarry, MD, senior vice president and deputy chief clinical officer at Eisai US
Michael Irizarry, MD, senior vice president and deputy chief clinical officer at Eisai US, put it bluntly: “Alzheimer’s is being used as the example of precision medicine.” That is a striking statement, because for years Alzheimer’s was more often framed as the place where precision medicine had failed to arrive. What changed is that biomarkers, imaging, and fluid measures have advanced enough to stage disease more accurately and begin matching interventions to biology and timing.
Irizarry also described an emerging combination logic already being tested clinically. “The hope is that by targeting multiple processes we can get a greater treatment effect,” he said, referring to efforts to combine anti-amyloid therapy with a tau-directed antibody strategy. The reasoning is straightforward: if amyloid clearance slows disease but does not stop it, then other mechanisms—including tau propagation—remain actionable targets.
Kerchner made the same point in even broader terms. “The combination of therapies attacking different aspects of Alzheimer’s disease and Parkinson’s disease is almost surely going to be needed,” he said. He compared the situation to hypertension, diabetes, and cardiovascular disease—complex chronic illnesses that are almost never controlled with one intervention alone.
If the field is moving toward a wider therapeutic lens, with multiple mechanisms and intervention points in play, then there is value in creating space for a broader range of emerging approaches. That was visible in the Startup Hub, now in its second year, where early-stage companies gave short five-minute pitches that often echoed the meeting’s main scientific themes. ScandBio was one example: its Phase III clinical trial of a combined metabolic drug targeting mitochondrial dysfunction in Alzheimer’s disease connected to the conference session on mitochondrial pathways in neurodegeneration and therapy.
Taken together, these developments pointed to the same conclusion: as the biology becomes more layered, the response from the field is becoming more layered too. Combination therapy only becomes rational if disease heterogeneity is measurable. It only becomes practical if blood-based biomarkers can help define stage, likely response, and co-pathology burden without requiring every patient to undergo repeated PET imaging. And it only becomes truly precise if inflammation, synaptic injury, lysosomal dysfunction, vascular change, can be integrated into the treatment model rather than treated as background noise.
(gemcitabine), an intravesical drug releasing system (iDRS) designed to provide sustained local delivery of a cancer treatment into the bladder. Two other newer therapies are Adstiladrin® (nadofaragene firadenovec-vncg), a nonreplicating adenoviral vector-based gene therapy indicated for high-risk BCG-unresponsive NMIBC with CIS±papillary and marketed by privately held Ferring Pharmaceuticals (which 
