New AI tool identifies 1,000 ‘questionable’ scientific journals
University of Colorado at Boulder
A team of computer scientists led by the University of Colorado Boulder has developed a new artificial intelligence platform that automatically seeks out “questionable” scientific journals.
The study, published Aug. 27 in the journal “Science Advances,” tackles an alarming trend in the world of research.
Daniel Acuña, lead author of the study and associate professor in the Department of Computer Science, gets a reminder of that several times a week in his email inbox: These spam messages come from people who purport to be editors at scientific journals, usually ones Acuña has never heard of, and offer to publish his papers—for a hefty fee.
Such publications are sometimes referred to as “predatory” journals. They target scientists, convincing them to pay hundreds or even thousands of dollars to publish their research without proper vetting.
“There has been a growing effort among scientists and organizations to vet these journals,” Acuña said. “But it’s like whack-a-mole. You catch one, and then another appears, usually from the same company. They just create a new website and come up with a new name.”
His group’s new AI tool automatically screens scientific journals, evaluating their websites and other online data for certain criteria: Do the journals have an editorial board featuring established researchers? Do their websites contain a lot of grammatical errors?
Acuña emphasizes that the tool isn’t perfect. Ultimately, he thinks human experts, not machines, should make the final call on whether a journal is reputable.
But in an era when prominent figures are questioning the legitimacy of science, stopping the spread of questionable publications has become more important than ever before, he said.
“In science, you don’t start from scratch. You build on top of the research of others,” Acuña said. “So if the foundation of that tower crumbles, then the entire thing collapses.”
The shake down
When scientists submit a new study to a reputable publication, that study usually undergoes a practice called peer review. Outside experts read the study and evaluate it for quality—or, at least, that’s the goal.
A growing number of companies have sought to circumvent that process to turn a profit. In 2009, Jeffrey Beall, a librarian at CU Denver, coined the phrase “predatory” journals to describe these publications.
Often, they target researchers outside of the United States and Europe, such as in China, India and Iran—countries where scientific institutions may be young, and the pressure and incentives for researchers to publish are high.
“They will say, ‘If you pay $500 or $1,000, we will review your paper,’” Acuña said. “In reality, they don’t provide any service. They just take the PDF and post it on their website.”
A few different groups have sought to curb the practice. Among them is a nonprofit organization called the Directory of Open Access Journals (DOAJ). Since 2003, volunteers at the DOAJ have flagged thousands of journals as suspicious based on six criteria. (Reputable publications, for example, tend to include a detailed description of their peer review policies on their websites.)
But keeping pace with the spread of those publications has been daunting for humans.
To speed up the process, Acuña and his colleagues turned to AI. The team trained its system using the DOAJ’s data, then asked the AI to sift through a list of nearly 15,200 open-access journals on the internet.
Among those journals, the AI initially flagged more than 1,400 as potentially problematic.
Acuña and his colleagues asked human experts to review a subset of the suspicious journals. The AI made mistakes, according to the humans, flagging an estimated 350 publications as questionable when they were likely legitimate. That still left more than 1,000 journals that the researchers identified as questionable.
“I think this should be used as a helper to prescreen large numbers of journals,” he said. “But human professionals should do the final analysis.”
A firewall for science
Acuña added that the researchers didn't want their system to be a "black box" like some other AI platforms.
“With ChatGPT, for example, you often don’t understand why it’s suggesting something,” Acuña said. “We tried to make ours as interpretable as possible.”
The team discovered, for example, that questionable journals published an unusually high number of articles. They also included authors with a larger number of affiliations than more legitimate journals, and authors who cited their own research, rather than the research of other scientists, to an unusually high level.
The new AI system isn’t publicly accessible, but the researchers hope to make it available to universities and publishing companies soon. Acuña sees the tool as one way that researchers can protect their fields from bad data—what he calls a “firewall for science.”
“As a computer scientist, I often give the example of when a new smartphone comes out,” he said. “We know the phone's software will have flaws, and we expect bug fixes to come in the future. We should probably do the same with science.”
Co-authors on the study included Han Zhuang at the Eastern Institute of Technology in China and Lizheng Liang at Syracuse University in the United States.
