Marinka Zitnik @marinkazitnik Twitter profile

Last Seen Profiles

@chloepunkprice

@UoECrim

@sukeakur3

@AndiGigoloAsli

@Izzy_SweetSoul2

@fotudissim

@coolmahoshj228

@FlavioBh2

@Rhythm_As1

@nicholas_bapst

@OORer85176510

@hassallmatt

@SAlqmyshy41610

@KelvionR

@preston_vanloon

@FellowMeme81532

@KarnaSelim50958

@Prima72323313

@watedayo1

@AizaKea

@javipdr

@tomryanauthor

@an_gonda

@frogspa_miyu

@riskyadpathways

@CaravanAOM

@Anwalt_Jun

@dhym_hmd87605

@dbrust1030

@maiwa_kawaii

@KatherinPa27802

@CBCS

@nehirloj

@jandakembangstw

@00000ut

@1405C4RT

Marinka Zitnik

@marinkazitnik

2 years

Excited to teach a course on #biomedical #AI this semester @Harvard @harvardmed Follow our course materials, reading lists and paper highlights which we will release throughout the semester Thankful for star TA team @YEktefaie @richardjchen Y Huang

13

150

787

Marinka Zitnik

@marinkazitnik

2 years

Deep learning on #graphs is poised to address major gaps in biology and medicine In Nature Biomed Eng @natBME , we describe the next generation of #graphAI #GNN methods and opportunities that build models from data using structure, geometry & knowledge

13

179

771

Marinka Zitnik

@marinkazitnik

1 year

Excited to share our @Nature paper on the role of AI in scientific discovery 🌟🔬 #AI4Science AI is transforming discovery across sciences 🤖🔍 From hypothesis generation to data interpretation, it is reshaping all stages of research in ways we could not imagine using

11

198

654

Marinka Zitnik

@marinkazitnik

2 years

Can we infuse #structure into a time series ( #TS ) model from a diverse dataset so as to greatly improve #generalization on new TS coming from different datasets? Yes, via a new principle called #Representational Time-Frequency Consistency (TF-C) 1/3

3

102

516

Marinka Zitnik

@marinkazitnik

4 years

Survey on Representation Learning for Networks in Biology and Medicine Long-standing principles of biomed nets (often unspoken in ML) provide grounding for representation learning, explain successes & limitations @_michellemli @KexinHuang5 #netbio #GNN #ML

3

111

446

Marinka Zitnik

@marinkazitnik

1 month

Excited to share TxGNN, a model that identifies potential therapies from existing medicines for thousands of diseases. Trained across 17,080 diseases, TxGNN predicts drug candidates for conditions with limited or no treatment options, including rare diseases @NatureMedicine

9

114

394

Marinka Zitnik

@marinkazitnik

1 year

Introducing PINNACLE, a contextual graph AI model for comprehensive protein understanding PINNACLE dynamically adjusts its outputs based on molecular contexts in which it operates Providing outputs tailored to molecular contexts is essential for broader use of foundational

5

78

306

Marinka Zitnik

@marinkazitnik

3 months

Excited to share our new paper on Contextual AI models for context-specific prediction in biology in @NatureMethods led by stellar @_michellemli Understanding how proteins work and developing new therapies requires knowing which cell types proteins act

7

62

296

Marinka Zitnik

@marinkazitnik

10 months

Introducing PDGrapher - Combinatorial prediction of therapeutically useful chemical and genetic perturbations using causally-inspired neural networks Many methods learn responses to perturbations, but PDGrapher is addressing the inverse problem, which is to infer the perturbagen

4

68

279

Marinka Zitnik

@marinkazitnik

5 months

On knowing a gene: Distributional hypothesis of gene function Just as words derive meanings from context, genes can switch their roles with biological surroundings. Traditional gene annotations miss this Advances in transformers suggest a new perspective: gene functions as

2

65

282

Marinka Zitnik

@marinkazitnik

2 years

With @payal_chandak and @KexinHuang5 , we are excited to share PrimeKG, a precision medicine-oriented knowledge graph providing holistic and multimodal view of human disease (1/8)

4

48

223

Marinka Zitnik

@marinkazitnik

2 years

Meet TxGNN, a model that utilizes geometric deep learning and human-centered AI to make zero-shot predictions of therapeutic use across a vast range of 17,080 diseases @HarvardDBMI @IcahnMountSinai @Stanford @harvard_data @harvardmed @MIT_CSAIL 1/9

