The NIH created The Common Fund Data Ecosystem (CFDE) program to enhance the findability, accessibility, interoperability, and reusability of data generated by NIH Common Fund programs to ensure adherence to the FAIR guiding principles for scientific data. Researchers can efficiently explore NIH Common Fund-produced datasets to facilitate new biomedical discoveries and will enable scientists to search across Common Fund-produced datasets to ask complex scientific and clinical questions to catalyze new biomedical discoveries, according to an Icahn Mount Sinai spokesperson.

“By integrating data from various omics technologies and by making these datasets readily available for analysis and visualization with artificial intelligence and machine learning, many discoveries can emerge,” says the Contact Principal Investigator of the CFDE Data Resource Center, Avi Ma’ayan, PhD, director of the Mount Sinai Center for Bioinformatics and professor of pharmacological sciences, and artificial intelligence and human health. “We are delighted that the NIH has recognized our past contributions to the CFDE, the library of integrated cellular-based signatures (LINCS), and the illuminating the druggable genome (IDG) Common Fund programs and trusts us to lead this new effort.”

Unique opportunity

“This is a unique opportunity to enable a biomedical researcher to make innovative discoveries through full utilization of the data that has emerged from the large investments the National Institutes of Health have made under the aegis of the NIH Common Fund,” adds Principal Investigator of the CFDE Data Resource Center, Shankar Subramaniam, PhD. Subramaniam, the Joan and Irwin Endowed Chair of Bioengineering and Systems Biology at UC San Diego. Subramaniam is the PI of the NIH Common Fund Metabolomics Project.

Currently, most Common Fund datasets are dispersed across distinct data portals, resulting in underutilization due to the absence of standardized community practices and shared data processing protocols, notes Ma’ayan. By enabling seamless discovery of datasets across the Common Fund data, uniformly processing the data, and better combining data from different programs, the investigators anticipate the emergence of synergistic discoveries, he adds.

By working with the Common Fund data coordination centers, the Data Resource Center and Knowledge Center are expected to produce highly valuable computational resources for the entire field of biomedical research, continues Ma’ayan.

“As one example, by integrating exercise-induced gene expression changes from the Common Fund MoTRPAC program, tissue expression data from the GTEx Common Fund program, and drug response data from the LINCS Common Fund program, we can discover new drug candidates and potential treatment targets for muscular dystrophies,” he says.

The post Icahn Mount Sinai and UC San Diego to Establish a Data Integration Hub appeared first on GEN - Genetic Engineering and Biotechnology News.

This work is published in Nature in the paper, “Learning from prepandemic data to forecast viral escape.”

The researchers first developed EVE (evolutionary model of variant effect) in the context of uncovering mutations that cause human diseases. The core of EVE is a generative model that learns to predict the functionality of proteins based on large-scale evolutionary data across species. In a previous study, EVE allowed researchers to discern disease-causing from benign mutations in genes implicated in various conditions, including cancers and heart rhythm disorders.

“You can use these generative models to learn amazing things from evolutionary information—the data have hidden secrets that you can reveal,” said Debora Marks, PhD, associate professor of systems biology in the Blavatnik Institute at Harvard Medical School.

During the pandemic, Marks and her team saw an opportunity to apply EVE. They took the generative model from EVE—which can predict mutations in viral proteins that won’t interfere with the virus’s function—and added biological and structural details about the virus, including information about regions most easily targeted by the immune system.

“We’re taking biological information about how the immune system works and layering it on our learnings from the broader evolutionary history of the virus,” explained co-lead author Nicole Thadani, a former research fellow in the Marks lab.

Such an approach, Marks emphasized, means that EVEscape has a flexible framework that can be easily adapted to any virus.

In the new study, the team turned the clock back to January 2020, just before the COVID-19 pandemic started. Then they asked EVEscape to predict what would happen with SARS-CoV-2.

“It’s as if you have a time machine. You go back to day one, and you say, I only have that data, what am I going to say is happening?” Marks said.

EVEscape predicted which SARS-CoV-2 mutations would occur during the pandemic with accuracy similar to this of experimental approaches that test the virus’s ability to bind to antibodies made by the immune system. EVEscape outperformed experimental approaches in predicting which of those mutations would be most prevalent. More importantly, EVEscape could make its predictions more quickly and efficiently than lab-based testing since it didn’t need to wait for relevant antibodies to arise in the population and become available for testing.

The researchers are now using EVEscape to look ahead at SARS-CoV-2 and predict future variants of concern; every two weeks, they release a ranking of new variants. Eventually, this information could help scientists develop more effective vaccines and therapies. The team is also broadening the work to include more viruses as they demonstrated that EVEscape could be generalized to other viruses, including HIV and influenza.

“We want to know if we can anticipate the variation in viruses and forecast new variants— because if we can, that’s going to be extremely important for designing vaccines and therapies,” notes Marks.

Additionally, EVEscape predicted which antibody-based therapies would lose their efficacy as the pandemic progressed and the virus developed mutations to escape these treatments. The tool was also able to sift through the tens of thousands of new SARS-CoV-2 variants produced each week and identify the ones most likely to become problematic.

“By rapidly determining the threat level of new variants, we can help inform earlier public health decisions,” said Sarah Gurev, a graduate student in the Marks lab from the Electrical Engineering and Computer Science program at MIT.

The team is now applying EVEscape to SARS-CoV-2 in real time, using all of the information available to make predictions about how it might evolve next. They are also testing EVEscape on understudied viruses such as Lassa and Nipah, two pathogens of pandemic potential for which relatively little information exists. Such less-studied viruses can have a huge impact on human health across the globe, the researchers noted.

The researchers publish a biweekly ranking of new SARS-CoV-2 variants on their website and share this information with entities such as the World Health Organization. The complete code for EVEscape is also freely available online.

Another important application of EVEscape would be to evaluate vaccines and therapies against current and future viral variants. The ability to do so can help scientists design treatments that are able to withstand the escape mechanisms a virus acquires.

The post SARS-CoV-2 Variants Predicted by New AI Tool, EVEscape appeared first on GEN - Genetic Engineering and Biotechnology News.

Their findings are published in Acta Neuropathologica in an article titled, “Histopathologic Brain Age Estimation via Multiple Instance Learning.”

“Understanding age acceleration, the discordance between biological and chronological age, in the brain can reveal mechanistic insights into normal physiology as well as elucidate pathological determinants of age-related functional decline and identify early disease changes in the context of Alzheimer’s and other disorders,” wrote the researchers. “Histopathological whole slide images provide a wealth of pathologic data on the cellular level that can be leveraged to build deep learning models to assess age acceleration. Here, we used a collection of digitized human post-mortem hippocampal sections to develop a histological brain age estimation model.”

The researchers examined a collection of over 700 digitized images of slides with human hippocampal sections from aged brain donors to develop the histological brain age estimation algorithm. They used the difference between the model-predicted age and actual age to derive the amount of age acceleration in the brain.

When compared with current measures of age acceleration, the researchers observed that HistoAge-based age acceleration had stronger associations with cognitive impairment, cerebrovascular disease, and the levels of Alzheimer’s-type abnormal degenerative protein aggregation. Their study found that the HistoAge model is a reliable, independent metric for determining brain age and understanding factors that drive neurodegeneration over time.

Looking toward the future, the researchers will next build a multicenter collaboration to develop a large AI-ready dataset that will be used to develop even more AI models that have the potential to transform and enhance our understanding of brain diseases.

The post Brain Age Acceleration May Be Predicted by AI Algorithm appeared first on GEN - Genetic Engineering and Biotechnology News.

