TetraScience’s Post

"Every business wants to be an AI business" - I had an opportunity to attend the Data AI Summit last week and was blown away by the pace of innovation and the business outcomes the companies can drive for their customers. I put down some of my thoughts in this blog post. I couldn't be more excited about our mission and the platform we are building to help our customers in this journey along with our partner Databricks.

Today, SciLifeLab Serve opens for users to share #MachineLearning models and data science apps. Development of cutting-edge services that enable data-driven life science research are an important part of the SciLifeLab & Wallenberg National Program for #datadriven #lifescience (#DDLS). SciLifeLab Serve https://lnkd.in/dGjpyVwr, is an important part of the SciLifeLab digital infrastructure SciLifeLab Data Centre is building. Over the past year, a pilot testing has been carried out of a prototype of SciLifeLab Serve, and over 70 applications and models have already been shared. -The service is free of charge for #lifescience researchers, and infrastructure, affiliated with a Swedish university or research institution. - Allows users to e.g. share trained #MachineLearning (ML) models with the scientific community or host prototype services (#Gradio, #Streamlit, #FastApi, #Flask etc.) built on top of a trained #ML model as part of the commercialization efforts. - Allows users to host #DataScience applications (#Shiny, #Dash, etc.) -Support from the SciLifeLab Serve team Meet two of our users: ”We have set up our database about the association between the intestinal flora and the plasma metabolome, GutsyAtlas, as an app on SciLifeLab Serve. The app allows for users to create their own tables and figures based on which bacteria or metabolite they are interested in. We received fantastic support from the SciLifeLab Data Centre Serve team in the process. Using SciLifeLab Serve had several advantages for us. Compared to the commercial alternative it was, of course, a lower cost. In addition, Serve also offered more space for data, a reliable Swedish URL and faster server. All of which is important when there are such large amounts of data”, says Tove Fall, professor at the Department of Medical Science at Uppsala University. ”SciLifeLab Serve has allowed us to host the methylR app, a complete tool for Illumina DNA methylation array data analysis, and make it easily available for our users.,” says JYOTIRMOY DAS, Principal Research Engineer, Linköping University and Clinical Genomics Linköping, infrastructure unit at SciLifeLab. Contact the Serve team [email protected]. Read the article here: https://lnkd.in/dh5giVWg SciLifeLab Knut och Alice Wallenbergs Stiftelse

We all know that lab data typically can end up as #datasilos, but it’s the magnitude of this challenge that our conversation with TetraScience elucidated. We’re talking about tens of thousands independent data sources at large companies. Learn how Tetrascience is addressing this bottleneck in our recent briefing, "Liberating Raw Lab Data for AI and Analytics." Check it out. Dr. Daniela Pedersen (Jansen) Mike Tarselli Ken Fountain Axendia, Inc. Daniel Matlis Mónica V. M. Sandra Rodriguez Kelly Doering Robyn Barnes #TetraScience #LifeSciences #DataAnalytics #DigitalTransformation  #ScientificData #AIinLifeSciences #Biopharma #DataReadiness  #ConnectedPlant #LabData #datasilos For additional insights tailored to the Life Sciences industry, please follow Axendia, Inc.

Scientists, are you tired of struggling with broken data and legacy architectures? The key to modern science and AI lies in tearing down the barriers to data adoption and use. Introducing JARVIS, the brand-new approach to integration. Schedule a demo with me today and discover the future of scientific data management. #JARVIS #Science #AI #DataManagement #labautomation #labofthefuture

Thrilled to be attending the Databricks #DataAISummit this week! It's an opportunity to get immersed in the forefront of data and AI, discovering the latest trends, insights, and innovations that are reshaping industries worldwide. I'm also excited to leverage this event to strengthen our #partnership with Databricks. Collaborating closely with industry leaders like Databricks opens doors to new possibilities and enables us to deliver even greater value to our clients. Looking forward to deepening our #alliance and exploring how we can jointly drive innovation in the dynamic landscape of data and AI. #BigData #GenAI #MachineLearning

🙏 Thanks, Pharmexec.com, for covering Domino Data Lab's announcement of the #SCE coalition involving major #biopharma players and of Domino Flows, the solution to automate SCE. If you want to learn more, join us tomorrow in Philadelphia for the #RevX24 #LifeSciences edition, an event dedicated to #datascience and #IT leaders involved in #AI. #generativeAI #GenAI #machinelearning #ml #mlops #EnterpriseAI #AIatscale #ResponsibleAI

