Jeffrey A. Ruffolo
Research Subjects
Jeffrey A. Ruffolo has a total of 109 co-authors. Here are the top co-authors by number of shared publications:
- Jeffrey J. Gray
Johns Hopkins University
16 shared publications - Ali Madani
Profluent Bio, Berkeley, CA, USA
8 shared publications Aadyot Bhatnagar
Profluent Bio, Emeryville, CA, USA
5 shared publicationsSai Pooja Mahajan
Department of Chemical and Biomolecular Engineering, The Johns Hopkins University, Baltimore, USA
5 shared publicationsEmily Hill
Profluent Bio, Emeryville, CA, USA
4 shared publicationsJoel Beazer
4 shared publications
Latest Publications
- Top Cited Papers
- 2 February 2026
- Published by Springer Nature in Nature Biotechnology
Customizing CRISPR–Cas PAM specificity with protein language models
CRISPR-Cas enzymes must recognize a protospacer-adjacent motif (PAM) to edit a genomic site, greatly limiting the range of targetable sequences in a genome. Although engineering strategies to alter PAM specificity exist, they typically require labor-intensive, iterative experimentation. We introduce an evolution-informed deep learning model, Protein2PAM, to efficiently guide the design of Cas protein variants tailored to recognize specific PAMs. Trained on a dataset of over 45,000 CRISPR-Cas PAMs, Protein2PAM rapidly and accurately predicts PAM specificity directly from Cas proteins across type I, II and V CRISPR-Cas systems. Using in silico mutagenesis, the model identifies residues critical for PAM recognition in Cas9 without using structural information. We use Protein2PAM to computationally evolve Nme1Cas9, generating variants with broadened PAM recognition and up to a 50-fold increase in PAM cleavage rates compared to the wild type in vitro. Our machine learning approach allows Cas enzymes to target sequences that were previously inaccessible because of PAM constraints, potentially increasing target flexibility in personalized genome editing.
- 2 February 2026
- Published by Springer Nature in Nature Biotechnology
Top Cited PapersCustomizing CRISPR–Cas PAM specificity with protein language models
CRISPR-Cas enzymes must recognize a protospacer-adjacent motif (PAM) to edit a genomic site, greatly limiting the range of targetable sequences in a genome. Although engineering strategies to alter PAM specificity exist, they typically require labor-intensive, iterative experimentation. We introduce an evolution-informed deep learning model, Protein2PAM, to efficiently guide the design of Cas protein variants tailored to recognize specific PAMs. Trained on a dataset of over 45,000 CRISPR-Cas PAMs, Protein2PAM rapidly and accurately predicts PAM specificity directly from Cas proteins across type I, II and V CRISPR-Cas systems. Using in silico mutagenesis, the model identifies residues critical for PAM recognition in Cas9 without using structural information. We use Protein2PAM to computationally evolve Nme1Cas9, generating variants with broadened PAM recognition and up to a 50-fold increase in PAM cleavage rates compared to the wild type in vitro. Our machine learning approach allows Cas enzymes to target sequences that were previously inaccessible because of PAM constraints, potentially increasing target flexibility in personalized genome editing.
- Open Access
E1: Retrieval-Augmented Protein Encoder Models
Large language models trained on natural proteins learn powerful representations of protein sequences that are useful for downstream understanding and prediction tasks. Because they are only exposed to individual protein sequences during pretraining without any additional contextual information, conventional protein language models suffer from parameter inefficiencies in learning, baked-in phylogenetic biases, and functional performance issues at larger scales. To address these challenges, we have built Profluent-E1, a family of retrieval-augmented protein language models that explicitly condition on homologous sequences. By integrating retrieved evolutionary context through block-causal multi-sequence attention, E1 captures both general and family-specific constraints without fine-tuning. We train E1 models on four trillion tokens from the Profluent Protein Atlas and achieve state-of-the-art performance across zero-shot fitness and unsupervised contact-map prediction benchmarks – surpassing alternative sequence-only models. Performance scales with model size from 150M to 600M parameters, and E1 can be used flexibly in single-sequence or retrieval-augmented inference mode for fitness prediction, variant ranking, and embeddings for structural tasks. To encourage open science and further development in retrieval-augmented protein language models, we release three models for free research and commercial use at https://github.com/Profluent-AI/E1 .
