クライオ電子顕微鏡を用いてタンパク質の立体構造が次々と解明されています。昨日、東北大学と理化学研究所の、高性能国産クライオ電子顕微鏡(CRYO ARM 300)を用いた共同研究で、アポフェリチン(apoferritin)というタンパク質内のほとんどの水素原子の位置や、化学結合の様子、アミノ酸の示す正負の電荷分布などをなんと1.2Å以下の精度で決定することに成功したという論文が発表されました。アポフェリチンというのは、鉄を運ぶタンパク質ですが、クライオ電顕の性能テストに標準品としてよく使われるので有名なタンパク質です。今回の論文の著者らによる立体構造がこちらに掲載されているので眺めてみてください。 https://pdbj.org/emnavi/quick.php?lang=ja&id=emdb-9890 今回は、高性能のクライオ電子顕微鏡を使って、ついにこのアポフェリチンの立体構造を原子が一個一個見えるほどの精度で決定することができたそうです。タンパク質内に存在するほとんどの水素原子を(上のtwitterの図に緑で示しているように)、球殻としてみることができるようになりました。これは水溶液中のほとんどの水素原子の分布が原子レベルでみられるということで、アミノ酸の水素原子や水素結合の他、タンパク質内の水分子も見えています。結晶化することなくタンパク質の構造がわかるクライオ電子顕微鏡をつかって、水溶液中に存在するタンパク質の立体構造を原子一個一個のレベルで見ることができるのは画期的です。サンプルは凍っているので、生体内の体温で動いている分子の構造とは(水分子の空間分布が水溶液と氷とではがちがうので)同じとはいえません。しかしこの凍結しているタンパク質の構造をもとに、常温でのタンパク質の水和構造や水素結合、プロトン移動反応などを解明するための第一歩がふみだされたのは間違いありません。私達の研究している糖鎖が付加された蛋白質の糖鎖の構造も読めるようになることを期待しています。 Saori Maki-Yonekura, Keisuke Kawakami, Kiyofumi Takaba, Tasuku Hamaguchi, Koji Yonekura, “Measurement of charges and chemical bonding in a cryo-EM structure”, Communications Chemistry, 10.1038/s42004-023-00900-x 論文はこちらからダウンロードできます。https://www.nature.com/articles/s42004-023-00900-x
さて動画の要約ですが、上に述べた三つのプラグインは、英語のpluginなのでどうやら英語のスクリプトを探してそれをもとに要約する仕組みのようです。Video Insightsはさらに動画の長さが60分より短いものでなくては要約できないという制限がありました。 ChatWithVideoのプラグインにはその制限はないようです。ただYouTube以外では要約できないようでした。 実は最近、NIH videocastでOverview of ChatGPT and other Large Language Models and their applications in Biomedicineという動画が公開されています。 https://videocast.nih.gov/watch=49795
これはNIHのサイトでしかまだ見ることができない (もちろんダウンロードはいつものようにできます)ので、上のurlをChatGPTのプロンプトにいれてみました。するとWebpilotが動き出して以下のように要約してくれました。 【私】Could you please summarize the following video? https://videocast.nih.gov/watch=49795 【ChatGPT】Used WebPilot The video titled “Overview of ChatGPT and other Large Language Models and their applications in Biomedicine” is a comprehensive review of Large Language Models (LLMs), focusing on their use in Biomedical and Clinical applications. The talk was given by Dr. Shubo Tian and Dr. Qiao Jin, both of whom are research scientists with extensive experience in the field.
Here’s a brief summary of the video:
Introduction and Overview of LLMs: The talk begins with an introduction to LLMs, particularly focusing on ChatGPT and GPT-4 by OpenAI. These models have garnered significant attention from both the general public and professionals in various domains.
Applications in Biomedicine: The speakers discuss how LLMs can be used in various biomedical and clinical applications. This includes information retrieval, information extraction (such as named entity recognition and relation extraction), entity linking, and health outcome predictions.
Potential and Challenges: The talk also addresses the potential of LLMs in driving innovation and improving outcomes in the biomedical field. It discusses the current challenges in the field and how LLMs can help overcome them.
Case Studies and Examples: The speakers provide examples and case studies to illustrate their points. These include the use of pre-trained language models in biomedicine and the development of benchmarks for evaluating LLMs.
Conclusion and Q&A: The talk concludes with a Q&A session where the speakers answer questions from the audience.
Please note that this is a high-level summary and the actual content may contain more detailed information and nuanced discussions.