{
  "docId": "019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "docSlug": "bf350dd574c19997",
  "documentTitle": "2021 Air Street Capital The State of AI Report 2021",
  "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": 26,
  "pageCount": 188,
  "prevPage": 25,
  "nextPage": 27,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "dense",
  "nDataPoints": 0,
  "notes": "The slide contrasts a traditional 'Brute Force' approach with a 'MolPAL' (Molecular Pool-based Active Learning) approach.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "process_diagram"
  ],
  "metadataConfidence": 0.95,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-fd5012384ae3/26",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-fd5012384ae3#slide-26",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Deep learning models can learn drug-protein binding relationships from a small number of empirical experiments in order to help prioritise which areas of vast chemical spaces to virtually screen.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c3-7407-8d2b-4d8ae2e7d7c9",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.5,
        "w": 0.35,
        "x": 0.63,
        "y": 0.35
      },
      "kind": "image",
      "text": "Comparison diagram of Brute Force vs MolPAL process",
      "attrs": null,
      "subkind": "infographic",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "11fbb831-11c9-4a2e-94e0-ea2d4f158ce3",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.55,
        "w": 0.6,
        "x": 0.02,
        "y": 0.31
      },
      "kind": "list",
      "text": "Structure-based drug discovery searches for drugs that bind a protein of interest whose 3D structure is available. This process, referred to as “docking”, can be run virtually using simulations. However, with databases of small molecule chemicals exploding past billions of records, virtually screening all combinations becomes computationally and commercially intractable.\nA solution is to train a model on a sample of drug-protein interactions with empirically determined docking scores.\nThis model can be used to virtually score a library of interest, followed by docking the top scoring drug candidates. These results are used to update the model with active learning. With several iterations, model-guided search ultimately generates hits faster.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "dad2175a-15a5-48d1-9b11-d31fe71a5ed6",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.07,
        "w": 0.6,
        "x": 0.02,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "Deep learning models can learn drug-protein binding relationships from a small number of empirical experiments in order to help prioritise which areas of vast chemical spaces to virtually screen.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "1c80f75b-6cdd-4f8f-bd69-5819d075536a",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.6,
        "x": 0.02,
        "y": 0.14
      },
      "kind": "title",
      "text": "Accelerating high-throughput virtual drug screening with model-guided search",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a44c1e82-5623-4fec-916f-e127b2fdb8f8",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Problem-Agitate-Solve (PAS)",
      "slug": "problem-agitate-solve-pas",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "17d53d88-1139-4059-bb12-ab158895a490",
      "evidence": "The slide presents a problem (virtual drug screening), agitates it (by highlighting the challenges), and offers a solution (model-guided search).",
      "confidence": 0.6
    }
  ],
  "frameworks": [
    {
      "name": "active-learning",
      "slug": null,
      "matchId": "0c990d14-6cec-480c-856d-9a9868ca2189",
      "evidence": "The slide describes using model-guided search and updating the model with results from docking top candidates.",
      "confidence": 0.9
    }
  ],
  "arcBeats": [
    {
      "to": 152,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-0affbadec38e",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions p.5-6, Exec Summary p.7, then Sections 1-3 catalog evidence.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 152,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e35-1b3ee3a1c012",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Three sections accumulating evidence of accelerating progress.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 27,
      "from": 19,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-4a8c359eb5db",
      "evidence": "AlphaFold2 -> protein generation -> RNA structure -> cryo-EM -> drug screening; consistent pattern.",
      "position": 3,
      "objective": "Demonstrate AI's expansion into structural biology and drug discovery",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 80,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}