Aganitha

🧠 AI-powered solutions for Organoid research 🚀 Organoids help model complex diseases, identify new targets, and test therapeutic candidates. Organoid studies produce a torrent of imaging, omics, and physiological data. 🧬 We at Aganitha are using AI to drive faster processing and analysis of these data streams. Our solutions enable organoid model development, validation, disease modeling, drug efficacy testing, and toxicity evaluation. 🔍 If you are a researcher leveraging organoids, you can know more about what AI can do for you at https://lnkd.in/gmG__QSD #Organoids #DrugDiscovery #AI 💡

🧬 Long-Read Sequencing (LRS), with Oxford Nanopore Technologies (ONT), is proving useful for analyzing tough to nail down quality issues in biosynthesis. 🧬 DNAnexus is enabling user-friendly access to NGS pipelines that process ONT LRS data. 🔗 More about these in our blog at https://lnkd.in/g7SY5zZk #LRS #ONT #DNAnexus #Biosynthesis #NGS #Genomics

Manasvi Sharma, Debleena Guin and Neha Singhal are at CSIR-IGIB today, sharing with fellow genomics researchers, our work at Aganitha.ai bridging DeepScience and DeepTech to accelerate disease research, therapeutic design and clinical affairs.

Last week, my team at Aganitha and I participated in an industry roundtable on "Accelerating drug discovery and development". A question that came our way was: How is generative AI powered drug design different from traditional drug design? There are of course, many differences, and a key one our team emphasized is the ability to factor-in safety and developability concerns upfront during design and not as an afterthought. There was a second key difference our team emphasized. When embarking on generative AI powered drug design exercises, or for that matter, any in silico drug design exercise, prior understanding of target structure and function becomes very important. Given that we are in the era of AlphaFold-like AI powered structure prediction models, this prerequisite does not seem too onerous but like for any step in drug discovery - nothing is as simple as it first seems. 🔗 We wrote more about this topic in a blog. Check it out at

🏥 LLMs in medical affairs #AI is becoming a powerful collaborator for scientists and specialists in #Biopharma. We are illustrating this through a series of blogs. A few weeks ago, we shared how #LLMs can be used in Biopharma R&D. Now, we are sharing examples from medical affairs. Chart review automation has so far been powered by Natural Language Processing (#NLP) with techniques such as named entity extraction, relationship extraction, and negation detection. Resulting automation was limited and fragile as these techniques relied on previous generation ML technologies. Large Language Models (LLMs) are now transforming chart review automation, not only enabling faster and more accurate extraction of relevant clinical information but also expanding the type and scope of information that can be extracted. To see how, read our blog at https://lnkd.in/gZYVKmjw.

Understanding Drug Selectivity: A Computational Perspective Our latest blog explores the role of computational studies in drug design and how molecular dynamics (MD) simulations are transforming our understanding of ligand-receptor interactions.  Siponimod is an FDA-approved drug used for the treatment of relapsing forms of Multiple Sclerosis. It targets sphingosine-1-phosphate receptor 1 (S1PR1), a member of the G Protein-Coupled Receptor (GPCR) family. Interestingly, Siponimod activates S1PR1 but not S1PR2, despite their structural similarity. How does Siponimod achieve this selectivity? Our blog explores the mechanisms behind this phenomenon and highlights how computational approaches can be used to understand drug selectivity. Read the full blog here: https://lnkd.in/eQB6f5Rg #DrugDesign #ComputationalChemistry #MolecularDynamics #DrugSelectivity #Biopharma #InSilicoResearch

Can Biopharma researchers leverage Large Language Models(LLMs)? Making AI your Research Collaborator: Examples from Biopharma 💡 Since OpenAI released ChatGPT 18+ months ago, Generative AI has been transforming productivity across various fields. Programmers benefit from LLM-powered tools like Github Co-pilot, while marketing professionals create content swiftly with Adobe Firefly. In R&D, LLMs are proving to be powerful collaborators for scientists in Biopharma. They are helping researchers for some obvious use cases such as contextual literature searches, going beyond search – answering questions, and helping identify next best actions in specific research contexts. Can we do something more non-trivial/significant with LLMs? Read our blog for such an example, and decide for yourself. 🔍 Read the Full Blog in the link below #Biopharma #ChatGPT #CoPilot #Omics #LLM #Research #R&D #AIinBiopharma