Just to check that you remember – Big Data Technology Warsaw Summit 2024 is coming back soon! It will be an amazing, anniversary edition – and you can decide if you want to join in person in Warsaw or online! 🔥 📅 Save the date: April 10 - 11, 2024   What’s most important - I would like to invite you to my presentation 👉 „Don't trust the tip of the iceberg: uncovering the main challenges in replacing lambda with kappa architecture”   I hope you will join us! It's going to be 2 days of an intense journey through the world of BigData and AI! 💡  We shouldn't forget about the anniversary! A special evening meeting awaits us! 😍   If you are still not sure –  ✔️ check the upcoming conference agenda: https://lnkd.in/dySUmEfy Choose the most interesting points of the program and join among the #BigData enthusiasts! 💙   Remember to use the promo code from the banner to receive a 200PLN discount – only until March 15!   I hope to meet you there – April 10-11, 2024! 💥   #BigDataTechnologyWarsawSummit #BigData2024

🚀 Excited to share my latest project in data science: "Predicting Drug Types using Machine Learning!" 📊 Problem Statement: The goal was to create a model capable of predicting the type of drugs based on various patient attributes. The dataset contained information such as age, sex, blood pressure, cholesterol levels, and drug types. 🔍 Exploratory Data Analysis (EDA): Explored the dataset to understand its structure and characteristics. Visualized the distribution of drug types based on gender, blood pressure, and cholesterol levels using insightful plots. Conducted pair plots to identify potential correlations between variables. 🛠️ Data Preprocessing and Feature Engineering: Handled missing values and converted categorical variables into numerical format. Performed feature scaling and power transformation to normalize the data distribution. Utilized pipelines for seamless data preprocessing. 🤖 Model Building: Implemented a Mixed Naive Bayes model to handle mixed data types (both numerical and categorical). Trained the model using the transformed data and evaluated its performance on the test set. 📈 Results: Achieved an accuracy score of [insert accuracy score] on the test data. The classification report demonstrates the model's effectiveness in predicting drug types across different classes. 🔮 Deployment: Developed a pipeline for preprocessing and model creation, which can be easily deployed in real-world applications. Saved the final pipeline and model using pickle for future use. 📝 Looking Forward: Excited to leverage this model in healthcare settings to assist medical professionals in making informed decisions about drug prescriptions. Open to collaborations and further discussions on how to enhance the model's performance and applicability. 🚀 Let's revolutionize healthcare with the power of data science! I have completed this project under the guidance of SAXON K SHA , I'm grateful for the learning opportunities in Innomatics Research Labs . Thank you for helping me grow and explore new horizons in the field of machine learning. Feel free to check out the project and can find the streamlit web application on my GitHub https://lnkd.in/gDgQRMdm #DataScience #MachineLearning #Healthcare #PredictiveAnalytics #DrugClassification

Attention Scientists! Are you tired of struggling with broken data and legacy architectures? Look no further than JARVIS, the brand-new approach to integration. The key to modern science and AI lies in tearing down the barriers to data adoption and use. With JARVIS, you can discover the future of scientific data management. Schedule a demo today and take the first step towards lab automation and the lab of the future. Learn more about why a scientific data management system is crucial for your work at the link below. #JARVIS #Science #AI #DataManagement #labautomation #labofthefuture https://lnkd.in/g8vTiBH3

QUESTION: Why is everybody talking about data curation right now? ANSWER: “Previously, “data aggregation” was the name of the game when it came to monetizing data and a rudimentary perspective on data economics. In the health care sector, we previously believed that data from a single patient or clinician wasn’t valuable or relevant on its own, and we couldn’t really use that type of data anyway due to important regulatory and privacy concerns. Now, we’re in a new era where we’ve realized that patient-specific data can lend itself to really interesting scientific discoveries. Data broker companies that are living in the previous mindset, where volume of data equates to value of data, are about to be left behind. We’re in a new world where distributed data systems, federated learning, and a renewed recognition by patients around the value and ownership of their own data, particularly molecular and genomic data, are enabling new data economic models and accelerated scientific discovery. As a result, data curation and data economics are becoming their own disciplines alongside data science and AI/ML.” - Jennifer Hinkel, Managing Director of The Data Economics Company #DataEconomy #DataAssets #healthdata #patientdata #datascience #lifesciences #data