Thomas Bikias
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Thomas Bikias has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Sai T. Reddy
ETH Zurich
4 shared publications - Evangelos Stamkopoulos
Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland
2 shared publications Joseph M. Taft
Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland
2 shared publications- Mason Minot
ETH Zürich, Department of Biosystems Science and Engineering
2 shared publications - Alexander Yermanos
University Medical Center Utrecht Center for Translational Immunology Lundlaan 6 , 3584 EA Utrecht
1 shared publication Andreas Agrafiotis
Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland
1 shared publication
Latest Publications
- 15 July 2025
- Published by Elsevier in Dermatologic Clinics
- Vol. 43 (4) , 573-583
Artificial Intelligence in Dermatology Research and Drug Discovery
- 15 July 2025
- Published by Elsevier in Dermatologic Clinics
- Vol. 43 (4) , 573-583
Artificial Intelligence in Dermatology Research and Drug Discovery
- Open Access
- 2 July 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (4)
PLMFit: benchmarking transfer learning with protein language models for protein engineering
Protein language models (PLMs) have emerged as a useful resource for protein engineering applications. Transfer learning (TL) leverages pre-trained parameters to extract features to train machine learning models or adjust the weights of PLMs for novel tasks via fine-tuning (FT) through back-propagation. TL methods have shown potential for enhancing protein predictions performance when paired with PLMs, however there is a notable lack of comparative analyses that benchmark TL methods applied to state-of-the-art PLMs, identify optimal strategies for transferring knowledge and determine the most suitable approach for specific tasks. Here, we report PLMFit, a benchmarking study that combines, three state-of-the-art PLMs (ESM2, ProGen2, ProteinBert), with three TL methods (feature extraction, low-rank adaptation, bottleneck adapters) for five protein engineering datasets. We conducted over >3150 in silico experiments, altering PLM sizes and layers, TL hyperparameters and different training procedures. Our experiments reveal three key findings: (i) utilizing a partial fraction of PLM for TL does not detrimentally impact performance, (ii) the choice between feature extraction (FE) and fine-tuning is primarily dictated by the amount and diversity of data, and (iii) FT is most effective when generalization is necessary and only limited data is available. We provide PLMFit as an open-source software package, serving as a valuable resource for the scientific community to facilitate the FE and FT of PLMs for various applications.
- 2 July 2025
- Published by Oxford University Press (OUP) in Briefings in Bioinformatics
- Vol. 26 (4)
Open AccessPLMFit: benchmarking transfer learning with protein language models for protein engineering
Protein language models (PLMs) have emerged as a useful resource for protein engineering applications. Transfer learning (TL) leverages pre-trained parameters to extract features to train machine learning models or adjust the weights of PLMs for novel tasks via fine-tuning (FT) through back-propagation. TL methods have shown potential for enhancing protein predictions performance when paired with PLMs, however there is a notable lack of comparative analyses that benchmark TL methods applied to state-of-the-art PLMs, identify optimal strategies for transferring knowledge and determine the most suitable approach for specific tasks. Here, we report PLMFit, a benchmarking study that combines, three state-of-the-art PLMs (ESM2, ProGen2, ProteinBert), with three TL methods (feature extraction, low-rank adaptation, bottleneck adapters) for five protein engineering datasets. We conducted over >3150 in silico experiments, altering PLM sizes and layers, TL hyperparameters and different training procedures. Our experiments reveal three key findings: (i) utilizing a partial fraction of PLM for TL does not detrimentally impact performance, (ii) the choice between feature extraction (FE) and fine-tuning is primarily dictated by the amount and diversity of data, and (iii) FT is most effective when generalization is necessary and only limited data is available. We provide PLMFit as an open-source software package, serving as a valuable resource for the scientific community to facilitate the FE and FT of PLMs for various applications.
- Open Access
Dissecting serum polyclonal antibody escape to SARS-CoV-2 variants by deep mutational learning
The rapid emergence of SARS-CoV-2 variants harboring multiple receptor-binding domain (RBD) mutations continues to challenge the efficacy of vaccines and antibody therapeutics. While deep mutational scanning (DMS) has been instrumental in mapping single-mutation effects on antibody binding and immune escape, it remains limited in its ability to assess combinatorial mutational landscapes. Here, we extend deep mutational learning (DML), a method integrating combinatorial mutagenesis, yeast surface display, deep sequencing, and machine learning, to analyze serum polyclonal antibody escape. Human sera from COVID-19-vaccinated individuals were screened against diverse RBD variant libraries, validating 300 serum-variant interactions across 10 individuals by comparing predicted and observed binding to 30 RBD variants, confirming accurate mapping of binding and escape profiles. Model performance remained consistent across machine learning architectures, suggesting that serum binding and escape are governed by distinct, localized RBD sequence features. Notably, escape profiles were highly individualized, whereas binding signatures were more conserved, reflecting convergent epitope targeting. This approach highlights the potential of DML to generalize beyond observed RBD variants, assess cohort-specific immune breadth, and inform vaccine and therapeutic design in the face of viral evolution.