Open AccessE1: Retrieval-Augmented Protein Encoder Models
Large language models trained on natural proteins learn powerful representations of protein sequences that are useful for downstream understanding and prediction tasks. Because they are only exposed to individual protein sequences during pretraining without any additional contextual information, conventional protein language models suffer from parameter inefficiencies in learning, baked-in phylogenetic biases, and functional performance issues at larger scales. To address these challenges, we have built Profluent-E1, a family of retrieval-augmented protein language models that explicitly condition on homologous sequences. By integrating retrieved evolutionary context through block-causal multi-sequence attention, E1 captures both general and family-specific constraints without fine-tuning. We train E1 models on four trillion tokens from the Profluent Protein Atlas and achieve state-of-the-art performance across zero-shot fitness and unsupervised contact-map prediction benchmarks – surpassing alternative sequence-only models. Performance scales with model size from 150M to 600M parameters, and E1 can be used flexibly in single-sequence or retrieval-augmented inference mode for fitness prediction, variant ranking, and embeddings for structural tasks. To encourage open science and further development in retrieval-augmented protein language models, we release three models for free research and commercial use at https://github.com/Profluent-AI/E1 .
- 29 September 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (10) , 2017-2019
What does a language model know about proteins?
- 29 September 2025
- Published by Springer Nature in Nature Methods
- Vol. 22 (10) , 2017-2019
What does a language model know about proteins?
- Top Cited PapersOpen Access
- 30 July 2025
- Published by Springer Nature in Nature
- Vol. 645 (8080) , 518-525
Design of highly functional genome editors by modelling CRISPR–Cas sequences
Gene editing has the potential to solve fundamental challenges in agriculture, biotechnology and human health. CRISPR-based gene editors derived from microorganisms, although powerful, often show notable functional tradeoffs when ported into non-native environments, such as human cells1. Artificial-intelligence-enabled design provides a powerful alternative with the potential to bypass evolutionary constraints and generate editors with optimal properties. Here, using large language models2 trained on biological diversity at scale, we demonstrate successful precision editing of the human genome with a programmable gene editor designed with artificial intelligence. To achieve this goal, we curated a dataset of more than 1 million CRISPR operons through systematic mining of 26 terabases of assembled genomes and metagenomes. We demonstrate the capacity of our models by generating 4.8× the number of protein clusters across CRISPR–Cas families found in nature and tailoring single-guide RNA sequences for Cas9-like effector proteins. Several of the generated gene editors show comparable or improved activity and specificity relative to SpCas9, the prototypical gene editing effector, while being 400 mutations away in sequence. Finally, we demonstrate that an artificial-intelligence-generated gene editor, denoted as OpenCRISPR-1, exhibits compatibility with base editing. We release OpenCRISPR-1 to facilitate broad, ethical use across research and commercial applications.
- 30 July 2025
- Published by Springer Nature in Nature
- Vol. 645 (8080) , 518-525
Top Cited PapersOpen AccessDesign of highly functional genome editors by modelling CRISPR–Cas sequences
Gene editing has the potential to solve fundamental challenges in agriculture, biotechnology and human health. CRISPR-based gene editors derived from microorganisms, although powerful, often show notable functional tradeoffs when ported into non-native environments, such as human cells1. Artificial-intelligence-enabled design provides a powerful alternative with the potential to bypass evolutionary constraints and generate editors with optimal properties. Here, using large language models2 trained on biological diversity at scale, we demonstrate successful precision editing of the human genome with a programmable gene editor designed with artificial intelligence. To achieve this goal, we curated a dataset of more than 1 million CRISPR operons through systematic mining of 26 terabases of assembled genomes and metagenomes. We demonstrate the capacity of our models by generating 4.8× the number of protein clusters across CRISPR–Cas families found in nature and tailoring single-guide RNA sequences for Cas9-like effector proteins. Several of the generated gene editors show comparable or improved activity and specificity relative to SpCas9, the prototypical gene editing effector, while being 400 mutations away in sequence. Finally, we demonstrate that an artificial-intelligence-generated gene editor, denoted as OpenCRISPR-1, exhibits compatibility with base editing. We release OpenCRISPR-1 to facilitate broad, ethical use across research and commercial applications.
