logo
Studying a galaxy far, far away could become easier with help from AI, says researcher

Studying a galaxy far, far away could become easier with help from AI, says researcher

CBC4 days ago
A recent Memorial University of Newfoundland graduate says his research may help study galaxies more efficiently — with help from Artificial Intelligence.
As part of Youssef Zaazou's master's of science, he developed an AI-based image-processing technique that generates predictions of what certain galaxies may look like in a given wavelength of light.
"Think of it as translating galaxy images across different wavelengths of light," Zaazou told CBC News over email.
He did this by researching past methods for similar tasks, adapting current AI tools for his specific purposes, finding and curating the right dataset to train the models, along with plenty of trial and error.
"Instead of … having to look at an entire region of sky, we can get predictions for certain regions and figure out, 'Oh this might be interesting to look at,'" said Zaazou. "So we can then prioritize how we use our telescope resources."
Zaazou recently teamed up with his supervisors Terrence Tricco and Alex Bihlo to co-author a paper on his research in The Astrophysical Journal, which is published by The American Astronomical Society.
Tricco says this research could also help justify allocation of high-demand telescopes like the Hubble Space Telescope, which has a competitive process to assign its use.
A future for AI in astronomy
Both Tricco and Zaazou emphasised the research does not use AI to replace current methods but to augment them.
Tricco says that Zaazou's findings have the potential to help guide future telescope development, and predict what astronomers might expect to see, making for more efficient exploration.
Calling The Astrophysical Journal the "gold standard" for astronomy journals in the world, Tricco hopes the wider astronomical community will take notice of Zaazou's findings.
"We want to have them be aware of this because as I was mentioning, AI, machine learning, and physics, astronomy, it's still very new for physicists and for astronomers, and they're a little bit hesitant about these tools," said Tricco.
Tricco praised the growing presence of space research in general at Memorial University.
"We are here, we're doing great research," he said.
He added growing AI expertise is also transferable to other disciplines.
"I think that builds into our just tech ecosystem here as well."
'Only the beginning'
Though Zaazou's time as a Memorial University student is over, he hopes to see research in this area continue to grow.
"I'm hoping this is the beginning of further research to be done," he said.
Though Zaazou described his contribution to the field as merely a "pebble," he's happy to have been able to do his part.
"I'm an astronomer. And it just feels great to be able to say that and to be able to have that little contribution because I just love the field and I'm fascinated by everything out there," said Zaazou.
Orange background

Try Our AI Features

Explore what Daily8 AI can do for you:

Comments

No comments yet...

Related Articles

UW researchers figured out how to bypass anti-deepfake markers on AI images

timean hour ago

UW researchers figured out how to bypass anti-deepfake markers on AI images

University of Waterloo researchers have built a tool that can quickly remove watermarks identifying content as artificially generated — and they say it proves that global efforts to combat deepfakes are most likely on the wrong track. Academia and industry have focused on watermarking as the best way to fight deepfakes and basically abandoned all other approaches, said Andre Kassis, a PhD candidate in computer science who led the research. At a White House event in 2023, the leading AI companies — including OpenAI, Meta, Google and Amazon — pledged to implement mechanisms such as watermarking to clearly identify AI-generated content. AI companies' systems embed a watermark, which is a hidden signature or pattern that isn't visible to a person but can be identified by another system, Kassis explained. He said the research shows the use of watermarks is most likely not a viable shield against the hazards posed by AI content. It tells us that the danger of deepfakes is something that we don't even have the tools to start tackling at this point, he said. The tool developed at the University of Waterloo, called UnMarker, follows other academic research on removing watermarks. That includes work at the University of Maryland, a collaboration between researchers at the University of California and Carnegie Mellon, and work at ETH Zurich. Kassis said his research goes further than earlier efforts and is the first to expose a systemic vulnerability that undermines the very premise of watermarking as a defence against deepfakes. In a follow-up email statement, he said that what sets UnMarker apart is that it requires no knowledge of the watermarking algorithm, no access to internal parameters, and no interaction with the detector at all. When tested, the tool worked more than 50 per cent of the time on different AI models, a university press release said. AI systems can be misused to create deepfakes, spread misinformation and perpetrate scams — creating a need for a reliable way to identify content as AI-generated, Kassis said. WATCH | How to spot a deepfake : After AI tools became too advanced for AI detectors to work well, attention turned to watermarking. The idea is that if we cannot post facto understand or detect what's real and what's not, it's possible to inject "some kind of hidden signature or some kind of hidden pattern" earlier on, when the content is created, Kassis said. The European Union's AI Act requires providers of systems that put out large quantities of synthetic content to implement techniques and methods to make AI-generated or manipulated content identifiable, such as watermarks. In Canada, a voluntary code of conduct launched by the federal government in 2023 requires those behind AI systems to develop and implement a reliable and freely available method to detect content generated by the system, with a near term focus on audio-visual content (e.g., watermarking). Watermark removed 'within 2 minutes max' Kassis said UnMarker can remove watermarks without knowing anything about the system that generated it, or anything about the watermark itself. We can just apply this tool and within two minutes max, it will output an image that is visually identical to the watermark image which can then be distributed, he said. "It kind of is ironic that there's billions that are being poured into this technology and then, just with two buttons that you press, you can just get an image that is watermark-free." Kassis said that while the major AI players are racing to implement watermarking technology, more effort should be put into finding alternative solutions. Watermarks have been declared as the de facto standard for future defence against these systems, he said. I guess it's a call for everyone to take a step back and then try to think about this problem again. Anja Karadeglija (new window) · The Canadian Press

