Absci | Investor Presentation Deck | 30 slides

Absci · 2022-10

arc beats above · slides in the middle · loops below · scroll → 2 LOOPS

Deck intelligence map

coverage by narrative range · generated from this deck JSON

Narrative range 29 total

Metadata

Components

Metrics

Tools

Frameworks

Beats

Loops

Problem 3 slides 100% 3/3 slides 100% 3/3 slides · 15 hits

— 0/3 slides

66.7% 2/3 slides 100% 3/3 slides 100% 3/3 slides · 4 hits

— 0/3 slides

Agitate 2 slides 100% 2/2 slides 100% 2/2 slides · 10 hits

— 0/2 slides

100% 2/2 slides 100% 2/2 slides 100% 2/2 slides · 4 hits 50% 1/2 slides Solution 24 slides 100% 24/24 slides 100% 24/24 slides · 120 hits

— 0/24 slides

66.7% 16/24 slides · 17 hits 41.7% 10/24 slides 100% 24/24 slides · 25 hits 100% 24/24 slides · 27 hits

Slide inventory

every slide · same image gating as the playbook

Includes company logo, tagline, date, and copyright notice.front_matter

Open slide detail

other

Open slide detail

Uses a comparison to the scale of the universe to frame the problem as an intractable search space.frame_problem

Open slide detailBeat · Problem

Uses a simple visual metaphor of a subset circle to illustrate the problem of low success rates in drug discovery.frame_problem

Open slide detailBeat · Problem

Uses a Venn-style diagram to illustrate the small overlap between screening and successful drug candidates.frame_problem

Open slide detailBeat · Problem

The diagram uses a Venn-like overlap to visually represent the expansion of 'right sequences' explored.present_solution

Open slide detailBeat · AgitateLoop · Jobs To Be Done

The slide uses a flywheel/cycle diagram to represent the iterative nature of their platform.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The central circular diagram represents a flywheel or iterative process.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a process flow diagram to explain the drug discovery pipeline from patient cohort to manufacturing.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a process flow diagram to illustrate the transformation of biological targets into optimized drug candidates.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a process-flow visual to contrast discovery vs. optimization.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide features the company logo and a stylized 'a' graphic.front_matter

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide highlights a specific Nature Biomedical Engineering paper as validation of the company's core technology approach.cite_precedent

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a process flow diagram to show the transition from parental mAb to optimized mAb via AI.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide outlines a technical methodology for biological data generation.present_framework

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide includes a small schematic icon representing the scatter plot and a callout box emphasizing the necessity of high-quality data for AI training.show_traction

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The table outlines the experimental design for antibody optimization models, specifically highlighting the differences in sampling strategies and mutational loaanalyze_data

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide explains the methodology behind the dataset used for AI lead optimization, specifically focusing on the combinatorial space of amino acid mutations.analyze_data

Open slide detailBeat · SolutionLoop · Jobs To Be Done

Includes scatter plots showing correlation and a bar chart comparing model performance metrics against experimental replicates.show_traction

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The chart shows density vs -log10Kd, comparing design vs validation vs measured trastuzumab.show_traction

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide highlights the methodology of sampling sequence space and validating predictive models against measured binding affinity.show_traction

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The chart compares High vs Low Fidelity models with and without pretraining across different training data sizes.show_traction

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide shows scatter plots for quadruple and quintuple mutants and a summary bar chart for performance metrics.analyze_data

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a combination of diagrams and a summary box to explain the methodology of using AI to predict antibody naturalness.frame_problem

Open slide detailBeat · SolutionLoop · Cost Of Inaction

The slide uses box plots and bar charts to show statistical correlation between naturalness and clinical/developability outcomes.analyze_data

Open slide detailBeat · SolutionLoop · Cost Of Inaction

The slide uses box plots and density plots to demonstrate that higher naturalness correlates with better expression and lower mutational burden.analyze_data

Open slide detailBeat · SolutionLoop · Cost Of Inaction

The charts show the progression of antibody variants over generations, highlighting the improvement in ACE score and naturalness metrics.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a process diagram to illustrate the 'in silico' lead optimization workflow.summarize

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a process flow diagram to show the integration of AI in drug development.present_solution

Open slide detailBeat · SolutionLoop · Jobs To Be Done

The slide uses a lightbulb icon as a metaphor for innovation.inspire_vision

Open slide detail