{"podcast":{"title":"Latent Space: The AI Engineer Podcast","slug":"latent-space-ai-engineer","podcast_index_feed_id":6058902,"rss_url":"https://api.substack.com/feed/podcast/1084089.rss","website_url":"https://www.latent.space/podcast","image_url":"https://substackcdn.com/feed/podcast/1084089/ca7468da5614a246d2906ee8926f6de7.jpg","author":"Latent.Space","episode_count":217,"summary":"The AI Engineer newsletter + Top technical AI podcast. How leading labs build Agents, Models, Infra, & AI for Science. See https://latent.space/about for highlights from Greg Brockman, Andrej Karpathy, George Hotz, Simon Willison, Soumith Chintala et al!","last_synced_at":"2026-08-02T15:06:40.969607+00:00","page_url":"https://stenobird.com/podcast/latent-space-ai-engineer"},"episode":{"title":"🔬Causal Models Need Causal Data - Xaira’s X-Cell model for Drug Discovery (Bo Wang & Ci Chu, Chief Discovery Officer & Chief AI Scientist)","slug":"causal-models-need-causal-data-xaira-s-x-cell-model-for-drug-discovery-bo-wang-ci-chu-chief-discovery-officer-chief-ai-scientist","published_at":"2026-07-21T19:34:06+00:00","page_url":"https://stenobird.com/podcast/latent-space-ai-engineer/causal-models-need-causal-data-xaira-s-x-cell-model-for-drug-discovery-bo-wang-ci-chu-chief-discovery-officer-chief-ai-scientist","show_page_url":"https://stenobird.com/podcast/latent-space-ai-engineer","url":"https://www.latent.space/p/xaira","audio_url":"https://api.substack.com/feed/podcast/207941607/06ca3e4bd112d187109d3b25b2c9d8fc.mp3","summary":"Scaling AI for drug discovery requires moving beyond parameter count to information-rich causal data. Xaira Therapeutics' X-Cell model demonstrates that integrating high-throughput perturbation data allows models to predict how unseen cell lines respond to interventions.","meta_description":"Learn how Xaira Therapeutics uses diffusion language models and causal biological data to build the X-Cell model for predicting cellular responses.","key_points":["Main idea: Scaling laws for biological models are limited by data information content, not just compute or parameters","Technical shift: Moving from auto-regressive models (like scGPT) to diffusion-based architectures allows for better modeling of high-dimensional gene expression as an 'editing' process","Practical takeaway: High-throughput experimentation is essential to generate the causal datasets needed to predict gene expression changes after perturbations","Failure mode: Training on static datasets like CELLxGENE can capture cell states but fails to predict the dynamics of cellular interventions","Future frontier: The next breakthrough in 'virtual cell' modeling depends on longitudinal sequencing technology that can track the same cell over multiple time points"],"chapters":[{"start_ms":60000,"title":"Introduction to Xaira Therapeutics","summary":"An introduction to Bo Wang and Ci Chu and their mission to build an AI-driven drug discovery platform."},{"start_ms":480000,"title":"The Power of Predictive Models","summary":"Discussing the 'wow moment' when models successfully predict responses to unseen cell line perturbations."},{"start_ms":900000,"title":"The Shift to Data-Driven Interventions","summary":"Exploring how the rise of LLMs has influenced the approach to modeling biological interventions."},{"start_ms":1260000,"title":"The Necessity of Causal Data","summary":"Why large-scale datasets like CELLxGENE are foundational but require causal context for true predictive power."},{"start_ms":1680000,"title":"Scaling Perturbation Response","summary":"The challenges and opportunities in using high-throughput techniques to scale biological data collection."},{"start_ms":2520000,"title":"Diffusion vs. Auto-regressive Models","summary":"A technical deep dive into why diffusion models are superior for modeling gene expression as an iterative refinement process."},{"start_ms":3300000,"title":"Validating New Biology","summary":"Discussing the recent results from the X-Cell preprint and the discovery of new biological insights."}],"topics":["Drug Discovery","Diffusion Language Models","Gene Expression","Single-cell RNA sequencing","Causal Inference","Bioinformatics","Xaira Therapeutics","Virtual Cell Models"],"duration_seconds":5387,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/latent-space-ai-engineer/episodes/causal-models-need-causal-data-xaira-s-x-cell-model-for-drug-discovery-bo-wang-ci-chu-chief-discovery-officer-chief-ai-scientist/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/latent-space-ai-engineer/causal-models-need-causal-data-xaira-s-x-cell-model-for-drug-discovery-bo-wang-ci-chu-chief-discovery-officer-chief-ai-scientist.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}