On this #WorldBrainDay let's remember that brain disorders are a major source of suffering globally. With over 3.4 billion people affected by nervous system disorders and 11.1 million deaths annually, advancing research is imperative. This #WBD24, let’s prioritize collaboration and advancement of research. We at Aganitha are humbled to contribute to CNS research. Our recent collaboration with CSIR-CCMB to develop nanobody binders targeting GluD1 receptors is a significant stride for us in neuroscience and pharmacology. These nanobodies might serve as precise molecular tools to modulate GluD1 receptor activity, potentially unlocking novel therapeutic avenues for neurological disorders. Complementing wet lab techniques, in our recent preprint, we analyzed drug selectivity in an approved drug for relapsing forms of Multiple sclerosis. Our work shows that MD powered in silico studies can model and predict selectivity of candidate molecules to GPCRs, the largest family of drugs targeted by approved drugs. #WorldBrainDay 2024 provides an occasion to remind ourselves of the importance of these research activities & collaborations. Research into CNS disorders can alleviate individual suffering & have positive implications for all of humanity.  #WorldBrainDay #Neuroscience #BrainHealth #Aganitha #Biopharma #Innovation #Prevention #Awareness #Collaboration #Education #Advocacy #who #WBD  #CNS #neurological disorders #Alzheimer's #MS #Nanobody #Epilepsy #research

🔬 Decoding GPCR Target Selectivity with Molecular Dynamics We’re delighted to share our research on Siponimod’s selectivity for S1PR1 over S1PR2, now on bioRxiv! 📜 🔍 Background Selectivity in drug design is crucial, especially with homologous off-targets. For relapsing forms of Multiple Sclerosis, activating S1PR1 while avoiding S1PR2 and S1PR3 is key. Fingolimod, the first-in-class drug, avoided S1PR2 but activated S1PR3, causing adverse cardiac effects. A February 2022 Nature Communications article by Liu et al., claimed that the second generation therapeutic for relapsing MS, Siponimod, activates S1PR1 & S1PR5 but does not bind to  S1PR2 due to steric clashes. We tested this hypothesis using bioinformatics, molecular docking, and MD simulations, taking advantage of a cryo-EM structure of S1PR2 bound to its native ligand, S1P, published by Chen et al in March 2022.  🎯 Key Findings Siponimod binds to S1PR2’s active site but doesn’t induce necessary structural changes for activation. The identification of key residues at the active site of S1PR2 revealed interactions that are essential for preventing activation of S1PR2. Our in silico predicted binding affinities matched well with experimentally available  pEC50 values. 📚 Research Impact This work shows that MD powered in silico studies can be used to model and predict selectivity of candidate molecules to GPCRs, the largest family of membrane receptors targeted by approved drugs. 🔗 Read the full preprint at https://lnkd.in/g6bnbM_P 👥 Authors K. Soniya Malik, Chanukya Nanduru and Antarip Halder #MolecularDynamics #Bioinformatics #GPCR #DrugDiscovery

🔬 Unlocking the Power of LLMs in Biopharma with Aganitha’s ARC™ Framework Large Language Models (LLMs) like ChatGPT will transform biomedical research, clinical trials, and medical affairs, but their integration requires strategic solutions. 🔍 Challenges in implementing LLMs for Biopharma 1. Common Pitfalls: Off-the-shelf models may produce hallucinations, struggle with math & stats, and fail to meet stringent Protected Health Information (PHI) requirements. 2. Private data integration: Cannot leverage valuable private data out of the box  3. Operational Hurdles: Training costs and deployment complexities pose significant barriers. 🚀 Aganitha’s Solution: The ARC™ Framework ARC™ combines LLM capabilities with biopharma expertise, offering customized tools and services. - Omics Data Insights: Utilize AI-powered tools to analyze genomic, transcriptomic, and proteomic data. - Hypothesis Generation: Analyze diverse datasets to generate testable hypotheses and discover novel drug targets and biomarkers. - Document workflows: Generate, update, compare and review documents such as regulatory submissions and contracts. - Reduced Hallucination: Minimize inaccurate outputs by incorporating authoritative datasets and ontologies. 👉 📽️ Watch ARC™ demos at https://lnkd.in/gWw5QKQj #Biopharma #AI #LLM #ChatGPT