machine learning and AI

Cary, North Carolina–based analytics stalwart SAS has launched SAS Clinical Acceleration, a cloud based software platform designed to help manage clinical trial data, analyze results and prepare regulatory submissions. The modular system combines a content repository with a statistical computing environment so clinical development teams can manage, analyze, report and review clinical and medical data…

In drug discovery, the difference between a breakthrough and a breakdown can be as small as the twist of a bond. Stereochemistry, the three-dimensional arrangement of atoms, governs how otherwise identical molecules behave in the body: whether they bind the intended target, trigger off-targets, or get cleared in minutes rather than hours. “Shape really does…

COVID-19’s grip may have loosened, but its effects on pregnancies linger in data showing higher preterm birth risks for infected mothers. A new analysis from Panalgo, a Norstella company, presented at ICPE 2025, used linked U.S. claims data to match COVID-positive pregnant women against controls. The data revealed a statistically significant increase in preterm deliveries;…

Biomarkers are strategic assets for biopharma companies, significantly improving the success rate of clinical trials1. Yet, discovering them often feels like navigating through a blizzard of unstructured information, searching for the one true signal that can guide the way. While laboratory automation has eased benchwork, the real storm rages in the data, obscuring access to…

While diagnostic pathologists can review scanned slides remotely with AI assistance and instant global collaboration, much of the clinical trial pathology world still ships physical glass slides between labs, dealing with FedEx delays and proprietary file formats. “For exploratory assays, yes, it’s exploding. Everyone’s enjoying artificial intelligence and machine learning for various aspects, but there’s…

AI agents have moved from pilots to practice: 14% of large enterprises report partial or full deployments and 23% are piloting, according to the “Rise of agentic AI” report from Capgemini. But as adoption ticks up, trust in fully autonomous agents slid from 43% to 27% over the past year. What does that mix mean…

Scalability is a common issue facing pharma leaders who have deployed Generative AI (GenAI) applications as a proof of concept (PoC). Many are dazzled by their promise of streamlining staid work processes. Agentic AI and other new GenAI technologies can make PoCs faster and easier to launch, advancing scalability as well as security and development…

A new foundation model called GREmLN from a Columbia and Chan Zuckerberg Biohub team, delivers superior cell-type classification with only 10.3 million parameters, outpacing rivals like the 100-million-parameter scFoundation. Released July 9 on bioRxiv, it taps gene regulatory networks to achieve a 0.929 macro F1 score on immune cell data. “Instead of using large language…

One of the overlooked areas where artificial intelligence (AI) and machine learning (ML) are showing promise is in life sciences instrumentation.  Clearly, AI/ML models hold enormous potential for increasing the speed, accuracy and reliability of drug development, disease research and more. Although use cases for AI vary across the pharmaceutical industry, 59% of pharma and…

2025 was predicted to be the “year of the agent,” referring to the AI technology that can perform autonomous tasks on behalf of a user. And the trends are lining up. “I think agents are already here,” said Raja Shankar, IQVIA’s vice president, machine learning. With adoption gaining ground in retail, financial services, customer service,…

Free-energy perturbation (FEP) has long been pharma’s gold standard for gauging how tightly a small molecule binds its protein target, yet each simulation can take 6 to 24 hours and cost hundreds of dollars. Boltz-2, a new open-source model from MIT and Recursion available on GitHub, delivers FEP-class accuracy in about 18 seconds on a…

Labcorp says it can now move tumor slides at internet speed instead of parcel speed. The diagnostics giant today rolled out a Leica-scanner–based digital-pathology network across its central labs and paired it with new next-generation-sequencing panels and homologous-recombination-deficiency (HRD) testing, a package the company claims will dramatically accelerate biomarker screening for oncology studies, with the potential to significantly…

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…

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…

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…

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…

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,…

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…

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…

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,…

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…

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 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…

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…

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…