diff --git a/2024/10/19/ACAnet/index.html b/2024/10/19/ACAnet/index.html index cad62123..644ea223 100644 --- a/2024/10/19/ACAnet/index.html +++ b/2024/10/19/ACAnet/index.html @@ -4,16 +4,16 @@ - Activity Cliffs in Molecular Property Prediction - Zitnik Lab + Activity Cliffs in Molecular Properties - Zitnik Lab -Activity Cliffs in Molecular Property Prediction | Zitnik Lab +Activity Cliffs in Molecular Properties | Zitnik Lab - + @@ -24,11 +24,11 @@ - + +{"url":"https://zitniklab.hms.harvard.edu/2024/10/19/ACAnet/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/2024/10/19/ACAnet/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Activity Cliffs in Molecular Properties","dateModified":"2024-10-19T00:00:00-04:00","description":"New paper on activity-cliff informed contrastive learning for molecular property prediction.","datePublished":"2024-10-19T00:00:00-04:00","@type":"BlogPosting","@context":"https://schema.org"} + +SPECTRA in Nature Machine Intelligence | Zitnik Lab + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+

SPECTRA in Nature Machine Intelligence

+

+ +
+
+
+ + + + +
+
+
+ +
+ + +
+ + +

Published: Dec 7, 2024

+ +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ +
+ +
+ +
+ + + +
+ +
+
+
+ + + + + +
+
+

Zitnik Lab +  ·  Artificial Intelligence in Medicine and Science +  ·  Harvard +  ·  Department of Biomedical Informatics

+
+
+ + diff --git a/2024/12/07/UnifiedClinicalVocabularyEmbeddings/index.html b/2024/12/07/UnifiedClinicalVocabularyEmbeddings/index.html new file mode 100644 index 00000000..d11505c1 --- /dev/null +++ b/2024/12/07/UnifiedClinicalVocabularyEmbeddings/index.html @@ -0,0 +1,182 @@ + + + + + + + Unified Clinical Vocabulary Embeddings - Zitnik Lab + + + + +Unified Clinical Vocabulary Embeddings | Zitnik Lab + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+

Unified Clinical Vocabulary Embeddings

+

+ +
+
+
+ + + + +
+
+
+ +
+ + +
+ + +

Published: Dec 7, 2024

+ +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ +
+ +
+ +
+ + + +
+ +
+
+
+ + + + + +
+
+

Zitnik Lab +  ·  Artificial Intelligence in Medicine and Science +  ·  Harvard +  ·  Department of Biomedical Informatics

+
+
+ + diff --git a/2024/12/16/ProCyon/index.html b/2024/12/16/ProCyon/index.html new file mode 100644 index 00000000..edf2c861 --- /dev/null +++ b/2024/12/16/ProCyon/index.html @@ -0,0 +1,182 @@ + + + + + + + Foundation Model for Protein Phenotypes - Zitnik Lab + + + + +Foundation Model for Protein Phenotypes | Zitnik Lab + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+

Foundation Model for Protein Phenotypes

+

+ +
+
+
+ + + + +
+
+
+ +
+ + +
+ + +

Published: Dec 16, 2024

+ +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ +
+ +
+ +
+ + + +
+ +
+
+
+ + + + + +
+
+

Zitnik Lab +  ·  Artificial Intelligence in Medicine and Science +  ·  Harvard +  ·  Department of Biomedical Informatics

+
+
+ + diff --git a/DMAI/index.html b/DMAI/index.html index d6772830..b27a06ef 100644 --- a/DMAI/index.html +++ b/DMAI/index.html @@ -202,6 +202,90 @@

Coordinator

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -290,8 +374,8 @@

Coordinator

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -678,90 +762,6 @@

Coordinator

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/data/index.html b/data/index.html index 47cfaddb..d5c159c4 100644 --- a/data/index.html +++ b/data/index.html @@ -146,6 +146,41 @@
+
+ + + +
+
+
+

ProCyon-Instruct

+

Foundation Model for Protein Phenotypes

+ + + +
+

ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes across five interrelated knowledge domains: molecular functions, therapeutic mechanisms, disease associations, functional protein domains, and molecular interactions. To train ProCyon, we created ProCyon-Instruct, a dataset of 33 million protein phenotype instructions, representing a comprehensive resource for multiscale protein phenotypes.

