https://webinars.biorelate.com/how-to-get-the-best-out-of-rag-for-1 https://webinars.biorelate.com/v.ihtml/player.html?photo_id=109083319 https://webinars.biorelate.com/64968578/109083319/ddf228b98b86f182bb510825237e7f3a/video_medium/how-to-get-the-best-out-of-rag-for-1-video.mp4 https://webinars.biorelate.com/64968578/109083319/ddf228b98b86f182bb510825237e7f3a/small/how-to-get-the-best-out-of-rag-for-1-thumbnail.jpg How to get the best out of RAG for scientific research The webinar will be held Weds Jan 22 2025 at 3.30-4.30pm GMT, 10.30-11.30am EST, 7.30-8.30am PST, 4.30-5.30pm CET Many biopharma organisations are struggling with the challenges of poorly implemented GenAI and RAG, often related to not being able to clearly reference where information has come from and thus not being able to trust the resulting data. How can data quality be better prioritised in RAG implementation? This fireside chat webinar features data science in pharma experts speaking to the perspective of implementing RAG for biopharma research.  Daniel Jamieson, CEO at Biorelate and Michaël Ughetto (Director of AI Strategy & Innovation for R&D IT at AstraZeneca) will dive into the present and future of RAG in scientific research settings. This is a not-to-miss discussion for anyone in data science at biopharma organisations seeking to optimise their RAG strategy and usage. 2025-01-22T16:31:11+00:00 yes 3445 Recordings https://webinars.biorelate.com/building-causal-hypotheses-in-drug-1 https://webinars.biorelate.com/v.ihtml/player.html?photo_id=107475624 https://webinars.biorelate.com/64968569/107475624/2f1ff58017f8c1cc0bf33d90def1f404/video_medium/building-causal-hypotheses-in-drug-1-video.mp4 https://webinars.biorelate.com/64968569/107475624/2f1ff58017f8c1cc0bf33d90def1f404/small/building-causal-hypotheses-in-drug-1-thumbnail.jpg Building causal hypotheses in drug discovery The webinar will be held Thurs Dec 5, 2024, 4-5pm GMT, 5-6pm CET, 11am-12pm EST, 8-9am PST.   A panel discussion with Nicola McCarthy (Head of Research, Milner Therapeutics Institute), Namshik Han (Head of Computational Biology and AI, Milner Therapeutics Institute) and Ben Sidders (Chief Scientific Officer, Biorelate), chaired by Biorelate CEO Daniel Jamieson. In this webinar, drug discovery research experts discuss opportunities to use AI and data driven approaches to create more robust models for developing actionable hypotheses. In particular, we dive into the opportunities for biopharma to make better use of data for developing mechanistic rationales which will improve drug discovery outcomes for drug developers as well as patients. The thought-leading panelists bring expertise across computational biology as well as experimental design, in vitro testing and functional genomics screening. 2024-12-05T17:01:15+00:00 yes 3594 Recordings https://webinars.biorelate.com/full-conference-recording-knowledge https://webinars.biorelate.com/v.ihtml/player.html?photo_id=106117006 https://webinars.biorelate.com/64968568/106117006/84e3177c099c38b185f0b2585c4bf988/video_medium/full-conference-recording-knowledge-video.mp4 https://webinars.biorelate.com/64968568/106117006/84e3177c099c38b185f0b2585c4bf988/small/full-conference-recording-knowledge-thumbnail.jpg Full conference recording: Knowledge Graphs in Drug Discovery p10 Agenda: This conference features 3 talks followed by a panel discussion with the speakers. An Ignorance-Base for Prenatal Nutrition: A Knowledge Graph to Explore the Literature's Known Unknowns Mayla R. Boguslav, Research Associate, Southern California Clinical and Translational Science Institute (USC Keck School of Medicine) Research progresses through accumulating knowledge such that a previously unexplored subject (an unknown unknown) becomes an active research area exploring the questions (known unknowns), until a body of established facts emerges (known knowns). Many knowledge-bases exists for known knowns, but no ignorance-bases exist for known unknowns. What novel connections and insights are in the unknowns? Using a knowledge graph, we created the first ignorance-base for prenatal nutrition to help find pertinent questions that could affect mothers and offspring globally. Knowledge Graphs and Graph Neural Networks for Early Drug Target Characterization Andrei Zinovyev, In Silico R&D Department, Evotec Biomedical knowledge graphs serve as powerful data integration platforms and are widely utilized in early drug discovery by biotech and pharmaceutical companies. Knowledge graphs facilitate efficient retrieval of existing data and