Machine learning optimization of candidate antibody yields highly diverse sub-nanomolar affinity antibody libraries.

Therapeutic antibodies are an important and rapidly growing drug modality. However, the design and discovery of early-stage antibody therapeutics remain a time and cost-intensive endeavor. Here we present an end-to-end Bayesian, language model-based method for designing large and diverse libraries of high-affinity single-chain variable fragments (scFvs) that are then empirically measured. In a head-to-head comparison with a directed evolution approach, we show that the best scFv generated from our method represents a 28.7-fold improvement in binding over the best scFv from the directed evolution. Additionally, 99% of designed scFvs in our most successful library are improvements over the initial candidate scFv. By comparing a library's predicted success to actual measurements, we demonstrate our method's ability to explore tradeoffs between library success and diversity. Results of our work highlight the significant impact machine learning models can have on scFv development. We expect our method to be broadly applicable and provide value to other protein engineering tasks.

Massively multiplexed affinity characterization of therapeutic antibodies against SARS-CoV-2 variants.

Antibody therapies represent a valuable tool to reduce COVID-19 deaths and hospitalizations. Multiple antibody candidates have been granted emergency use authorization by the Food and Drug Administration and many more are in clinical trials. Most antibody therapies for COVID-19 are engineered to bind to the receptor-binding domain (RBD) of the SARS-CoV-2 Spike protein and disrupt its interaction with angiotensin-converting enzyme 2 (ACE2). Notably, several SARS-CoV-2 strains have accrued mutations throughout the RBD that improve ACE2 binding affinity, enhance viral transmission and escape some existing antibody therapies. Here, we measure the binding affinity of 33 therapeutic antibodies against a large panel of SARS-CoV-2 variants and related strains of clinical significance using AlphaSeq, a high-throughput yeast mating-based assay to determine epitopic residues, determine which mutations result in loss of binding and predict how future RBD variants may impact antibody efficacy.

A dataset comprised of binding interactions for 104,972 antibodies against a SARS-CoV-2 peptide.

The dataset presented here contains quantitative binding scores of scFv-format antibodies against a SARS-CoV-2 target peptide collected via an AlphaSeq assay that can be used in the development and benchmarking of machine learning models. Starting from three seed sequences identified from a phage display campaign using a human naïve library, four sets of 29,900 antibodies were designed in silico by creating all k = 1 mutations and random k = 2 and k = 3 mutations throughout the complementary-determining regions (CDRs). Of the 119,600 designs, 104,972 were successfully built in to the AlphaSeq library and target binding was subsequently measured with 71,384 designs resulting in a predicted affinity value for at least one of the triplicate measurements. Data include antibodies with predicted affinity measurements ranging from 37 pM to 22 mM. To our knowledge, this dataset is the largest, publicly available dataset that contains antibody sequences, antigen sequence and quantitative measurements of binding scores and provides an opportunity to serve as a benchmark to evaluate antibody-specific representation models for machine learning.

Probing the physical limits of reliable DNA data retrieval.

Synthetic DNA is gaining momentum as a potential storage medium for archival data storage. In this process, digital information is translated into sequences of nucleotides and the resulting synthetic DNA strands are then stored for later retrieval. Here, we demonstrate reliable file recovery with PCR-based random access when as few as ten copies per sequence are stored, on average. This results in density of about 17 exabytes/gram, nearly two orders of magnitude greater than prior work has shown. We successfully retrieve the same data in a complex pool of over 1010 unique sequences per microliter with no evidence that we have begun to approach complexity limits. Finally, we also investigate the effects of file size and sequencing coverage on successful file retrieval and look for systematic DNA strand drop out. These findings substantiate the robustness and high data density of the process examined here.

Author Correction: Probing the physical limits of reliable DNA data retrieval.

An amendment to this paper has been published and can be accessed via a link at the top of the paper.

DNA assembly for nanopore data storage readout.

Synthetic DNA is becoming an attractive substrate for digital data storage due to its density, durability, and relevance in biological research. A major challenge in making DNA data storage a reality is that reading DNA back into data using sequencing by synthesis remains a laborious, slow and expensive process. Here, we demonstrate successful decoding of 1.67 megabytes of information stored in short fragments of synthetic DNA using a portable nanopore sequencing platform. We design and validate an assembly strategy for DNA storage that drastically increases the throughput of nanopore sequencing. Importantly, this assembly strategy is generalizable to any application that requires nanopore sequencing of small DNA amplicons.

A molecular multi-gene classifier for disease diagnostics.

Despite its early promise as a diagnostic and prognostic tool, gene expression profiling remains cost-prohibitive and challenging to implement in a clinical setting. Here, we introduce a molecular computation strategy for analysing the information contained in complex gene expression signatures without the need for costly instrumentation. Our workflow begins by training a computational classifier on labelled gene expression data. This in silico classifier is then realized at the molecular level to enable expression analysis and classification of previously uncharacterized samples. Classification occurs through a series of molecular interactions between RNA inputs and engineered DNA probes designed to differentially weigh each input according to its importance. We validate our technology with two applications: a classifier for early cancer diagnostics and a classifier for differentiating viral and bacterial respiratory infections based on host gene expression. Together, our results demonstrate a general and modular framework for low-cost gene expression analysis.

Random access in large-scale DNA data storage.

Synthetic DNA is durable and can encode digital data with high density, making it an attractive medium for data storage. However, recovering stored data on a large-scale currently requires all the DNA in a pool to be sequenced, even if only a subset of the information needs to be extracted. Here, we encode and store 35 distinct files (over 200 MB of data), in more than 13 million DNA oligonucleotides, and show that we can recover each file individually and with no errors, using a random access approach. We design and validate a large library of primers that enable individual recovery of all files stored within the DNA. We also develop an algorithm that greatly reduces the sequencing read coverage required for error-free decoding by maximizing information from all sequence reads. These advances demonstrate a viable, large-scale system for DNA data storage and retrieval.

A 12-year experience using the Brown two-portal endoscopic procedure of transverse carpal ligament release in 14,722 patients: defining a new paradigm in the treatment of carpal tunnel syndrome.

BACKGROUND: Compared with the open technique, endoscopic carpal tunnel release has a shorter postoperative recovery period but has been associated with an increased risk of iatrogenic injury. Because of morbidity of the open method, including painful scars, pillar pain, tendon adhesions, scar entrapment of the median nerve, chronic regional pain syndrome, and a longer postoperative recovery period, many patients have been treated nonoperatively to circumvent or forestall surgery, resulting in unrelieved median nerve compression and an increased risk of permanent nerve injury. METHODS: Inclusion criteria included a diagnosis of carpal tunnel syndrome based on history and physical examination and electrodiagnostic studies; failure of a short trial of conservative therapy; and advanced disease as evidenced by sensory, motor, or atrophic changes in the median nerve distribution. Exclusion criteria included prior surgery, wrist extension of less [corrected] than 40 degrees, mass within the carpal tunnel, Guyon's syndrome, and bony carpal tunnel abnormalities. Patients meeting these criteria were treated by the Brown two-portal endoscopic technique. RESULTS: A total of 14,722 patients were treated with the Brown endoscopic procedure. Eleven patients (0.07 percent) required conversion to an open procedure. There was one iatrogenic injury. Postoperative results were inversely related to the severity of the preoperative electrodiagnostic studies and the duration of symptoms regardless of the method of nonoperative treatment given. CONCLUSIONS: Operative decompression should be carried out promptly if symptoms have been present for 2 months or longer, as the occurrence of permanent nerve damage has been noted within this time frame. The authors advocate use of the two-portal endoscopic technique as previously described by Brown et al. for this purpose.