2

42

222

Marinka Zitnik

@marinkazitnik

4 years

Excited to share preprint on Therapeutics Data Commons! Paper: Website: TDC is a unifying framework across the entire range of #therapeutics #ML . Ecosystem of tools, leaderboards & community resr 66 ML-ready datasets 22 ML tasks

1

62

220

Marinka Zitnik

@marinkazitnik

2 years

How can we delete data from a big model without training the model from scratch and sacrificing performance? Having models unlearn is notoriously difficult Our new #ICLR2023 paper introduces a general strategy for unlearning on graphs

George Dasoulas

@GDasoulas

2 years

Exciting news 🥳: Our new research paper on Graph Unlearning is accepted at ICLR 2023 @iclr_conf ! Thanks to my coauthors Jiali Cheng, Huan He, @_cagarwal , and @marinkazitnik for the great collaboration!! More info about our work will be out soon! #ICLR2023 #ML #GNN #graphs

1

6

78

1

33

213

Marinka Zitnik

@marinkazitnik

6 months

Empowering Biomedical Discovery with AI Agents 🤖 Long-standing ambition for biomedical AI is the development of AI systems that can make major scientific discoveries with the potential to be worthy of a Nobel Prize—fulfilling the Nobel Turing Challenge

3

56

212

Marinka Zitnik

@marinkazitnik

2 years

1/ Have you ever wondered why AI models struggle to perform well when faced with new data outside their training set? This can be due to feature and label shifts which we can address using #ICML2023 Raincoat @icmlconf @harvard @harvard_data @MITLL @MIT

6

53

211

Marinka Zitnik

@marinkazitnik

2 years

Excited to share the blueprint for multimodal graph learning in @NatMachIntell We envision graph AI playing a key role in future image-intensive, knowledge-grounded, and language-intensive systems 1/5

1

48

207

Marinka Zitnik

@marinkazitnik

1 year

So excited about this new PhD program in Artificial Intelligence in Medicine @Harvard 🎓🎓🎓 Join our info session on October 17th. Apply by December 1st @HarvardDBMI #ML4H #AI4Medicine #health #research

2

32

183

Marinka Zitnik

@marinkazitnik

3 years

Our #ICLR2022 paper introduces Raindrop, #graph neural network learning on irregularly sampled and multivariate #time series Check it out: website: code: @xiangzhang1015 @MIT @MITLL @iclr_conf #GNN (1/7)

4

41

183

Marinka Zitnik

@marinkazitnik

4 years

Thrilled that our lab has 4/4 papers accepted at #NeurIPS2020 ! Not bad for a lab just 5 months old at submission deadline. Congrats to fantastic students and collaborators @_michellemli @xiangzhang1015 @KexinHuang5 @IAmSamFin @Emily_Alsentzer @Harvard @HarvardDBMI @harvard_data

11

7

181

Marinka Zitnik

@marinkazitnik

2 years

I was very happy to receive @harvardmed Young Mentor Award today. Feeling fortunate to be working together with so many outstanding students @HarvardDBMI and am excited to see the bright future they are creating for themselves and our world

5

6

167

Marinka Zitnik

@marinkazitnik

6 months

That's a wrap on this semester's @HarvardDBMI BMI702 Intro to #Biomedical #AI class! 🎓 Explore the syllabus and course materials, open to all: @harvardmed @harvard_data @KempnerInst

2

37

163

Marinka Zitnik

@marinkazitnik

2 months

Excited to share a new perspective on Graph Artificial Intelligence in Medicine | Annual Reviews @AnnualReviews - Led by fantastic @ruthie_johnson @_michellemli @ayushnoori @oq_35 @harvard_data @broadinstitute @KempnerInst @HarvardDBMI

2

40

166

Marinka Zitnik

@marinkazitnik

3 years

Excited to be elected to @ELLISforEurope as ELLIS Scholar in Geometric Deep Learning. Can't wait for new opportunities to further graph ML research on both sides of the Atlantic. Many thanks to the ELLIS community for the support, esp @mmbronstein @maxwelling @tacocohen

7

4

144

Marinka Zitnik

@marinkazitnik

5 years

How to design effective figures for research papers? Slides from my workshops @Stanford #research #scicomm #cs #science

