machine learning and AI

Today’s large language models can be as unreliable as they are eloquent. Their tendency to fabricate facts and lose the thread makes them risky tools for scientific research, especially in highly regulated industries like pharmaceuticals and chemistry. They also struggle to provide sources and will fabricate a bogus academic journal without batting an eye. Speaking…

The global AI drug discovery market, valued around $1 to $1.7 billion in 2023, will be worth a multiple of that by the decade’s end. Analysts project the sector could be worth $9 billion or more. 2024 Nobel Prize in Chemistry Recipients: David Baker Demis Hassabis John Jumper Achievement: Computational protein design and structure prediction…

In 2024, we saw the expanded use of synthetic data and natural language processing transform drug discovery and development. In a batch of predictions published in December of 2023, one expert predicted that synthetic data was set to “take off” in drug research. In 2025, the pendulum could begin swinging back the other way, according…

The digital pathology firm PathAI has released PathExplore Fibrosis, an AI-based tool that analyzes fibrosis and collagen structures from H&E-stained whole-slide tissue images. The software quantifies fibrotic areas and collagen fibers from standard pathology slides, replacing specialized staining techniques and microscopy equipment. The tool processes large datasets of tissue images, designed to work with existing…

Pharmaceutical companies could slash their pharmacovigilance costs by half while significantly improving accuracy through generative AI, according to IQVIA’s Global Practice Lead of Pharmacovigilance Technologies, Uwe Trinks. “The idea is: we can save 50% of the cost and get the quality to above 99%,” Trinks said. “That means when we have human verification, we only…

The conceptual and technological underpinnings of digital pathology have been around for decades, with the virtual microscope emerging in the 1990s. But mainstream adoption remained elusive. For instance, when the digital histopathology service company HistoWiz launched in 2013, its focus was straightforward: provide faster turnaround times than traditional histology labs. Over the years, the company…

While many AI companies focus on analyzing existing scientific literature, this approach faces a fundamental challenge: the reliability of the source material itself. “Up to 70% of experiments described in publications cannot be replicated,” notes Yochi Slonim, CEO of Anima Biotech. “You do it once and you publish it. You do it again, it doesn’t…

Swiss pharma giants Novartis and Roche consistently rank among the top pharma companies in terms of revenue. In 2024, the two companies are also leading in total international patent volume. Meanwhile, smaller firms like Incyte and Vertex Pharma are punching above their weight in market impact. For instance, Incyte, with a market cap of just…

Clinical trials are notoriously expensive, with Phase 3 studies costing upwards of around $55,000 per day and completed trials routinely costing in the tens of millions of dollars. The startup Unlearn aims to chip away at those costs using digital twin technology, a concept pioneered by NASA during the Apollo era to create ‘living models’…

Breast cancer is the most common cancer for women in the nation, with over 300,000 new cases expected to be diagnosed this year. While the narrative for breast cancer early detection centers around mammograms, the gold standard for diagnosis, clinicians have tapped into enhancing radiology and X-ray imaging using artificial intelligence (AI). This AI-enhanced approach…

ChatGPT may be one of the quickest adopted tech platforms in recent memory, but the potential of it and other large language models ability transform the world has also been met with occasional provider outages, hallucinations, and memory problems. “There’s a lot of resentment towards the hype,” notes Christopher M. McSpiritt, head of life sciences…

Honeywell and Salesforce have announced an expansion of their strategic alliance to deliver an enhanced software platform tailored for the life sciences industry. This expanded platform integrates Honeywell’s TrackWise Quality suite with Salesforce Life Sciences Cloud, Agentforce, Data Cloud, Analytics, and other solutions, aiming to expedite the delivery of vital medications and healthcare devices to…

Traditionally, only a small fraction of oncology drugs make it from phase 1 to commercialization. And biopharmaceutical companies continue to face significant challenges in understanding how new oncology drug approvals affect treatment patterns and market share. To deal with such hurdles, Oracle has recently launched CancerMPact Treatment Architecture Trends (PDF overview here), a resource that…

Researchers at Cleveland Clinic’s Global Center for Immunotherapy, in collaboration with Bristol Myers Squibb, have published a comprehensive study on how the immune system remodels the tumor microenvironment in response to immune checkpoint therapy. This research represents the most detailed analysis of this process to date. Under the leadership of Timothy Chan, MD, PhD, Chair…

Let’s face it: Cloud-based High-Performance Computing (HPC) offers unprecedented computational power. These systems can perform quadrillions of calculations per second. But that computational horsepower comes at a price – not just financially, but in the form of a steep learning curve and a constant battle against configuration headaches, unpredictable costs, and delays. For researchers working…

Boston-based DeepCure may be an AI-focused biotech, but it sets itself apart by focusing its AI-powered platform on historically challenging drug targets that have eluded traditional approaches. “While AI in drug discovery is often viewed as a means to accelerate and reduce costs, our focus at DeepCure is on achieving true novelty in drug development…

Redwood City, California–based Earli is, in many ways, a quintessential Silicon Valley startup. As is often the case, there’s not only a Stanford connection but a grand ambition. The company is developing a “synthetic biopsy” platform that aims to detect cancer at its earliest stages by programming cancer cells to reveal themselves and even self-destruct.…

 “Nearly all diseases stem from a molecular mechanism going wrong,” writes Sergei Yakneen, chief technology officer of Alphabet’s Isomorphic Labs in a recent blog post. “Whether it’s an infectious agent disrupting our cellular machinery or a breakdown in processes like DNA repair, identifying the right protein and finding molecules to interact with it is…

Google Cloud’s Shweta Maniar is on a mission to revamp drug discovery with the power of generative AI, the trendy type of AI that can create new content. The tech is well-suited for a range of applications in drug discovery and across the life sciences. Whether it’s supporting organizations in their drug discovery efforts or…

Alzheimer’s clinical trials are among the most challenging and expensive studies to conduct with a 2021 study pegging the total costs since 1995 at $42.5 billion. Phase 3 trials are the biggest cost drivers, involving hundreds or thousands of participants. “We’re talking about studies with sometimes two thousand people per phase three clinical trial in…

QuantHealth, an AI-focused clinical trial design company based out of Tel Aviv, has announced the completion of more than 100 simulated clinical trials, reporting an 85% accuracy rate. The company, which received $17 million in a Series A funding round with backing from Accenture, aims to chip away at the steep costs and stubborn timelines…

Recursion Pharmaceuticals and Exscientia, two of the most prominent AI-driven drug discovery companies, are merging. The deal, which the firms expect to be official in early 2025, would create a portfolio of clinical and near-clinical programs with an expected 10 clinical readouts over the the next 18 months with “peak sales opportunities in excess of…

Two years ago, Deep Genomics was juggling about 40 different machine learning models to decode RNA biology. Now, they’ve revamped their approach with a single, powerful AI system known as BigRNA. This foundation model is capable of predicting how genes behave in different tissues, how they’re spliced, and how they interact with other cellular components…

When it comes to medical AI, the biggest names aren’t necessarily delivering the best results. While tech giants race to build ever-larger language models, a new preprint reveals that when it comes to clinical accuracy and physician trust, a smaller player is outperforming the industry heavyweights. Putting large language model-based systems to the test Researchers…

As a journalist interested in decoding AI and its impact on the research landscape, I recently took Insilico Medicine’s DORA (Draft Outline Research Assistant) for a test drive, a new platform summarized here. DORA, a specialized agentic-based tool aims to draft scientific content while promising to slash the time and effort required to produce first…