Valence Labs’ Post

Reliable data is the foundation of meaningful method benchmarks. That's why we're thrilled to introduce certification for datasets on Polaris! Certified datasets meet essential curation standards and gain increased visibility on the platform: https://lnkd.in/e3p7K3sf These initial checks lay the groundwork for improved data standards, focusing on: 1. Ensuring real-world relevance 2. Consistency in dataset sources 3. Eliminating obvious duplicates, invalid, or ambiguous data Learn more here: https://lnkd.in/eNjxuy55

Certified datasets on Polaris meet the basic data curation checks that are outlined in our new Datasets 101 page. It's a preliminary resource that we hope will help guide the community toward the development of methods that matter. These basic checks are: 1. The dataset is representative of applications in real-world drug discovery. 2. The dataset is coming from a consistent, original source. 3. The dataset does not contain obvious errors (i.e. duplicates, invalid or ambiguous data) More details and examples about these checks can be found on the page: https://lnkd.in/g6cRinw6 Explore the platform, check out the first two certified datasets, and consider submitting a result to the molecular property prediction (adme-fang) and protein binding (pkis2) benchmarks! I already see some submissions from Dominique Beaini, Frederik Wenkel and the rest of the MolGPS team on the leaderboard 👀 https://lnkd.in/g5XdRuVx

Benchmarks for methods that matter start with reliable data. That’s why we’re excited to introduce certification for datasets on Polaris! Certified datasets meet the criteria for basic curation checks and are more visible on the platform: https://lnkd.in/gVaS2TMh These basic checks serve as a preliminary set of criteria that builds towards better data standards such as: 🧐 Ensuring real-world relevance 📖 Consistent dataset source ❌ No obvious duplicates, invalid, or ambiguous data Datasets 101: https://lnkd.in/gtmdaD3J Explore the first certified datasets and see how they were curated: 1️⃣ ADME-Fang - a DMPK dataset of 6 ADME in vitro endpoints 2️⃣ PKIS2 - kinase dataset for EGFR, RET, KIT, LOK, and SLK (640 small molecules for 468 kinases) Certified datasets pave the way for better benchmarks. There are 13 related benchmarks across the adme-fang and pkis2 datasets. If you’re building models related to molecular property prediction or protein binding, test your performance here! Want to certify your dataset? The submission and review process is done transparently on GitHub. This is early so we’re open for suggestions around the review process! Submit something today: https://lnkd.in/gCyVTRMJ

Hope you can join us for all the great presentations tomorrow to learn how many of us are utilizing AI in pharma to drive innovation in clinical data and analytics!

Cell type annotation is the most critical step in any downstream analysis workflows for single-cell data. To support quick and easy cell type annotation, we have recently integrated #SingleR, a reference-based cell type prediction tool, into the #CDIAM Multi-Omics Studio UI, so that you can get your data annotated with just a few clicks! Want to try it on your scRNA-seq data? Request a trial for CDIAM here: https://lnkd.in/ga5ZQRtk If you are curious to learn more about the latest methods, approaches and challenges of cell type prediction, don't forget to sign up for our upcoming webinar, happening this Mar 6: https://lnkd.in/g_4UX2bE

