diff --git a/products/ivy_liang/index.html b/2024/08/15/PINNACLENews/index.html
similarity index 70%
rename from products/ivy_liang/index.html
rename to 2024/08/15/PINNACLENews/index.html
index be425c64..c3dacfe7 100644
--- a/products/ivy_liang/index.html
+++ b/2024/08/15/PINNACLENews/index.html
@@ -4,33 +4,31 @@
- <a href="#">Ivy Liang</a> - Zitnik Lab
+ How Proteins Behave in Context - Zitnik Lab
-Ivy Liang | Zitnik Lab
+How Proteins Behave in Context | Zitnik Lab
-
+
-
-
-
-
+
+
+
+
-
-
+
-
-
+
+{"url":"https://zitniklab.hms.harvard.edu/2024/08/15/PINNACLENews/","mainEntityOfPage":{"@type":"WebPage","@id":"https://zitniklab.hms.harvard.edu/2024/08/15/PINNACLENews/"},"author":{"@type":"Person","name":"Marinka Zitnik"},"headline":"How Proteins Behave in Context","dateModified":"2024-08-15T00:00:00-04:00","description":"Harvard 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.","datePublished":"2024-08-15T00:00:00-04:00","@type":"BlogPosting","@context":"https://schema.org"}
Harvard 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.
Harvard 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.
diff --git a/docs/marinka_zitnik_CV.pdf b/docs/marinka_zitnik_CV.pdf
deleted file mode 100644
index 7ce3a759..00000000
Binary files a/docs/marinka_zitnik_CV.pdf and /dev/null differ
diff --git a/feed.xml b/feed.xml
index 33a63b7c..1fe178d8 100644
--- a/feed.xml
+++ b/feed.xml
@@ -1 +1 @@
-Jekyll2024-07-27T17:49:29-04:00https://zitniklab.hms.harvard.edu/feed.xmlZitnik LabHarvard Machine Learning for Medicine and ScienceMarinka ZitnikPINNACLE 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.Digital Twins as Global Health and Disease Models of Individuals2024-07-15T00:00:00-04:002024-07-15T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/07/15/DigitalTwins<p><a href="https://www.preprints.org/manuscript/202406.0357/">Paper on digitial twins</a> outlining strategies to leverage molecular and computational techniques to construct dynamic digital twins on the scale of populations to individuals.</p>Marinka ZitnikPaper on digitial twins outlining strategies to leverage molecular and computational techniques to construct dynamic digital twins on the scale of populations to individuals.Graph Diffusion Convolutions at ICML2024-07-14T00:00:00-04:002024-07-14T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/07/14/GraphAdversarialDiffusion<p><a href="https://arxiv.org/abs/2406.02059">Graph diffusion convolution is a geometric deep learning architecture that aggregates information from higher-order network neighbors through a generalized graph diffusion</a> to enhance model robustness to noisy and incomplete datasets. <a href="https://arxiv.org/abs/2406.02059">Paper at ICML.</a></p>Marinka ZitnikGraph diffusion convolution is a geometric deep learning architecture that aggregates information from higher-order network neighbors through a generalized graph diffusion to enhance model robustness to noisy and incomplete datasets. Paper at ICML.Three Papers: TrialBench, 3D Structure Design, LLM Editing2024-07-13T00:00:00-04:002024-07-13T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/07/13/TrialBenchLLM3DStructure<p>New papers on <a href="https://arxiv.org/abs/2407.00631">TrialBench with AI-ready clinical trial datasets</a>, <a href="https://arxiv.org/abs/2406.03403">structure-based drug design benchmark</a>, and <a href="https://arxiv.org/abs/2407.06483">composable interventions for language models</a>.</p>Marinka ZitnikNew papers on TrialBench with AI-ready clinical trial datasets, structure-based drug design benchmark, and composable interventions for language models.TDC-2: Multimodal Foundation for Therapeutics2024-06-23T00:00:00-04:002024-06-23T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/06/23/TDC2<p><a href="https://tdcommons.ai/">The Commons 2.0 (TDC-2)</a> is an overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new tasks and benchmarks. <a href="https://www.biorxiv.org/content/10.1101/2024.06.12.598655v2">Our paper.