- Open Access
Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins
Generative protein language models (PLMs) are powerful tools for designing proteins purpose-built to solve problems in medicine, agriculture, and industrial processes. Recent work has trained ever larger language models, but there has been little systematic study of the optimal training distributions and the influence of model scale on the sequences generated by PLMs. We introduce the ProGen3 family of sparse generative PLMs, and we develop compute-optimal scaling laws to scale up to a 46B-parameter model pre-trained on 1.5T amino acid tokens. Pro-Gen3’s pre-training data is sampled from an optimized data distribution over the Profluent Protein Atlas v1, a carefully curated dataset of 3.4B full-length proteins. We evaluate for the first time in the wet lab the influence of model scale on the sequences generated by PLMs, and we find that larger models generate viable proteins for a much wider diversity of protein families. Finally, we find both computationally and experimentally that larger models are more responsive to alignment with laboratory data, resulting in improved protein fitness prediction and sequence generation capabilities. These results indicate that larger PLMs like ProGen3-46B trained on larger, well-curated datasets are powerful foundation models that push the frontier of protein design. 1
Open AccessScaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins
Generative protein language models (PLMs) are powerful tools for designing proteins purpose-built to solve problems in medicine, agriculture, and industrial processes. Recent work has trained ever larger language models, but there has been little systematic study of the optimal training distributions and the influence of model scale on the sequences generated by PLMs. We introduce the ProGen3 family of sparse generative PLMs, and we develop compute-optimal scaling laws to scale up to a 46B-parameter model pre-trained on 1.5T amino acid tokens. Pro-Gen3’s pre-training data is sampled from an optimized data distribution over the Profluent Protein Atlas v1, a carefully curated dataset of 3.4B full-length proteins. We evaluate for the first time in the wet lab the influence of model scale on the sequences generated by PLMs, and we find that larger models generate viable proteins for a much wider diversity of protein families. Finally, we find both computationally and experimentally that larger models are more responsive to alignment with laboratory data, resulting in improved protein fitness prediction and sequence generation capabilities. These results indicate that larger PLMs like ProGen3-46B trained on larger, well-curated datasets are powerful foundation models that push the frontier of protein design. 1
- Open Access
Engineering of CRISPR-Cas PAM recognition using deep learning of vast evolutionary data
CRISPR-Cas enzymes must recognize a protospacer-adjacent motif (PAM) to edit a genomic site, significantly limiting the range of targetable sequences in a genome. Machine learning-based protein engineering provides a powerful solution to efficiently generate Cas protein variants tailored to recognize specific PAMs. Here, we present Protein2PAM, an evolution-informed deep learning model trained on a dataset of over 45,000 CRISPR-Cas PAMs. Protein2PAM rapidly and accurately predicts PAM specificity directly from Cas proteins across Type I, II, and V CRISPR-Cas systems. Using in silico deep mutational scanning, we demonstrate that the model can identify residues critical for PAM recognition in Cas9 without utilizing structural information. As a proof of concept for protein engineering, we employ Protein2PAM to computationally evolve Nme1Cas9, generating variants with broadened PAM recognition and up to a 50-fold increase in PAM cleavage rates compared to the wild-type under in vitro conditions. This work represents the first successful application of machine learning to achieve customization of Cas enzymes for alternate PAM recognition, paving the way for personalized genome editing.
Open AccessEngineering of CRISPR-Cas PAM recognition using deep learning of vast evolutionary data
CRISPR-Cas enzymes must recognize a protospacer-adjacent motif (PAM) to edit a genomic site, significantly limiting the range of targetable sequences in a genome. Machine learning-based protein engineering provides a powerful solution to efficiently generate Cas protein variants tailored to recognize specific PAMs. Here, we present Protein2PAM, an evolution-informed deep learning model trained on a dataset of over 45,000 CRISPR-Cas PAMs. Protein2PAM rapidly and accurately predicts PAM specificity directly from Cas proteins across Type I, II, and V CRISPR-Cas systems. Using in silico deep mutational scanning, we demonstrate that the model can identify residues critical for PAM recognition in Cas9 without utilizing structural information. As a proof of concept for protein engineering, we employ Protein2PAM to computationally evolve Nme1Cas9, generating variants with broadened PAM recognition and up to a 50-fold increase in PAM cleavage rates compared to the wild-type under in vitro conditions. This work represents the first successful application of machine learning to achieve customization of Cas enzymes for alternate PAM recognition, paving the way for personalized genome editing.
- 4 November 2024
- Published by Springer Nature in Nature Biotechnology
- Vol. 42 (11) , 1637-1642
AIntibody: an experimentally validated in silico antibody discovery design challenge
- 4 November 2024
- Published by Springer Nature in Nature Biotechnology
- Vol. 42 (11) , 1637-1642
AIntibody: an experimentally validated in silico antibody discovery design challenge
- Open Access
Adapting protein language models for structure-conditioned design
Generative models for protein design trained on experimentally determined structures have proven useful for a variety of design tasks. However, such methods are limited by the quantity and diversity of structures used for training, which represent a small, biased fraction of protein space. Here, we describe proseLM, a method for protein sequence design based on adaptation of protein language models to incorporate structural and functional context. We show that proseLM benefits from the scaling trends of underlying language models, and that the addition of non-protein context – nucleic acids, ligands, and ions – improves recovery of native residues during design by 4-5% across model scales. These improvements are most pronounced for residues that directly interface with non-protein context, which are faithfully recovered at rates >70% by the most capable proseLM models. We experimentally validated proseLM by optimizing the editing efficiency of genome editors in human cells, achieving a 50% increase in base editing activity, and by redesigning therapeutic antibodies, resulting in a PD-1 binder with 2.2 nM affinity.