Data serves as the foundation of today’s biotechnology and pharmaceutical industries, and that foundation keeps expanding. “The appreciation of the value of data and need for quality data has grown in recent years,” says Anastasia Christianson, PhD, vice president and global head of AI, machine learning and data, Pfizer. She notes that the concept of FAIR data—Findable, Accessible, Interoperable, and Reusable data¹—is becoming more widely accepted and more closely achieved.

Part of the transition in data use arises almost philosophically. “There has been a cultural shift or mindset change from data management for the purpose of storage and archiving to data management for the purpose of data analysis and reuse,” Christianson explains. “This is probably the most significant advance. The exponential growth of analytics capabilities and artificial intelligence have probably raised both the expectations for and appreciation of the value of data and the need for good data management and data quality.”

A recent project at Recursion Pharmaceuticals highlights a key data-related challenge: size. The company’s scientists connected biology and chemistry by predicting the protein binding of 36 billion chemical compounds. According to Recursion, “This screen digitally evaluated more than 2.8 quadrillion small molecule–target pairs.” That’s an awful lot of data to create and manage. Consequently, Recursion relied on its own supercomputer to run the simulations and capture the data.

Despite the crucial need to make the most of data, various challenges stand in the way. “Data quality and metadata tagging remain a challenge even though they have improved and are continuing to improve,” Christianson observes. “Multimodal data integration also remains a challenge, not least due to continued exponential growth of data volume, velocity, and variety, and to greater scrutiny of data veracity.”

Integrating data has been difficult for some time. “Companies that develop hardware typically don’t have the right competency to build the best software, especially outside of their platforms, and vice versa,” says Veerle d’Haenens, general manager, global therapeutic systems and cell therapy technologies, Terumo Blood and Cell Technologies. Companies address interoperability challenges in various ways. “Some solutions specific to cell and gene therapy have come to market to meet these needs,” d’Haenens remarks, “but many manufacturers have invested in their own solutions.”

This article explores how some companies already address and overcome this collection of data-related challenges.

Seeking solutions in cell and gene therapies

Data management plays a crucial role from start to finish in cell and gene therapies (CGTs). “In many sectors, it can be the number of data points that causes challenges, but in the CGT sector, it tends to be the depth of the data needed for each patient’s therapy that offers the biggest challenge,” says Matt Lakelin, PhD, co-founder and vice president of scientific affairs and product development, TrakCel.

Another challenge in the sector is the urgency with which GCTs are needed. “The often personalized nature of the therapies paired with their relatively delicate nature causes tight timelines,” Lakelin explains.

Various companies work on ways to speed up the production of CGTs. Terumo Blood and Cell Technologies, for example, takes several approaches that improve the management of data in developing and manufacturing cell therapies.

“The first benefits we’ve enabled with enhanced data management capabilities are for our automated Quantum Flex Cell Expansion System and our Finia Fill and Finish system with fleet management,” d’Haenens points out. “These include remote process monitoring and alarming, which can provide more insight to issues before entering the cleanroom space.” Such capabilities meet a crucial therapeutic need, she says, because “cell expansion is the most time-consuming part of cell therapy manufacturing.”

Keeping data confidential

CGT production depends on data sharing, but there is a proviso: Protect the privacy of patients. “With personalized medicine,” Lakelin stresses, “the patient’s data is inextricably linked to the drug product to ensure that the correct therapy reaches the correct person.”

Various companies, though, must see patient-related data and manage it to manufacture CGTs. “Data flowing between critical partners is vital to keep time-sensitive therapies progressing through the supply chain and to optimize drug product supply,” Lakelin says. “However, these time pressures can lead to data breaches or errors if manual processes are relied on.”

Such data breaches can arise through connecting data points. “As an example, single patient-specific data points may not reveal a patient’s identity but in combination may indicate their identity, and thus be construed as a data breach,” Lakelin explains. “Where paper records would have to be redacted, data flows within an automated system can select only the correct information to share, as well as the correct partner to share it with.”

But how does a company ensure that data is safe and secure? According to Lakelin, a company must use industry-standard encryption. “Developing an in-depth understanding of the value chain can help when deciding when and where it is possible to use pseudoanonymized identifiers instead of personally identifiable information, or PII,” he elaborates. “And restricting access to PII can be undertaken simply by electronic orchestration systems.”

For example, TrakCel’s orchestration system, OCELLOS, can be used for real-time data exchange. “This facilitates more efficient and safer value chain management than using paper-based systems,” Lakelin asserts. “Introducing integrations can further improve the efficiency and safety of advanced therapy supply.”

Still, in the future, additional GCT solutions will be needed. “To date, the CGT industry has been focused on data use in a ‘micro’ form,” Lakelin explains. “As the industry develops and partner technology progresses, considerably larger data volumes will require consideration.” That will include various challenges, including the tracking of data from a particular therapy journey, or the creation of larger pools of cross-patient or cross-therapy data that can be used for predictive analysis.

“There are some very exciting artificial intelligence techniques that are being used in other industry supply chains to assist with forecasting and resource management,” Lakelin says. “Up to now, the quantity of CGT data available to power this has been a challenge as the industry is relatively new and still small, but as it grows, these methods have the potential to unlock powerful possibilities.”

The potential in pictures

Whereas a picture is worth a thousand words, a medical image can summarize billions of data points. “When analyzed properly, scans from different imaging modalities—X-ray imaging, magnetic resonance imaging, computed tomography imaging, and so on—can be applied to better characterize disease mechanisms and therapeutic responses, thereby improving predictive models,” says Costas Tsougarakis, vice president, life sciences solutions, Flywheel. “Such approaches can inform clinical trials by supporting patient-related decisions, such as selection and classification, and novel biomarkers that can become objective study endpoints.”

Data management of images, however, must overcome several obstacles. For example, medical imaging data is unstructured. “Images are acquired with a variety of protocols across imaging sites and modalities,” Tsougarakis points out. “Data classification is primarily based on human input, which leads to inconsistencies and errors.” These challenges make it difficult to develop standardized analytic approaches.

In addition, the size of datasets from imaging creates other complications. “Imaging data must be de-identified, harmonized, and uniformly curated,” Tsougarakis insists. “When traditional methods are used, completing these tasks at scale can take many weeks or even months.” Plus, running computational analyses of such large files—a gigabyte for one magnetic resonance imaging scan, for example—requires high-performance and often cloud-based computing.

Flywheel is a medical imaging data and artificial intelligence platform that automates data processing and workflows to help scientists get the most from their medical images. “The ultimate goal of modern data management strategies,” Tsougarakis declares, “is to turn complex medical imaging data into analysis-ready datasets that can be reused over time for accelerated algorithm development and clinical research.”

According to Tsougarakis, Flywheel is working toward this goal by partnering “with one of the largest pharmaceutical companies in the world to enable the aggregation and management of medical imaging and associated data to accelerate drug discovery.” He adds that Flywheel is using automated pipelines to organize and process imaging data while “minimizing the potential for human error and saving significant time.”

A dream of simpler solutions

The complexity of biotechnology’s data environment notwithstanding, scientists and companies look forward to simpler solutions to data management. “We can see a future where all systems can be managed through a single software in a single location, which is powerful on its own,” d’Haenens says. “But it will also make possible the kind of iterative data analyses that lead to true advances, helping individual developers and the field writ large to understand what can be done to improve product quality and efficacy, reduce manufacturing time, and drive productivity to increase patient access.”

