Generative artificial intelligence (AI) has the potential to greatly increase the speed, quality and controllability of antibody design. Traditional de novo antibody discovery requires time and resource intensive screening of large immune or synthetic libraries. These methods also offer little control over the output sequences, which can result in lead candidates with sub-optimal binding and poor developability attributes. Several groups have introduced models for generative antibody design with promising in silico evidence, however, no such method has demonstrated de novo antibody design with experimental validation. Here we use generative deep learning models to de novo design antibodies against three distinct targets, in a zero-shot fashion, where all designs are the result of a single round of model generations with no follow-up optimization. In particular, we screen over 400,000 antibody variants designed for binding to human epidermal growth factor receptor 2 (HER2) using our high-throughput wet lab capabilities. From these screens, we further characterize 421 binders using surface plasmon resonance (SPR), finding three that bind tighter than the therapeutic antibody trastuzumab. The binders are highly diverse, have low sequence identity to known antibodies, and adopt variable structural conformations. Additionally, these binders score highly on our previously introduced Naturalness metric, indicating they are likely to possess desirable developability profiles and low immunogenicity. We open source the HER2 binders and report the measured binding affinities. These results unlock a path to accelerated drug creation for novel therapeutic targets using generative AI combined with high-throughput experimentation.

Increasing recombinant protein expression is of broad interest in industrial biotechnology, synthetic biology, and basic research. Codon optimization is an important step in heterologous gene expression that can have dramatic effects on protein expression level. Several codon optimization strategies have been developed to enhance expression, but these are largely based on bulk usage of highly frequent codons in the host genome, and can produce unreliable results. Here, we develop deep contextual language models that learn the codon usage rules from natural protein coding sequences across members of theEnterobacteralesorder. We then fine-tune these models with over 150,000 functional expression measurements of synonymous coding sequences from three proteins to predict expression inE. coli. We find that our models recapitulate natural context- specific patterns of codon usage and can accurately predict expression levels across synonymous sequences. Finally, we show that expression predictions can generalize across proteins unseen during training, allowing forin silicodesign of gene sequences for optimal expression. Our approach provides a novel and reliable method for tuning gene expression with many potential applications in biotechnology and biomanufacturing.

Konzo, a distinct upper motor neuron disease associated with a cyanogenic diet and chronic malnutrition, predominately affects children and women of childbearing age in sub-Saharan Africa. While the exact biological mechanisms that cause this disease have largely remained elusive, host-genetics and environmental components such as the gut microbiome have been implicated. Using a large study population of 180 individuals from the Democratic Republic of the Congo, where konzo is most frequent, we investigate how the structure of the gut microbiome varied across geographical contexts, as well as provide the first insight into the gut flora of children affected with this debilitating disease using shotgun metagenomic sequencing. Our findings indicate that the gut microbiome structure is highly variable depending on region of sampling, but most interestingly, we identify unique enrichments of bacterial species and functional pathways that potentially modulate the susceptibility of konzo in prone regions of the Congo.

From a fringe idea with limited wider support, the goal of a four-day working week has moved into the spotlight in contemporary policy debates. Indeed, a growing number of businesses have agreed to pilot a four-day working week. This article examines what the turn to this goal means for a politics of work. It argues that its adoption by business interests can dilute its impacts, while its stress in some radical circles can distract from other pressing goals such as higher wages and improvement in work's quality. The article is sceptical that a four-day working week, as currently conceived, would necessarily transform work for the better. Building on a different politics, it proposes an alternative agenda that would allow for fewer work hours alongside higher quality work. The barriers to the realisation of this agenda reinforce the fact that radical change in society requires deeper institutional reform, including within workplaces.

No abstract