Ellarion blog

One of the core tasks that has been completely overtaken by LLMs is reading blocks of text and pulling out the most relevant information. A quick description of a pattern I tend to overuse in this space.

Tabular data remains the last bastion unconquered by deep learning. This might change soon.

If you have a dataset that could be valuable for biomedical research, here are a few key points to consider from our perspective as data integrators and users in research-centric biotech and pharma projects.

We have recently deployed a biomedical LLM system that now helps with finding drugging opportunities for a novel modality. In this post, we share the technical stack we used.

This post tries to explain, using an enormous simplification, the difference between two leading families of data models that are in use in modern data workflows, especially in the context of feeding ML/AI - relational and document/object representations.

For the past several months, we have been finalising the first usable release of a system that we think would remedy some high-impact pain points we have seen in working with data in high-paced bio- and med-tech companies.

Health and clinical data is a central part of understanding the reality of dealing with diseases. The need for it only increases while the access-related challenges make it complicated to acquire. Thankfully due to a recent effort by HDRUK, more and more datasets can be shared.

There is an unprecedented demand for biomedical data both for research and application, driven by the availability of large-scale processing technology and the resurgence of predictive modelling / AI. Given the vast amount of possible sources, how does one know which one they should be using?

There are so many available solutions to website or blog hosting that it almost seems like a non-problem. One does not even need any technical skills to set some of them up. The question remains, how do you decide what to use?