Where possible, biopharmaceutical companies already take advantage of advances in data management. As Christianson explains, “The technology stack for data management has evolved, making more use of cloud-based solutions, automated pipelines, data cataloging, master data management, and federated learning solutions—all of which lower the barriers to and costs of enhanced data management solutions.”

Although data management makes up the foundation of today’s biotechnology and pharmaceutical industries, patients depend on even more improvements in these processes. “As the whole industry gains a better understanding of each element of the production process,” d’Haenens maintains, “we expect it will help improve safety and efficacy.”

Reference

1. Wilkinson MD, Dumontier M, Aalbersberg IJ, et al. The FAIR Guiding Principles for scientific data management and stewardship. Sci Data. 2016; 3: 160018.

The post Manage Data Better or Die appeared first on GEN - Genetic Engineering and Biotechnology News.

An analyst and an influential American investor appeared to hold more sway over the price of Nvidia (NVDA) shares over the past week than French authorities investigating the Silicon Valley-based microprocessing giant with a growing presence in the life sciences, judging by recent stock activity.

Investigators from France’s Autorité de la Concurrence—the French Competition Authority—raided Nvidia’s French offices at dawn on September 27 on suspicion that it may carried out “anticompetitve practices” in the “graphics cards” sector.

The authority’s statement did not spell out the practices being investigated, or the company raided. However, numerous news outlets including Reuters and The Wall Street Journal cited Nvidia by name, after the French business magazine Challenges earlier reported that Nvidia was the target of the raid.

The authority emphasized in a statement that dawn raids like the “unannounced inspection” carried out last week “do not pre-suppose the existence of a breach of the law,” but as a step toward a complete investigation of competitive practices within a given industry.

Nvidia has declined to comment.

Nvidia was not among companies mentioned in a French government report issued June 29 that outlined concerns over a lack of competition in the sector—although the report did mention other companies, such as Amazon Web Services, Google Cloud, and Microsoft Azure.

The authority’s action had no apparent effect on Nvidia shares, which rose 1% the day of the raid, from $419.11 to $424.68. Shares continued to climb 5% through Monday, reaching a high for the week of $447.82 before declining 3%, to $435.17, then rebounding 3% over two days, to $446.88 at the close of trading Thursday.

Monday’s rise came after Toshiya Hari, lead semiconductors sector analyst with Goldman Sachs Research, added Nvidia’s stock to the firm’s “Conviction List” of top picks—although Hari did not change Goldman’s “Buy” rating or 12-month price target of $605 a share.

However, the French raid has led the European Commission to begin “informally” examining potential unfair practices related to the graphics processing units (GPUs) used for artificial intelligence (AI) applications, Bloomberg News reported, citing unnamed sources.

Stock selloff

Also on Monday, the influential electronic transfer fund ARK Genomic Revolution ETF (ARKG) had sold 8,983 shares of Nvidia stock, shrinking its holding in the company from 88,223 to 79,240 shares as of Tuesday, according to ARKG’s chart detailing its Nvidia holdings. That stake dipped further when ARKG sold another 499 shares on Wednesday, then another 15,696 shares on Thursday, bringing its stake in Nvidia to 63,045 shares with a total market value of about $28.2 million.

The fund’s ownership in Nvidia carries a “weight” of 1.7% of the 39-company portfolio, according to the website of ARKG parent ARK Investment Management (ARK Invest), whose chief investment officer and portfolio manager is Catherine D. (Cathie) Wood.

ARKG is an electronic transfer fund concentrating on healthcare and other sectors “expected to substantially benefit from extending and enhancing the quality of human and other life.”

Over the past year, ARKG has shed about two-thirds (66.5%) of its 12-month high of 188,160 shares held on November 18, 2022. Since August 24, when ARKG held 134,323 Nvidia shares, the ETF has sold off a combined 71,278 shares in six transactions, including the three that took place this week.

In January another ARK ETF, its flagship ARK Innovation ETF (ARKK), sold off 800,000 Nvidia shares in January—thus missing practically all of the company’s stock surge in the first half of this year, as investors jumped on the AI bandwagon.

As GEN reported in June, Nvidia shares rocketed 180% between January 3 and May 30 (when it finished at $401.11), then climbed another 5.5%, finishing on June 30 at $423.02 or up 196% from $143.15 at the start of 2023 trading on January 3.

“$NVDA is priced ahead of the curve,” Wood posted on Twitter (now X) May 25, when Nvidia’s stock price stood at 25x its expected revenue for this year.

On September 1, Wood promoted an ARK paper about potential opportunities stemming from investment in AI by posting on X her fund’s current thinking—namely that AI growth won’t be limited to giants like Nvidia: “Since 2014, our analysts have been dissecting the AI revolution. While big benchmarks highlight mega tech, we think AI’s true potential lies beyond them in focused, agile companies.”

Demand stays high

CapEdge cited a possible reason why Nvidia shares didn’t dip further this week: Demand for the company’s GPUs remains high despite rising costs reflected in a 16% hike last month in the price of Nvidia’s H100 GPU set by a sales partner, GDEP Advance.

The H100 now costs ¥5.44 million (just over $36,550), up ¥700,000 (about $4,700), according to a report in Nikkei Asia, in which GDEP blamed the price hike on the declining value of the Japanese yen. Another news report pegs the cost of H100 at about $40,000, with Nvidia spending only $3,320 on manufacturing the GPU.

The AI boom explains why this week one analyst raised his firm’s 12-month price target on Nvidia shares: John Vinn, a managing director and senior research analyst covering the semiconductor industry for KeyBanc Capital Markets, increased its target 12%, from $670 to $750, while maintaining KeyBanc’s “Overweight” rating on the stock.

Headquartered in Santa Clara, CA, Nvidia revolutionized gaming by inventing the GPU more than two decades ago. By 2021, as GEN reported, Nvidia doubled down on expanding its presence in AI-based drug discovery through a trio of partnerships.

Earlier this year, Nvidia announced initiatives that included BioNeMo, a generative AI cloud-based service designed to enable faster discovery and design of drugs; Tokyo-1, in which Nvidia and Mitsui & Co., are partnering to develop Japan’s first generative AI supercomputer for that nation’s pharma industry; and Clara, an AI-based platform used by more than 100 healthcare enterprises worldwide.

And in July, Recursion Pharmaceuticals (RXRX) agreed to accelerate development of its AI foundation models for biology and chemistry by using the cloud services of Nvidia, after it invested $50 million in Recursion.