Journal
Science Advances
Article Title
Estimating the predictability of questionable open-access journals
Article Publication Date
27-Aug-2025
Raina Biosciences unveils breakthrough generative AI platform for mRNA therapeutics featured in Science
GEMORNA is world’s first generative AI platform purpose-built for mRNA design and optimization, demonstrating state-of-the-art performance across diverse mRNA therapeutic applications
CAMBRIDGE, Mass., August 28, 2025 – Raina Biosciences Inc., (“Raina”), an mRNA technology and therapeutics company, today announced the publication of data from its generative AI platform in Science. The data supports Raina's pioneering approach to mRNA design using its GEMORNA platform to generate novel sequences with superior drug properties over existing mRNA discovery methods. Founded by a team with deep RNA therapeutics and AI expertise, the Company’s mission is to transform the mRNA-based therapeutics landscape by accelerating drug discovery timelines and opening new therapeutic areas for mRNA with best-in-class AI-designed therapeutics.
The Science article, titled, "Deep generative models design mRNA sequences with enhanced translational capacity and stability," marks a significant landmark for optimizing novel mRNAs with enhanced expression and durability to facilitate a wide range of therapeutic mRNA applications.
The article, which was published online today by the journal Science, is summarized as follows:
- Raina’s GEMORNA platform designs superior linear and circular mRNA drug molecules with optimized expression levels and durability, addressing two major issues that have limited the effectiveness of mRNA-based therapeutics
- GEMORNA is highly differentiated from prior RNA language models developed for predictive tasks through its direct design of novel sequences from a near infinite design space
- GEMORNA-generated mRNAs:
- Elicited significantly higher immune response in mice compared to a leading commercially available mRNA vaccine sequence, potentially supporting mRNA therapeutic vaccine applications for diseases such as cancer
- Achieved up to a 150-fold increase in human erythropoietin (hEPO) expression compared to an optimized benchmark, potentially supporting mRNA medicines for gene therapy
- Demonstrated a 5-fold increase in CD19 CAR expression and a 2-fold improvement in durability compared to a patented benchmark, resulting in nearly 100% anti-tumor efficacy in primary human T cells, potentially supporting mRNA therapies for in vivo CAR-T
"Raina’s GEMORNA platform is built upon a decade of the team’s foundational work in synthetic biology and artificial intelligence," said Jicong Cao, Ph.D., Chief Executive Officer and co-founder of Raina Biosciences, and corresponding author of the Science paper. "We are excited to work with industry-leading pharma and biotech companies to expand the usage of mRNA-based therapeutics while we prepare to build an internal pipeline."
"Raina has the potential to transform mRNA therapeutics by rapidly and reliably generating novel sequences with greater performance, precision and efficacy," said Timothy Lu, M.D., Ph.D., Raina’s Chairman of the Board and former MIT faculty member. "The GEMORNA platform could be a sea change for biopharma companies pursuing mRNA-based medicines beyond traditional infectious disease vaccines ranging from neoantigen cancer vaccines, in vivo CARs, to gene editing or gene therapy applications."
The Science publication can be found here.
Based in Boston, Raina Biosciences is a spinout company from the Massachusetts Institute of Technology (MIT), founded by leaders in mRNA and AI with a strong track record in the biotech industry. Jicong Cao, Ph.D. (co-founder, Chief Executive Officer) is a former mRNA researcher at MIT and co-founder of Bota Biosciences. He Zhang, Ph.D. (co-founder, Chief Technology Officer and first author of the Science paper) was previously a Senior Staff Scientist at Baidu Research. Timothy Lu, M.D., Ph.D., Raina’s co-founder and Chairman of the Board, is a serial biotech entrepreneur having co-founded a number of biotechnology and biopharmaceutical companies, and served on the MIT faculty from 2010–2022. Joel Edwards, Chief Corporate Development Officer, brings over 25 years of leadership in corporate strategy and deal-making across biotech, including his tenure as Vice President of Corporate Strategy at Ionis Pharmaceuticals. Raina is also supported by its key scientific advisor Jeff Coller, Ph.D., Bloomberg Distinguished Professor and Inaugural Director of the RNA Innovation Center at Johns Hopkins University. Raina closed an angel round of $5.7 million upon company formation.
About Raina Biosciences
Raina is pioneering the world's first and leading generative AI platform for mRNA-based therapeutics. Using its proprietary platform, GEMORNA, Raina navigates new frontiers in mRNA engineering to design sequences with optimal profiles for expression, durability, and stability. Raina is partnering with leading pharma and biotech companies to create next generation and best-in-class mRNA-based therapeutics. To learn more about Raina Biosciences visit www.rainabio.com and follow us on LinkedIn.
Media Contact:
Kelli Perkins
kelli@redhousecomms.com
Journal
Science
Method of Research
Experimental study
Subject of Research
Animals
Article Title
Deep generative models design mRNA sequences with enhanced translational capacity and stability
Article Publication Date
28-Aug-2025
No comments:
Post a Comment