Calico LLC

There are always trade-offs to make when studying cells. A biologist either kills the cell to scrutinize its insides or has to run more complex experiments, using tools like fluorescent tags to detect certain biomolecules. A biotech startup believes it has a new solution to this longstanding problem. Stately Bio has raised a $12 million seed round led by AIX Ventures to advance machine learning techniques that recognize signals from simple images of living cells, CEO Frank Li told Endpoints News. The Palo Alto, CA-based startup will officially launch on Friday after three years in stealth mode. Like many in AI bio, Li comes from the world of technology, not biology. He worked as a software engineer at Palantir and Google X before being recruited by Daphne Koller to join her new machine learning team at Calico Life Sciences, an Alphabet-backed biotech. Li spent four years leading Calico’s ML group after Koller left shortly after his arrival to found insitro , another AI-focused biotech. Those were formative years, according to Li, now 34. He reported directly to Calico CEO Art Levinson, the legendary biotech figure who previously ran Genentech, and started to see the potential for ML techniques in cell imaging. In 2019, Li entered a competition at NeurIPS, a top machine learning conference, to find signals from cell images. His team went in thinking 50% accuracy would be a great outcome. They achieved over 99% accuracy, finishing second out of over 800 entrants. What he discovered is the same computer vision techniques that have fueled progress in fields like self-driving cars could also work in biology. “There was a surprising amount of richness to those images that lay beyond our human eye’s ability to comprehend,” Li said. “It was one of those moments that made me go, ‘There’s something really special here.’” Li left Calico in 2021 to found Stately Bio, which began operating in March 2022 with a pre-seed round to focus on cell imaging. Today, Stately is using what Li called “grade-school microscopes” to perform brightfield imaging, which shines light on living cells and takes an image of the other side. Machine learning algorithms find the correlations between cell shapes and textures and their biological functions. “Historically, so much of biology has been learned by looking through a microscope,” Li said. “But it’s only until recently that we’ve been able to take a more quantitative and systematic approach.” Stately isn’t completely alone with this idea. Two years ago, Recursion switched from a more complicated cell-painting technique to brightfield imaging. Other startups like Eikon Therapeutics are working on complementary approaches. Eikon created its own super-resolution microscopes to track single particles inside of living cells. Stately takes a zoomed-out view compared to Eikon, Li said. While observing cells at lower resolutions, the company’s method can watch way more cells, Li said, which is a benefit in building the datasets that power algorithms. For results, Li said Stately improved the ability to differentiate stem cells into liver cells. They have seen 3x to 10x better scores on tests of key liver functions than today’s best techniques, Li said. While the company isn’t yet sharing details about its own pipeline, Li said he sees potential in using lab-made liver cells as a cell replacement therapy for certain liver diseases. Stately is also building AI models that can predict an experiment’s chances of success at very early stages. For instance, the company can take data from the second day of an experiment to predict how those cells will look in a couple of weeks, suggesting if that experiment is worth carrying out or stopping early.