Leaders & laggards

• ALX Oncology (ALXO) shares surged 56% on Tuesday, from $4.81 to $7.51, after the company announced positive prespecified interim data from its Phase II ASPEN-06 trial (NCT05002127) showing a confirmed overall response rate of 52% for the combination of its CD47 inhibitor evorpacept with Eli Lilly’s Cyramza^® (ramucirumab) and paclitaxel, compared to 22% for control treatment. The randomized multi-center international study assessed the combination as a treatment for patients with HER2-positive gastric/gastroesophageal junction (“GEJ”) cancer. ALX said it will release a final analysis from the trial in Q2 2024, and plans to launched the Phase III portion of ASPEN-06 in late 2024.
• Apellis (APLS) shares rose 5% on Thursday, from $37.62 to $39.64, after the company projected preliminary U.S. net revenue of approximately $74 million in the third quarter for its Syfovre^® (pegcetacoplan injection) for geographic atrophy (GA) secondary to age-related macular degeneration (AMD), and approximately $160 million from its launch in March through September 30. Apellis said demand has stayed strong, with more than 100,000 vials (commercial and sample) distributed to date. Apellis also reported that growth in week-over-week demand resumed in August following a decline linked to safety concerns that touched off a 73% share price plunge and was cited by a short seller last month.
• Ginkgo Bioworks Holdings (DNA) shares fell 5.5% on Monday, from $1.81 to $1.71, after its Zymergen subsidiary filed for Chapter 11 bankruptcy in U.S. District Court for the District of Delaware. In a regulatory filing, Ginkgo disclosed that it entered into an agreement with Zymergen to be the “stalking horse” bidder to acquire exclusive rights to substantially all of Zymergen’s intellectual property assets and “other assets that are relevant to Ginkgo’s business going forward.” Ginkgo’s bid includes $5 million cash and assumption of up to $77 million of potential future liabilities, including a lease, employee compensation, and severance costs. Ginkgo insisted that it and its other subsidiaries “will continue to operate their businesses as usual.”
• POINT Biopharma Global (PNT) shares nearly doubled, leaping 85% on Tuesday from $6.68 to $12.36 after the radiopharmaceutical drug developer agreed to be acquired by Eli Lilly for approximately $1.4 billion. The company’s pipeline of radioligand therapies to treat cancer is led by two late-phase candidates. One is PNT2002, a prostate-specific membrane antigen targeted radioligand therapy for metastatic castration-resistant prostate cancer (mCRPC) after progression on hormonal treatment, set to release topline data from the Phase III SPLASH trial (NCT04647526) later this quarter. The other is PNT2003, a somatostatin receptor (SSTR) targeted radioligand treatment for gastroenteropancreatic neuroendocrine tumors (GEP-NETs).The deal is expected to close near year’s end, subject to customary closing conditions.
• Nuvalent (NUVL) shares jumped 36% on Wednesday, from $42.42 to $57.51, after the company announced preliminary data from the Phase I dose-escalation portion of its ongoing ALKOVE-1 Phase I/II trial (NCT05384626) assessing NVL-655 in patients with advanced ALK-positive non-small cell lung cancer (NSCLC) and other solid tumors. Data showed partial responses to NVL-655 in 45% of response-evaluable patients with ALK-positive NSCLC who received the drug at doses ranging from 15–150 mg once daily (15 of 33 patients, with eight patients pending confirmation). An objective response rate (ORR) of 65% (11 of 17 patients) was seen in patients with baseline ALK resistance mutations, and an ORR of 41% (12 of 29 patients) was seen patients receiving third-generation ALK tyrosine kinase inhibitor lorlatinib, including cases with compound resistance mutations.
• Standard BioTools (LAB) shares tumbled 22% on Wednesday, from $2.70 to $2.10, after it agreed to merge with SomaLogic (SLGC) in an all-stock deal creating a combined company valued at more than $1 billion, to retain Standard’s name and be run by its CEO Michael Egholm, PhD. The new company expects to generate $80 million in “synergies” by 2026—but will have more than $500 million in estimated cash and cash equivalents upon closing. The deal is set to close in the first quarter of 2024 subject to conditions that include shareholder approval and expiration of the Hart-Scott-Rodino waiting period. Standard (formerly Fluidigm) raised its 2023 revenue guidance to $100–105 million, while SomaLogic reaffirmed its 2023 revenue guidance of $80–84 million. SomaLogic shares fell 10%, from $2.30 to $2.07.

Alex Philippidis is Senior Business Editor of GEN. 

The post StockWatch: French Raid Shows Little Effect on Nvidia Price appeared first on GEN - Genetic Engineering and Biotechnology News.

Atomwise, which has historically used its AI platform to help drug developers identify compounds for their pipelines, is entering a new phase of its journey. This week, it announced the nomination of its first AI-driven development candidate, a small molecule focused on TYK2 inhibition, officially marking its transition into a pharmaceutical company.

Neely Mozaffarian, MD, PhD, a veteran in the inflammatory disease drug discovery market, has joined the company as its chief medical officer responsible for driving the TYK2 inhibitor as well as other drugs in the Atomwise pipeline into clinical trials.

Atomwise’s evolution into an AI-driven pharma company aligns with its overall mission to invent a better way to discover medicines that improve patients’ outcomes For Heifets, that means identifying small molecule drugs that are first in class and best in class. “These are really the only two ways of providing value to patients and they are also the only ways of capturing value,” he said in an interview with GEN.  In order to do that, “you have to be able to find molecules where nobody else has found them…and you have to provide meaningful differentiation from what’s out there,” he said. “That’s what patients need and so that’s what we focused on.” 

Initially, Atomwise focused on working with drug discovery and development partners interested in using its proprietary AI/ML drug discovery platform, AtomNet®, to identify potential small molecule candidates from millions of synthesizable compounds. It was the right approach for the company, according to Heifets, who comes from a computer science background, because it allowed them to adopt a high volume, low touch business model for the last several years that leveraged its strengths in artificial intelligence and machine learning. 

Over the years, “we [tried] to be very creative and flexible in the kind of deals that we were doing…all driven by the idea of playing to [our] strong suit,” he said. Atomwise forged partnerships with large and small pharmaceutical companies as well as academic groups. Last year, they signed an agreement with Sanofi to use AtomNet for computational discovery and research. Under the terms of the agreement, Sanofi agreed to pay Atomwise $20 million upfront to identify, synthesize, and advance lead compounds for up to five undisclosed targets which will be exclusive to Sanofi. Subsequent payments pegged to key research, development, and sales milestones could total more than $1 billion in addition to royalties for products developed through the collaboration. And in 2019, the company announced drug discovery partnerships with both Hansoh Pharma and Eli Lilly.

But Atomwise is moving away from a purely collaborative model and focusing on building a pipeline of drug assets internally. It began working on the pipeline some years ago culminating in the nomination of its first candidate—an orally bioavailable and allosteric TYK2 inhibitor discovered using its AI platform. TYK2 is a key mediator in cytokine signaling pathways linked to a broad range of immune-mediated inflammatory conditions. By modulating the TYK2 pathway, this compound could be used to treat various autoimmune and autoinflammatory diseases. Atomwise plans to submit an investigational new drug application for the drug in submission in the second half of 2024.

“We [have] always focused on accessing new parts of chemical space that hadn’t been explored. And so that was what our technology had always been optimized for,” Heifets explained. Taking this approach means “you have an obligation, a duty to prove that those molecules that you’re finding don’t have some hidden liability.” Being able to advance the TYK2 inhibitor into the clinic is “a validation of the whole [Atomwise] platform. That the kinds of things that we find can be valuable and meaningful.” 

Atomwise’s novel approach to finding small molecules was part of what attracted Mozaffarian to the CMO position. Drugs that successfully pass through clinical development have to be more effective than current treatments while simultaneously being just as safe if not safer than existing alternatives. “The hope is always that you can make a therapy that is better than existing therapies for the patient. But it’s really difficult if the drug is not very different from the drugs that are currently out there,” she said in an interview with GEN. “[Atomwise is] able to create, design, and screen hundreds of thousands of molecules to ensure that they can find something that has the qualities that one would look for in a new investigational therapy. The odds that it will have better characteristics for patients increase.”

Among her responsibilities as CMO, Mozaffarian is responsible for thinking through which diseases make sense to pursue for the TYK2 inhibitor as well as which patient populations Atomwise should consider for the drug. The drug could potentially be used to treat conditions such as inflammatory bowel disease, systemic lupus erythematosus, psoriasis, and psoriatic arthritis. She will also support efforts to build on the company’s understanding of the drug based on information about its structure and other preclinical data in ways that improve its performance in patients. She will also be responsible for getting the drug into clinical trials and managing the logistics of the process including working with regulatory bodies and liaising with clinicians to enroll patients at various trial sites. 