+

+
+ + + + + + + + + View ProCyon Website + + + + +
+
+ +
+
+
@@ -780,6 +815,90 @@
+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -868,8 +987,8 @@
- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -1256,90 +1375,6 @@
-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/feed.xml b/feed.xml index e7c61d9f..9e110594 100644 --- a/feed.xml +++ b/feed.xml @@ -1 +1 @@ -Jekyll2024-12-02T21:40:57-05:00https://zitniklab.hms.harvard.edu/feed.xmlZitnik LabHarvard Machine Learning for Medicine and ScienceMarinka ZitnikAyush Noori Selected as a Rhodes Scholar2024-11-17T00:00:00-05:002024-11-17T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/11/17/RhodesScholar<p>Congratulations to <a href="https://www.thecrimson.com/article/2024/11/18/rhodes-scholars-announced-harvard-students/">Ayush Noori on being named a Rhodes Scholar</a>! Such an incredible achievement!</p>Marinka ZitnikCongratulations to Ayush Noori on being named a Rhodes Scholar! Such an incredible achievement!PocketGen in Nature Machine Intelligence2024-11-15T00:00:00-05:002024-11-15T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/11/15/PocketGen<p>PocketGen is a <a href="https://www.nature.com/articles/s42256-024-00920-9">multimodal sequence-structure generative model for designing full-atom ligand-binding protein pockets.</a></p>Marinka ZitnikPocketGen is a multimodal sequence-structure generative model for designing full-atom ligand-binding protein pockets.Biomedical AI Agents in Cell2024-11-01T00:00:00-04:002024-11-01T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/11/01/AIScientist<p>We envision “AI scientists” as <a href="https://www.cell.com/cell/fulltext/S0092-8674(24)01070-5">AI agents capable of skeptical learning and reasoning that empower biomedical research by integrating ML models and biomedical tools with experimental platforms.</a></p>Marinka ZitnikWe envision “AI scientists” as AI agents capable of skeptical learning and reasoning that empower biomedical research by integrating ML models and biomedical tools with experimental platforms.Activity Cliffs in Molecular Property Prediction2024-10-19T00:00:00-04:002024-10-19T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/10/19/ACAnet<p>New paper on <a href="https://chemrxiv.org/engage/chemrxiv/article-details/6470c963be16ad5c57f5526c">activity-cliff informed contrastive learning for molecular property prediction.</a></p>Marinka ZitnikNew paper on activity-cliff informed contrastive learning for molecular property prediction.Knowledge Graph Agent for Medical Reasoning2024-10-09T00:00:00-04:002024-10-09T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/10/09/KGARevion<p>New paper introducing a <a href="https://arxiv.org/abs/2410.04660">knowledge graph agent for complex, knowledge-intensive medical reasoning.</a></p>Marinka ZitnikNew paper introducing a knowledge graph agent for complex, knowledge-intensive medical reasoning.Three Papers Accepted to NeurIPS2024-09-27T00:00:00-04:002024-09-27T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/09/27/NeurIPS2024Papers<p>Exciting projects include a unified multi-task time series model, a flow-matching approach for generating protein pockets using geometric priors, and a tokenization method that produces invariant molecular representations for integration into large language models.</p>Marinka ZitnikExciting projects include a unified multi-task time series model, a flow-matching approach for generating protein pockets using geometric priors, and a tokenization method that produces invariant molecular representations for integration into large language models.TxGNN Published in Nature Medicine2024-09-25T00:00:00-04:002024-09-25T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/09/25/TxGNNNatureMedicine<p>Graph foundation model for drug repurposing published in <a href="https://www.nature.com/articles/s41591-024-03233-x">Nature Medicine</a>. <a href="https://news.harvard.edu/gazette/story/2024/09/using-ai-to-repurpose-existing-drugs-for-treatment-of-rare-diseases/">[Harvard Gazette]</a> <a href="https://hms.harvard.edu/news/researchers-harness-ai-repurpose-existing-drugs-treatment-rare-diseases">[Harvard Medicine News]</a> <a href="https://www.forbes.com/sites/greglicholai/2024/09/26/ai-tool-speeds-drug-repurposing-and-its-free/">[Forbes]</a> <a href="https://developer.nvidia.com/blog/ai-uses-zero-shot-learning-to-find-existing-drugs-for-treating-rare-diseases/">[NVIDIA]</a> <a