augment this with predictive inference, leveraging advanced analytical tools such as graph neural networks (GNNs). In this presentation, we will demonstrate the application of predictive approaches to two representative tasks in drug target characterization. The first application involves the analysis of high-throughput cell imaging, where GNN-based modeling aids in evaluating the novelty of experimentally determined genetic associations. The second application showcases the use of GNNs to develop predictive AI models for early drug target safety assessment (TSA), integrated into Evotec's internally developed TSA platform. Mastering LLMs and Knowledge Graphs Tony Seale, 'The Knowledge Graph Guy' Tony has been passionate about data integration for well over a decade. He has widely shared his creative vision for the widespread use of Large Language Models (LLMs) and Knowledge Graphs in large organisations through his popular weekly LinkedIn posts, earning him the reputation of ‘The Knowledge Graph Guy.’ Tony's interest in AI and Knowledge Graphs began as a secret side project on a computer under his desk while working at Deutsche Bank 10 years ago. By the time he left, he had leveraged the technology to resolve an audit point for double barrier options, provide systematic intelligence across the total FX trade population, and integrate the Fixed Income Derivatives desk. Since then, Tony has delivered several mission-critical Knowledge Graphs into production for Tier 1 investment banks, including architecting the UBS Knowledge Graph. Tony now specialises in the intersection of Large Language Models and Knowledge Graphs, a combination poised to be crucial in the next wave of AI adoption. 2024-11-05T11:09:52+00:00 yes 8837 Recordings https://webinars.biorelate.com/mastering-llms-and-knowledge-graphs https://webinars.biorelate.com/v.ihtml/player.html?photo_id=106117003 https://webinars.biorelate.com/64968568/106117003/0533df249a15c5cd14d1287db2ad875a/video_medium/mastering-llms-and-knowledge-graphs-video.mp4 https://webinars.biorelate.com/64968568/106117003/0533df249a15c5cd14d1287db2ad875a/small/mastering-llms-and-knowledge-graphs-thumbnail.jpg Mastering LLMs and Knowledge Graphs Tony Seale, 'The Knowledge Graph Guy' Tony has been passionate about data integration for well over a decade. He has widely shared his creative vision for the widespread use of Large Language Models (LLMs) and Knowledge Graphs in large organisations through his popular weekly LinkedIn posts, earning him the reputation of ‘The Knowledge Graph Guy.’ Tony's interest in AI and Knowledge Graphs began as a secret side project on a computer under his desk while working at Deutsche Bank 10 years ago. By the time he left, he had leveraged the technology to resolve an audit point for double barrier options, provide systematic intelligence across the total FX trade population, and integrate the Fixed Income Derivatives desk. Since then, Tony has delivered several mission-critical Knowledge Graphs into production for Tier 1 investment banks, including architecting the UBS Knowledge Graph. Tony now specialises in the intersection of Large Language Models and Knowledge Graphs, a combination poised to be crucial in the next wave of AI adoption. 2024-11-05T11:09:46+00:00 yes 1295 Recordings https://webinars.biorelate.com/knowledge-graphs-and-graph-neural https://webinars.biorelate.com/v.ihtml/player.html?photo_id=106117002 https://webinars.biorelate.com/64968568/106117002/2f3f92e3babbbcb2adb7f0a3cd77b9de/video_medium/knowledge-graphs-and-graph-neural-video.mp4 https://webinars.biorelate.com/64968568/106117002/2f3f92e3babbbcb2adb7f0a3cd77b9de/small/knowledge-graphs-and-graph-neural-thumbnail.jpg Knowledge Graphs and Graph Neural Networks for Early Drug Target Characterization Knowledge Graphs and Graph Neural Networks for Early Drug Target Characterization Andrei Zinovyev, In Silico R&D Department, Evotec Biomedical knowledge graphs serve as powerful data integration platforms and are widely utilized in early drug discovery by biotech and pharmaceutical companies. Knowledge graphs facilitate efficient retrieval of existing data and augment this with predictive inference, leveraging advanced analytical tools such as graph neural networks (GNNs). In this presentation, we will demonstrate the application of predictive approaches to two representative tasks in drug target characterization. The first application involves the analysis of high-throughput cell imaging, where GNN-based modeling aids in evaluating the novelty of experimentally determined genetic associations. The second application showcases the use of GNNs to develop predictive AI models for early drug target safety assessment (TSA), integrated into Evotec's internally developed TSA platform. 