David Baker Team Paper: AI Can Design Thousands of Proteins. How Does the Lab Keep Up?

SAPP turns protein experiments into a batch workflow

Where the old queue stalledAfter DNA assembly, a conventional workflow still transforms, plates, picks a single colony, grows it, prepares plasmid, verifies the sequence and then moves the confirmed construct into an expression strain. This takes days and colony picking is difficult to parallelize at scale.^[S1]

Engineering tradeoffSAPP uses Golden Gate Assembly and places the lethal ccdB gene in the destination vector. A correct insert replaces ccdB, while empty background vector is strongly suppressed. The assembly can therefore enter an E. coli expression strain directly. Moving 192 reactions from linear DNA to inoculated expression cultures takes about two hours.^[S1][S4]

Is the shortcut reliable?The shortcut does not eliminate DNA synthesis and cloning errors. Across 929 assembly reactions, 89.3% had a dominant clone above 90% purity. Mass spectrometry of 863 purified proteins found about 90% within ±1 Da of the expected mass. The intended construct usually dominates enough for screening, at the cost of occasional false negatives.^[S1]

The point is not that sequencing no longer matters. Screening and final validation are designed as separate stages: a faster workflow with some tolerance for missed positives first covers hundreds or thousands of candidates, while final hits still receive strict clonal and sequence confirmation.

The more important step: SEC for every sample turns experiments into a data line

Traditional 96-well screens often stop at SDS-PAGE to see what expressed, then scale up a few candidates. Expression is far from proving that a protein is good: it may aggregate, form the wrong oligomer or fail to preserve the intended native state.^[S1]

SAPP sends every sample through affinity purification and then directly into size-exclusion chromatography (SEC). SEC is not only purification: each chromatogram reports soluble yield, dispersity, estimated molecular weight, aggregation and oligomeric state. A batch of 192 samples runs overnight in about 15 hours, under five minutes per sample.^[S1]

A Python pipeline analyzes chromatograms in batches and generates liquid-handler instructions for fraction pooling and concentration normalization. The output is not only a 96-well plate of purified proteins but also a standardized file containing the experimental results. The full SAPP workflow takes about 48 hours, with approximately six hours of bench work.^[S1][S3]

From an AI4S perspective, SAPP matters not only because experiments are faster, but because every design returns comparable, machine-readable physical data in the same format.

Why does throughput matter? Geometry is hard to rank in advance

A fluorescent-protein study first showed that SAPP could return comparable data for 96 redesigned constructs within a week. Some variants shared only 50–80% sequence identity with the wild type yet remained monomeric and retained absorbance after one hour at 95°C; others showed clear shifts in emission spectra.^[S1]

The RSV study makes the case more clearly. The team screened about 31,000 minibinders targeting site III of RSV F, identified cb13 at 35 nM affinity and found by cryo-EM that the observed complex closely matched the design, with a binder-backbone Cα RMSD of 1.9 Å. They then placed cb13 on 27 oligomerization scaffolds to make 58 constructs. SAPP selected 19 with suitable expression and assembly for live-virus neutralization.^[S1][S5]

Two constructs reached IC50 values of 40 pM and 59 pM, compared with 5.4 nM for monomeric cb13 and 156 pM for the MPE8 antibody control. The failures and branches are more informative: two cb13 dimers differed by about 25-fold; moving the binding domain from the N to C terminus on the same trimerization scaffold changed potency by nearly tenfold; and C6 or C8 architectures did not automatically improve activity.^[S1]

Throughput therefore does more than validate a model's top few candidates faster. It lets researchers search a geometry space that is still difficult to rank reliably. When only three or five constructs can be made, this systematic exploration rarely happens. At dozens or hundreds, it becomes an experimentally answerable question.

Once SAPP worked, the next bottleneck appeared: DNA cost

This is the paper's clearest systems story: bottlenecks move. Once protein expression, purification and initial characterization accelerated, DNA synthesis became the dominant cost of large campaigns. Ordering individual gene fragments is convenient, but at hundreds or thousands of designs DNA absorbs most of the budget.^[S1]

Cheap DNA is pooled, but experiments need it arrayed: one construct per well, with a known identity.

Oligo pools are much cheaper, but all sequences arrive mixed together. DMX does not solve a new protein problem; it solves this format mismatch by turning a mixed pool back into a clone library that can enter experiments one known construct per well.^[S1][S2]

DMX: one sequence per well, with its identity known

DMX clones a DNA library into a common vector and picks colonies into 384-well plates. Genes in each bacterial lysate receive combinatorial barcodes, are pooled again and sequenced with Nanopore long reads to map barcodes to gene sequences. An automated pipeline outputs a pick list, and a liquid handler re-arrays confirmed colonies into new plates.^[S1][S3]

Four sets of 24 barcodes can theoretically identify 24⁴, or 331,776 wells. In a test library of 1,500 designs, the team analyzed 4,608 colonies and recovered 78% of target variants, approaching the roughly 92% theoretical limit at that sampling depth.^[S1]

The paper estimates that DNA for a 500-design campaign is about fivefold cheaper than individual gene fragments, and an approximately 2,000-design campaign about eightfold cheaper. The cost is roughly five extra days. SAPP alone is simpler for one or two hundred designs; at thousand-design scale, DMX followed by SAPP becomes more attractive.^[S1][S2]