href="https://kempnerinstitute.harvard.edu/news/txgnn-ai-dr-house-for-disease-treatment/">[Kempner Institute]</a> <a href="https://www.thecrimson.com/article/2024/10/9/drug-repurposing-ai-model/">[Harvard Crimson]</a></p>Marinka ZitnikGraph foundation model for drug repurposing published in Nature Medicine. [Harvard Gazette] [Harvard Medicine News] [Forbes] [NVIDIA] [Kempner Institute] [Harvard Crimson]Graph AI in Medicine2024-08-28T00:00:00-04:002024-08-28T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/08/28/GraphAI<p>Excited to share a new perspective on <a href="https://go.shr.lc/4g0KpLV">Graph Artificial Intelligence in Medicine</a> in Annual Reviews.</p>Marinka ZitnikExcited to share a new perspective on Graph Artificial Intelligence in Medicine in Annual Reviews.How Proteins Behave in Context2024-08-15T00:00:00-04:002024-08-15T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/08/15/PINNACLENews<p><a href="https://hms.harvard.edu/news/new-ai-tool-captures-how-proteins-behave-context">Harvard Medicine News</a> on our new AI tool that captures how proteins behave in context. <a href="https://kempnerinstitute.harvard.edu/research/deeper-learning/context-matters-for-foundation-models-in-biology/">Kempner Institute</a> on how context matters for foundation models in biology.</p>Marinka ZitnikHarvard Medicine News on our new AI tool that captures how proteins behave in context. Kempner Institute on how context matters for foundation models in biology.PINNACLE in Nature Methods2024-07-27T00:00:00-04:002024-07-27T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/07/27/PINNACLENatureMethods<p>PINNACLE contextual AI model is published in Nature Methods. <a href="https://www.nature.com/articles/s41592-024-02341-3">Paper.</a> <a href="https://www.nature.com/articles/s41592-024-02342-2">Research Briefing.</a> <a href="https://zitniklab.hms.harvard.edu/projects/PINNACLE/">Project website.</a></p>Marinka ZitnikPINNACLE contextual AI model is published in Nature Methods. Paper. Research Briefing. Project website. \ No newline at end of file +Jekyll2024-12-16T01:30:20-05:00https://zitniklab.hms.harvard.edu/feed.xmlZitnik LabHarvard Machine Learning for Medicine and ScienceMarinka ZitnikFoundation Model for Protein Phenotypes2024-12-16T00:00:00-05:002024-12-16T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/12/16/ProCyon<p>New paper: <a href="https://www.biorxiv.org/content/10.1101/2024.12.10.627665v1">ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes</a>. <a href="https://zitniklab.hms.harvard.edu/ProCyon/">[Project website]</a> <a href="https://github.com/mims-harvard/ProCyon">[Code]</a></p>Marinka ZitnikNew paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]SPECTRA in Nature Machine Intelligence2024-12-07T00:00:00-05:002024-12-07T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/12/07/SPECTRA<p>Are biomedical AI models truly as smart as they seem? <a href="https://www.nature.com/articles/s42256-024-00931-6">SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity.</a> SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.</p>Marinka ZitnikAre biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.Unified Clinical Vocabulary Embeddings2024-12-07T00:00:00-05:002024-12-07T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/12/07/UnifiedClinicalVocabularyEmbeddings<p>New paper: <a href="https://www.medrxiv.org/content/10.1101/2024.12.03.24318322">A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies.</a> (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.</p>Marinka ZitnikNew paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.Ayush Noori Selected as a Rhodes Scholar2024-11-17T00:00:00-05:002024-11-17T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/11/17/RhodesScholar<p>Congratulations to <a href="https://www.thecrimson.com/article/2024/11/18/rhodes-scholars-announced-harvard-students/">Ayush Noori on being named a Rhodes Scholar</a>! Such an incredible achievement!</p>Marinka ZitnikCongratulations to Ayush Noori on being named a Rhodes Scholar! Such an incredible achievement!PocketGen in Nature Machine Intelligence2024-11-15T00:00:00-05:002024-11-15T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/11/15/PocketGen<p>PocketGen is a <a href="https://www.nature.com/articles/s42256-024-00920-9">multimodal sequence-structure generative model for designing full-atom ligand-binding protein pockets.