🚀 Diving Deep into QSAR with the ChEMBL Dataset: Predicting IC50 for Drug Discovery 🧬 Hey there, fellow data science and drug discovery enthusiasts! Today, I'm excited to share my latest blog, where we explore the fascinating world of Quantitative Structure-Activity Relationship (QSAR) modeling using the ChEMBL dataset. 🌍✨ In this post, we focus on predicting IC50 values—a key measure of a drug's potency. Understanding these values is crucial for advancing drug discovery efforts. What is ChEMBL? 🤔 ChEMBL is a large, open-access bioactivity database packed with information on drug-like molecules and their interactions with biological targets. It's a treasure trove of data, making it an invaluable resource for researchers aiming to develop predictive models for drug development. Key Highlights of the Blog: 📝 Loading and Preprocessing Data: Using the chembl_webresource_client to filter for specific assay types and IC50 values. Calculating Molecular Descriptors & Fingerprints: Essential features for our predictive models. Building the QSAR Model: We use a Random Forest Regressor to predict IC50 values effectively. Analyzing Results: Exploring model performance and the significance of MSE in evaluating accuracy. This approach not only helps predict potency but also aligns biological activity with potential therapeutic applications. It’s a holistic strategy for drug discovery! 💊🔬 Check out the full blog for detailed code snippets and insights on how to leverage QSAR modeling for your research. Let’s push the boundaries of drug discovery together! 💡🌟 🔗 Read the full blog on Medium Happy coding! Here's to making the next big breakthrough in drug discovery! 🥳 #QSAR #DrugDiscovery #MachineLearning #DataScience #ChEMBL #Bioinformatics #IC50 #PredictiveModeling #Pharmaceuticals #RDKit #Chemoinformatics

🔬 Visualizing Drug-Protein Interactions with M3 Hive At M3 Hive, we're transforming how researchers and clinicians explore drug interactions. Our advanced Drug Target Profiler platform offers: 1️⃣ Dynamic Interaction Visualizations: Dive deep into drug and protein interactions effortlessly. 2️⃣ Intuitive Exploration: Our user-friendly platform makes it easy for researchers to navigate complex data. 3️⃣ Comprehensive Profiling: Gain valuable insights into clinical statuses, interaction types, and more. 🤝 Collaborate with Us: Enhance your drug therapy research with M3 Hive's state-of-the-art visualization tools. Discover the future of drug therapy research with M3 Hive. Let's innovate together! #DrugResearch #ClinicalResearch #M3Hive #DrugTargetProfiler #m3hive #reprogrammingtheworld #PharmaceuticalInnovation #HealthcareInnovation

We have used #microsampling for over 10 years to collect and analyze small volumes of biofluid from test subjects while still achieving scientifically sound results. In this #webinar our experts share their learnings on the ethical benefits and scientific advantages of microsampling. Watch the webinar: https://okt.to/uU5xp1

🌟 Physiomics' Year-End Results! 🌟 We are pleased to share our year-end presentation with our valued investors and stakeholders! 🎥 In this video, we highlight our accomplishments and financial performance, while focusing on the incredible growth opportunities ahead. Key takeaways include: 👏 Strong Positioning for Growth: By expanding our quantitative pharmacology and data science offerings, we are setting the stage for our next phase of growth. 👏 Launch of Biostatistics Services: With the introduction of our biostatistics services, we are now able to provide clients with a fully integrated, data-driven service offering. This expansion will significantly broaden our business opportunities. 👏 Thriving Market Opportunities: We are operating in an exciting market with increasing demand for our expertise, driven by a shift towards data-driven decision-making in drug development. 🔗 Watch the Presentation Here https://lnkd.in/ekNdK3zR We appreciate your continued support, which has been instrumental in our success. Together, we look forward to driving even greater results in the future. Thank you for being part of our journey! #YearEndResults #InvestorPresentation #BusinessGrowth #DataScience #Biostatistics #Opportunity

Highlights for CGC 2024! We're thrilled to announce our two new posters, shedding light on key developments. Perspectives on FDA’s Final Rule on Laboratory Developed Tests: Our poster provides valuable insights on how Velsera can support labs with regulatory compliance and streamline processes in light of recent FDA LDT final ruling. Learn more: https://lnkd.in/gec24Ywu CGW Plus: A New Standard In Clinical Genomics Reporting: Discover how our Clinical Genomics Workspace (CGW) platform enhances data analysis, reporting, and operational efficiency. Dive into the features that make CGW Plus a game-changer in genomics. Learn more: https://lnkd.in/gi2F6jwq Stop by and explore these innovations and see how Velsera is paving the way for a more efficient and compliant future in clinical genomics! #EraofVelsera #ClinicalGenomics #FDARuling #LDT #CGC2024