{
  "docId": "019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "docSlug": "8757f1b44ef7f176",
  "documentTitle": "2024 Air Street Capital The State of AI Report 2024",
  "authorId": "AirStreetCapital",
  "authorName": "Air Street Capital",
  "documentKindSlug": "consulting-deck",
  "documentKindLabel": "Consulting deck",
  "sourceTypeSlug": "vc_research",
  "sourceTypeLabel": "VC research",
  "presentationDate": null,
  "orientation": "landscape",
  "aspectRatio": 1.777,
  "pageNumber": 54,
  "pageCount": 213,
  "prevPage": 53,
  "nextPage": 55,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 2,
  "notes": "The slide presents a technical case study on protein structure generation using AI models.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "paragraph",
    "process_diagram",
    "other"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/54",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-54",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "It was also possible to generate soluble analogues of membrane-only folds which could massively speed up drug discovery targeting membrane-bound receptor proteins.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d13-c0028ab52717",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.5,
        "w": 0.4,
        "x": 0.58,
        "y": 0.42
      },
      "kind": "image",
      "text": "Diagrams showing the SCOP database distribution and the AF2-MPNN pipeline workflow.",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9caa6768-3967-4416-8800-00590183ebb5",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.55,
        "x": 0.02,
        "y": 0.42
      },
      "kind": "list",
      "text": "To do so, the authors first use an inverted AF2 model that generates an initial sequence given a target fold structure. These sequences are then optimised by ProteinMPNN before structures are re-predicted by AF2 followed by filtering on the basis of structure similarity to the target structure.\nThis AF2-MPNN pipeline was tested on three challenging folds: IGF, BBF and TBF, which have therapeutic utility.\nIt was also possible to generate soluble analogues of membrane-only folds which could massively speed up drug discovery targeting membrane-bound receptor proteins.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "ba681441-fcc9-430a-99e6-fa65b7da098c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.95,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "paragraph",
      "text": "Characterising and generating structures for proteins that are not found in soluble form but are in membrane environments is challenging and hinders the development of drugs meant to target membrane receptors. So too is the design of protein folds that are large and include non-local topologies. Can AF2 and sequence models remedy this and give drug designers access to a larger soluble proteome with previously inaccessible folds?",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "75621059-7cf1-4b99-91fb-63f2b40f6a4b",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.95,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Expanding the protein function design space: challenging folds and soluble analogues",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "47d3d0dd-c434-4cef-8b7d-e600531c3414",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 153,
      "from": 9,
      "beatId": "019dd95a-0682-776c-8e35-5f2398b8d1d0",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Exec summary + Research + Industry sections inventory the year",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 85,
      "from": 12,
      "beatId": "019dd95a-0682-776c-8e35-6d9d8ee06d0a",
      "arcName": "Voyage and Return",
      "arcSlug": "voyage-return",
      "beatName": "The Unknown",
      "beatSlug": "voyage-return-the-unknown",
      "evidence": "Research section explores frontier model uncharted territory",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Complication",
      "parentBeatSlug": "complication"
    }
  ],
  "loops": [
    {
      "to": 58,
      "from": 45,
      "name": "Zoom In",
      "slug": "06-zoom-in",
      "bestFor": "Technical deep-dives, case studies, detailed analysis",
      "matchId": "019dd95a-07fe-70ce-8d3e-3bc439910222",
      "evidence": "Nobels, AlphaFold3, AlphaProteo, ESM3, gene editors, materials, brain fMRI, speech-from-cortex case studies",
      "position": 7,
      "objective": "Zoom into AI for science domain by domain",
      "structure": "The Big Picture -> Key Area of Focus -> Specific Detail -> Implication",
      "confidence": 80,
      "description": "Start broad, then progressively focus on specific details that prove your point"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}