It’s a lot for a small company like Atomwise to take on. Large pharma companies typically have large teams of people dedicated to developing new small molecule drugs and much of the infrastructure for moving viable candidates through the clinical development process is already in place. Having worked for small startups as well as large pharma companies, Mozaffarian has the requisite experience to help build out the team and resources that Atomwise needs to move its candidates through clinical development, something she is looking forward to doing. 

“Obviously there are a lot of very talented people here and we are going to add to them in a thoughtful manner,” she said. Atomwise has numerous connections within industry and academia so finding the right talent won’t be difficult. The company is also based in a biotech hotspot on the west coast which has a large pool of people with the kinds of skills and expertise that Atomwise might need. 

Mozaffarian is also looking forward to working on other candidates in the Atomwise pipeline. In the next few years, In addition to inflammatory disease, the company is also focused on targets in oncology and immunology. “It’s one thing to say on paper that we can design things differently and they have novel structures and behave differently in preclinical studies. Ultimately, we have to demonstrate what that means for the patient down the line,” she said. 

And Atomwise will have its work cut out for it as there are a number of competitors for the TYK2 inhibitor already available on the market. That is perhaps the biggest challenge, according to Mozaffarian. “We are not setting out to make a me-too version of an existing therapy. So figuring out, based on the data we have and are in the process of obtaining preclinically, what that means for where we can go [is] going to be the challenge.”

The post AI-Based Drug Discovery Company Atomwise Sets Its Sights on Inflammatory Disease Market appeared first on GEN - Genetic Engineering and Biotechnology News.

Lu Zhang started her first company, Acetone, a medical device company focused on non-invasive technology for the early diagnosis of Type 2 diabetes, when she was just 21 years old. A year earlier, in 2010, she had left Inner Mongolia for the United States to pursue a degree in materials science research at Stanford. Zhang sold Acetone to Boston Scientific in late 2013, and, with majority ownership, she received a hefty chunk of change that would pave the way for her personal investment portfolio.

“I started to make some personal investments with my capital and built a 13-company portfolio, four of which made IPOs,” Zhang told GEN Edge. “So, in 2014, I was thinking about what’s next for me and doing all this angel investing. In early 2015, I made a decision: I wanted to launch my fund.”

At the time, Zhang said that very few people were investing in and talking about healthcare deep tech, which is what ultimately drove her to start her venture capital (VC) firm in 2015 called NewGen Capital, now named Fusion Fund. In 2017, Zhang published an industry research report for the JP Morgan Healthcare Conference, proactively calling for people to invest more resources, capital, and talent into AI-driven healthcare. Today, she’s excited about the blossoming fields of generative AI, large language models (LLMs), and more in healthcare.

“The trend is really coming along—people realize that the largest industrial opportunity is within healthcare, and the next frontier might be within biology with digital biology,” said Zhang, who retains her Mongolian accent, something she points out because she takes pride in her journey as a first-generation immigrant.

Based out of Palo Alto, Zhang’s Fusion Fund currently invests in more than 80 technology startups in healthcare and life sciences, network AI, and industry automation in North America and has notably backed SpaceX and Lyft. The Healthcare and Life Sciences portfolio features 20 companies, including Element Biosciences, some of which are co-investments with larger VCs, such as Khosla Ventures, which Zhang said is also “pretty bullish on AI healthcare.” Other healthcare and life sciences investments from Fusion Fund include single-cell technology innovator Mission Bio, competitor Paradromics in the Neuralink space, biotech startup Quantapore, which is developing nanopore-based nucleic acid sequencing technology, and digital health startup Huma, which is utilizing generative AI.

Early bird gets the worm

Zhang has focused Fusion Fund on supporting early-stage companies, which stems from her conversations with founders about how to be helpful and supportive as a VC. She kept hearing that the critical point for many comes at the very beginning.

“That’s an opportunity to fundamentally do something different and also build a slightly different team to help founders, especially a technical founder,” said Zhang. “The best way to change something is to do it from scratch and brand new. So, we have capital in the initial investing fund at the earliest stage, before the seed stage, and then we continue to have capital in the A and B rounds and even later to support the founder along the way.”

“For the majority of the companies we work with,” Zhang continued, “we are the ones to help get some initial market validation and raise an official institutional seed round to build up a solid revenue pipeline. That’s the stage where we invest the most.”

Looking back, Zhang acknowledges that she benefited from some “beginner’s luck.” For example, it was for a company with a valuation of $4 million—today, that company makes $1.7 billion in revenue. The second investment in Fusion Fund I was an initial check for $5 million to a company now a major player in single-cell sequencing for cancer diagnostics. To date, Fusion Fund has raised $215.5M across three funds, their latest being Fusion Fund III, announced on Nov 1, 2021, and raised $120 million.

At the core of her vision is resiliency, which is essential in today’s market environment, which she said is like a trampoline—bouncing up and down daily.

“There’s always discussion about the great company established during an economic downturn, and that’s true for a reason: the only people who could survive this economic cycle and be able to attract concentrated capital and concentrated resources will grow much faster after the market rebound,” she said.

AI is a tool, not a solution

Fusion Fund primarily invests in platform technologies that utilize data to drive digital transformations.

“There are so many people talking about AI right now, but AI is essentially a tool,” said Zhang. “It’s a tool that will be implemented and used in different industries for different use cases. But why are we using this tool? We’re using this tool, together with other new technology, to push and boost digital transformation across different industries, including healthcare as a major one. So, we are looking for founders with similar convictions and a big vision about what they want to do with their technology solution.”

From there, Zhang said the founders she invests in need to understand market size and timing. They need strong industry insight and the ability to identify core problems to build an applicable solution.

“All these new terms we hear about now, including AI—they’re not new; they’ve been there for many years,” said Zhang. “The reason we should invest in them now is because market timing is here. Whether from the technology infrastructure level or the customer’s copy side, they’re ready to implement new technology. So, when the timing is right, we’ll be able to find the right people to use the right technology and focus on the right industry problem.”

Though Zhang wants to see the implementation of AI and LLMs impact the healthcare and life sciences industries, she thinks it all depends on the accessibility, uniqueness, and quality of the data it uses for training and execution.

“Digital healthcare, digital life science, digital biology, digital therapeutics—it’s just evolving so fast, and it’s not directly consumer-facing, so people don’t feel it right now,” said Zhang. “But in a few years, we will see something significant happen. The future of biology will fundamentally change our day-to-day lives, the food industry, the healthcare industry, and more.”

While the AI revolution has often been compared to the internet boom of the 1990s, Zhang said that the internet is only about the tech industry and that the reason that AI will be so transformational is that it is going to affect companies across all industries.

“It’s important for every single person and company to understand how important AI is and also be prepared to enable themselves with the knowledge and access to the technology,” said Zhang. “We won’t be replaced, but AI technologies will be used by humans. AI won’t replace the doctor who uses it, but it will replace others in a hospital or large organization that uses AI to offer digital and individualized healthcare solutions. This is the evolution we’re going through right now.”

The post Fusion Fund Powers Founders Bringing AI to Healthtech, Life Sciences, and More appeared first on GEN - Genetic Engineering and Biotechnology News.

In 2017, JBEI was selected as one of four DOE Bioenergy Research Centers to receive funding for biofuels and bioproducts research. At the time, the four centers were slated to receive $40 million in initial funding for fiscal year 2018 with plans to supply more funding for another four years. 

