Sarah Gurev
@sarahgurev.bsky.social
Postdoc @ Debbie Marks Lab, Harvard | Prev. PhD @ MIT EECS || ML for Proteins + Viruses 🦠
🦠The future of pathogen forecasting needs rigorous benchmarks and domain-specific modeling, not only bigger PLMs. EVEREST is a step in that direction.
🔗Paper: biorxiv.org/content/10.1...
💻Code + data: github.com/debbiemarksl...
12/12
🔗Paper: biorxiv.org/content/10.1...
💻Code + data: github.com/debbiemarksl...
12/12
Variant effect prediction with reliability estimation across priority viruses
Viruses pose a significant threat to global health due to their rapid evolution, adaptability, and increasing potential for cross-species transmission. While advances in machine learning and the growi...
biorxiv.org
August 17, 2025 at 3:42 AM
🦠The future of pathogen forecasting needs rigorous benchmarks and domain-specific modeling, not only bigger PLMs. EVEREST is a step in that direction.
🔗Paper: biorxiv.org/content/10.1...
💻Code + data: github.com/debbiemarksl...
12/12
🔗Paper: biorxiv.org/content/10.1...
💻Code + data: github.com/debbiemarksl...
12/12
🙏Amazing collaboration co-led with Noor Youssef
and Navami Jain, @deboramarks.bsky.social, and our funders @cepi.net!
11/12
and Navami Jain, @deboramarks.bsky.social, and our funders @cepi.net!
11/12
August 17, 2025 at 3:42 AM
🙏Amazing collaboration co-led with Noor Youssef
and Navami Jain, @deboramarks.bsky.social, and our funders @cepi.net!
11/12
and Navami Jain, @deboramarks.bsky.social, and our funders @cepi.net!
11/12
This matters for:
⚠️ Future-proof vaccine and therapeutics design
⚠️ Monitoring of high-pandemic risk viruses
⚠️ Dual-use biosecurity risk assessment
Without reliable models, we risk underestimating viral evolution—and overestimating our ability to counter it.
10/12
⚠️ Future-proof vaccine and therapeutics design
⚠️ Monitoring of high-pandemic risk viruses
⚠️ Dual-use biosecurity risk assessment
Without reliable models, we risk underestimating viral evolution—and overestimating our ability to counter it.
10/12
August 17, 2025 at 3:42 AM
This matters for:
⚠️ Future-proof vaccine and therapeutics design
⚠️ Monitoring of high-pandemic risk viruses
⚠️ Dual-use biosecurity risk assessment
Without reliable models, we risk underestimating viral evolution—and overestimating our ability to counter it.
10/12
⚠️ Future-proof vaccine and therapeutics design
⚠️ Monitoring of high-pandemic risk viruses
⚠️ Dual-use biosecurity risk assessment
Without reliable models, we risk underestimating viral evolution—and overestimating our ability to counter it.
10/12
EVEREST highlights:
✅ Where models fail—and why
✅ Which viruses are least/most predictable
✅ How to estimate per-protein, model-specific reliability
✅ Concrete steps to improve ML for viral mutation prediction
9/12
✅ Where models fail—and why
✅ Which viruses are least/most predictable
✅ How to estimate per-protein, model-specific reliability
✅ Concrete steps to improve ML for viral mutation prediction
9/12
August 17, 2025 at 3:42 AM
EVEREST highlights:
✅ Where models fail—and why
✅ Which viruses are least/most predictable
✅ How to estimate per-protein, model-specific reliability
✅ Concrete steps to improve ML for viral mutation prediction
9/12
✅ Where models fail—and why
✅ Which viruses are least/most predictable
✅ How to estimate per-protein, model-specific reliability
✅ Concrete steps to improve ML for viral mutation prediction
9/12
🌍Current models fail to reliably predict mutations in more than half of the high-priority viruses identified by the WHO.
8/12
8/12
August 17, 2025 at 3:42 AM
🌍Current models fail to reliably predict mutations in more than half of the high-priority viruses identified by the WHO.
8/12
8/12
💪Is bigger always better? Maybe not for other taxa but for viruses - yes! For viruses, models continue to improve with increased numbers of parameters.
7/12
7/12
August 17, 2025 at 3:42 AM
💪Is bigger always better? Maybe not for other taxa but for viruses - yes! For viruses, models continue to improve with increased numbers of parameters.
7/12
7/12
🤏Why? Viruses are severely underrepresented in training datasets (<1%) and are further downsampled after common clustering approaches.
6/12
6/12
August 17, 2025 at 3:42 AM
🤏Why? Viruses are severely underrepresented in training datasets (<1%) and are further downsampled after common clustering approaches.
6/12
6/12
📉Despite the hype, protein language models trained across the “protein universe” are outperformed by even the simplest, site-independent alignment-based model.
5/12
5/12
August 17, 2025 at 3:42 AM
📉Despite the hype, protein language models trained across the “protein universe” are outperformed by even the simplest, site-independent alignment-based model.
5/12
5/12
💭Imagine: It’s Day 0 of an outbreak and there’s little experiment data. Computational mutational effect predictions could provide valuable information…if we could trust them. Can we?
EVEREST doesn’t just assess performance. It also quantifies reliability for new viruses.
4/12
EVEREST doesn’t just assess performance. It also quantifies reliability for new viruses.
4/12
August 17, 2025 at 3:42 AM
💭Imagine: It’s Day 0 of an outbreak and there’s little experiment data. Computational mutational effect predictions could provide valuable information…if we could trust them. Can we?
EVEREST doesn’t just assess performance. It also quantifies reliability for new viruses.
4/12
EVEREST doesn’t just assess performance. It also quantifies reliability for new viruses.
4/12
🚀To find out, we built EVEREST: Evolutionary Variant Effect prediction with Reliability ESTimation.
We benchmark models across 45 viral deep mutational scanning datasets spanning >340,000 mutations.
3/12
We benchmark models across 45 viral deep mutational scanning datasets spanning >340,000 mutations.
3/12
August 17, 2025 at 3:42 AM
🚀To find out, we built EVEREST: Evolutionary Variant Effect prediction with Reliability ESTimation.
We benchmark models across 45 viral deep mutational scanning datasets spanning >340,000 mutations.
3/12
We benchmark models across 45 viral deep mutational scanning datasets spanning >340,000 mutations.
3/12
🦠 Protein language models (PLMs) have shown impressive performance in predicting mutation effects. But... viruses are a different beast.
They evolve fast, cross species, and are under pressure from host immunity. Do PLMs still work here?
2/12
They evolve fast, cross species, and are under pressure from host immunity. Do PLMs still work here?
2/12
August 17, 2025 at 3:42 AM
🦠 Protein language models (PLMs) have shown impressive performance in predicting mutation effects. But... viruses are a different beast.
They evolve fast, cross species, and are under pressure from host immunity. Do PLMs still work here?
2/12
They evolve fast, cross species, and are under pressure from host immunity. Do PLMs still work here?
2/12