PWPhillip R. Woolley

Phillip R. Woolley

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Phillip R. Woolley has a total of 23 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Overestimating zero-shot fitness prediction: Broad benchmarks mask local failures and practical limitations

    by Phillip R. Woolley, Aaron L. Feller, Andrew D. Ellington, Claus O. Wilke

    Deep learning models have emerged as promising tools in protein engineering. In particular, they can be used to predict mutation fitness without the need for task-specific training, a process known as zero-shot prediction. However, the respective strengths and limitations of zero-shot predictions remain poorly understood. Here, we argue that commonly used large-scale benchmarks obscure important failure modes relevant to practical protein engineering, including an inability to pinpoint highly fit mutations or variants driving new-to-nature functions. Beyond these practical failures, we identify a fundamental limitation of zero-shot prediction: a generic fitness score cannot simultaneously optimize for distinct, competing engineering targets, meaning it is inherently disconnected from the phenotype of interest. Moreover, in a systematic comparison of a wide range of available models, we demonstrate that most models show comparable zero-shot performance, irrespective of model architecture and/or input modality (sequence vs. structure). Ultimately, we find that zero-shot predictions serve only as coarse filters separating fit mutations from deleterious ones, failing to reliably identify the mutations that would be most valuable in protein engineering.


  • Open Access

    Validation and analysis of 12,000 AI-driven CAR-T designs in the Bits to Binders competition

    by Clayton W. Kosonocky, Alex M. Abel, Aaron L. Feller, Amanda E. Cifuentes Rieffer, Phillip R. Woolley, Jakub Lála, Daryl R. Barth, Tynan Gardner, Bits To Binders Competitors, Stephen C. Ekker, et al.

    Artificial intelligence (AI) methods for proteins have advanced rapidly, improving structure prediction and design, particularly for de novo binders. However, most evaluations emphasize binding affinity rather than higher-order biological function. We present Bits to Binders , a global competition benchmarking de novo binder design in the context of chimeric antigen receptor (CAR) T cells. Teams from 42 countries submitted 12,000 designs of 80-amino acid binders targeting human CD20 as CAR binding domains. Designs were screened by pooled CAR-T proliferation, identifying 707 designs exhibiting significant CD20-specific enrichment, with team hit rates from 0.6% to 38.4%. Top-performing candidates were validated as individual constructs, measuring CD20-specific proliferation, expansion, cytokine production, and targeted cell lysis. We identified common design methodologies and factors correlated with DNA synthesis, expression, and target-specific T cell activation which nearly double the success rates when applied as a retrospective filter. We release this dataset as an open resource, with practical recommendations to support more effective AI-driven binder design.


  • Open Access

    Senataxin deficiency disrupts proteostasis through nucleolar ncRNA-driven protein aggregation

    by Xuemei Wen, Hengyi Xu, Phillip R. Woolley, Olivia M. Conway, Jun Yao, Andreas Matouschek, Alan M. Lambowitz, Tanya T. Paull

    Senataxin is an evolutionarily conserved RNA-DNA helicase involved in DNA repair and transcription termination that is associated with human neurodegenerative disorders. Here, we investigated whether Senataxin loss affects protein homeostasis based on previous work showing R-loop-driven accumulation of DNA damage and protein aggregates in human cells. We find that Senataxin loss results in the accumulation of insoluble proteins, including many factors known to be prone to aggregation in neurodegenerative disorders. These aggregates are located primarily in the nucleolus and are promoted by upregulation of non-coding RNAs expressed from the intergenic spacer region of ribosomal DNA. We also map sites of R-loop accumulation in human cells lacking Senataxin and find higher RNA-DNA hybrids within the ribosomal DNA, peri-centromeric regions, and other intergenic sites but not at annotated protein-coding genes. These findings indicate that Senataxin loss affects the solubility of the proteome through the regulation of transcription-dependent lesions in the nucleus and the nucleolus.


  • Open Access

    Regulation of transcription patterns, poly-ADP-ribose, and RNA-DNA hybrids by the ATM protein kinase

    by Phillip R. Woolley, Xuemei Wen, Olivia M. Conway, Nicolette A. Ender, Ji-Hoon Lee, Tanya T. Paull

    Summary: The ATM protein kinase is a master regulator of the DNA damage response and also an important sensor of oxidative stress. Analysis of gene expression in Ataxia-telangiectasia patient brain tissue shows that large-scale transcriptional changes occur in patient cerebellum that correlate with expression level and GC content of transcribed genes. In human neuron-like cells in culture we map locations of poly-ADP-ribose and RNA-DNA hybrid accumulation genome-wide with ATM inhibition and find that these marks also coincide with high transcription levels, active transcription histone marks, and high GC content. Antioxidant treatment reverses the accumulation of R-loops in transcribed regions, consistent with the central role of ROS in promoting these lesions. Based on these results we postulate that transcription-associated lesions accumulate in ATM-deficient cells and that the single-strand breaks and PARylation at these sites ultimately generate changes in transcription that compromise cerebellum function and lead to neurodegeneration over time in A-T patients.