TeselaGen and JBEI have been collaborating since 2017 on bioinformatics tools for running JBEI’s synthetic biology workflows. The company’s platform has helped JBEI scientists develop and deliver renewable carbon-neutral biofuels from nonfood plant fibers. That work will continue under the renewed contract, and the partners plan to add expanded workflow capabilities to the TeselaGen platform. 

“We are honored to continue to work with JBEI with their ongoing efforts to enable the cost-effective biological production of fuels, products, and other components that are traditionally made through chemical processes,” Eduardo Abeliuk, PhD, TeselaGen’s CEO and co-founder, said in a statement. 

TeselaGen’s platform uses artificial intelligence and machine learning techniques to connect data, tools, and protocols enabling biologists, lab technicians, and bioinformaticians to run high-throughput biomanufacturing workflows seamlessly. Earlier this year, TeselaGen partnered with NinthBio to integrate that company’s Homology Path design algorithm to help users design and construct DNA variant libraries efficiently. 

Over the years, TeselaGen has forged several partnerships aimed at building the U.S. bioeconomy. Besides JBEI, TeselaGen has had a contract with BioMADE, a Department of Defense-sponsored bioindustrial manufacturing institute, that is focused on developing technologies for standardizing data exchange, connecting software systems, and implementing protocols for collaboration. 

Separately, TeselaGen has a partnership with the Advanced Biofuels and Bioproducts Process Development Unit (ABPDU) of the Lawrence Berkeley National Lab focused on advancing fermentation processes for developing renewable bioproducts. Under the terms of the agreement, ABPDU is using TeselaGen’s data acquisition capabilities to organize complex datasets throughout its biomanufacturing workflows. 

The post TeselaGen, JBEI Renew Biomanufacturing Partnership appeared first on GEN - Genetic Engineering and Biotechnology News.

By Alex Philippidis

Exelixis (EXEL) was one of “at least five” companies interested in licensing rights to Insilico Medicine’s ISM3091, a small molecule ubiquitin specific protease 1 (USP1) inhibitor being developed to treat BRCA-mutant tumors, the company’s founder, chairman, and CEO Alex Zhavoronkov, PhD, shared with GEN Edge recently.

Earlier this month, Exelixis prevailed over those other companies by inking an exclusive license agreement in which it agreed to pay Insilico $80 million upfront and undisclosed potential payments tied to achieving development, commercial, and sales-based milestones—“a very substantial downstream,” Zhavoronkov said.

Viewed strictly in terms of deal dollars, he said, “the level of interest was so high that I think that we could have gotten a better deal.”

So why did Insilico entrust ISM3091’s future clinical development to Exelixis?

“Exelixis actually presented a story that blew my mind away when we met,” Zhavoronkov recalled in a wide-ranging interview.

Based in Hong Kong, privately-held Insilico discovers and designs drug candidates using generative artificial intelligence (AI). The company’s AI platforms use deep generative models, reinforcement learning, transformers, and other machine learning techniques for discovering novel targets and generating novel molecular structures with desired properties.

Insilico’s attraction to Exelixis begins with its successful development of the cancer drug Cabometyx^® (cabozantinib), a kinase inhibitor indicated for renal cell carcinoma (RCC), both alone and in first-line treatment with Bristol-Myers Squibb’s Opdivo® (nivolumab); hepatocellular carcinoma in patients previously treated with sorafenib; and some patients with locally advanced or metastatic differentiated thyroid cancer (DTC).

Blockbuster franchise

Exelixis has grown Cabometyx into a blockbuster franchise. Cabometyx finished the first half of this year with U.S. net product revenue of $409.646 million, up 18% from $347.044 million in January–June 2022. For all of last year, Cabometyx racked up $1.401 billion, a 30% jump from $1.077 billion in 2021.

Exelixis’ results don’t include sales outside the U.S. Cabometyx is marketed by Ipsen in the rest of the world except Japan, where rights are held by Takeda Pharma.

Ipsen reported six-month 2023 cabo sales of €265.8 million ($281.5 million), up 25% from €212.2 million ($224.7) in January–June 2022, and 2022 sales of €448.7 million ($475.2 million), up 27% from €354.6 million ($375.6 million) in 2021.

Takeda racked up ¥2.1 billion ($14.1 million) in April–June of this year, down from ¥2.2 billion ($14.8 million) a year earlier. For the year ending March 31, cabo racked up ¥7.8 billion ($52.4 million), up from ¥6.5 billion ($43.7 million) in Takeda’s FY 2021.

Cabometyx won its first approval in the DTC indication in 2012, a year after the company made “cabo” its “sole focus” of development. But when the drug failed a Phase III trial in prostate cancer two years later, Exelixis eliminated about 70% of its workforce—160 jobs—and refocused its development of cabometyx on RCC, where it won its first FDA approval in 2016, second-line treatment in patients who already received an anti-angiogenic therapy. That was followed a year later by approvals for first-line treatment (2017) and combination with Bristol-Myers Squibb’s Opdio^® (nivolumab; 2021).

“If you look Exelixis’ CEO (Michael M. Morrissey, PhD), I think he is one of the best CEOs in the industry, period. I’ve never seen anybody that detailed. The guy is an Elon Musk of drug discovery,” Zhavoronkov enthused. “[Morrissey] spent 20 years doing great work and actually succeeding, now treating patients and driving revenue. The reason I’m so admiring of them is because they are like us a little bit. They made it as a biotech, and they rescued cabo a couple times.”

Keeping it real

And by not disclosing milestone dollars that may or may never materialize, Exelexis showed Zhavoronkov that its PR folks were as savvy as their researchers: “They want to show what’s real and what’s not. It’s a very interesting company which talks about facts. They’re saying, Look, let’s do it right. We believe in data, right? And we want to generate the data first.”

By contrast, when Merck KGaA, Darmstadt, Germany announced two AI-based drug collaborations on Wednesday, its partners disclosed more than $1 billion in combined potential milestone details: German Merck agreed to pay Exscientia $20 million upfront, up to $674 million in milestones—compared with $10 million upfront, up to $594 million in milestones for Benevolent^AI.

Investors seemed skeptical, however, as the stock prices of both partners fell: BenevolentAI dipped 1.5%, from 99 to 97.5 cents (returning to 99 cents on Friday), while Exscientia shares dropped 10.5%, from $5.06 to $4.53 (shares since more than rebounded, closing at $5.17 on Friday).

Asked if Insilico’s deal with Exelixis would be a model for future collaborations, Zhavoronkov replied: “I think this is a testament that AI, and generative AI very specifically, can produce really high quality assets that experts are willing to pay a lot of money for, and put their genius behind the targets you select.”

Discovered through Insilico’s Chemistry42 generative AI platform, ISM3091 is now under study in a Phase I trial (NCT05932862) that began in August and is projected to enroll 66 patients. The first-in-human, multicenter, open-label Phase I study consists of a dose escalation part followed by a dose selection optimization part. The study’s estimated primary completion date is July 27, 2024.

Zhavoronkov said ISM3091 represents a potentially best-in-class approach that has shown strong efficacy against multiple tumor cell lines and in vivo models with BRCA mutations, as well as in homologous recombination DNA repair (HRR)-proficient models, both alone and in combination with PARP inhibitors.