iStock/ dickcraft Misses from amyotrophic lateral sclerosis hopefuls Denali Therapeutics and partners AbbVie and Calico Life Sciences mark the latest setbacks for the controversial platform trial, the results from which have largely mirrored the dismal success rate in ALS overall. Launched in 2020 to expedite the development of an effective medicine for amyotrophic lateral sclerosis, the HEALEY ALS Platform Trial suffered two more disappointments this week as candidates from Denali Therapeutics and AbbVie and Calico Life Sciences missed the study’s primary endpoint, failing to significantly slow disease progression. Funded by Sean M. Healey—who died from amyotrophic lateral sclerosis (ALS) in 2020—and his global asset management firm, the HEALEY trial generated new hope for patients with the intractable neurological disease. Platform trials are a fairly new phenomenon, however, meaning successes have been limited and investigators are still refining the methodology. In a Monday investor note, Stifel analyst Paul Matteis called the trial “a very high-risk/high-reward option.” As with any novel venture, HEALEY has experienced challenges. In an earlier interview with BioSpace , Clene Nanomedicine CEO Rob Etherington noted certain inflexibilities in the trial’s protocol in addition to a six-month timeframe that is “too short of a window to prove efficacy.” For some drug developers, it is also an attractive business proposition. The HEALEY team recruited the first biotechs to the trial by covering some of their costs. “The good news was they paid for the drug, so we didn’t have to raise money for [that],” Prilenia Therapeutics CEO Michael Hayden told me in September. A platform trial also has the advantage of being patient-centric, using a shared placebo group between all regimens to boost the total number of patients receiving a potentially efficacious drug. But nearly five years on, the HEALEY trial has yet to produce a definitive success, instead serving up a string of failures. Hopefuls from Clene, Prilneia, Biohaven , UCB and Seelos Therapeutics all failed to hit the trial’s primary endpoint, and of these, only Prilenia and Clene saw enough positive signals to move their treatments forward. The other programs have all been terminated—a devastating development for the ALS community. It has also been hard, of course, on these companies. Seelos filed for bankruptcy in November after trehalose’s failure. That same month, Massachusetts General Hospital (MGH), which runs the HEALEY trial, sued Seelos over the company’s alleged failure to fully pay for the work MGH conducted on its candidate trehalose. Seelos, which has expressed disagreement regarding the data from its regimen in the HEALY trial, particularly concerning the use of Amylyx’s Relyvrio by some participants, is allegedly withholding payment as a result—to the tune of $2 million, according to the lawsuit. In a March 2024 update , Seelos stated that while the study did not meet statistical significance in the primary and secondary endpoint across all participants, it showed a potential signal of efficacy in a pre-specified subgroup not taking Relyvrio. These patients saw a 22% improvement in slope of change in the ALS Functional Rating Scale-Revised (ALSFRS-R) assessment adjusted for mortality, with an 89% success probability, at 24 weeks, according to the press release. “The HEALEY platform is designed to detect signals of efficacy and we believe the observed signal and success probability is competitive to other recently FDA-approved therapies for ALS which also failed to achieve statistical significance when measured for function and mortality on similar primary and efficacy endpoints,” Seelos CEO Raj Mehra said in the March statement. Relyvrio received approval in September 2022 as only the third-ever treatment for ALS. Given its subsequent withdrawal from U.S. and Canadian markets in April 2024 after failure to show efficacy in a Phase III trial, it would have been interesting to see how trehalose would have performed under different circumstances. Signals of Hope For followers of the HEALEY trial—and the ALS space in general—pulling signals of efficacy from the rubble is a familiar tune. For Prilenia and Clene, positive biomarker data supported moving their respective programs forward. In Prilenia’s case, a subgroup of patients with early-stage ALS who were rapidly declining had “substantially less decline” on the ALSFRS-R total score compared to the placebo group. Prilenia submitted a Marketing Authorisation Application to the European Medicines Agency that was accepted in September 2024. Certainly, there is precedent for moving a program forward based on patient subgroup data. “[ALS] is heterogeneous, and sometimes it’s really important, even when a drug doesn’t work in everybody, to look at if there’s a subset that might have benefited,” Merit Cudkowicz, director of the Healey & AMG Center for ALS, told me in 2021. Cudkowicz noted that results of the first trial for Radicava, developed by Mitsubishi Tanabe and approved by the FDA in May 2017, were also negative across the overall trial population. However, a subset of early fast progressors did respond, “and when they repeated the studies just in that group, it was positive and that led to marketing.” And embattled Israel and New York–based biotech BrainStorm Cell Therapeutics has consistently pointed to analysis from its Phase III trial of NurOwn showing that a prespecified subgroup of patients with early-stage disease, as determined by an ALSFRS-R baseline score of 35, saw a meaningful response across all primary and secondary endpoints. BrainStorm is now gearing up for a Phase IIIb study that president and CEO Chaim Lebovits said would be focused on these early-stage patients. After a 2024 campaign filled with disappointment, this is a space that desperately needs a break. ALS is uniformly fatal, typically claiming its victims within five years of diagnosis, and the disease continues to confound researchers. Given the dire need for effective treatments, patients, drug developers and journalists alike could be forgiven for celebrating signals of hope. As for the HEALEY trial, Cudkowicz shared that the team is currently considering amending the protocol based on learnings from the first five regimens. “My sense is that it is not a perfect clinical trial. It has its flaws,” Graig Suvannavejh, senior biopharmaceuticals and biotechnology equity research analyst at Mizuho Americas, told me . “But I think they’re trying to fix the situation at HEALEY.”

