skip to primary navigationskip to content

27.04.19 Discovering gene circuits using machine-learning algorithms

last modified Jun 03, 2019 01:19 PM
Tom Hiscock in the Simons group applied a computational approach to generate algorithms describing natural gene circuits and for designing circuits in synthetic biology. The work is published in BMC Bioinformatics

Adapting machine-learning algorithms to design gene circuits

Hiscock TW (2019) BMC Bioinformatics 20(1): 214. DOI: 10.1186/s12859-019-2788-3.




Abstract from the paper


Gene circuits are important in many aspects of biology, and perform a wide variety of different functions. For example, some circuits oscillate (e.g. the cell cycle), some are bistable (e.g. as cells differentiate), some respond sharply to environmental signals (e.g. ultrasensitivity), and some pattern multicellular tissues (e.g. Turing’s model). Often, one starts from a given circuit, and using simulations, asks what functions it can perform.

Here we want to do the opposite: starting from a prescribed function, can we find a circuit that executes this function? Whilst simple in principle, this task is challenging from a computational perspective, since gene circuit models are complex systems with many parameters. In this work, we adapted machine-learning algorithms to significantly accelerate gene circuit discovery.


We use gradient-descent optimization algorithms from machine learning to rapidly screen and design gene circuits. With this approach, we found that we could rapidly design circuits capable of executing a range of different functions, including those that: (1) recapitulate important in vivo phenomena, such as oscillators, and (2) perform complex tasks for synthetic biology, such as counting noisy biological events.


Our computational pipeline will facilitate the systematic study of natural circuits in a range of contexts, and allow the automatic design of circuits for synthetic biology. Our method can be readily applied to biological networks of any type and size, and is provided as an open-source and easy-to-use python module, GeneNet.


Read more about research in the Simons lab.

Watch Ben Simons describe his research on YouTube.


Studying development to understand disease

The Gurdon Institute is funded by Wellcome and Cancer Research UK to study the biology of development, and how normal growth and maintenance go wrong in cancer and other diseases.

combinedLogo x3 trans2018


Share this

Mutations in thyroid hormone receptor α1 cause premature neurogenesis and progenitor cell depletion in human cortical development

Neural stem cell temporal patterning and brain tumour growth rely on oxidative phosphorylation

Testing the role of SOX15 in human primordial germ cell fate

Genome architecture and stability in the Saccharomyces cerevisiae knockout collection

Long noncoding RNAs are involved in multiple immunological pathways in response to vaccination

Defining the Identity and Dynamics of Adult Gastric Isthmus Stem Cells

Interaction of Sox2 with RNA binding proteins in mouse embryonic stem cells

Disease modelling in human organoids

The role of integrins in Drosophila egg chamber morphogenesis

Tracing the cellular dynamics of sebaceous gland development in normal and perturbed states

Neural stem cell dynamics: the development of brain tumours

Liver organoids: from basic research to therapeutic applications

NSUN2 introduces 5-methylcytosines in mammalian mitochondrial tRNAs

The roles of DNA, RNA and histone methylation in ageing and cancer

Separating Golgi proteins from cis to trans reveals underlying properties of cisternal localization

Sequencing cell-type-specific transcriptomes with SLAM-ITseq

Mature sperm small-RNA profile in the sparrow: implications for transgenerational effects of age on fitness

Single-cell transcriptome analyses reveal novel targets modulating cardiac neovascularization by resident endothelial cells following myocardial infarction

Derivation and maintenance of mouse haploid embryonic stem cells

Establishment of porcine and human expanded potential stem cells

Adapting machine-learning algorithms to design gene circuits

Link to full list on PubMed