</a></p>Marinka ZitnikPocketGen is a multimodal sequence-structure generative model for designing full-atom ligand-binding protein pockets.Biomedical AI Agents in Cell2024-11-01T00:00:00-04:002024-11-01T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/11/01/AIScientist<p>We envision “AI scientists” as <a href="https://www.cell.com/cell/fulltext/S0092-8674(24)01070-5">AI agents capable of skeptical learning and reasoning that empower biomedical research by integrating ML models and biomedical tools with experimental platforms.</a></p>Marinka ZitnikWe envision “AI scientists” as AI agents capable of skeptical learning and reasoning that empower biomedical research by integrating ML models and biomedical tools with experimental platforms.Activity Cliffs in Molecular Properties2024-10-19T00:00:00-04:002024-10-19T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/10/19/ACAnet<p>New paper on <a href="https://chemrxiv.org/engage/chemrxiv/article-details/6470c963be16ad5c57f5526c">activity-cliff informed contrastive learning for molecular property prediction.</a></p>Marinka ZitnikNew paper on activity-cliff informed contrastive learning for molecular property prediction.Knowledge Graph Agent for Medical Reasoning2024-10-09T00:00:00-04:002024-10-09T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/10/09/KGARevion<p>New paper introducing a <a href="https://arxiv.org/abs/2410.04660">knowledge graph agent for complex, knowledge-intensive medical reasoning.</a></p>Marinka ZitnikNew paper introducing a knowledge graph agent for complex, knowledge-intensive medical reasoning.Three Papers Accepted to NeurIPS2024-09-27T00:00:00-04:002024-09-27T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/09/27/NeurIPS2024Papers<p>Exciting projects include a unified multi-task time series model, a flow-matching approach for generating protein pockets using geometric priors, and a tokenization method that produces invariant molecular representations for integration into large language models.</p>Marinka ZitnikExciting projects include a unified multi-task time series model, a flow-matching approach for generating protein pockets using geometric priors, and a tokenization method that produces invariant molecular representations for integration into large language models.TxGNN Published in Nature Medicine2024-09-25T00:00:00-04:002024-09-25T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/09/25/TxGNNNatureMedicine<p>Graph foundation model for drug repurposing published in <a href="https://www.nature.com/articles/s41591-024-03233-x">Nature Medicine</a>. <a href="https://news.harvard.edu/gazette/story/2024/09/using-ai-to-repurpose-existing-drugs-for-treatment-of-rare-diseases/">[Harvard Gazette]</a> <a href="https://hms.harvard.edu/news/researchers-harness-ai-repurpose-existing-drugs-treatment-rare-diseases">[Harvard Medicine News]</a> <a href="https://www.forbes.com/sites/greglicholai/2024/09/26/ai-tool-speeds-drug-repurposing-and-its-free/">[Forbes]</a> <a href="https://developer.nvidia.com/blog/ai-uses-zero-shot-learning-to-find-existing-drugs-for-treating-rare-diseases/">[NVIDIA]</a> <a href="https://kempnerinstitute.harvard.edu/news/txgnn-ai-dr-house-for-disease-treatment/">[Kempner Institute]</a> <a href="https://www.thecrimson.com/article/2024/10/9/drug-repurposing-ai-model/">[Harvard Crimson]</a></p>Marinka ZitnikGraph foundation model for drug repurposing published in Nature Medicine. [Harvard Gazette] [Harvard Medicine News] [Forbes] [NVIDIA] [Kempner Institute] [Harvard Crimson] \ No newline at end of file diff --git a/img/SPECTRA-overview.png b/img/SPECTRA-overview.png index f420ed61..1d690f23 100644 Binary files a/img/SPECTRA-overview.png and b/img/SPECTRA-overview.png differ diff --git a/img/aarthi_venkat.png b/img/aarthi_venkat.png new file mode 100644 index 00000000..3c5c5c6a Binary files /dev/null and b/img/aarthi_venkat.png differ diff --git a/img/katya_ivshina.png b/img/katya_ivshina.png new file mode 100644 index 00000000..d312fe78 Binary files /dev/null and b/img/katya_ivshina.png differ diff --git a/img/michael_sun.png b/img/michael_sun.png new file mode 100644 index 00000000..9f0a74f0 Binary files /dev/null and b/img/michael_sun.png differ diff --git a/index.html b/index.html index cf141ab2..e68f94ce 100644 --- a/index.html +++ b/index.html @@ -177,6 +177,90 @@

