{
  "docId": "019de073-9d67-725f-975b-68e2ea1578ba",
  "docSlug": "df4019524c1d62b73cca6d59915e8eef",
  "documentTitle": "Absci | Investor Presentation Deck | 30 slides",
  "authorId": "absci",
  "authorName": "Absci",
  "documentKindSlug": "pitchdeck",
  "documentKindLabel": "Pitch deck",
  "sourceTypeSlug": "investor_relations",
  "sourceTypeLabel": "Investor relations",
  "presentationDate": "2022-10-01 00:00:00",
  "orientation": "landscape",
  "aspectRatio": 1.7777778,
  "pageNumber": 22,
  "pageCount": 30,
  "prevPage": 21,
  "nextPage": 23,
  "slideType": "traction",
  "function": "show_traction",
  "density": "dense",
  "nDataPoints": 24,
  "notes": "The chart compares High vs Low Fidelity models with and without pretraining across different training data sizes.",
  "elementsJson": null,
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019de073-9d67-725f-975b-68e2ea1578ba/22",
  "deckHref": "/decks/019de073-9d67-725f-975b-68e2ea1578ba",
  "deckJsonHref": "/decks/019de073-9d67-725f-975b-68e2ea1578ba.json",
  "deckAnchorHref": "/decks/019de073-9d67-725f-975b-68e2ea1578ba#slide-22",
  "components": [
    {
      "bbox": {
        "h": 0.1,
        "w": 0.94,
        "x": 0.03,
        "y": 0.825
      },
      "kind": "callout",
      "text": "We can make predictions with actionable performance using <0.1% of the combinatorial sequence space as the training set",
      "attrs": null,
      "subkind": "primary",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "cb482e50-99c4-42b6-9f38-1c367f1e0a10",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.65,
        "w": 0.75,
        "x": 0.15,
        "y": 0.16
      },
      "kind": "chart",
      "text": "Line chart showing Pearson R vs Train Fraction",
      "attrs": null,
      "subkind": "line",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5a8d56f1-e5b7-49c6-9560-d415c6140256",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.5,
        "x": 0.1,
        "y": 0.94
      },
      "kind": "disclaimer",
      "text": "Bachas, S., Rakocevic, G. et al. Antibody optimization enabled by artificial intelligence predictions of binding affinity and naturalness (2022) pre-print in bioRxiv.",
      "attrs": null,
      "subkind": null,
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "fe00baa8-b377-43b1-bee2-7859d6e09215",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.18,
        "x": 0.18,
        "y": 0.415
      },
      "kind": "legend",
      "text": "Training Data: High Fidelity, Low Fidelity; Model: OAS pretrained, No pretraining",
      "attrs": null,
      "subkind": null,
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "1a920ddf-75eb-45c8-b6ea-d8bf9a52de68",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.1,
        "w": 0.9,
        "x": 0.05,
        "y": 0.71
      },
      "kind": "table",
      "text": "Train Fraction, Train Size, Coverage table",
      "attrs": null,
      "subkind": "data",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "5ca20d76-5527-4a4f-bc51-0852212b12d6",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.14,
        "w": 0.94,
        "x": 0.03,
        "y": 0.03
      },
      "kind": "title",
      "text": "Models learned to predict roughly 2,500 sequences for every sequence in the training dataset",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "acc2f107-223b-442d-b93d-5789a2a5878b",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Chart Selection Guide",
      "slug": "chart-selection-guide",
      "agent": "Designer",
      "layer": "slide",
      "matchId": "2963f28b-0270-4c64-9c94-a747bb2a8ca1",
      "evidence": "Line chart showing Pearson R vs Train Fraction",
      "confidence": 0.7
    }
  ],
  "frameworks": [],
  "arcBeats": [
    {
      "to": 29,
      "from": 6,
      "beatId": "8717afca-670f-4c53-9154-841d8d01c54d",
      "arcName": "Problem-Agitate-Solution",
      "arcSlug": "problem-agitate-solution",
      "beatName": "Solution",
      "beatSlug": "problem-agitate-solution-solution-provide-relief",
      "evidence": "The deck presents Absci's AI-enabled platform and active learning cycle as a solution to the challenges of biologic drug discovery.",
      "position": 2,
      "confidence": 0.8,
      "parentBeatName": "Resolution",
      "parentBeatSlug": "resolution"
    }
  ],
  "loops": [
    {
      "to": 29,
      "from": 6,
      "name": "Jobs To Be Done",
      "slug": "53-jobs-to-be-done",
      "bestFor": "Product innovation, market entry, competitive positioning",
      "matchId": "9ee18f27-0598-416a-8927-048571ff09f9",
      "evidence": "The deck presents Absci's AI-enabled platform and active learning cycle as a solution to the challenges of biologic drug discovery.",
      "position": 1,
      "objective": "Show how Absci's solution can accelerate the discovery and generation of optimized protein biologics",
      "structure": "The Customer's Job -> Current Solutions (Hired/Fired) -> Unmet Needs -> Our Solution Fit",
      "confidence": 0.6,
      "description": "Reframe the problem around what the customer is trying to accomplish, not what they're buying"
    }
  ],
  "imagePathAlt": null,
  "thumbSrc": null,
  "thumbSrcAlt": null,
  "locked": true
}