How AI Powers Synthetic Biology

Let's face it, we are living in a "century of biology" and artificial intelligence is a growing enabler of what comes next.

For billions of years, evolution was the only author of the genetic code. Modern synthetic biology opens doors for us to become active co-writers.

This May, researchers from the Centre for Genomic Regulation (CRG) reported the first use of generative AI to design DNA sequences that regulate gene expression within living mammalian cells. The team focused on synthetic enhancers—short DNA “switches” that control when and where genes are activated. In their proof-of-concept, they tasked the AI with generating enhancer sequences able to switch on a fluorescent reporter gene in specific mouse blood cells, while remaining silent elsewhere. The ~250-base-pair sequences were synthesized, delivered into cells by a virus (notably, they were integrated at random locations), and performed as intended in healthy mouse blood cells.

Stanley Norman Cohen's Genetic Engineering Laboratory, 1973 - NMAH
Stanley Norman Cohen‘s Genetic Engineering Laboratory, 1973 - National American History Museum’s Science in American Life exhibit. Courtesy of Ryan Somma. License: CC BY-SA 2.0

What CRG demonstrated fits into the typical synthetic biology workflow—where we define a functional specification, generate design candidates, synthesize them, and test them in cells. DNA elements are treated as modular parts composed into higher-order circuits and systems. Borrowing principles from classical engineering like standardization, abstraction, iteration, synthetic biology turns cellular programs into designable constructs.

These days, AI and machine learning are being applied all over the life sciences, and we’ve been tracking this closely across recent updates. Before diving into what’s happening in AI-SynBio today, let’s zoom out and see how the field emerged.

In this article: Historical Throughline — Where Do AI and Synbio Converge? — Sequence Acquisition and Analysis — Modelling Sequences and Predicting Functionality — Accelerating Therapeutics Design and Automating DBTL — Enabling Novel Biosystems — Increasing Access — Synthetic Biology, Natural Danger

Historical Throughline

💠 1961–1999: The Origins.

Although the term “synthetic biology” was first introduced in 1912 by Stéphane Leduc in his work on the physico-chemical basis of life and spontaneous generation, the field’s origins are often traced to 1961, when François Jacob and Jacques Monod introduced the lac operon model in E. coli, showing that cells use regulatory circuits to respond to their environment. This framed biology as a system of logic and control. Early achievements included Meselson’s discovery of restriction enzymes in 1968, Boyer and Cohen’s recombinant DNA technology in 1973 — which paved the way for the first production of a synthetic protein, human insulin, in E. coli by Riggs and Itakura in 1978—and Kary Mullis’s invention of PCR in 1983. At the start of the decade, Barbara Hobom reintroduced the term ‘synthetic biology’ describing genetically modified bacteria with recombinant DNA. Advances in sequencing, genome mapping, and “omics” in the 1990s generated vast cellular catalogs; at the same time computational biology revealed networks of genes and proteins as structured, modular systems.

💠 2000–2003: The Foundational Years.

At the turn of the millennium, synthetic biology achieved its first landmark breakthroughs. In 2000, Tim Gardner’s team from the Center of Biodynamics created the genetic toggle switch—a circuit that could flip between two stable states. The same year Elowitz and colleagues from Princeton unveiled the repressilator, an oscillator producing rhythmic pulses of gene expression. These works proved that living cells could be programmed with circuits resembling those in electrical engineering.

💠 2004–2007: Growth.

By the mid-2000s, the synthetic biology community was taking shape. The first Synthetic Biology 1.0 conference (2004, MIT) and the iGEM competition (2003) fostered a culture of collaboration and creativity. Researchers pushed circuit design further with RNA regulators, post-transcriptional control, multicellular pattern formation, and even light-responsive “bacterial photography”, designed by UCSF researchers. Circuits often behaved unpredictably, and the lack of standardized parts slowed progress. Efforts like the Registry of Standard Biological Parts by MIT began to streamline the work, but biology remained difficult to engineer reliably. This era was also highlighted by a production of artemisinin (malaria drug precursor) in engineered yeast in 2006, a remarkable biotechnological milestone.

💠 2008–2013: Acceleration and Size.