AI for Science | Therapeutic Science

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -265,8 +349,8 @@

AI for Science | Therapeutic Science

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -653,90 +737,6 @@

AI for Science | Therapeutic Science

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/jobs/index.html b/jobs/index.html index 60a6c2a6..cd4e27f6 100644 --- a/jobs/index.html +++ b/jobs/index.html @@ -259,6 +259,90 @@

Visitors, interns, and short-t
+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -347,8 +431,8 @@

Visitors, interns, and short-t
- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -735,90 +819,6 @@

Visitors, interns, and short-t

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/meetings/index.html b/meetings/index.html index 5ce5f251..9524ffc7 100644 --- a/meetings/index.html +++ b/meetings/index.html @@ -594,6 +594,90 @@

Biomedical Data Fusion (EMBC a
+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -682,8 +766,8 @@

Biomedical Data Fusion (EMBC a
- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -1070,90 +1154,6 @@

Biomedical Data Fusion (EMBC a

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/news/index.html b/news/index.html index d6d67629..03de2079 100644 --- a/news/index.html +++ b/news/index.html @@ -170,6 +170,90 @@
+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -258,8 +342,8 @@
- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -1534,94 +1618,6 @@
-
-
- -
- -

Feb 2023:   New Preprint on Distribution Shifts

- - -
- -
- - - -

New preprint on domain adaptation for time series under feature and label shifts. Project website.

- - - - - - -
- - - -
-
- -
-
- -
- -

Feb 2023:   PrimeKG published in Scientific Data

- - -
- -
- - - -

Our multimodal knowledge graph for precision medicine is published in Scientific Data. Project website.

- - - - - - -
- - - -
-
- -
-
- -
- -

Jan 2023:   GNNDelete published at ICLR 2023

- - -
- -
- - - -

New paper on machine unlearning for graph neural networks accepted at ICLR 2023. Project website.

- - - - - -
- - - -
-
-
+
+
+ +
+ +

Feb 2023:   New Preprint on Distribution Shifts

+ + +
+ +
+ + + +

New preprint on domain adaptation for time series under feature and label shifts. Project website.

+ + + + + + +
+ + + +
+
+ +
+
+ +
+ +

Feb 2023:   PrimeKG published in Scientific Data

+ + +
+ +
+ + + +

Our multimodal knowledge graph for precision medicine is published in Scientific Data. Project website.

+ + + + + + +
+ + + +
+
+ +
+
+ +
+ +

Jan 2023:   GNNDelete published at ICLR 2023

+ + +
+ +
+ + + +

New paper on machine unlearning for graph neural networks accepted at ICLR 2023. Project website.

+ + + + + +
+ + + +
+
+
@@ -1487,90 +1575,6 @@
-
-
- -
- -

Aug 2021:   AI for Science at NeurIPS

- - -
- -
- - - -

We are organizing the AI for Science workshop at NeurIPS 2021 and have a stellar lineup of invited speakers.

- - - - - -
- - - -
-
- -
-
- -
- -

Aug 2021:   Best Poster Award at ICML Comp Biology

- - -
- -
- - - -

Congratulations to Michelle for winning the Best Poster Award for her work on deep contextual learners for protein networks at the ICML Workshop on Computational Biology.

- - - - - -
- - - -
-
- -
-
- -
- -

Jul 2021:   Best Paper Award at ICML Interpretable ML

- - -
- -
- - - -

Our short paper on Interactive Visual Explanations for Deep Drug Repurposing received the Best Paper Award at the ICML Interpretable ML in Healthcare Workshop. Stay tuned for more news on this evolving project.

- - - - - -
- - - -
-
-
+
+
+ +
+ +

Aug 2021:   AI for Science at NeurIPS

+ + +
+ +
+ + + +

We are organizing the AI for Science workshop at NeurIPS 2021 and have a stellar lineup of invited speakers.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Aug 2021:   Best Poster Award at ICML Comp Biology

+ + +
+ +
+ + + +

Congratulations to Michelle for winning the Best Poster Award for her work on deep contextual learners for protein networks at the ICML Workshop on Computational Biology.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Jul 2021:   Best Paper Award at ICML Interpretable ML

+ + +
+ +
+ + + +

Our short paper on Interactive Visual Explanations for Deep Drug Repurposing received the Best Paper Award at the ICML Interpretable ML in Healthcare Workshop. Stay tuned for more news on this evolving project.

