Andrii Buvailo, PhD

A recent study conducted by Indivumed Therapeutics highlights a crucial, yet often overlooked, factor in cancer research: the cold ischemia time (CIT), or the time it takes to preserve tumor tissues after surgical removal. This seemingly technical detail—whether tissue samples are snap-frozen within 10 minutes or after a longer delay—can profoundly alter the molecular characteristics of the samples, which in turn impacts the discovery of new cancer drug targets.

The findings, published in Cell Death & Disease, reveal that even short delays in preservation can lead to significant shifts in gene expression and protein activity, complicating efforts to accurately identify novel drug targets. This research underscores the importance of rapid tissue handling protocols for ensuring the reliability of molecular data, a critical step in precision oncology.

Immunai, a New York-based AI biotech company, has entered a multi-year collaboration with AstraZeneca to optimize oncology clinical trials. This partnership will use Immunai’s proprietary AMICA platform and Immunodynamics Engine (IDE)—technologies combining multi-omic single-cell data and advanced AI models of the immune system—to improve trial design and clinical decision-making.

What does aging have in common with pathogens like bacteria and viruses? And how does the quest to tackle antimicrobial drug resistance -- an alarmingly growing healthcare crisis in its own right -- may also be a potential game changer for aging research?

Foundation models represent a new paradigm in artificial intelligence (AI), revolutionizing how machine learning models are developed and deployed. As these models grow increasingly capable, they become useful for applications across a wide range of economic functions and industries, including biotech. Foundation models are a class of large-scale machine learning models, typically based on deep learning architectures such as transformers, that are trained on massive datasets encompassing diverse types of data. The most prominent examples of general-purpose foundation models are the GPT-3 and GPT-4 models, which form the basis of ChatGPT, and BERT, or Bidirectional Encoder Representations from Transformers. These are gigantic models trained on enormous volumes of data, often in a self-supervised or unsupervised manner (without the need for labeled data).

Their scalability in terms of both model size and data volume enables them to capture intricate patterns and dependencies within the data. The pre-training phase of foundation models imparts them with a broad knowledge base, making them highly efficient in few-shot or zero-shot learning scenarios where minimal labeled data is available for specific tasks.

This approach demonstrates their high versatility and transfer learning capabilities, adapting to the nuances of particular challenges through additional training.

Below we summarized a number of companies building domain-specific foundation models for biology research and related areas, like chemistry.

Roche has announced an expansion of its Digital Pathology Open Environment, integrating over 20 artificial intelligence (AI) algorithms from eight new collaborators into its navify® Digital Pathology platform. This move is aimed at improving cancer diagnosis by using AI-driven image analysis tools that support pathologists in analyzing tissue samples more accurately, particularly for cancer-related diagnostics and research. The expansion aligns with Roche’s strategy to leverage its control over upstream hardware and software, offering a platform that facilitates integration with third-party AI tools.

As the demand for decentralized and hybrid clinical trials rises, Medable Inc. is positioning itself at the forefront of this transformation. Known for its cloud-based platform, Medable has facilitated over 300 decentralized and hybrid clinical trials in 60 countries, serving more than one million patients and research participants. The company’s software-as-a-service (SaaS) model has demonstrated impressive results, with customers reporting 200% faster patient enrollment and a 50% reduction in trial costs. Now, with the launch of Medable Studio, a no-code platform that drastically reduces trial setup times from months to hours, the company is looking to further streamline the clinical trial process.

At the core of Medable's mission is addressing the inefficiencies that have long plagued traditional clinical trials—delays in site activations, complicated vendor hand-offs, and opaque timelines.

Tim Smith, Co-Founder and Chief Technology Officer at Medable, has been integral to this mission, leading the company’s efforts to empower sponsors with more control and transparency. In this interview, Tim sheds light on the challenges in clinical trials, the innovation behind Medable Studio, and the future potential of digital tools in accelerating the development of new therapies.

(Last Update: May, 2024, by adding Labviva and more)

A life sciences marketplace is an online platform that operates with a "many-to-many" business logic, hosting multiple suppliers and buyers interacting via various e-commerce tools available as part of the website's functionality.

(Updated: 2.09.2024)

Nowadays mobile devices are ubiquitous with an estimated number of smartphones and tablet PCs to exceed two billion globally.

The availability of internet connection in most public places, powerful processors, and user-friendly touch screen technologies make mobile devices useful not only for spare time activities but also for education and science.

Noetik, an emerging biotech firm specializing in the application of artificial intelligence (AI) to oncology, has announced the successful closure of a $40 million Series A financing round. The funding will support the company's efforts to advance its precision cancer therapies, leveraging its proprietary machine learning platforms and extensive spatial omics datasets.

Researchers at the University of Queensland have identified a crucial mechanism in mitochondrial DNA (mtDNA) that helps regulate the inheritance of disease-causing mutations. This mechanism involves a chemical modification called adenine methylation (6mA), which the study found to be vital in controlling mutation accumulation in mtDNA. Mitochondrial DNA, inherited exclusively from mothers, is essential for cellular energy production and is known to mutate as we age, contributing to diseases such as dementia, cancer, and diabetes.