{
  "docId": "019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "docSlug": "cc8183ec02431b7a",
  "documentTitle": "2022 Air Street Capital The State of AI Report 2022",
  "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": 17,
  "pageCount": 114,
  "prevPage": 16,
  "nextPage": 18,
  "slideType": "case_study",
  "function": "illustrate_case",
  "density": "overcrowded",
  "nDataPoints": 30,
  "notes": "Includes a bar chart showing perplexity decrease with model size and a table of ESM-2 performance metrics.",
  "elementsJson": [
    "headline_text",
    "bullet_list",
    "bar_chart_vertical",
    "data_table",
    "logo_grid"
  ],
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc/17",
  "deckHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc",
  "deckJsonHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc.json",
  "deckAnchorHref": "/decks/019dd923-5e88-73ef-bd5d-01cf0d8a8fbc#slide-17",
  "components": [
    {
      "bbox": null,
      "kind": "callout",
      "text": "Researchers independently applied language models to the problems of protein generation and structure prediction while scaling model parameter. They both report large benefits from scaling their models.",
      "attrs": null,
      "subkind": null,
      "toolName": "Visual emphasis",
      "toolSlug": "visual-emphasis",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a215-0efb8cc8a2cb",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.215,
        "w": 0.185,
        "x": 0.798,
        "y": 0.338
      },
      "kind": "chart",
      "text": "ProGen2 perplexity chart",
      "attrs": null,
      "subkind": "bar-vertical",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "15cd68e4-1ee7-4dc9-b42f-c84085172408",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.55,
        "w": 0.75,
        "x": 0.03,
        "y": 0.31
      },
      "kind": "list",
      "text": "Salesforce researchers find that scaling their LMs allows them to better capture the training distribution of protein sequences (as measured by perplexity).\nUsing the 6B param ProGen2, they generated proteins with similar folds to natural proteins, but with a substantially different sequence identity. But to unlock the full potential of scale, the authors insist that more emphasis be placed on data distribution.\nMeta et al. introduced the ESM family of protein LMs, whose sizes range from 8M to 15B (dubbed ESM-2) parameters. Using ESM-2, they build ESMFold to predict protein structure. They show that ESMFold produces similar predictions to AlphaFold 2 and RoseTTAFold, but is an order of magnitude faster.\nThis is because ESMFold doesn't rely on the use of multiple sequence alignments (MSA) and templates like AlphaFold 2 and RoseTTAFold, and instead only uses protein sequences.",
      "attrs": null,
      "subkind": "bullet",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "68083aac-b786-40da-b1c4-c4f82f58e768",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": null,
      "kind": "metric",
      "text": "Validation Perplexity: 6.37",
      "attrs": null,
      "subkind": "primary",
      "toolName": "Quantification",
      "toolSlug": "quantification",
      "confidence": null,
      "componentId": "019dd952-47c4-7719-a215-116c1cfdb2e1",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.08,
        "w": 0.85,
        "x": 0.03,
        "y": 0.21
      },
      "kind": "paragraph",
      "text": "Researchers independently applied language models to the problems of protein generation and structure prediction while scaling model parameter. They both report large benefits from scaling their models.",
      "attrs": null,
      "subkind": "paragraph",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "a6e3f949-311e-484c-8b9c-c21821af2b01",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.185,
        "w": 0.398,
        "x": 0.585,
        "y": 0.725
      },
      "kind": "table",
      "text": "ESM-2 performance metrics table",
      "attrs": null,
      "subkind": "data",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "0580d737-f630-413c-a8b5-c2ee5d8a9e17",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.04,
        "w": 0.75,
        "x": 0.03,
        "y": 0.14
      },
      "kind": "title",
      "text": "Language models for proteins: a familiar story of open source and scaled models",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e4e1a9b1-4c54-4daa-baa3-5cfb3bab408b",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 80,
      "from": 5,
      "beatId": "019dd95a-0682-776c-8e35-2557e3799e96",
      "arcName": "The Triple Take",
      "arcSlug": "triple-take",
      "beatName": "The Facts (What)",
      "beatSlug": "triple-take-the-facts-what",
      "evidence": "Definitions, exec summary, Research and Industry sections inventory the state of AI.",
      "position": 1,
      "confidence": 78,
      "parentBeatName": "Setup",
      "parentBeatSlug": "setup"
    },
    {
      "to": 93,
      "from": 11,
      "beatId": "019dd95a-0682-776c-8e35-35abf646aa8b",
      "arcName": "The Mountain",
      "arcSlug": "mountain",
      "beatName": "Rising Action",
      "beatSlug": "mountain-rising-action",
      "evidence": "Research, Industry, Politics sections accumulate signals.",
      "position": 2,
      "confidence": 55,
      "parentBeatName": "Development",
      "parentBeatSlug": "development"
    }
  ],
  "loops": [
    {
      "to": 21,
      "from": 12,
      "name": "Pattern Hunter",
      "slug": "02-pattern-hunter",
      "bestFor": "Time-pressed audiences, building consensus, when data is strong",
      "matchId": "019dd95a-07fe-70ce-8d3d-9f07f56c535f",
      "evidence": "DeepMind math, fusion, AlphaFold, protein LMs, plastic enzymes, Minecraft agents — all evidence of one pattern.",
      "position": 2,
      "objective": "Compile case studies showing ML breakthroughs in physical/life sciences",
      "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
}