+ + + + + +
+ + + +
+
+
diff --git a/people/index.html b/people/index.html index bcf3522e..ee1cf9da 100644 --- a/people/index.html +++ b/people/index.html @@ -208,6 +208,35 @@ +
+ + + +
+ + +
+
+ <a href=Ada Fang" /> +
+
+ +
+ +

Ada Fang

+

PhD Student
Harvard CCB

+ +

+ +
+
+ + + +
+ + +
@@ -239,21 +268,50 @@
- +
- <a href=Ada Fang" /> + <a href=Katya Ivshina" />
-

Ada Fang

-

PhD Student
Harvard CCB

+

Katya Ivshina

+

PhD Student
Harvard Applied Mathematics

+ +

+ +
+
+ + + +
+ + + +
+ + + +
+ + +
+
+ <a href=Michael Sun" /> +
+
+ +
+ +

Michael Sun

+

PhD Student
MIT EECS

@@ -643,6 +701,35 @@ +
+ + + +
+ + +
+
+ <a href=Aarthi Venkat" /> +
+
+ +
+ +

Aarthi Venkat

+

Postdoctoral Fellow
Eric and Wendy Schmidt Fellow

+ +

+ +
+
+ + + +
+ + +
@@ -674,20 +761,20 @@
- +
- <a href=Pengwei Sui" /> + <a href=Michelle Dai" />
-

Pengwei Sui

+

Michelle Dai

Research Associate

@@ -703,20 +790,20 @@
- +
- <a href=Michelle Dai" /> + <a href=Pengwei Sui" />
-

Michelle Dai

+

Pengwei Sui

Research Associate

@@ -790,20 +877,20 @@
- +
- <a href=Richard Zhu" /> + <a href=Iñaki Arango" />
-

Richard Zhu

+

Iñaki Arango

Undergraduate Researcher
Harvard

@@ -819,20 +906,20 @@
- +
- <a href=Ayush Noori" /> + <a href=Richard Zhu" />
-

Ayush Noori

+

Richard Zhu

Undergraduate Researcher
Harvard

@@ -848,20 +935,20 @@
- +
- <a href=Iñaki Arango" /> + <a href=Ayush Noori" />
-

Iñaki Arango

+

Ayush Noori

Undergraduate Researcher
Harvard

@@ -936,6 +1023,12 @@

Associate members

+ + + + + + @@ -1014,6 +1107,90 @@

Lab alumni

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -1102,8 +1279,8 @@

Lab alumni

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -1490,90 +1667,6 @@

Lab alumni

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/postdoc-ML/index.html b/postdoc-ML/index.html index 9855a701..df1f6aea 100644 --- a/postdoc-ML/index.html +++ b/postdoc-ML/index.html @@ -191,6 +191,90 @@

Advisor

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -279,8 +363,8 @@

Advisor

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -667,90 +751,6 @@

Advisor

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/postdoc-TDC/index.html b/postdoc-TDC/index.html index 24028880..fcebe73f 100644 --- a/postdoc-TDC/index.html +++ b/postdoc-TDC/index.html @@ -203,6 +203,90 @@

Advisor

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -291,8 +375,8 @@

Advisor

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -679,90 +763,6 @@

Advisor

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/postdoc-biomedicalAI-MGB/index.html b/postdoc-biomedicalAI-MGB/index.html index 1816abb4..7495b91d 100644 --- a/postdoc-biomedicalAI-MGB/index.html +++ b/postdoc-biomedicalAI-MGB/index.html @@ -180,6 +180,90 @@

Application process

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -268,8 +352,8 @@

Application process

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -656,90 +740,6 @@

Application process

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/postdoc-cancerTxAI/index.html b/postdoc-cancerTxAI/index.html index 95eea48c..c10cc582 100644 --- a/postdoc-cancerTxAI/index.html +++ b/postdoc-cancerTxAI/index.html @@ -189,6 +189,90 @@

Faculty and mentors

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -277,8 +361,8 @@

Faculty and mentors

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -665,90 +749,6 @@

Faculty and mentors

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/postdoc-medicalAI/index.html b/postdoc-medicalAI/index.html index 5e5b3c78..3617bf32 100644 --- a/postdoc-medicalAI/index.html +++ b/postdoc-medicalAI/index.html @@ -196,6 +196,90 @@

Advisor

+
+
+ +
+ +

Dec 2024:   Foundation Model for Protein Phenotypes

+ + +
+ +
+ + + +

New paper: ProCyon is a groundbreaking foundation model for modeling, generating, and predicting protein phenotypes. [Project website] [Code]

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   Unified Clinical Vocabulary Embeddings

+ + +
+ +
+ + + +

New paper: A unified resource provides a new representation of clinical knowledge by unifying medical vocabularies. (1) Phenotype risk score analysis across 4.57 million patients, (2) Inter-institutional clinician panels evaluate alignment with clinical knowledge across 90 diseases and 3,000 clinical codes.