ImmunoPrecise Releases New Findings Showing LENSai™ Quickly Flags Anti-Drug-Antibody Risk--Long Before the Clinic
ImmunoPrecise Releases New Findings Showing LENSai™ Quickly Flags Anti-Drug-Antibody Risk--Long Before the Clinic

National Post

time2 hours ago

  • National Post

ImmunoPrecise Releases New Findings Showing LENSai™ Quickly Flags Anti-Drug-Antibody Risk--Long Before the Clinic

Article content AUSTIN, Texas — ImmunoPrecise Antibodies Ltd. (NASDAQ: IPA) ('IPA' or the 'Company'), a Bio-Native AI pioneer operating where TechBio meets true biological intelligence, today announced results of a newly expanded study demonstrating that its LENS ai ™ Immunogenicity Screening can reliably predict Anti-Drug-Antibody (ADA) risk for therapeutic proteins before they enter animal studies or human trials. Article content 'ADA-related failures still derail up to 40 percent of biologics in late development, costing companies billions of dollars,' said Dr. Jennifer Bath, President & CEO, IPA. 'With LENS ai, we can now triage candidates against clinical data in hours, not months, giving drug-developers a fast, objective way to de-risk programs early and focus resources on the safest molecules.' Article content Late‑stage ADA failures can wipe out $1–2 billion in projected revenue for a single biologic and push launch timelines back 12‑18 months. Yet many programs still lean on time‑intensive lab assays or first‑generation in‑silico screens that look only at peptide‑to‑MHC II binding across a few dozen HLA alleles—leaving large swaths of immune diversity untested and immunogenic 'self/non‑self' checks largely unaddressed. Article content LENS ai 's HYFT‑powered, alignment‑free immunogenicity screening compresses that entire workflow into one overnight run. It evaluates nearly 900 HLA variants and performs a whole‑proteome 'humanness' scan at residue resolution, instantly flagging hot‑spots that legacy tools miss. By revealing design‑level fixes before expensive animal studies or repeat GMP production, the platform can shorten pre‑clinical cycles, cut material costs, and de‑risk downstream development—delivering a speed‑and‑breadth advantage unattainable with traditional methods. Article content Study Highlights Article content 217 marketed and clinical-stage antibodies analyzed – the largest public ADA dataset to predict immunogenicity risk Single composite score tracks clinical reality – enables reliable ADA incidence risk classification; a score ≥ 54 flags high-risk candidates (> 30 % ADA in patients). The discriminative capability is very powerful as indicated by an AUC=0.92. Alignment-free, HYFT-powered engine – the proprietary screening algorithm combines state-of-the-art MHC II binding with IPA's proprietary HYFT® patterns, enabling whole-proteome humanness assessment without multiple-sequence alignments. Detailed amino acid and epitope-level immunogenicity 'self' scanning – quickly pinpoints immunogenic hot-spots and suggests sequence edits before expensive wet-lab assays. Article content Read the full case study: Article content [ Article content link Article content ] Article content About ImmunoPrecise Antibodies Ltd. Article content ImmunoPrecise Antibodies Ltd. (NASDAQ: IPA) is advancing Bio-Native™ AI at the intersection of biology and computation. The Company's LENSai™ and HYFT® platforms enable large-scale reasoning across sequence, structure, function, and scientific literature, powering next-generation workflows across drug discovery, diagnostics, vaccine design, and molecular systems biology. Article content Forward-Looking Statements Article content This press release contains forward looking statements within the meaning of applicable United States and Canadian securities laws. Forward looking statements are often identified by words such as 'expects,' 'intends,' 'plans,' 'anticipates,' 'believes,' 'potential,' or similar expressions, or by statements that certain actions, events, or results 'may,' 'will,' 'could,' or 'might' occur or be achieved. Examples include statements regarding the projected performance, scalability, and market adoption of the Company's LENSai™ Immunogenicity Screening; the ability of its HYFT® powered, alignment free platform to shorten development timelines, reduce program risk, or displace legacy wet lab and multiple sequence alignment methods; the economic impact of early, in-silico ADA prediction on biopharma R&D efficiency; and the Company's broader scientific, commercial, and capital markets objectives. Article content Forward looking statements are based on management's current expectations, assumptions, and projections about future events. Actual results could differ materially from those expressed or implied because of factors beyond the Company's control, including the pace of scientific and technological innovation in AI driven drug discovery, the accuracy and regulatory acceptance of in-silico ADA risk screening, competitive shifts as the industry transitions away from MS dependent workflows, customer adoption rates, operational or integration challenges, and changes in economic, market, or regulatory conditions. Additional information about these and other risks and uncertainties is set out in the Company's Annual Report on Form 20F, as amended, for the fiscal year ended April 30, 2024, available on the Company's SEDAR+ profile at and EDGAR profile at If any of these risks materialize, the Company's actual results, performance, or achievements could vary significantly from those currently anticipated. Article content Article content Article content Article content Contacts Article content Investor Relations Contact Article content Article content Article content Article content