</a></p>Marinka ZitnikThe Commons 2.0 (TDC-2) is an overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new tasks and benchmarks. Our paper.Broad MIA: Protein Language Models2024-05-29T00:00:00-04:002024-05-29T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/05/29/BroadMIA<p>Check out our Broad’s seminars on <a href="https://youtu.be/LcLmvtXHI1s?si=GABqGdFt5ze9leT_">Multimodal protein language models for deciphering protein function.</a></p>Marinka ZitnikCheck out our Broad’s seminars on Multimodal protein language models for deciphering protein function.On Knowing a Gene in Cell Systems2024-05-28T00:00:00-04:002024-05-28T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/05/28/KnowingAGene<p>We shed light on <a href="https://www.sciencedirect.com/science/article/pii/S2405471224001236">distributional gene representations and their potential applications in biology to characterize gene function from a broader and more holistic perspective.</a></p>Marinka ZitnikWe shed light on distributional gene representations and their potential applications in biology to characterize gene function from a broader and more holistic perspective.Biomedical AI Agents2024-04-04T00:00:00-04:002024-04-04T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/04/04/BIomedicalAIAgents<p>We envision <a href="https://arxiv.org/abs/2404.02831">‘AI scientists’ as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents</a> that integrate machine learning tools with experimental platforms.</p>Marinka ZitnikWe envision ‘AI scientists’ as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate machine learning tools with experimental platforms.Efficient ML Seminar Series2024-03-23T00:00:00-04:002024-03-23T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/03/23/EfficientMLSeminar<p>We started a <a href="https://efficientml.org/">Harvard University Efficient ML Seminar Series</a>. Congrats to Jonathan for spearheading this initiative. <a href="https://www.harvardmagazine.com/2024/03/scaling-artificial-intelligence">Harvard Magazine</a> covered the first meeting focusing on LLMs.</p>Marinka ZitnikWe started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.UniTS - Unified Time Series Model2024-03-04T00:00:00-05:002024-03-04T00:00:00-05:00https://zitniklab.hms.harvard.edu/2024/03/04/UniTS<p><a href="https://arxiv.org/abs/2403.00131">UniTS is a unified time series model</a> 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. <a href="https://zitniklab.hms.harvard.edu/projects/UniTS/">Project website.</a></p>Marinka ZitnikUniTS 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.
\ No newline at end of file
+Jekyll2024-08-18T16:00:56-04:00https://zitniklab.hms.harvard.edu/feed.xmlZitnik LabHarvard Machine Learning for Medicine and ScienceMarinka ZitnikHow 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.Digital Twins as Global Health and Disease Models of Individuals2024-07-15T00:00:00-04:002024-07-15T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/07/15/DigitalTwins<p><a href="https://www.preprints.org/manuscript/202406.0357/">Paper on digitial twins</a> outlining strategies to leverage molecular and computational techniques to construct dynamic digital twins on the scale of populations to individuals.</p>Marinka ZitnikPaper on digitial twins outlining strategies to leverage molecular and computational techniques to construct dynamic digital twins on the scale of populations to individuals.Graph Diffusion Convolutions at ICML2024-07-14T00:00:00-04:002024-07-14T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/07/14/GraphAdversarialDiffusion<p><a href="https://arxiv.org/abs/2406.02059">Graph diffusion convolution is a geometric deep learning architecture that aggregates information from higher-order network neighbors through a generalized graph diffusion</a> to enhance model robustness to noisy and incomplete datasets. <a href="https://arxiv.org/abs/2406.02059">Paper at ICML.