Alissa Hummer
@alissahummer.com
Schmidt Science Fellow | Postdoc @ Stanford | Prev. DPhil @ Oxford || ML for Biomolecular Modeling & Design
Excited to be pivoting from molecules to cells for my Schmidt Science Fellowship, advised by Emma Lundberg and Wah Chiu!
I’m looking forward to building ML models that better reflect how molecules & cells look in real life 🔬
I’m looking forward to building ML models that better reflect how molecules & cells look in real life 🔬
We're so excited to welcome our 2025 Fellows to Oxford for their first Science Leadership Program convening.
And for 2025 Fellow @alissahummer.com it is a homecoming!
Our 2025 Fellows' stories and our Science Leadership Program exemplify our mission.
schmidtsciencefellows.org/news/our-202...
And for 2025 Fellow @alissahummer.com it is a homecoming!
Our 2025 Fellows' stories and our Science Leadership Program exemplify our mission.
schmidtsciencefellows.org/news/our-202...
Our 2025 Fellows Embark on Their Leadership Journey • Schmidt Science Fellows
As we welcome our 2025 Fellows to Oxford for their first Science Leadership Program convening, we profile Alissa Hummer, who will be returning to familiar ground. With a PhD in machine learning from ...
schmidtsciencefellows.org
October 4, 2025 at 5:16 PM
Excited to be pivoting from molecules to cells for my Schmidt Science Fellowship, advised by Emma Lundberg and Wah Chiu!
I’m looking forward to building ML models that better reflect how molecules & cells look in real life 🔬
I’m looking forward to building ML models that better reflect how molecules & cells look in real life 🔬
Our paper on generalizable antibody-antigen binding affinity prediction has been featured on the cover of the August Issue of @natcomputsci.nature.com! 📔🎉
🚨Our August issue is now live and includes research on antibody-antigen binding, molecular screening for zeolite synthesis, psychological experiments with LLMs, and much more!
www.nature.com/natcomputsci...
www.nature.com/natcomputsci...
August 26, 2025 at 4:14 PM
Our paper on generalizable antibody-antigen binding affinity prediction has been featured on the cover of the August Issue of @natcomputsci.nature.com! 📔🎉
Reposted by Alissa Hummer
🚨Our August issue is now live and includes research on antibody-antigen binding, molecular screening for zeolite synthesis, psychological experiments with LLMs, and much more!
www.nature.com/natcomputsci...
www.nature.com/natcomputsci...
August 25, 2025 at 1:03 PM
🚨Our August issue is now live and includes research on antibody-antigen binding, molecular screening for zeolite synthesis, psychological experiments with LLMs, and much more!
www.nature.com/natcomputsci...
www.nature.com/natcomputsci...
Reposted by Alissa Hummer
Out now! @alissahummer.com @opig.stats.ox.ac.uk
and colleagues present Graphinity, a method to predict change in antibody-antigen binding affinity (∆∆G). Also featuring synthetic datasets of ~1 million FoldX-generated and >20,000 Rosetta Flex ddG-generated ∆∆G values!
www.nature.com/articles/s43...
and colleagues present Graphinity, a method to predict change in antibody-antigen binding affinity (∆∆G). Also featuring synthetic datasets of ~1 million FoldX-generated and >20,000 Rosetta Flex ddG-generated ∆∆G values!
www.nature.com/articles/s43...
Investigating the volume and diversity of data needed for generalizable antibody–antigen ΔΔG prediction - Nature Computational Science
Predicting the effects of mutations on antibody–antigen binding is a key challenge in therapeutic antibody development. Orders of magnitude more data will be needed to unlock accurate, robust predicti...
www.nature.com
July 8, 2025 at 12:05 PM
Out now! @alissahummer.com @opig.stats.ox.ac.uk
and colleagues present Graphinity, a method to predict change in antibody-antigen binding affinity (∆∆G). Also featuring synthetic datasets of ~1 million FoldX-generated and >20,000 Rosetta Flex ddG-generated ∆∆G values!
www.nature.com/articles/s43...
and colleagues present Graphinity, a method to predict change in antibody-antigen binding affinity (∆∆G). Also featuring synthetic datasets of ~1 million FoldX-generated and >20,000 Rosetta Flex ddG-generated ∆∆G values!
www.nature.com/articles/s43...
Our work exploring the ability of and requirements for ML to predict the effects of mutations on antibody-antigen binding affinity (ΔΔG) is out now in @natcomputsci.nature.com!
Out now! @alissahummer.com @opig.stats.ox.ac.uk
and colleagues present Graphinity, a method to predict change in antibody-antigen binding affinity (∆∆G). Also featuring synthetic datasets of ~1 million FoldX-generated and >20,000 Rosetta Flex ddG-generated ∆∆G values!
www.nature.com/articles/s43...
and colleagues present Graphinity, a method to predict change in antibody-antigen binding affinity (∆∆G). Also featuring synthetic datasets of ~1 million FoldX-generated and >20,000 Rosetta Flex ddG-generated ∆∆G values!
www.nature.com/articles/s43...
