Computational biologist. ML/AI for biomedical research. Alzheimer's Diseases and knowledge graph. Complex diseases genetics. Pharmacogenomics. https://bsky.app/profile/binglan.bsky.socialhttps://bsky.app/profile/binglan.bsky.social/post/3m3djb226u22rI have mixed feelings about this work. While it's interesting to visualize the impact of scientific works, metrics like patents and funding don't necessarily reflect social and ethical impacts, like cultural shifts. https://www.nature.com/articles/d41586-025-03120-616 Oct 2025 19:41 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3m3djb226u22rhttps://bsky.app/profile/binglan.bsky.social/post/3lz2nmwsjts2yA pleasant read on how Deep Learning models can facilitate the prediction of gene expression levels from DNA sequences. This question led me into the field of computational biology almost 15 years ago. [contains quote post or other embedded content]17 Sep 2025 20:15 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3lz2nmwsjts2yhttps://bsky.app/profile/binglan.bsky.social/post/3lyvg7btpbc2kCan't wait to try out the new features of Biomni. I wonder how these will help democratize scientific data for the whole biomedical community. https://biomni.stanford.edu/blog/sage-biomni-partnership/ https://biomni.stanford.edu/blog/consensus-biomni-partnership/15 Sep 2025 18:19 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3lyvg7btpbc2khttps://bsky.app/profile/binglan.bsky.social/post/3lyizjvrq322nLove how OpenAI's new paper demystifies the origin of LLM hallucination as a result of training and testing. LLMs are rewarded for making confident guesses rather than reporting uncertainty, hence returning guesses (hallucinated responses) in production. https://openai.com/index/why-language-models-hallucinate/10 Sep 2025 20:00 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3lyizjvrq322nhttps://bsky.app/profile/binglan.bsky.social/post/3lydubfumic2dProjects are finally freely available on ChatGPT apps. https://help.openai.com/en/articles/10169521-projects-in-chatgpt08 Sep 2025 18:43 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3lydubfumic2dhttps://bsky.app/profile/binglan.bsky.social/post/3ly23irlihs2tTransferTWAS: A transfer learning framework for cross-tissue transcriptome-wide association study: The American Journal of Human Genetics https://www.cell.com/ajhg/fulltext/S0002-9297%2825%2900236-804 Sep 2025 21:25 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3ly23irlihs2thttps://bsky.app/profile/binglan.bsky.social/post/3ly237ljwys2lGenomics-informed drug-repurposing strategy identifies two therapeutic targets for preventing liver disease associated with metabolic dysfunction: The American Journal of Human Genetics https://www.cell.com/ajhg/fulltext/S0002-9297%2825%2900245-904 Sep 2025 21:20 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3ly237ljwys2lhttps://bsky.app/profile/binglan.bsky.social/post/3lxlclnqw2s2pIt makes sense that parallel agents can improve performance, much like a team of experts can lead to better results. The study also discusses the relationship between costs and the number of agents. https://scalingintelligence.stanford.edu/pubs/codemonkeys/30 Aug 2025 00:22 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3lxlclnqw2s2phttps://bsky.app/profile/binglan.bsky.social/post/3lxks32caes24What it looks like when an agent gets stuck for no reason. It was tasked with creating a .gitignore file, following the GitHub template. It ended up reading a phantom .gitignore file. Any suggestions on how to better prompt the agent? Do I need to break down the task?29 Aug 2025 19:27 +0000at://did:plc:lt377khi4l5a52m72sn7gswg/app.bsky.feed.post/3lxks32caes24