2024-11-05T11:09:41+00:00 yes 1616 Recordings https://webinars.biorelate.com/an-ignorance-base-for-prenatal https://webinars.biorelate.com/v.ihtml/player.html?photo_id=106116999 https://webinars.biorelate.com/64968568/106116999/84e67178790b67d5957a938522bcc036/video_medium/an-ignorance-base-for-prenatal-video.mp4 https://webinars.biorelate.com/64968568/106116999/84e67178790b67d5957a938522bcc036/small/an-ignorance-base-for-prenatal-thumbnail.jpg An Ignorance-Base for Prenatal Nutrition: A Knowledge Graph to Explore the Literature's Known Unknowns An Ignorance-Base for Prenatal Nutrition: A Knowledge Graph to Explore the Literature's Known Unknowns Mayla R. Boguslav, Research Associate, Southern California Clinical and Translational Science Institute (USC Keck School of Medicine) Research progresses through accumulating knowledge such that a previously unexplored subject (an unknown unknown) becomes an active research area exploring the questions (known unknowns), until a body of established facts emerges (known knowns). Many knowledge-bases exists for known knowns, but no ignorance-bases exist for known unknowns. What novel connections and insights are in the unknowns? Using a knowledge graph, we created the first ignorance-base for prenatal nutrition to help find pertinent questions that could affect mothers and offspring globally. 2024-11-05T11:09:17+00:00 yes 1734 Recordings https://webinars.biorelate.com/large-language-models-in-the-real-2 https://webinars.biorelate.com/v.ihtml/player.html?photo_id=102458754 https://webinars.biorelate.com/64968568/102458754/c49e47df94ba32d83f7246c7e1945f54/video_medium/large-language-models-in-the-real-2-video.mp4 https://webinars.biorelate.com/64968568/102458754/c49e47df94ba32d83f7246c7e1945f54/small/large-language-models-in-the-real-2-thumbnail.jpg Large Language Models in the Real World p2, a Pistoia Alliance and Biorelate co-hosted webinar Following a very well-received panel discussion in March, the speakers return by popular demand to continue the conversation: We know enough about the LLM technology at this time to move it from popular hype into production. We are, however, still at the beginning of this journey. What does biopharma research need to focus on to ensure they are implementing LLMs effectively? How do we benchmark and standardise best practices for LLM usage? Join knowledge management thought leaders from AbbVie, Roche and Biorelate to take the LLM conversation forward from ‘if and why’ to ‘how, what, when and where.’ Join us for our webinar in which the panelists will discuss applications of Large Language Models in pharmaceutical R&D. SPEAKERS: Daniel Jamieson, Biorelate  Etzard Stolte, Roche  Jon Stevens, Abbvie  2024-06-26T17:02:04+00:00 yes 3626 Recordings https://webinars.biorelate.com/miguel-gonalves-astrazeneca-1 https://webinars.biorelate.com/v.ihtml/player.html?photo_id=102097671 https://webinars.biorelate.com/64968561/102097671/ebf7bb25bfe1ceff645646e0b20dca38/video_medium/miguel-gonalves-astrazeneca-1-video.mp4 https://webinars.biorelate.com/64968561/102097671/ebf7bb25bfe1ceff645646e0b20dca38/small/miguel-gonalves-astrazeneca-1-thumbnail.jpg Miguel Gonçalves (AstraZeneca) - Multi-modal Knowledge Graphs for Precision Oncology Multi-modal Knowledge Graphs for Precision Oncology Miguel Gonçalves (AstraZeneca) In this talk, I will go over the work we have been doing with Knowledge Graphs to uncover clinical insights in specific indications via incorporating multi-modal data. I will describe our flexible KG approach and provide examples on how this is making an impact at AZ. Our previous conferences have brought in an average of over 150 attendees each and have featured speakers from organisations including Roche, AstraZeneca, Boehringer Ingelheim, Bayer, Novo Nordisk, and NASA, and many other leading biopharma research leaders. Most recent webinar recordings can be accessed<a href="https://www.gotostage.com/channel/fa31f911674a418ca272a3533209723b"> here </a>and some recordings are also available on <a href="https://www.yo">YouTube</a>. 