Barbara Killian’s Post

Below is a great article discussing how #logica can accelerate a client's drug discovery pipeline by deploying a combination of AI/ML and wet science approaches. #ai #aidrugdiscovery

Learn how AI is revolutionizing drug discovery. Discover how Valo Health and Charles River Laboratories are infusing AI and human-centric data into the process to find innovative drug candidates faster and more efficiently. Read more in this Nature article. https://okt.to/vCDyde

Creating structured and standardised data, and implementing the tools to effectively manage this is a key step in successful implementation of AI. Great to be partnering with L7 Informatics on supporting our mutual customers achieve this goal as a precursor to successful AI implementation. I look forward to reading this and the rest of the blog series. #ontologies #AI #LLM #datascience #ELN

This is a great piece by our very own Brigitte Ganter, Ph.D., digging into how ESP builds the infrastructure and access to contextualized and curated life science data, to accelerate and support your Machine learning and AI aspirations.

Missed our webinar on how to successfully implement AI in drug discovery with panel insights from John Overington, Darren Green and Matthew Segall? No worries - you can catch up whenever you like with our recording! https://lnkd.in/dG9PwRFB #ArtificialIntelligence #MachineLearning #DrugDiscovery

“To derive high-value insights from an AI model requires high-quality and contextualized data as an input”…SciBite's partner L7 Informatics emphasizes the importance of well-managed, structured, and standardized data as foundational for successful AI applications. #Ontologies are a key contributor to #dataquality.

A nice tour de force around AI in drug discovery with a panel having veterans & new age academic-industry experts working with AI to see where in drug discovery and development value chain it can make an impact. There is hype but there are also promises but one important thing, no AI can do magic if your assays are non-optimal & knowledge bases are limited, doesn’t matter how much we can churn out hits from it. Some very nice discussion to say where it is working, where it needs more time, where we have too much hype, and that it’s not a one stop solution which will work for all therapy areas. Sadly it won’t as we don’t have enough data in some areas. We need to think of it as an enablement & empowering tool for humans receiving assistance to accelerate & de-risk drug discovery & development phases. 😉

In the race to develop life-saving protein drugs faster, AI is the game-changer. But here's the secret ingredient: annotated data. Why? Because behind every successful drug candidate lies a wealth of annotated data. By feeding AI models with this rich dataset, we amplify their predictive power. AI is not just accelerating drug discovery, but also revolutionizing it. 👉 https://lnkd.in/dMMhCadD #aiindrugdiscovery #aiinmedicnies #dataannotation #medicaldata #healthcare

In that cultural moment when ChatGPT burst onto the scene, it caught most of us by surprise. The domain of ML/NLP was reserved to the extremely technical and successful use cases were few and far between, especially in the Regulatory and Quality domains of Life Sciences. This white paper is a great read if you are looking to get caught up on the past 70 (!) years of AI development with a view to where things are going. And definitely follow Ennov for more in this space!

AI for target discovery: the start of a long road. In the fifth and final article in BioCentury's Back to School 2024, Editor in Chief Simone Fishburn and colleague write that investments in AI in drug discovery are picking up, as the picture starts to form of how target discovery may benefit