+ + + + + +
+ + + +
+
+ +
+
+ +
+ +

Dec 2024:   SPECTRA in Nature Machine Intelligence

+ + +
+ +
+ + + +

Are biomedical AI models truly as smart as they seem? SPECTRA is a framework that evaluates models by considering the full spectrum of cross-split overlap: train-test similarity. SPECTRA reveals gaps in benchmarks for molecular sequence data across 19 models, including LLMs, GNNs, diffusion models, and conv nets.

+ + + + + +
+ + + +
+
+
@@ -284,8 +368,8 @@

Advisor

- -

Oct 2024:   Activity Cliffs in Molecular Property Prediction

+ +

Oct 2024:   Activity Cliffs in Molecular Properties

@@ -672,90 +756,6 @@

Advisor

-
-
- -
- -

Mar 2024:   Efficient ML Seminar Series

- - -
- -
- - - -

We started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   UniTS - Unified Time Series Model

- - -
- -
- - - -

UniTS is a unified time series model that can process classification, forecasting, anomaly detection and imputation tasks within a single model with no task-specific modules. UniTS has zero-shot, few-shot, and prompt learning capabilities. Project website.

- - - - - -
- - - -
-
- -
-
- -
- -

Mar 2024:   Weintraub Graduate Student Award

- - -
- -
- - - -

Michelle receives the 2024 Harold M. Weintraub Graduate Student Award. The award recognizes exceptional achievement in graduate studies in biological sciences. News Story. Congratulations!

- - - - - -
- - - -
-
-
diff --git a/products/jason_poulos/index.html b/products/aarthi_venkat/index.html similarity index 80% rename from products/jason_poulos/index.html rename to products/aarthi_venkat/index.html index 2d9421e0..15d90777 100644 --- a/products/jason_poulos/index.html +++ b/products/aarthi_venkat/index.html @@ -4,33 +4,33 @@ - <a href="https://jasonvpoulos.com/">Jason Poulos</a> - Zitnik Lab + <a href="https://scholar.google.com/citations?user=Z8c9_0QAAAAJ&hl=en">Aarthi Venkat</a> - Zitnik Lab -Jason Poulos | Zitnik Lab +Aarthi Venkat | Zitnik Lab - + - - + + - + - + - - + + +{"image":"https://zitniklab.hms.harvard.edu/img/aarthi_venkat.png","url":"https://zitniklab.hms.harvard.edu/products/aarthi_venkat/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/aarthi_venkat/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Aarthi Venkat","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/ada_fang.png","url":"https://zitniklab.hms.harvard.edu/products/ada_fang/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/ada_fang/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Ada Fang","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/alex_verce.png","url":"https://zitniklab.hms.harvard.edu/products/alejandro_velez_arce/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/alejandro_velez_arce/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Alejandro Velez Arce","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/andrew_shen.png","url":"https://zitniklab.hms.harvard.edu/products/andrew_shen/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/andrew_shen/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Andrew Shen","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/ayush_noori.png","url":"https://zitniklab.hms.harvard.edu/products/ayush_noori/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/ayush_noori/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Ayush Noori","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/grey_kuling.png","url":"https://zitniklab.hms.harvard.edu/products/grey_kuling/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/grey_kuling/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Grey Kuling","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/inaki_arango.png","url":"https://zitniklab.hms.harvard.edu/products/inaki_arango/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/inaki_arango/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Iñaki Arango","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/intae_moon.png","url":"https://zitniklab.hms.harvard.edu/products/intae_moon/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/intae_moon/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Intae Moon","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} + +Katya Ivshina | Zitnik Lab + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+

Katya Ivshina

+

PhD Student
Harvard Applied Mathematics

+ +
+
+
+ + + + +
+
+
+ +
+ + +
+ +
+
+ +
+
+ +
+

Katya Ivshina

+

PhD Student
Harvard Applied Mathematics

+

+ + + + + +
+ +
+

Description

+
+ + + + +
+
+ + + +
+ + +
+ +
+
+
+ + + + + diff --git a/products/kevin_li/index.html b/products/kevin_li/index.html index 70962747..6011de5f 100644 --- a/products/kevin_li/index.html +++ b/products/kevin_li/index.html @@ -23,14 +23,14 @@ - + +{"image":"https://zitniklab.hms.harvard.edu/img/kevin_li.png","url":"https://zitniklab.hms.harvard.edu/products/kevin_li/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/kevin_li/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Kevin Li","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/kexin_chen.png","url":"https://zitniklab.hms.harvard.edu/products/kexin_chen/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/kexin_chen/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Kexin Chen","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/marinka_zitnik.png","url":"https://zitniklab.hms.harvard.edu/products/marinka_zitnik/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/marinka_zitnik/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Marinka Zitnik","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} + +Michael Sun | Zitnik Lab + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+