By the 2010s, synthetic biology had matured. Cheaper DNA synthesis, sequencing, and modeling enabled larger, more reliable circuits—synchronized oscillators, logic operations, event counters, and even biological edge detection. New assembly methods (Golden Gate, Gibson) were invented for more efficient cloning. RNA devices advanced as computational elements, while CRISPR–Cas systems transformed the field. In 2012, Jennifer Doudna and Emmanuelle Charpentier introduced CRISPR–Cas9 as a programmable gene-editing tool, unlocking precise genome cutting and repair. Subsequent variants expanded to gene activation, repression, base editing, and RNA targeting, offering modular control over cellular programs.

Applications flourished with microbes for biofuels, bioplastics, and chemicals; Sanofi’s artemisinin production (2013); and therapeutic microbes engineered to fight tumors, pathogens, and biofilms. Safety strategies like kill switches (2010) emerged to mitigate the potential risks of synthetic organisms. Ambitious genome-scale efforts also advanced—Craig Venter’s team synthesized the M. mycoides JCVI-syn1.0 genome (2010), while a team from Johns Hopkins started a synthetic yeast genome project Sc2.0 (2011). Tools such as MAGE, developed by George Church lab, and CRISPR further accelerated genome-wide engineering, shifting the field from isolated circuits to whole-genome design.

💠 2014–2025: Synthetic Biology Taking Over.

Synthetic biology in the past decade has shifted from proof-of-concept circuits to genome-scale engineering, AI-driven design, and real medical applications.

Genome rewriting: In 2016, the Venter Institute introduced JCVI-syn3.0, a streamlined version of JCVI-syn1.0 reduced to just 473 genes, representing the first engineered minimal genome. In 2019, ETH Zurich achieved a design milestone, unveiling Caulobacter ethensis-2.0, a computer-designed bacterial genome; the same year a group from MRC Laboratory of Molecular Biology compressed E. coli’s genetic code from 64 to 61 codons. Following the trend, Sc2.0 was completed in 2023, resulting in all 16 yeast chromosomes being synthesized.
CRISPR setup: Since its 2012 debut, CRISPR–Cas9 has become the universal editing tool, enabling fast and precise genome engineering across species. In 2016, base editing, developed by Liu lab (Harvard) advanced the approach by allowing direct, single-letter DNA conversions without double-stranded breaks, greatly reducing unintended mutations. Building on this, prime editing in 2019 introduced even broader versatility, combining Cas9 nickase with reverse transcriptase and a guide RNA to enable targeted insertions, deletions, and all twelve possible base-to-base changes with fewer off-target effects. Such CRISPR development ended up in the 2023 milestone FDA approval of Casgevy—first legally regulated CRISPR-Cas9-based gene therapy for Sickle Cell Disease.
Novel lifeforms: In 2020, a team, co-led by Michael Levin (Tufts) and Joshua Bongard (University of Vermont) created the first xenobots from frog cells, designed by AI. By 2021, they self-replicated, highlighting new frontiers where biology meets robotics.
AI breakthroughs: DeepMind’s AlphaFold2 (2020) (kind of) solved the protein-folding problem, opening the way to design enzymes and understand disease mechanisms.
RNA rise: The success of mRNA-based COVID-19 vaccines established RNA therapies as faster-to-develop platforms than DNA systems.

💠 Since 2014, synthetic biology has grown into a global engineering discipline, now facing challenges in predictability, safety, and ethics. AI is accelerating progress by shortening development cycles, facilitating complex biosystems through automation, modeling, and large language models. This sets the stage for digital biodesign, where systems can rapidly generate constructs from molecules to entire metabolisms.

Present

Modern AI is reshaping synthetic biology at a structural level. As by authors from , and the fusion of AI and synthetic biology is providing a “ of possibilities: generative models that can propose novel genes, circuits, or proteins; automated laboratories that can execute cycles with minimal human input; and data-driven systems that rapidly expand the scale and complexity of achievable biosystems. But the very abundance of outputs, this flood of designs and data, creates new vulnerabilities.

To read the rest of this article, upgrade to a BiopharmaTrend Pro subscription.

Gain full access to all of our deep dives and content archives.

Upgrade to Pro

Already a member? Sign in here.