Genesis: Towards the Automation of Systems Biology Research

TL;DR

The next generation robot scientist Genesis is developing, designed to automatically improve system biology models with thousands of interacting causal components, to demonstrate that an area of science can be investigated using robot scientists unambiguously faster, and at lower cost, than with human scientists.

Abstract

The cutting edge of applying AI to science is the closed-loop automation of scientific research: robot scientists. We have previously developed two robot scientists: `Adam' (for yeast functional biology), and `Eve' (for early-stage drug design)). We are now developing a next generation robot scientist Genesis. With Genesis we aim to demonstrate that an area of science can be investigated using robot scientists unambiguously faster, and at lower cost, than with human scientists. Here we report progress on the Genesis project. Genesis is designed to automatically improve system biology models with thousands of interacting causal components. When complete Genesis will be able to initiate and execute in parallel one thousand hypothesis-led closed-loop cycles of experiment per-day. Here we describe the core Genesis hardware: the one thousand computer-controlled $μ$-bioreactors. For the integrated Mass Spectrometry platform we have developed AutonoMS, a system to automatically run, process, and analyse high-throughput experiments. We have also developed Genesis-DB, a database system designed to enable software agents access to large quantities of structured domain information. We have developed RIMBO (Revisions for Improvements of Models in Biology Ontology) to describe the planned hundreds of thousands of changes to the models. We have demonstrated the utility of this infrastructure by developed two relational learning bioinformatic projects. Finally, we describe LGEM+ a relational learning system for the automated abductive improvement of genome-scale metabolic models.

Figures (7)

• Figure 1: The overall architecture of the Genesis system. The main hardware system will have 1,000 computer-controlled $\mu$-bioreactors. These will be connected to a mass-spectrometer to read-out the metabolomic (small-molecules) state of the yeast population, and to an RNA-SEQ system to read-out the transcriptome (tRNA) state of the yeast population. The software consists of many modules, going from low-level bioreactor control, to high-level AI units. The units in italics are currently incomplete.
• Figure 2: Genesis Hardware. (a) Is the initial 12 $\mu$-bioreactor system working in Chalmers. (2) The schematics of the fluidics and micro-formulator design.
• Figure 3: The Gensis Mass Spectrometry platform: an Agilent RapidFire (the robotics) and a 6560 ion mobility-mass spectrometry (IM-MS) system.
• Figure 4: Visualisation of database usage from demonstration software agent utilisation of experimental metadata for systems biology model improvement. It represents a cycle of model improvement. (a) First a gene regulatory network is reconstructed from gene counts retrieved from the database with query. (b) Then the experimental conditions are retrieved and the space visualised. (c) A hypothesis along with the experimental procedures to test it are written to the database. (d) Then the regulatory network is recreated including data including the new high temperature experiment. (e) New visualisation with high temperature data.
• Figure 5: Overview of RIMBO, showing the classes and their relationships.