A landmark study hoping to find new treatments for ALS has notched two more failures, as experimental medicines from Denali Therapeutics and Calico Life Sciences proved no better than a placebo at slowing the nerve-destroying disease or keeping patients alive longer.Denali disclosed high-level results from the study Monday. After about six months, treatment with the companys drug didnt result in any significant changes in the severity of the disease, nor did it substantially help patients muscle strength or respiratory function.Denali plans to further examine the data and look at biological markers of the disease, including one, neurofilament light chain, thats become increasingly important to researchers focused on amyotrophic lateral sclerosis. The company expects to conduct those analyses later this year.Though the initial top-line clinical results of this trial were not what we hoped, the data collected is valuable in helping to understand the next stage of ALS research, said Merit Cudkowicz, director of the Sean M. Healey & AMG Center for ALS at Massachusetts General Hospital, in a statement.Cudkowicz and her team came up with and for the last several years have been running the Healey platform trial, an innovative experiment structured to quickly test a variety of potential ALS therapies. The trial has so far evaluated more than half a dozen drugs, but none have successfully hit its main goals.Alongside the Denali news, the Healey center announced a similar medicine from Calico and AbbVie had failed, too. Both Denalis and Calicos drugs are supposed to activate eIF2B, a complex molecule cells use to make proteins. Research indicates stress and disease inhibits this molecule, which in turn can exacerbate the accumulation of stress-related proteins like TDP-43.While helpful when functioning normally, TDP-43 can, under certain conditions, become a bad actor in nerve cells. It is tied to ALS and other neurodegenerative diseases, and has therefore attracted interest from a handful of brain-focused biotechnology companies. Just two months ago, a San Francisco-area startup launched with a drug designed to work around this TDP-43 problem. Named Trace Neuroscience, the startup came equipped with $101 million from a group of prominent life sciences investors that includes Third Rock Ventures, Atlas Venture, RA Capital Management and Alphabets venture capital arm, GV.Cudkowicz said the Healey team remains deeply committed to fully understanding the effects of Denalis drug and will further evaluate the data before determining next steps.Some Denali investors may not be willing to wait, however. Shares of the company, which had already dipped more than 6% while the stock market was open Monday, fell further in after-hours trading. Calico is a privately held subsidiary of Google parent Alphabet.This was always a low expectations, high-risk study for Denali,wrote Michael Yee, an analyst at the investment bank Jefferies, in a note to clients. The failure of AbbVie and Calicos therapy to also hit the same goals in its own study arm points to a difficulty with the drug class in a challenging disease.In its own statement, Calico pointed to an assessment of muscle strength that hinted at slower deterioration among those given the companys drug. Bill Cho, the companys head of clinical sciences, said the finding supports further investigation.Like many brain diseases, ALS has been exceptionally difficult to crack for even the worlds most powerful drug developers. Only a few medicines have received approval from the Food and Drug Administration, and their effects are considered modest. Patients still typically live just two to five years following a diagnosis.The list of approved therapies got shorter last spring, when Amylyx Pharmaceuticals voluntarily removed its once-promising medication Relyvrio from the market. Amylyx made that decision after a key study meant to confirm the Relyvrio was an effective ALS treatment instead found it no better than a placebo. '