Open AccessAdapting protein language models for structure-conditioned design
Generative models for protein design trained on experimentally determined structures have proven useful for a variety of design tasks. However, such methods are limited by the quantity and diversity of structures used for training, which represent a small, biased fraction of protein space. Here, we describe proseLM, a method for protein sequence design based on adaptation of protein language models to incorporate structural and functional context. We show that proseLM benefits from the scaling trends of underlying language models, and that the addition of non-protein context – nucleic acids, ligands, and ions – improves recovery of native residues during design by 4-5% across model scales. These improvements are most pronounced for residues that directly interface with non-protein context, which are faithfully recovered at rates >70% by the most capable proseLM models. We experimentally validated proseLM by optimizing the editing efficiency of genome editors in human cells, achieving a 50% increase in base editing activity, and by redesigning therapeutic antibodies, resulting in a PD-1 binder with 2.2 nM affinity.
- Open Access
- 20 June 2024
- Published by Taylor & Francis in mAbs
- Vol. 16 (1) , 2362775
Toward enhancement of antibody thermostability and affinity by computational design in the absence of antigen
Over the past two decades, therapeutic antibodies have emerged as a rapidly expanding domain within the field of biologics. In silico tools that can streamline the process of antibody discovery and optimization are critical to support a pipeline that is growing more numerous and complex every year. High-quality structural information remains critical for the antibody optimization process, but antibody-antigen complex structures are often unavailable and in silico antibody docking methods are still unreliable. In this study, DeepAb, a deep learning model for predicting antibody Fv structure directly from sequence, was used in conjunction with single-point experimental deep mutational scanning (DMS) enrichment data to design 200 potentially optimized variants of an anti-hen egg lysozyme (HEL) antibody. We sought to determine whether DeepAb-designed variants containing combinations of beneficial mutations from the DMS exhibit enhanced thermostability and whether this optimization affected their developability profile. The 200 variants were produced through a robust high-throughput method and tested for thermal and colloidal stability (Tonset, Tm, Tagg), affinity (KD) relative to the parental antibody, and for developability parameters (nonspecific binding, aggregation propensity, self-association). Of the designed clones, 91% and 94% exhibited increased thermal and colloidal stability and affinity, respectively. Of these, 10% showed a significantly increased affinity for HEL (5- to 21-fold increase) and thermostability (>2.5C increase in Tm1), with most clones retaining the favorable developability profile of the parental antibody. Additional in silico tests suggest that these methods would enrich for binding affinity even without first collecting experimental DMS measurements. These data open the possibility of in silico antibody optimization without the need to predict the antibody-antigen interface, which is notoriously difficult in the absence of crystal structures.
- 20 June 2024
- Published by Taylor & Francis in mAbs
- Vol. 16 (1) , 2362775
Open AccessToward enhancement of antibody thermostability and affinity by computational design in the absence of antigen
Over the past two decades, therapeutic antibodies have emerged as a rapidly expanding domain within the field of biologics. In silico tools that can streamline the process of antibody discovery and optimization are critical to support a pipeline that is growing more numerous and complex every year. High-quality structural information remains critical for the antibody optimization process, but antibody-antigen complex structures are often unavailable and in silico antibody docking methods are still unreliable. In this study, DeepAb, a deep learning model for predicting antibody Fv structure directly from sequence, was used in conjunction with single-point experimental deep mutational scanning (DMS) enrichment data to design 200 potentially optimized variants of an anti-hen egg lysozyme (HEL) antibody. We sought to determine whether DeepAb-designed variants containing combinations of beneficial mutations from the DMS exhibit enhanced thermostability and whether this optimization affected their developability profile. The 200 variants were produced through a robust high-throughput method and tested for thermal and colloidal stability (Tonset, Tm, Tagg), affinity (KD) relative to the parental antibody, and for developability parameters (nonspecific binding, aggregation propensity, self-association). Of the designed clones, 91% and 94% exhibited increased thermal and colloidal stability and affinity, respectively. Of these, 10% showed a significantly increased affinity for HEL (5- to 21-fold increase) and thermostability (>2.5C increase in Tm1), with most clones retaining the favorable developability profile of the parental antibody. Additional in silico tests suggest that these methods would enrich for binding affinity even without first collecting experimental DMS measurements. These data open the possibility of in silico antibody optimization without the need to predict the antibody-antigen interface, which is notoriously difficult in the absence of crystal structures.
- Top Cited Papers
- 15 February 2024
- Published by Springer Nature in Nature Biotechnology
- Vol. 42 (2) , 200-202
Designing proteins with language models
- 15 February 2024
- Published by Springer Nature in Nature Biotechnology
- Vol. 42 (2) , 200-202
Top Cited PapersDesigning proteins with language models