Pramana Receives Health Canada Authorization for Digital Pathology Scanners
Pramana Receives Health Canada Authorization for Digital Pathology Scanners

National Post

time2 hours ago

  • National Post

Pramana Receives Health Canada Authorization for Digital Pathology Scanners

Article content CAMBRIDGE, Mass. — Pramana, an AI-enabled health tech company modernizing the pathology sector, today announced it has received Health Canada Medical Device Licenses for its flagship digital pathology scanners, the SpectralM and SpectralHT Cubiq systems. The approval authorizes Pramana to import, market, and sell its devices in Canada, expanding access to its advanced imaging and workflow solutions. Article content Health Canada authorization is required to commercialize Class II medical devices and affirms the product's safety, effectiveness, and quality. The approval opens the door for Pramana to support Canadian hospitals, pathology labs, and research institutions, helping modernize diagnostic workflows with scalable, AI-powered digital pathology tools. This recognition marks a critical step in Pramana's international expansion, building on its growing regulatory footprint. Article content 'Receiving Health Canada authorization is a major milestone in our commercialization strategy,' said Prasanth Perugupalli, Chief Product Officer at Pramana. 'It reflects the strength of our product development, quality, and regulatory readiness, and it opens the door to expanding access to our technology in a market known for strong clinical and academic institutions.' Article content Pramana's scanners are designed to digitize a wide range of pathology slides, producing high-resolution whole-slide images with automated quality control and AI-powered decision support. The platform supports both FFPE tissue and Liquid Based Cytology (LBC) samples prepared using methods such as the ThinPrep® Pap test (Hologic) and BD SurePath™ (Becton Dickinson). Unlike most digital pathology systems focused solely on anatomic pathology, Pramana expands digital workflows to include hematopathology, microbiology, and cytology, delivering flexibility across all major slide types. Article content 'Our research at the University of Toronto highlights the need for adaptable platforms that can manage these technical demands while still supporting routine histology and cytology workflows,' said Dr. Carlo Hojilla, Consultant Pathologist at the University of Toronto. 'Pramana's technology meets that standard, and its Health Canada authorization reflects both its clinical utility and the rigorous quality required for widespread adoption.' Article content Prior to receiving Health Canada authorization, Pramana secured Medical Device Single Audit Program (MDSAP) certification, a requirement that validated its quality management system and streamlined regulatory access in Canada, the United States, Brazil, Australia, and Japan, highlighting Pramana's commitment to modernizing digital pathology worldwide. Article content To discover how Pramana's whole-slide imaging solution can help healthcare organizations across Canada, visit Article content About Pramana, Inc. Article content Pramana is a health tech company transforming digital pathology with AI-powered imaging solutions that support seamless adoption across labs, health systems, and medical centers. Pramana's Spectral scanners deliver industry-leading image quality and unprecedented accuracy. Built-in AI algorithms and automated quality control streamline workflows, increase efficiency, and capture previously undetectable tissue features, empowering pathologists with the tools needed to improve clinical diagnostics and research. The company is headquartered in Cambridge, Mass. For more information, visit Article content Article content Article content Article content Article content Article content

DOWNLOAD THE APP

Get Started Now: Download the App

Ready to dive into a world of global content with local flavor? Download Daily8 app today from your preferred app store and start exploring.
app-storeplay-store