{
  "docId": "019dd923-5e88-73ef-bd5c-f812573a947a",
  "docSlug": "eea7524c557036f4",
  "documentTitle": "2020 Air Street Capital The State of AI Report 2020",
  "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": 38,
  "pageCount": 177,
  "prevPage": 37,
  "nextPage": 39,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "overcrowded",
  "nDataPoints": 40,
  "notes": "The slide uses a combination of box plots for distribution visualization and a summary table for performance metrics.",
  "elementsJson": [
    "bullet_list",
    "boxplot",
    "data_table",
    "paragraph"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5c-f812573a947a/38",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5c-f812573a947a#slide-38",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Molecules generated using REACTOR are synthetically-accessible and drug-like by default, even without explicit consideration of these constraints as optimization objectives.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c5-73ac-aa62-79213129f27c",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.22,
        "x": 0.75,
        "y": 0.3
      },
      "kind": "chart",
      "text": "Drug-Likeness of DRD2-optimized Molecules",
      "attrs": null,
      "subkind": "box",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "6f850603-6629-4071-a511-cda91aab0d5b",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.35,
        "w": 0.22,
        "x": 0.5,
        "y": 0.3
      },
      "kind": "chart",
      "text": "Synthetic Accessibility Score of DRD2-optimized Molecules",
      "attrs": null,
      "subkind": "box",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "f9b4f3ed-b095-4d9f-8932-61b29b688b3e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.6,
        "w": 0.45,
        "x": 0.05,
        "y": 0.25
      },
      "kind": "list",
      "text": "RL agent designs molecules using step-wise transitions defined by chemical reaction templates. REACTOR frames molecular building blocks as initial states and chemical reactions as the actions that alter these states. Molecules generated using REACTOR are synthetically-accessible and drug-like by default, even without explicit consideration of these constraints as optimization objectives (top graphs). REACTOR generates a higher proportion of unique molecules that are also predicted to be active by the underlying reward model (bottom table).",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "806edbbd-fec5-4b72-8e9e-d7ee67faf81e",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Activity: 98%",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c5-73ac-aa62-7ddeebbf66a1",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.45,
        "x": 0.5,
        "y": 0.9
      },
      "kind": "source-note",
      "text": "Computation of Scaffold Similarity requires the presence of a ring system, thus the N/A.",
      "attrs": null,
      "subkind": null,
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "db0de47e-3a67-485b-9737-9c59987f2e41",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.45,
        "x": 0.5,
        "y": 0.68
      },
      "kind": "table",
      "text": "Performance metrics table comparing REACTOR to Hill Climbing, ORGAN, JTVAE, GCPN, and MolDQN across Activity, Diversity, Scaff. Similarity, and Uniqueness.",
      "attrs": null,
      "subkind": "data",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "9246f1cd-cc0d-4bc5-97f4-40f3272a9030",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.1,
        "w": 0.9,
        "x": 0.05,
        "y": 0.13
      },
      "kind": "title",
      "text": "Reinforcement learning helps ensure that molecules you discover in silico can actually be synthesized in the lab. This helps chemists avoid dead ends during drug discovery.",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "55aa64f8-c25f-4196-8339-5e5040c44acc",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Concrete Language",
      "slug": "concrete-language",
      "agent": "Storyteller",
      "layer": "slide",
      "matchId": "019dd95a-0fd5-7148-8ece-c29ee74c7b4a",
      "evidence": "98% synthesizable molecules statistic.",
      "confidence": 70
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-ed2a8f38a754",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Research, Talent, Industry sections inventory what happened in AI in 2020.",
      "position": 1,
      "confidence": 60,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 129,
      "from": 10,
      "beatId": "019dd95a-0682-776c-8e34-fc384f439bba",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Talent and Industry sections build momentum of AI progress.",
      "position": 2,
      "confidence": 40,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 46,
      "from": 30,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3c-f421814661f3",
      "evidence": "p.30 'AI moment' framing then 16 case-study slides on bio/medical applications.",
      "position": 4,
      "objective": "Survey AI breakthroughs across biology, drug discovery and COVID",
      "structure": "Evidence A -> Evidence B -> Evidence C -> Pattern/Conclusion",
      "confidence": 75,
      "description": "Group multiple pieces of evidence that together point to a pattern or conclusion"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}