Generative Biology

Absci Corporation

by Absci Corporation

4.2
0

Generative AI drug creation platform designing and validating novel antibodies at unprecedented speed

Category

Generative Biology

Founded

2011

Headquarters

Portland, OR, USA

Overview

Absci is a generative AI drug creation company that combines large-scale AI-driven antibody design with an integrated wet-lab validation platform. The Absci Drug Creation Platform uses proprietary zero-shot generative AI models — trained on billions of protein sequences — to design de novo antibodies with desired binding, selectivity, and developability properties, then experimentally validates candidates at scale using high-throughput cell-free expression and binding assays. Pharma and biotech partners use Absci's platform through collaborative drug creation programs targeting oncology, immunology, and infectious disease. A landmark 2023 Nature paper demonstrated that Absci's AI designed functional antibodies from scratch — with no starting sequence — in a process validated by wet lab experiments, marking one of the first demonstrations of zero-shot generative AI antibody design. Absci's core differentiation is the closed-loop integration of generative AI with experimental validation. The company's SoluPro cell-free expression system can produce and screen thousands of AI-designed antibody variants per week, generating training data that continuously improves the generative models. This data flywheel accelerates both the AI platform and partner drug programs simultaneously.

Key Features

Inverse Design

Specify desired biological functions and automatically generate candidate sequences and structures.

Cross-Domain Generation

Unified generative capabilities spanning small molecules, peptides, proteins, and nucleic acids.

Transfer Learning Engine

Leverage large biological datasets to enable generation in low-data domains and novel targets.

Interpretable Design Rationale

Explainable models reveal structure-function relationships driving design decisions.

Rapid Candidate Enumeration

Generate thousands of diverse candidates for experimental validation in hours.

Pros & Cons

Pros

  • +Interpretable models reveal structure-function relationships driving design decisions
  • +Rapid iteration cycles generate thousands of candidates for experimental validation in hours
  • +Inverse design capabilities specify desired functions and generate candidate sequences automatically
  • +Transfer learning from large biological datasets enables design in low-data domains
  • +Multi-objective optimization balances efficacy, selectivity, toxicity, and synthesizability simultaneously
  • +Generative models design novel molecules, proteins, and genetic sequences with desired properties
  • +Cross-domain generative capabilities span small molecules, peptides, proteins, and nucleic acids

Cons

  • Computational costs for training and inference of large generative models can be substantial
  • Interpretability of generative model decisions remains limited for regulatory submissions
  • Training data biases can limit diversity and novelty of generated biological sequences
  • Generated designs require experimental validation — computational predictions don't guarantee function

Use Cases

Research Workflow Optimization

AI-powered optimization of research workflows to accelerate discovery timelines and improve reproducibility.

Data Analysis & Insights

Machine learning analysis of complex biological datasets to extract actionable insights and identify patterns.

Collaboration & Knowledge Management

Platform-enabled collaboration across distributed research teams with integrated data sharing and knowledge capture.

Last updated: February 19, 2026