2024-06-14T10:02:56+00:00 yes 1049 Recordings https://webinars.biorelate.com/knowledge-graphs-in-drug-discovery-2 https://webinars.biorelate.com/v.ihtml/player.html?photo_id=102076804 https://webinars.biorelate.com/64968575/102076804/ed865be441f9e0dce1db1ee6f5043ef2/video_medium/knowledge-graphs-in-drug-discovery-2-video.mp4 https://webinars.biorelate.com/64968575/102076804/ed865be441f9e0dce1db1ee6f5043ef2/small/knowledge-graphs-in-drug-discovery-2-thumbnail.jpg Knowledge Graphs in Drug Discovery part 9 The webinar conference will last approximately 2.5 hours. If you register for the event, you will receive the recording when it is ready via email even if you are unable to attend the live event. Please <a href="https://www.linkedin.com/company/biorelate-limited/">follow Biorelate on LinkedIn </a>for more webinars and data science news. The conference takes place Wednesday, June 12th at 15.00 BST, 16.00 CEST, 10am EST, 9am CDT, 7am PDT. Talks will include: Using Retrieval Augmented Generation Approaches To Gather Information for Drug Discovery Jon Hill (Boehringer Ingelheim) Large language models have captured the public imagination; but how can they be useful for work in drug discovery? What about the risks of introducing false information? This talk will provide an overview of different approaches to using LLMs in a pragmatic way in early research, including the management of hallucination. These models are increasingly accessible to non-AI experts who are aware of their limitations and can improve the speed and comprehensiveness of the information that you bring to your research. Multi-modal Knowledge Graphs for Precision Oncology Miguel Gonçalves (AstraZeneca) In this talk, I will go over the work we have been doing with Knowledge Graphs to uncover clinical insights in specific indications via incorporating multi-modal data. I will describe our flexible KG approach and provide examples on how this is making an impact at AZ. Ask ARCH: LLM Question Answering over Large-Scale Knowledge Graphs Jon Stevens (AbbVie, Inc.) Knowledge graphs provide a vehicle for grounding LLM answers in harmonized structured data, reducing hallucinations and allowing easy fact-checking. In turn, LLMs provide a natural way for end users to query knowledge graph data, without requiring a query language or deep understanding of database structure. We present our integration of AbbVie's 30-million-node R&D knowledge graph, the ARCH Graph, with GPT-based LLMs to create a scientific question-answering system. The ARCH Graph is a Neo4J graph that harmonizes and connects molecules, drugs, genes, health conditions, and other entities from a variety of data sources, allowing scientists to make connections between disparate data points. However, querying the graph can be challenging for end users without a natural language interface. The new Ask ARCH Graph provides such an interface, allowing users to ask questions in natural language (e.g., "What genetic markers are associated with acute myeloid leukemia?") and receive natural language answers ("Some genetic markers associated with acute myeloid leukemia include PICALM (ENSG00000073921), CEBPA (ENSG00000245848), ...") along with the underlying data and the Cypher query used to retrieve it. To achieve this, the system utilizes a combination of vector search, Cypher query generation and validation, and LLM-based summarization of the Cypher output. The process of accurately retrieving information from a large-scale knowledge graph is more complex and less researched than simpler RAG methods on document corpora. We discuss the evolution of our approach and evaluate its accuracy and performance. The integration of LLMs with knowledge graphs helps reduce hallucinations, improve reliability in specialized domains, enhance reasoning with context, and enable dynamic and interactive knowledge discovery. At this virtual free-to-attend conference for the biopharma data professional community, the speakers from across biopharma research give 30-minute presentations on knowledge graphs, NLP, and other related topics of interest to the data science, bioinformatics, computational biology and greater biopharma communities, then at the end, we have a roundtable Q&A session with all of the speakers.  Our previous conferences have brought in an average of over 150 attendees each and have featured speakers from organisations including Roche, AstraZeneca, Boehringer Ingelheim, Bayer, Novo Nordisk, and NASA, and many other leading biopharma research leaders. Most recent webinar recordings can be accessed<a href="https://www.gotostage.com/channel/fa31f911674a418ca272a3533209723b"> here </a>and some recordings are also available on <a href="https://www.yo">YouTube</a>. 