Michael Sun

+

PhD Student
MIT EECS

+ +
+
+
+ + + + +
+
+
+ +
+ + +
+ +
+
+ +
+
+ +
+

Michael Sun

+

PhD Student
MIT EECS

+

+ + + + + +
+ +
+

Description

+
+ + + + +
+
+ + + +
+ + +
+ +
+
+
+ + + + + diff --git a/products/michelle_dai/index.html b/products/michelle_dai/index.html index 12b33cd6..a8c86847 100644 --- a/products/michelle_dai/index.html +++ b/products/michelle_dai/index.html @@ -23,14 +23,14 @@ - + +{"image":"https://zitniklab.hms.harvard.edu/img/michelle_dai.png","url":"https://zitniklab.hms.harvard.edu/products/michelle_dai/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/michelle_dai/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Michelle Dai","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/michelle_li.png","url":"https://zitniklab.hms.harvard.edu/products/michelle_li/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/michelle_li/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Michelle M. Li","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/pengwei_sui.png","url":"https://zitniklab.hms.harvard.edu/products/pengwei_sui/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/pengwei_sui/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Pengwei Sui","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/richard_zhu.png","url":"https://zitniklab.hms.harvard.edu/products/richard_zhu/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/richard_zhu/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Richard Zhu","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/robert_calef.png","url":"https://zitniklab.hms.harvard.edu/products/robert_calef/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/robert_calef/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Robert Calef","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/ruth_johnson.png","url":"https://zitniklab.hms.harvard.edu/products/ruth_johnson/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/ruth_johnson/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Ruth Johnson","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/shanghua_gao.png","url":"https://zitniklab.hms.harvard.edu/products/shanghua_gao/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/shanghua_gao/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Shanghua Gao","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/valentina_giunchiglia.png","url":"https://zitniklab.hms.harvard.edu/products/valentina_giunchiglia/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/valentina_giunchiglia/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Valentina Giunchiglia","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/wanxiang_shen.png","url":"https://zitniklab.hms.harvard.edu/products/wanxiang_shen/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/wanxiang_shen/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Wanxiang Shen","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/xiang_lin.png","url":"https://zitniklab.hms.harvard.edu/products/xiang_lin/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/xiang_lin/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Xiang Lin","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/xiaorui_su.png","url":"https://zitniklab.hms.harvard.edu/products/xiaorui_su/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/xiaorui_su/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Xiaorui Su","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/yasha_ektefaie.png","url":"https://zitniklab.hms.harvard.edu/products/yasha_ektefaie/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/yasha_ektefaie/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Yasha Ektefaie","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Biomedical Machine Learning, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/yepeng_huang.png","url":"https://zitniklab.hms.harvard.edu/products/yepeng_huang/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/yepeng_huang/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Yepeng Huang","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/ying_jin.png","url":"https://zitniklab.hms.harvard.edu/products/ying_jin/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/ying_jin/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Ying Jin","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} +{"image":"https://zitniklab.hms.harvard.edu/img/zhenglun_kong.png","url":"https://zitniklab.hms.harvard.edu/products/zhenglun_kong/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/products/zhenglun_kong/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Zhenglun Kong","dateModified":"2024-12-16T01:30:20-05:00","description":"Artificial Intelligence (AI), Medicine, Science, and Drug Discovery","datePublished":"2024-12-16T01:30:20-05:00","@type":"BlogPosting","@context":"https://schema.org"} -Evaluating Generalizability of Artificial Intelligence Models for Molecular Datasets | Zitnik Lab +Evaluating Generalizability of Molecular AI Models | Zitnik Lab - + @@ -22,11 +22,11 @@ - + +{"url":"https://zitniklab.hms.harvard.edu/projects/SPECTRA/","author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"Evaluating Generalizability of Molecular AI Models","description":"SPECTRA paves the way for a more comprehensive evaluation of foundation models in molecular biology.","@type":"WebPage","@context":"https://schema.org"}