{
  "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": 48,
  "pageCount": 213,
  "prevPage": 47,
  "nextPage": 49,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 16,
  "notes": "The slide highlights the importance of in silico filtering in protein design and compares AlphaProteo's performance against previous methods across various targets.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "process_diagram",
    "bar_chart_grouped"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-0856e1444fb9/48",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-0856e1444fb9#slide-48",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "The model was able to design protein binders with 3- to 300-fold better binding affinities than previous works (e.g. RFDiffusion).",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d12-76e51b9b1452",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.3,
        "x": 0.65,
        "y": 0.55
      },
      "kind": "chart",
      "text": "Experimental success rate comparison across targets (BHRF1, SC2RBD, IL-7RA, PD-L1, TrkA, IL-17A, VEGF-A, TNFα)",
      "attrs": null,
      "subkind": "bar-grouped",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c54e5079-8bf6-48d8-9a07-c5a57ef95dd7",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.3,
        "x": 0.65,
        "y": 0.25
      },
      "kind": "diagram",
      "text": "AlphaProteo workflow: Generator -> Filter -> Experiment -> Confirmed/Predicted binders",
      "attrs": null,
      "subkind": "process",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "4501e0d1-e4e6-4be6-b633-93fd594e2b40",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.6,
        "w": 0.6,
        "x": 0.02,
        "y": 0.22
      },
      "kind": "list",
      "text": "The secretive protein design team at DeepMind finally “came out of stealth” with their first model AlphaProteo, a generative model that is able to design sub-nanomolar protein binders with 3- to 300-fold better affinities.\nWhile few technical details were given, it seems it was built on top of AlphaFold3 and is likely a diffusion model. ‘Hotspots’ on the target epitope can also be specified.\nThe model was able to design protein binders with 3- to 300-fold better binding affinities than previous works (e.g. RFDiffusion).\nThe “dirty secret” of the protein design field is that the in silico filtering is just as (if not more) important than the generative modelling, with the paper suggesting that AF3-based scoring is key.\nThey also use their confidence metrics to screen a large number of possible novel targets for which future protein binders could be designed.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "1fe5f2e0-6665-4453-8409-3871dd0dffda",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Experimental success rate: 300-fold",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d12-7811a40a3ddd",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.6,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "AlphaProteo: DeepMind flexes new experimental biology capabilities",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "fb83ca29-93bd-46de-b349-3871f9fce87d",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Action Titles",
      "slug": "action-titles",
      "agent": "Architect",
      "layer": "slide",
      "matchId": "019dd95a-1055-74e0-a958-efa255f38a80",
      "evidence": "Title 'AlphaProteo: DeepMind flexes new experimental biology capabilities'",
      "confidence": 85
    },
    {
      "name": "Waterfall chart",
      "slug": "waterfall-chart",
      "agent": null,
      "layer": "slide",
      "matchId": "d2b45c62-71e3-4257-b0d5-9740b6eaade7",
      "evidence": "Experimental success rate comparison across targets",
      "confidence": 0.7
    }
  ],
  "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
}