Machine learning (ML) has become a cornerstone of modern drug discovery. Today, many companies are taking ML developments a step further using generative AI (GenAI) to search for molecules under specific constraints, such as solubility and patent status, and to optimize for desired properties like potential therapeutic success. In doing so, GenAI can enhance the efficiency, speed…
Intrepid Labs raises $7 million to expand AI-driven formulation platform
Toronto-based Intrepid Labs, which we profiled a year ago, has closed an Avant Bio-backed $7 million seed round, bringing its total financing to over $11 million. The company’s Valiant platform is an autonomous lab technology that pairs machine-learning algorithms with robotics to potentially explore up to 1 billion possible formulations. It aims to cut drug-product design…
AI agents could shoulder 55% of biopharma work, Accenture/Wharton study finds
Are AI agents more substance or hype in biopharma? A new report from Accenture and Wharton suggests they are the real deal in biopharma. The two organizations found AI agents, essentially software and physical bots working with minimal oversight, can impact approximately 55% of total workforce hours within a typical biopharma firm. By mapping 300…
Lokavant’s Spectrum turns clinical-trial planning into a live simulation
The clinical-trial intelligence company Lokavant has debuted Spectrum, an AI-powered tool that crunches weeks of feasibility work down to minutes. Pfizer, an early adopter, now refreshes enrollment and timeline projections almost in real time. “Instead of it being five weeks to five minutes, essentially it’s a simulation every five minutes,” said Jonathan Crowther, Pfizer’s head…
Lokavant’s Spectrum v15 uses AI to cut trial-feasibility modeling from weeks to minutes
In an industry where each lost day can drain roughly $40,000 in direct clinical-trial costs, Lokavant says its newly launched Spectrum v15 can crunch data from 500,000 past studies and deliver enrollment forecasts in five minutes, work that typically takes study teams five weeks. The company claims that the platform boasts 80+% confidence. The company,…
University of Miami achieves 10x speedup in HIV drug research with new compute alliance
The ALAFIA AIVAS desktop supercomputer accelerates complex molecular dynamics and AI applications, delivering performance speedups as high as 80-100X for some research applications. Researchers at the University of Miami have achieved a roughly 10x acceleration in complex HIV drug simulations, thanks to a new compute alliance with Miami-based ALAFIA. This dramatic speedup, powered by ALAFIA’s…
How scGPT pioneer Bo Wang, Ph.D. and Xaira’s $1B+ war chest aim to build a ‘virtual cell’
Bo Wang, Ph.D., is a Xairanaut. That is, he’s the latest high-profile scientific leader to join the unicorn Xaira Therapeutics, taking the helm as SVP and Head of Biomedical AI. Wang has experience as Assistant Professor in the Departments of Computer Science and Laboratory Medicine & Pathobiology at the University of Toronto, Temerty Professor in…
Unlocking ‘bench-to-bedside’ discoveries requires better data sharing and collaboration
One of the biggest frustrations for anyone involved in clinical research or patient care is the continued challenges of advancing pre-clinical research into a clinical trial. Likewise, finding and recruiting ideal clinical trial participants for each trial phase, such as those with rare conditions or whose current health condition matches stringent clinical trial inclusion criteria,…
Inside NVIDIA and ConcertAI’s alliance to build AI agents for oncology trials
In 2025, AI “agents” are a growing trend—from coding applications like Claude Code to content retrieval tools like OpenAI’s DeepResearch. But while many organizations are merely wading into these new waters, ConcertAI is diving headfirst alongside NVIDIA. By pairing clinical-grade, multi-modal oncology data with an integrated network of specialized AI “agents” (including a blend of…
How Proscia is using AI embeddings to transform drug discovery in pathology
Picture this: A lung cancer drug candidate was headed for abandonment until AI-powered pathology analysis identified which patients would benefit from it. Using machine learning and digital pathology, the two sponsors backing the candidate built an algorithm capable of distinguishing responders from non-responders to the compound they were developing. “Without that AI model and digital…
COTA Healthcare announces AI milestone in real-world oncology data
COTA Healthcare recently unveiled what it calls a major breakthrough in real-world oncology data (RWD). At the heart of this achievement is a generative AI (GenAI) platform that the company says makes large-scale curation of cancer data both accurate and profitable, marking a significant shift from previous industry attempts to automate the labor-intensive RWD abstraction…
Atropos Health CEO Dr. Brigham Hyde on closing healthcare’s evidence gap with AI-driven insight