Open AccessDissecting serum polyclonal antibody escape to SARS-CoV-2 variants by deep mutational learning
The rapid emergence of SARS-CoV-2 variants harboring multiple receptor-binding domain (RBD) mutations continues to challenge the efficacy of vaccines and antibody therapeutics. While deep mutational scanning (DMS) has been instrumental in mapping single-mutation effects on antibody binding and immune escape, it remains limited in its ability to assess combinatorial mutational landscapes. Here, we extend deep mutational learning (DML), a method integrating combinatorial mutagenesis, yeast surface display, deep sequencing, and machine learning, to analyze serum polyclonal antibody escape. Human sera from COVID-19-vaccinated individuals were screened against diverse RBD variant libraries, validating 300 serum-variant interactions across 10 individuals by comparing predicted and observed binding to 30 RBD variants, confirming accurate mapping of binding and escape profiles. Model performance remained consistent across machine learning architectures, suggesting that serum binding and escape are governed by distinct, localized RBD sequence features. Notably, escape profiles were highly individualized, whereas binding signatures were more conserved, reflecting convergent epitope targeting. This approach highlights the potential of DML to generalize beyond observed RBD variants, assess cohort-specific immune breadth, and inform vaccine and therapeutic design in the face of viral evolution.
- Open Access
PLMFit : Benchmarking Transfer Learning with Protein Language Models for Protein Engineering
Protein language models (PLMs) have emerged as a useful resource for protein engineering applications. Transfer learning (TL) leverages pre-trained parameters to extract features to train machine learning models or adjust the weights of PLMs for novel tasks via fine-tuning through back-propagation. TL methods have shown potential for enhancing protein predictions performance when paired with PLMs, however there is a notable lack of comparative analyses that benchmark TL methods applied to state-of-the-art PLMs, identify optimal strategies for transferring knowledge and determine the most suitable approach for specific tasks. Here, we report PLMFit, a benchmarking study that combines, three state-of-the-art PLMs (ESM2, ProGen2, ProteinBert), with three TL methods (feature extraction, low-rank adaptation, bottleneck adapters) for five protein engineering datasets. We conducted over >3,150 in silico experiments, altering PLM sizes and layers, TL hyperparameters and different training procedures. Our experiments reveal three key findings: (i) utilizing a partial fraction of PLM for TL does not detrimentally impact performance, (ii) the choice between feature extraction and fine-tuning is primarily dictated by the amount and diversity of data and (iii) fine-tuning is most effective when generalization is necessary and only limited data is available. We provide PLMFit as an open-source software package, serving as a valuable resource for the scientific community to facilitate the feature extraction and fine-tuning of PLMs for various applications. ONE SENTENCE SUMMARY: PLMFit is a comparative analysis aimed at identifying the most effective strategies for transfer knowledge from protein language models by benchmarking fine-tuning techniques on a range of protein engineering tasks.
Open AccessPLMFit : Benchmarking Transfer Learning with Protein Language Models for Protein Engineering
Protein language models (PLMs) have emerged as a useful resource for protein engineering applications. Transfer learning (TL) leverages pre-trained parameters to extract features to train machine learning models or adjust the weights of PLMs for novel tasks via fine-tuning through back-propagation. TL methods have shown potential for enhancing protein predictions performance when paired with PLMs, however there is a notable lack of comparative analyses that benchmark TL methods applied to state-of-the-art PLMs, identify optimal strategies for transferring knowledge and determine the most suitable approach for specific tasks. Here, we report PLMFit, a benchmarking study that combines, three state-of-the-art PLMs (ESM2, ProGen2, ProteinBert), with three TL methods (feature extraction, low-rank adaptation, bottleneck adapters) for five protein engineering datasets. We conducted over >3,150 in silico experiments, altering PLM sizes and layers, TL hyperparameters and different training procedures. Our experiments reveal three key findings: (i) utilizing a partial fraction of PLM for TL does not detrimentally impact performance, (ii) the choice between feature extraction and fine-tuning is primarily dictated by the amount and diversity of data and (iii) fine-tuning is most effective when generalization is necessary and only limited data is available. We provide PLMFit as an open-source software package, serving as a valuable resource for the scientific community to facilitate the feature extraction and fine-tuning of PLMs for various applications. ONE SENTENCE SUMMARY: PLMFit is a comparative analysis aimed at identifying the most effective strategies for transfer knowledge from protein language models by benchmarking fine-tuning techniques on a range of protein engineering tasks.
- Open Access
Synthetic coevolution reveals adaptive mutational trajectories of neutralizing antibodies and SARS-CoV-2
The Covid-19 pandemic showcases a coevolutionary race between the human immune system and SARS-CoV-2, mirroring the Red Queen hypothesis of evolutionary biology. The immune system generates neutralizing antibodies targeting the SARS-CoV-2 spike protein’s receptor binding domain (RBD), crucial for host cell invasion, while the virus evolves to evade antibody recognition. Here, we establish a synthetic coevolution system combining high-throughput screening of antibody and RBD variant libraries with protein mutagenesis, surface display, and deep sequencing. Additionally, we train a protein language machine learning model that predicts antibody escape to RBD variants. Synthetic coevolution reveals antagonistic and compensatory mutational trajectories of neutralizing antibodies and SARS-CoV-2 variants, enhancing the understanding of this evolutionary conflict.
Open AccessSynthetic coevolution reveals adaptive mutational trajectories of neutralizing antibodies and SARS-CoV-2
The Covid-19 pandemic showcases a coevolutionary race between the human immune system and SARS-CoV-2, mirroring the Red Queen hypothesis of evolutionary biology. The immune system generates neutralizing antibodies targeting the SARS-CoV-2 spike protein’s receptor binding domain (RBD), crucial for host cell invasion, while the virus evolves to evade antibody recognition. Here, we establish a synthetic coevolution system combining high-throughput screening of antibody and RBD variant libraries with protein mutagenesis, surface display, and deep sequencing. Additionally, we train a protein language machine learning model that predicts antibody escape to RBD variants. Synthetic coevolution reveals antagonistic and compensatory mutational trajectories of neutralizing antibodies and SARS-CoV-2 variants, enhancing the understanding of this evolutionary conflict.