2024-06-13T14:21:39+00:00 yes 8857 Recordings https://webinars.biorelate.com/jon-hill-boehringer-ingelheim https://webinars.biorelate.com/v.ihtml/player.html?photo_id=102076714 https://webinars.biorelate.com/64968575/102076714/50c29a2a2f24ce3c56a73c18bb376eca/video_medium/jon-hill-boehringer-ingelheim-video.mp4 https://webinars.biorelate.com/64968575/102076714/50c29a2a2f24ce3c56a73c18bb376eca/small/jon-hill-boehringer-ingelheim-thumbnail.jpg Jon Hill (Boehringer Ingelheim)- Using Retrieval Augmented Generation Approaches To Gather Information for Drug Discovery Using Retrieval Augmented Generation Approaches To Gather Information for Drug Discovery Jon Hill (Boehringer Ingelheim) Large language models have captured the public imagination; but how can they be useful for work in drug discovery? What about the risks of introducing false information? This talk will provide an overview of different approaches to using LLMs in a pragmatic way in early research, including the management of hallucination. These models are increasingly accessible to non-AI experts who are aware of their limitations and can improve the speed and comprehensiveness of the information that you bring to your research. Our previous conferences have brought in an average of over 150 attendees each and have featured speakers from organisations including Roche, AstraZeneca, Boehringer Ingelheim, Bayer, Novo Nordisk, and NASA, and many other leading biopharma research leaders. Most recent webinar recordings can be accessed<a href="https://www.gotostage.com/channel/fa31f911674a418ca272a3533209723b"> here </a>and some recordings are also available on <a href="https://www.yo/">YouTube</a>. 2024-06-13T14:21:36+00:00 yes 2174 Recordings https://webinars.biorelate.com/jon-stevens-abbvie-inc-ask-arch https://webinars.biorelate.com/v.ihtml/player.html?photo_id=102076145 https://webinars.biorelate.com/64968575/102076145/6e9387fe22da579f53bf0a83fe0c4081/video_medium/jon-stevens-abbvie-inc-ask-arch-video.mp4 https://webinars.biorelate.com/64968575/102076145/6e9387fe22da579f53bf0a83fe0c4081/small/jon-stevens-abbvie-inc-ask-arch-thumbnail.jpg Jon Stevens (AbbVie, Inc.) - Ask ARCH: LLM Question Answering over Large-Scale Knowledge Graphs Ask ARCH: LLM Question Answering over Large-Scale Knowledge Graphs Jon Stevens (AbbVie, Inc.)Knowledge graphs provide a vehicle for grounding LLM answers in harmonized structured data, reducing hallucinations and allowing easy fact-checking. In turn, LLMs provide a natural way for end users to query knowledge graph data, without requiring a query language or deep understanding of database structure. We present our integration of AbbVie's 30-million-node R&D knowledge graph, the ARCH Graph, with GPT-based LLMs to create a scientific question-answering system. The ARCH Graph is a Neo4J graph that harmonizes and connects molecules, drugs, genes, health conditions, and other entities from a variety of data sources, allowing scientists to make connections between disparate data points. However, querying the graph can be challenging for end users without a natural language interface. The new Ask ARCH Graph provides such an interface, allowing users to ask questions in natural language (e.g., "What genetic markers are associated with acute myeloid leukemia?") and receive natural language answers ("Some genetic markers associated with acute myeloid leukemia include PICALM (ENSG00000073921), CEBPA (ENSG00000245848), ...") along with the underlying data and the Cypher query used to retrieve it. To achieve this, the system utilizes a combination of vector search, Cypher query generation and validation, and LLM-based summarization of the Cypher output. The process of accurately retrieving information from a large-scale knowledge graph is more complex and less researched than simpler RAG methods on document corpora. We discuss the evolution of our approach and evaluate its accuracy and performance. The integration of LLMs with knowledge graphs helps reduce hallucinations, improve reliability in specialized domains, enhance reasoning with context, and enable dynamic and interactive knowledge discovery. Our previous conferences have brought in an average of over 150 attendees each and have featured speakers from organisations including Roche, AstraZeneca, Boehringer Ingelheim, Bayer, Novo Nordisk, and NASA, and many other leading biopharma research leaders. Most recent webinar recordings can be accessed<a href="https://www.gotostage.com/channel/fa31f911674a418ca272a3533209723b"> here </a>and some recordings are also available on <a href="https://www.yo/">YouTube</a>. 2024-06-13T14:21:13+00:00 yes 1317 Recordings