</a></p>Marinka ZitnikGraph diffusion convolution is a geometric deep learning architecture that aggregates information from higher-order network neighbors through a generalized graph diffusion to enhance model robustness to noisy and incomplete datasets. Paper at ICML.Three Papers: TrialBench, 3D Structure Design, LLM Editing2024-07-13T00:00:00-04:002024-07-13T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/07/13/TrialBenchLLM3DStructure<p>New papers on <a href="https://arxiv.org/abs/2407.00631">TrialBench with AI-ready clinical trial datasets</a>, <a href="https://arxiv.org/abs/2406.03403">structure-based drug design benchmark</a>, and <a href="https://arxiv.org/abs/2407.06483">composable interventions for language models</a>.</p>Marinka ZitnikNew papers on TrialBench with AI-ready clinical trial datasets, structure-based drug design benchmark, and composable interventions for language models.TDC-2: Multimodal Foundation for Therapeutics2024-06-23T00:00:00-04:002024-06-23T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/06/23/TDC2<p><a href="https://tdcommons.ai/">The Commons 2.0 (TDC-2)</a> is an overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new tasks and benchmarks. <a href="https://www.biorxiv.org/content/10.1101/2024.06.12.598655v2">Our paper.</a></p>Marinka ZitnikThe Commons 2.0 (TDC-2) is an overhaul of Therapeutic Data Commons to catalyze research in multimodal models for drug discovery by unifying single-cell biology of diseases, biochemistry of molecules, and effects of drugs through multimodal datasets, AI-powered API endpoints, new tasks and benchmarks. Our paper.Broad MIA: Protein Language Models2024-05-29T00:00:00-04:002024-05-29T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/05/29/BroadMIA<p>Check out our Broad’s seminars on <a href="https://youtu.be/LcLmvtXHI1s?si=GABqGdFt5ze9leT_">Multimodal protein language models for deciphering protein function.</a></p>Marinka ZitnikCheck out our Broad’s seminars on Multimodal protein language models for deciphering protein function.On Knowing a Gene in Cell Systems2024-05-28T00:00:00-04:002024-05-28T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/05/28/KnowingAGene<p>We shed light on <a href="https://www.sciencedirect.com/science/article/pii/S2405471224001236">distributional gene representations and their potential applications in biology to characterize gene function from a broader and more holistic perspective.</a></p>Marinka ZitnikWe shed light on distributional gene representations and their potential applications in biology to characterize gene function from a broader and more holistic perspective.Biomedical AI Agents2024-04-04T00:00:00-04:002024-04-04T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/04/04/BIomedicalAIAgents<p>We envision <a href="https://arxiv.org/abs/2404.02831">‘AI scientists’ as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents</a> that integrate machine learning tools with experimental platforms.</p>Marinka ZitnikWe envision ‘AI scientists’ as systems capable of skeptical learning and reasoning that empower biomedical research through collaborative agents that integrate machine learning tools with experimental platforms.Efficient ML Seminar Series2024-03-23T00:00:00-04:002024-03-23T00:00:00-04:00https://zitniklab.hms.harvard.edu/2024/03/23/EfficientMLSeminar<p>We started a <a href="https://efficientml.org/">Harvard University Efficient ML Seminar Series</a>. Congrats to Jonathan for spearheading this initiative. <a href="https://www.harvardmagazine.com/2024/03/scaling-artificial-intelligence">Harvard Magazine</a> covered the first meeting focusing on LLMs.</p>Marinka ZitnikWe started a Harvard University Efficient ML Seminar Series. Congrats to Jonathan for spearheading this initiative. Harvard Magazine covered the first meeting focusing on LLMs.
\ No newline at end of file
diff --git a/index.html b/index.html
index 4eb9d9a1..f353966f 100644
--- a/index.html
+++ b/index.html
@@ -177,6 +177,34 @@
AI for Science | Therapeutic Science
+
+
+
+
+
+
Aug 2024: How Proteins Behave in Context
+
+
+
+
+
+
+
+
+
Harvard 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.
Thank you for being so interested in joining our group! Impactful research requires excellent mentoring. Prof. Zitnik is the recipient of the Young Mentor Award at Harvard Medical School—this prestigious award acknowledges that recognition to her.
