{
  "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": 19,
  "pageCount": 30,
  "prevPage": 18,
  "nextPage": 20,
  "slideType": "traction",
  "function": "show_traction",
  "density": "overcrowded",
  "nDataPoints": 12,
  "notes": "Includes scatter plots showing correlation and a bar chart comparing model performance metrics against experimental replicates.",
  "elementsJson": null,
  "metadataConfidence": 1,
  "imagePath": null,
  "slideHref": "/slides/019de073-9d67-725f-975b-68e2ea1578ba/19",
  "deckHref": "/decks/019de073-9d67-725f-975b-68e2ea1578ba",
  "deckJsonHref": "/decks/019de073-9d67-725f-975b-68e2ea1578ba.json",
  "deckAnchorHref": "/decks/019de073-9d67-725f-975b-68e2ea1578ba#slide-19",
  "components": [
    {
      "bbox": {
        "h": 0.2,
        "w": 0.28,
        "x": 0.67,
        "y": 0.7
      },
      "kind": "callout",
      "text": "Strong predictive performance against a hold-out set uniformly distributed with respect to binding affinity",
      "attrs": null,
      "subkind": "primary",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "08f7db1c-753b-4435-87dc-3e07c9620596",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.28,
        "x": 0.05,
        "y": 0.7
      },
      "kind": "callout",
      "text": "Predictive performance with a Pearson R correlation of 0.97 - trained on 90 % of trast-1 variants - evaluated remaining 10 % of sequences",
      "attrs": null,
      "subkind": "primary",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "7a9ab6db-d279-4984-9d6e-00d17e5b9a4d",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.2,
        "w": 0.28,
        "x": 0.36,
        "y": 0.7
      },
      "kind": "callout",
      "text": "Comparing the inaccuracy of measurement to inaccuracy of predictions strongly illustrates the predictive ability of our models",
      "attrs": null,
      "subkind": "primary",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "c5aa743d-8f80-4b28-8470-1b20fd549139",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.3,
        "x": 0.35,
        "y": 0.18
      },
      "kind": "chart",
      "text": "Comparison of Pearson R, Spearman rho, and RMSE across replicates",
      "attrs": null,
      "subkind": "bar-grouped",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "724ab688-d511-48f9-93a5-f2daf792aba7",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.28,
        "x": 0.67,
        "y": 0.18
      },
      "kind": "chart",
      "text": "Scatter plot of Predicted vs Measured ACE score (hold-out set)",
      "attrs": null,
      "subkind": "scatter",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "1c7d8bb7-81fa-4773-b632-d0a10351d254",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.45,
        "w": 0.28,
        "x": 0.05,
        "y": 0.18
      },
      "kind": "chart",
      "text": "Scatter plot of Predicted vs Measured ACE score",
      "attrs": null,
      "subkind": "scatter",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "493f534e-5f9f-4a75-a3dc-08af39f06cce",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.05,
        "w": 0.5,
        "x": 0.1,
        "y": 0.94
      },
      "kind": "disclaimer",
      "text": "Bahas, 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": "1047432c-e148-44a0-814a-5fd73fa0de44",
      "frameworkName": null,
      "frameworkSlug": null
    },
    {
      "bbox": {
        "h": 0.15,
        "w": 0.9,
        "x": 0.05,
        "y": 0.05
      },
      "kind": "title",
      "text": "Deep learning models trained with the ACE Assay-generated trast-1 dataset quantitatively predict antibody binding affinity",
      "attrs": null,
      "subkind": "headline",
      "toolName": null,
      "toolSlug": null,
      "confidence": null,
      "componentId": "e44a1f78-6645-4344-bff8-39a564f6f8f5",
      "frameworkName": null,
      "frameworkSlug": null
    }
  ],
  "metrics": [],
  "tools": [
    {
      "name": "Chartjunk Elimination",
      "slug": "chartjunk-elimination",
      "agent": "Designer",
      "layer": "slide",
      "matchId": "09d4c9f0-c3e6-4194-94eb-4ef676e06dcd",
      "evidence": "Comparison of Pearson R, Spearman rho, and RMSE across replicates",
      "confidence": 0.7
    },
    {
      "name": "Data-Ink Ratio",
      "slug": "data-ink-ratio",
      "agent": "Designer",
      "layer": "slide",
      "matchId": "8fb36a2e-4347-4e1c-b434-72ea3e20a9f7",
      "evidence": "Scatter plot of Predicted vs Measured ACE score (hold-out set)",
      "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
}