Investigating the volume and diversity of data needed for generalizable antibody–antigen ΔΔG prediction - Nature Computational Science
Predicting the effects of mutations on antibody–antigen binding is a key challenge in therapeutic antibody development. Orders of magnitude more data will be needed to unlock accurate, robust predicti...
www.nature.com
July 9, 2025 at 4:18 PM
Our work exploring the ability of and requirements for ML to predict the effects of mutations on antibody-antigen binding affinity (ΔΔG) is out now in @natcomputsci.nature.com!
Reposted by Alissa Hummer
What is the status of nucleic acid structure prediction? Our analysis of CASP16 (doi.org/10.1101/2025...) reveals human expertise is still necessary for the most accurate prediction, but accuracy still heavily relies on templates; having seen a similar structure already.
Assessment of nucleic acid structure prediction in CASP16
Consistently accurate 3D nucleic acid structure prediction would facilitate studies of the diverse RNA and DNA molecules underlying life. In CASP16, blind predictions for 42 targets canvassing a full ...
doi.org
May 20, 2025 at 9:01 PM
What is the status of nucleic acid structure prediction? Our analysis of CASP16 (doi.org/10.1101/2025...) reveals human expertise is still necessary for the most accurate prediction, but accuracy still heavily relies on templates; having seen a similar structure already.
It was great to be involved in the evaluation of nucleic acid structure prediction in CASP16! 🧬
RNA modeling remains challenging for deep learning, esp. in the absence of templates and for long-range tertiary/quaternary interactions. Encouraging signs from deep evolutionary data though.
RNA modeling remains challenging for deep learning, esp. in the absence of templates and for long-range tertiary/quaternary interactions. Encouraging signs from deep evolutionary data though.
Assessment of nucleic acid structure prediction in CASP16
Consistently accurate 3D nucleic acid structure prediction would facilitate studies of the diverse RNA and DNA molecules underlying life. In CASP16, blind predictions for 42 targets canvassing a full ...
www.biorxiv.org
May 14, 2025 at 3:32 AM
It was great to be involved in the evaluation of nucleic acid structure prediction in CASP16! 🧬
RNA modeling remains challenging for deep learning, esp. in the absence of templates and for long-range tertiary/quaternary interactions. Encouraging signs from deep evolutionary data though.
RNA modeling remains challenging for deep learning, esp. in the absence of templates and for long-range tertiary/quaternary interactions. Encouraging signs from deep evolutionary data though.
I'm so excited to join this interdisciplinary community as a 2025 Schmidt Science Fellow!
After years behind a keyboard, I will be pivoting toward the wet lab. To unlock the true potential of ML for biology/biomedicine, we need high-quality data and robust evaluation 🔬🧫🧪
After years behind a keyboard, I will be pivoting toward the wet lab. To unlock the true potential of ML for biology/biomedicine, we need high-quality data and robust evaluation 🔬🧫🧪
We are excited to announce our 2025 Schmidt Science Fellows! 32 early career researchers, nominated by the world’s leading research universities, who will take an interdisciplinary approach to advancing discovery schmidtsciencefellows.org/news/2025-fe...
April 3, 2025 at 3:35 PM
I'm so excited to join this interdisciplinary community as a 2025 Schmidt Science Fellow!
After years behind a keyboard, I will be pivoting toward the wet lab. To unlock the true potential of ML for biology/biomedicine, we need high-quality data and robust evaluation 🔬🧫🧪
After years behind a keyboard, I will be pivoting toward the wet lab. To unlock the true potential of ML for biology/biomedicine, we need high-quality data and robust evaluation 🔬🧫🧪
Reposted by Alissa Hummer
AntiFold, our antibody inverse folding model, has been published at Bioinformatics Advances. Work led by @magnushoie.bsky.social & @alissahummer.com.
Paper: academic.oup.com/bioinformati...
Webserver: opig.stats.ox.ac.uk/webapps/anti...
Codebase available on Github: github.com/oxpig/AntiFold
Paper: academic.oup.com/bioinformati...
Webserver: opig.stats.ox.ac.uk/webapps/anti...
Codebase available on Github: github.com/oxpig/AntiFold
AntiFold: Improved structure-based antibody design using inverse folding
AbstractSummary. The design and optimization of antibodies requires an intricate balance across multiple properties. Protein inverse folding models, capabl
academic.oup.com
March 27, 2025 at 11:30 AM
AntiFold, our antibody inverse folding model, has been published at Bioinformatics Advances. Work led by @magnushoie.bsky.social & @alissahummer.com.
Paper: academic.oup.com/bioinformati...
Webserver: opig.stats.ox.ac.uk/webapps/anti...
Codebase available on Github: github.com/oxpig/AntiFold
Paper: academic.oup.com/bioinformati...
Webserver: opig.stats.ox.ac.uk/webapps/anti...
Codebase available on Github: github.com/oxpig/AntiFold