+
Thank you for being so interested in joining our group! Impactful research requires excellent mentoring. Prof. Zitnik is the recipient of the Young Mentor Award at Harvard Medical School—this prestigious award acknowledges that recognition to her.
Graduate students
@@ -170,9 +170,9 @@
Postdoct
Postdoctoral research fellows in foundation AI
-
We have multiple openings for postdoctoral research fellows in the broad area of foundation models focusing on geometric deep learning, multimodal learning, large-scale knowledge graphs, large language models, generative AI, and AI agents.
+
We have multiple openings for postdoctoral research fellows in foundation models focusing on geometric deep learning, multimodal learning, large-scale knowledge graphs, large language models, generative AI, and AI agents.
-
Applications are reviewed on a rolling basis. Interested candidates are encouraged to submit their applications as soon as possible.
+
This position is available immediately. Interested candidates are encouraged to submit their applications as soon as possible.
We have an opening for a postdoctoral research fellowship in novel methods in the broad area of medical AI.
+
We have multiple openings for postdoctoral research fellows in medical AI.
This position is available immediately. Interested candidates are encouraged to submit their applications as soon as possible.
@@ -259,6 +259,34 @@
Visitors, interns, and short-t
+
+
+
+
+
+
Aug 2024: How Proteins Behave in Context
+
+
+
+
+
+
+
+
+
Harvard 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.
Harvard 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.
Harvard 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.
Mar 2021: Hot Off the Press: Multiscale Interactome
-
-
-
-
-
-
-
-
-
Hot off the press! We develop a multiscale interactome approach to explain disease treatments. The approach can predict drug-disease treatments, identify proteins and biological functions related to treatment, and identify genes that alter treatment’s efficacy and adverse reactions.
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
Mar 2021: Hot Off the Press: Multiscale Interactome
+
+
+
+
+
+
+
+
+
Hot off the press! We develop a multiscale interactome approach to explain disease treatments. The approach can predict drug-disease treatments, identify proteins and biological functions related to treatment, and identify genes that alter treatment’s efficacy and adverse reactions.
Harvard 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.
We are looking for applicants with demonstrably strong research skills, ideally, with multiple publications in top venues in machine learning and artificial intelligence, and/or top-tier scientific journals.
-
Candidates must have a Ph.D. or equivalent degree in computer science, statistics, or a closely related field. Strong programming skills and practical experience with leading machine learning frameworks are required. Experience and/or interest in applications of AI to science, biology and medicine is a strong plus.
+
Candidates must have a Ph.D. or equivalent degree in computer science. Strong programming skills and practical experience with leading machine learning frameworks are required. Experience and/or interest in applications of AI to science, biology and medicine is a strong plus.
Application process
@@ -191,6 +191,34 @@
Advisor
+
+
+
+
+
+
Aug 2024: How Proteins Behave in Context
+
+
+
+
+
+
+
+
+
Harvard 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.
Harvard 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.
Harvard 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.
Harvard 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.
We are looking for applicants with demonstrably strong research skills, ideally, with multiple publications in top venues in machine learning and artificial intelligence, and/or top-tier medical journals.
-
Candidates must have a Ph.D. or equivalent degree in computer science, statistics, or a closely related field. Strong programming skills and practical experience with leading machine learning frameworks are required. Experience and/or interest in medical AI is a strong plus.
+
Candidates must have a Ph.D. or equivalent degree in computer science. Strong programming skills and practical experience with leading machine learning frameworks are required. Experience and/or interest in medical AI is a strong plus.
Application process
@@ -196,6 +196,34 @@
Advisor
+
+
+
+
+
+
Aug 2024: How Proteins Behave in Context
+
+
+
+
+
+
+
+
+
Harvard 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.
Pengwei Sui" />
+ 
Michelle Dai" />
Owen Queen" />
+ 
Zaixi Zhang" />
+ 
-