According to an abstract of a poster presented at the American Association for Cancer Research (AACR)’s Annual Meeting 2023, held in Orlando, FL, ISM3091 as a single agent showed tumor growth inhibition (TGI) of 66% at 30 mg/kg BID in triple-negative breast cancer (TNBC), and 60% at 50 mg/kg BID in ovarian cancer. ISM3091 also showed strong single-agent TGI of 72% at 50 mg/kg BID in an ovarian patient-derived xenograft (PDX) model with acquired resistance to olaparib in BRCA wild type—a result that suggests the USP1 inhibitor has the potential to treat tumors with HRD beyond patients with BRCA mutations, and overcome PARP inhibitor resistance.

When given in combination with AstraZeneca’s Lynparza^® (olaparib), ISM3091 showed stronger and more durable anti-tumor response, even at low doses. The combo of ISM3091 3 mg/kg BID plus olaparib, 50 mg/kg QD showed TGI of 91% in TNBC, while ISM3091 50 mg/kg BID + olaparib, 50 mg/kg QD demonstrated a 110% TGI in ovarian.

“We believe preclinical data on ISM3091’s potent anti-tumor activity, tolerability, and pharmacokinetics set the compound apart from competing USP1 inhibitors and make it an important addition to Exelixis’ growing clinical-stage pipeline,” Dana Aftab, PhD, Exelixis executive vice president, Discovery and Translational Research and chief scientific officer, said in a statement.

Growing Interest

USP1 is a target of growing interest in biopharma circles given its crucial role in DNA damage response and repair, namely by removing ubiquitin from multiple substrates including proteins that stabilize the “replication fork”—the region where the two strands of DNA are separated to allow replication of each strand.

That has led to its emergence as a new synthetic lethal target for cancer treatment. The first drugs approved to leverage synthetic lethality have been poly (ADP-ribose) polymerase (PARP) inhibitors, which have shown positive clinical effects in many patients. However, between 40% and 70% of patients have developed resistance over time to PARP inhibitors, which has fueled interest in alternatives by Insilico and other drug developers.

Furthest ahead in USP1-targeted clinical development until now has been KSQ Therapeutics, which last December launched the Phase I KSQ-4279-1101 trial (NCT05240898), designed to assess the company’s USP1-targeting small molecule KSQ-4279 in patients with advanced solid tumors across multiple indications. KSQ-4279 is being studied both in combination with a PARP inhibitor, and in combination with chemotherapy. Estimated primary completion date for the 64-patient trial is June 24, 2024.

In July, Roche agreed to be fully responsible for further development of KSQ-4279 as of 2024, through a global license and collaboration agreement whose financial terms were undisclosed. Roche agreed to pay KSQ an upfront payment plus potential milestones and royalty payments.

Also developing a USP1-targeting drug is Debiopharm, which in March acquired for an undisclosed price global rights from Novo Nordisk to FT-3171 (renamed Debio 0432), which targets an undisclosed novel DNA damage repair pathway and is in late preclinical phases.

Zhavoronkov said the growing interest in USP1 was just one reason why Insilico chose to partner ISM3091 rather than develop it in-house. The other was Insilico’s crowded pipeline, which consists of 31 programs aimed at 29 targets.

ISM3091 is one of nine disclosed Insilico pipeline programs for oncology indications, making cancer the company’s largest therapeutic area.

Pipeline updates

Zhavoronkov also offered updates on several Insilico pipeline candidates:

• ISM018_055: Insilico’s lead candidate is a small molecule inhibitor treatment for idiopathic pulmonary fibrosis (IPF) that dosed its first Phase II patient earlier this year and is now in two Phase II 60-patient double blind placebo control trials—one in the U.S., one in China. One trial is assessing a once-daily 60 mg dose; the other, two 30 mg doses. Data is likely to be released at the end of next year, Zhavoronkov said. Citing competitive reasons, Insilico has not disclosed the drug’s target, calling it “Target X,” though Zhavoronkov told GEN last year the target was a regulator of at least three pathways implicated in fibrosis.
• ISM3312: The oral small molecule 3CLPro inhibitor designed to treat COVID-19 is in a Phase I trial launched earlier this year. Zhavoronkov said earlier this month ISM3312 is envisioned as an alternative to Pfizer’s COVID antiviral Paxlovid^® (nirmatrelvir tablets and ritonavir tablets) and Merck & Co.’s Lagevrio (molnupiravir).
• ISM8207: The small molecule QPCTL inhibitor, which Insilico says is potentially first-in-class, is being co-developed with Fosun Pharma as a treatment for advanced malignant tumor In August, Insilico said the companies had advanced ISM8027 into Phase I studies. The companies agreed to partner last year, with Insilico licensing to Fosun 50% rights to the drug. Fosun paid Insilico $13 million upfront and agreed to make an equity payment into Insilico, plus pay up to $82 million tied to achieving milestones.
• MAT2A inhibitor: A methionine adenosyltransferase 2α (MAT2A) inhibitor envisioned as a treatment for MTAP-deficient cancer though synthetic lethality is in the IND-enabling phase. Zhavoronkov contrasted Insilico’s commitment to the target vs. GlaxoSmithKline’s termination last year of a collaboration to develop IDEAYA Biosciences’s MAT2A inhibitor IDE397, now under development as monotherapy and in combo with Amgen’s AMG 193: “We didn’t stop working on MAT2A. We actually proceeded. So that kind of shows you my approach target picking.”

• ENPP1 inhibitor: An ectonucleotide pyrophosphatase/phosphodiesterase 1 (ENPP1) inhibitor envisioned to treat solid tumor cancers is in the IND-enabling phase: “ENPP1 is likely to be like the hottest target a year from now.”

The deal with Insilico hardly budged Exelixis stock, which inched up 0.5% the day it was announced September 12, from $21.99 to $22.09. Shares have since dipped 3%, closing Friday at $21.48.

Filing for IPO

Unlike Exelixis, Insilico is not public—yet. But on June 28, Insilico disclosed plans for an initial public offering on the Stock Exchange of Hong Kong, in a public filing that listed Morgan Stanley and China International Capital Corp. (CICC) as joint sponsors.

The amount of capital the company plans to raise, and the timetable for the offering, were among details redacted from the public version of the filing—though the South China Morning Post, citing unnamed sources, has reported that the company plans to raise approximately $200 million. Zhavoronkov would not comment on the IPO filing.

According to the filing, Insilico had raised up to that point a total $407.5 million in seven financings that included three series C rounds totaling $270 million in 2021, and two Series D closings totaling $94.7 million last year.

Also in 2022, Insilico generated $27.3 million in revenue from its top five customers, accounting for 90.6% of total revenues, the filing stated. That would put Insilico’s 2022 revenues at over $30.1 million.

Insilico disclosed in the filing that a single unnamed customer accounted for more than half (56.6%) of its revenues in 2022, $17.066 million. Insilico described that customer as “a global innovation-driven pharmaceutical and healthcare industry group, operates businesses including pharmaceutical manufacturing, medical devices, medical diagnosis, and healthcare program.”

If Insilico carries out the Hong Kong IPO, it would be a change from what Bloomberg News reported in 2021 was an earlier plan to go public through a confidential filing in the U.S. seeking to raise “around $300 million.” Insilico has not commented on that report, for which Bloomberg cited unnamed sources.

Speaking to the South China Morning Post in June, however, Zhavoronkov offered a rationale for an IPO filing in Hong Kong: “We are a truly global company with R&D centers in many countries and regions. But Hong Kong is where we discover our targets—the most important part of drug discovery and I built an expert team to focus on this and to become the best in the world in this area.”