As the CEO and cofounder of Atropos Health, Dr. Brigham Hyde is focused on closing the “evidence gap” that frequently arises in modern medicine. While healthcare decisions often boil down to detective work, the pursuit of the best data to guide decisions is sometimes hamstrung by limited or partial guidance from clinical trials or established…
With Deep Research, the CEO of OMNY Health says we’re still ‘in the first inning’ of AI-assisted research
It may not be perfect, but OpenAI’s Deep Research tool can significantly accelerate mundane internet-based research tasks. You give it an assignment, it asks a few follow-up questions, which you reply and there it goes, thinking and researching your query for about five minutes — or as long as half an hour. Built on OpenAI’s…
Flatiron Health sees shift from “what if” to “what is” in real-world evidence in oncology
“The era of ‘what if’ for AI in healthcare is over. Now, it’s all about ‘what is.’ ” So says Blythe Adamson, head of outcomes research and evidence generation at the real-world evidence platform Flatiron Health, a company reimagining cancer care infrastructure. “Post-ChatGPT,” she states, “the skepticism has vanished.” The proof? Flatiron is seeing data…
For sparse data classification, VersAI’s Extreme AutoML is more accurate and orders of magnitude faster than Google’s AutoML
A new AI technology known as VersAI, a proprietary AI technology from Verseon, is challenging the dominance of deep learning—especially in areas where data is scarce. In a recent preprint, Verseon researchers and a colleague at the Missouri University of Science and Technology show that VersAI can train predictive models considerably faster than Google AutoML, based…
How conversational AI can detect pharma safety events
Pharmaceutical manufacturers are tasked with monitoring and reporting safety events (adverse events, product quality complaints, special situations, etc.) to protect patient safety. This process – detecting, documenting, evaluating, reporting, and following up – is essential to meeting regulatory standards and ensuring optimal patient outcomes. However, many of these critical events are not being captured today. …
From Graz to global — Innophore’s journey with NVIDIA’s BioNeMo
When a 30-person Austrian startup gets showcased by Jensen Huang, CEO of the trillion-dollar tech giant NVIDIA, schedules tend to fill up fast. That’s precisely the case for Innophore, a biotech company tapping NVIDIA’s computational clout with its Catalophore platform to accelerate AI-driven drug safety screening and binding-site analysis. This year, the company was highlighted…
NVIDIA allies with IQVIA, Mayo Clinic and Illumina on healthcare AI
NVIDIA today announced at JP Morgan partnerships with IQVIA, Illumina, Mayo Clinic and Arc Institute that center on accelerating biomedical AI across genomics, drug development, and clinical diagnostics. The collaborations aim to tap advanced computing across the healthcare sector, with IQVIA deploying AI agents for clinical trials, Illumina integrating genomic analysis tools, Mayo Clinic developing…
QuantHealth bolsters leadership to accelerate enterprise-grade clinical AI
Tel Aviv-based QuantHealth is on a roll. In August 2024, it surpasses the 100th mark in simulated clinical trials with an 85% accuracy rate and reported cost savings upwards of $215 million for one major pharmaceutical partner. In March of the same year, Fast Company recognized QuantHealth as one of the most innovative companies in…
Merck taps Atropos Health to accelerate real-world evidence generation
Building on existing integrations with cloud leaders AWS and Google Cloud and collaborations with Arcadia and TD2, Atropos Health is now partnering with Merck. This new collaboration will tap Atropos Health’s GENEVA OS (Generative Evidence Acceleration Operating System) and related tools with the aim of speeding the generation of real-world evidence. Under the agreement, Merck’s…
From biology-first AI to structured digital twin adoption, 4 shifts coming to biopharma R&D in 2025
In 2023, the composite success rate for clinical development in biopharma hit its highest level since 2018 thanks to the adoption of novel trial designs, predictive biomarkers, and digital methodologies, according to IQVIA. But waning R&D productivity is a significant industry concern. A substantial number of life science executives believe their organizations need to rethink…
Why scientific AI needs clear lines of sight — especially for fields like drug development
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…
2024: The year AI drug discovery and protein structure prediction took center stage—2025 set to amplify growth
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…
Drug development in 2025: 5 expert predictions cover synthetic data, hybrid trials and more
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…
PathAI launches AI tool for analyzing fibrosis in cancer tissue samples
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…