Leaders & laggards

• ARS Pharma (SPRY) shares plunged 56% on Wednesday, from $6.605 to $2.92, after the FDA stunned the company by refusing to approve its neffy^® (epinephrine nasal spray) as a treatment for allergic reactions (Type I), including anaphylaxis for adults and children weighing ≥30 kg (≥66 lbs.). Instead, the agency issued a complete response letter (CRL) requesting a PK/PD study assessing repeat doses of neffy compared to repeat doses of an epinephrine injection product under allergen-induced allergic rhinitis conditions. The request was an about face for the agency, which in August agreed with the company to conduct the trial as a post-marketing study. In May, the FDA’s Pulmonary-Allergy Drugs Advisory Committee (PADAC) recommended approval of neffy without additional studies. ARS plans to appeal the CRL by filing a Formal Dispute Resolution Request.
• Seelos Therapeutics (SEEL) shares cratered 84% over three days, starting with a 69% slide from an even $1 to 31 cents on Wednesday, after the company acknowledged that a Phase II trial (NCT04669665) assessing its lead pipeline candidate SLS-002 in adults with major depressive disorder who are at imminent risk of suicide did not meet the pre-defined primary endpoint (MADRS ANCOVA at 24 hours post dosing). Only 147 patients were randomized—67% of the study’s target enrollment of 220 patients, due to financial constraints, Seelos said. Chief Medical Officer Tim Whitaker, MD, stated, however, that SLS-002 showed both meaningful early and persistent improvement in depressive symptoms, as well as clinically meaningful reduction in acute suicidality symptoms relative to standard of care. Investors didn’t agree; shares nosedived another 39% to 19 cents after Cantor Fitzgerald downgraded the stock from “Overweight” to “Neutral,” then fell another 16% to 16 cents on Friday.
• Travere Therapeutics (TVTX) shares plummeted 41% on Thursday, from $12.88 to $7.64, after the company released topline two-year confirmatory secondary endpoint results stating that its pivotal Phase III PROTECT trial (NCT03762850) assessing Filspari^® (sparsentan) versus irbesartan in IgA nephropathy (IgAN) narrowly missed statistical significance in estimated glomerular filtration rate (eGFR) total slope—but achieved statistical significance in eGFR chronic slope, for purposes of regulatory review in the European Union. Travere said it expects to submit a supplemental New Drug Application (sNDA) in the first half of 2024 for full approval of Filspari, which the FDA approved in February under accelerated approval.

Alex Philippidis is Senior Business Editor of GEN.

The post StockWatch: Insilico CEO Breaks Down Exelixis Deal appeared first on GEN - Genetic Engineering and Biotechnology News.

The Lasker Foundation has awarded more than 410 prizes since 1945 recognizing scientists whose contributions have advanced the understanding of human health and biology and improved the diagnosis, treatment, and prevention of human disease. 

That long list of winners now includes Demis Hassabis and John Jumper of Google DeepMind, who won the Albert Lasker Basic Medical Research award for the development of AlphaFold, an AI system for predicting protein’s 3D structure from their amino acid sequences. Their work solved the long-standing structure prediction problem that has plagued protein studies for decades. The complexity of 3D protein structures and the sheer number of possible conformations meant scientists had to use time-consuming experimental approaches to try to determine the correct architecture of the proteins they studied. 

Computational methods developed to help with structure prediction had some success. One approach developed by David Baker at the University of Washington, for example, used short protein segments from the Protein Data Bank to predict protein architecture but the strategy was slow and not broadly applicable across proteins.

Things changed in 2018 when Hassabis, Jumper, and their team released AlphaFold. Their first iteration of the solution, AlphaFold1, outperformed other computational protein prediction approaches in the 13th edition of the Critical Assessment of Structure Prediction competition, a biannual community initiative that challenges participants to use their methods to predict protein structures directly from amino acid sequences. The challenge used proteins whose structures have been solved experimentally but not yet made public. Judges compared the submitted structures to the experimental answer and ranked them. 

Following their early success, Hassabis, Jumper, and their team continued improving AlphaFold using a combination of computational strategies and collective wisdom on proteins and protein structure. The changes they made included allowing the underlying network to adjust calculations at any point during the predictive process. They also prioritized three-dimensional relationships between amino acids and protein subunits over linear proximity. 

These changes paid off handsomely as the updated system, AlphaFold2, made more precise structure predictions even for proteins that lack a template. Once again, it bested other methods during CASP14 in 2020. And the DeepMind team did not stop there. By 2021, they had predicted structures for 350,000 proteins including the roughly 20,000 proteins that make up the human proteome. That same year, they published details of the method in a paper in Nature.  Even more impressive is that the scientists have now used AlphaFold2 to predict structures for about 200 million proteins gleaned from all of the organisms sequenced to date. All of this data is publicly available and has been accessed by more than a million investigators worldwide for vaccine and drug design projects as well as to develop gene therapies among other uses.  

The Lasker Foundation is also honoring James G. Fujimoto, PhD, David Huang, MD, PhD, and Eric A. Swanson this year. The trio are sharing the 2023 Lasker-DeBakey Clinical Medical Research award for inventing optical coherence tomography (OCT), a technology that uses light beams to visualize microscopic structures in body tissue. 

The technology has had its biggest impact in the field of ophthalmology where it is used to rapidly detect conditions that lead to impaired vision including diabetic retinopathy, glaucoma, and macular degeneration often before patients experience physical symptoms. Beyond ophthalmology, the technology is also used to assess medical conditions in the heart, brain, skin, and digestive tract. Increasingly, cardiovascular specialists use OCT to evaluate plaque buildup and guide stent placement inside blocked arteries. OCT has also been used to diagnose skin cancer and measure neurodegeneration from multiple sclerosis and other neurologic conditions.

OCT’s development grew out of Fujimoto’s interest in finding practical applications for ultrafast lasers that generate extremely short pulses of light. He recruited Huang and Swanson to work with him on possible applications of these lasers in eye surgery and for measuring the thickness of eye structures. Together, they developed what would become the first OCT system, which scanned a beam of light across tissue structures to develop images that could reveal microscopic structures inside the retina and the coronary artery. They published their first paper on the technique in 1991. 

The technology has come a long way since its early days. An important application is its use in stratifying patients with age-related macular degeneration for treatment with an anti-VEGF antibody. The treatment blocks the inappropriate blood vessel formation that characterizes the condition and can cause blindness but it does not work for all patients. OCT helps doctors identify which patients would best benefit from the therapy and when additional treatment is needed. 

“It’s a great honor to receive the Lasker-DeBakey Award with my fellow OCT co-inventors,” Huang, now director of research and associate director of the OHSU Casey Eye Institute, and professor of ophthalmology and biomedical engineering in the OHSU School of Medicine, said in a statement. He continues to improve the technology through research at the Center for Ophthalmic Optics and Lasers at OHSU. Swanson and Fujimoto are both at the Massachusetts Institute of Technology. 

“OCT may not be as well-known as other major imaging modalities, such as MRI or CT scans, but if you have a serious eye condition, chances are that you received an OCT scan to help diagnose and manage your condition,” Huang said. “I am proud that millions of people have benefited from a technology that I helped invent three decades ago.”

The final award, the Lasker-Koshland Special Achievement Award in Medical Science, went to Pier Borst, former group leader and scientific director at the Netherlands Cancer Institute in recognition of his 50-year career of scientific discovery, mentorship, and leadership. Among other discoveries, his research has helped reveal how the parasite that causes African sleeping sickness evades the immune system and provided insights into the activity of molecular pumps in cancer drug resistance. 

The winners will receive their awards at a gala ceremony in New York City on September 29.

The post 2023 Lasker Awards Honor Creators of AI Protein Structure Prediction Among Others appeared first on GEN - Genetic Engineering and Biotechnology News.