2

48

140

Marinka Zitnik

@marinkazitnik

4 years

Super excited about winning @amazon Amazon Faculty Research Award on "Actionable Graph Learning for Finding Cures for Emerging Diseases" Thank you @AmazonScience for this recognition! More details soon @HarvardDBMI @harvardmed @harvard_data

4

8

132

Marinka Zitnik

@marinkazitnik

1 month

Couldn't do it without the GPUs — they’re basically our co-workers at this point. Shoutout to @harvardmed @HarvardDBMI @KempnerInst @nvidia for the compute power

AI Uses Zero-Shot Learning to Find Existing Drugs for Treating Rare Diseases | NVIDIA Technical Blog

A groundbreaking drug-repurposing AI model could bring new hope to doctors and patients trying to treat diseases with limited or no existing treatment options. Called TxGNN, this zero-shot tool helps…

developer.nvidia.com

0

21

123

Marinka Zitnik

@marinkazitnik

4 months

Join us for the AI for Genomics and Health Conference, the 2024 @Harvard PQG Conference, to discuss advances of AI in translational medicine and health Fantastic co-organizers @james_y_zou @elhamazizi @XihongLin @jmuiuc @BoWang87 K Vogan @HarvardChanSPH

3

28

117

Marinka Zitnik

@marinkazitnik

1 year

Excited to share our @NeurIPSConf papers accepted as spotlights! @ZaixiZhang @oq_35 #NeurIPS2023 Full-Atom Protein Pocket Design via Iterative Refinement 🧬 Designing functional proteins for specific ligand binding is key for therapy & bio-engineering. A

0

22

119

Marinka Zitnik

@marinkazitnik

11 months

🚨 JOB ALERT 🚨 We are building the next generation of Therapeutics Commons @ProjectTDC ! Our vision is to lay the foundations for AI & therapeutics, eventually enabling AI to learn on its own and acquire knowledge through continual refinement We are seeking postdoctoral

0

26

119

Marinka Zitnik

@marinkazitnik

2 years

Today we share a paper introducing graph neural network #GNN powered mutual interactors to predict #molecular #phenotypes Excited about this paper because it shows how thoughtful probing of AI model behavior can pave the way to improvements on many downstream tasks [1/6]

1

29

110

Marinka Zitnik

@marinkazitnik

4 years

Enjoy Subgraph Neural Networks! Sub- #GNNs learn powerful #representations for #subgraph prediction. Going beyond predictions on nodes, edges and entire #graphs by @Emily_Alsentzer @IAmSamFin @_michellemli @HarvardDBMI @harvard_data @harvardmed @MIT_CSAIL

3

20

101

Marinka Zitnik

@marinkazitnik

17 days

Introducing KGARevion, a KG+LLM agent 🤖designed for knowledge-intensive medical QA. Led by @xiaorui_su @GaoShanghua @valegiunca Here's why it is unique: 1️⃣ Open-ended reasoning: Generates nuanced answers without relying on predefined options 2️⃣ Robustness: LLMs can be

0

22

109

Marinka Zitnik

@marinkazitnik

1 year

Envisioning a bright path ahead for networks, graphs, molecules, relational structures, and knowledge systems in biology and medicine 🧬🔬💊🩺

Dr. Tijana Milenkovic

@ProfMilenkovic

1 year

Our review+perspective paper on "Current and future directions in network biology" is online (). This has been a Herculean effort by many co-authors, thank you all! Special thanks to @marinkazitnik , @_michellemli , @aydin_wells , and all section coordinators.

2

131

405

0

9

97

Marinka Zitnik

@marinkazitnik

4 years

Hot off the press! A meta-learning algorithm for finding and naming novel cell types in single-cell datasets.

Nature Methods

@naturemethods

4 years

MARS uses a meta-learning strategy for annotating known cell types and identifying novel ones across single-cell RNA-seq datasets. @jure , @mariabrbic , @marinkazitnik , @Rbaltman

0

62

163

4

13

94

Marinka Zitnik

@marinkazitnik

4 years

We are thrilled to announce the National Symposium on Drugs for Future Pandemics (Nov 17-18)! Tune in for two days of visionary talks by stellar speakers. Registration is free and open #futuretx20

3

27

90

Marinka Zitnik

@marinkazitnik

1 year

Whoa, the current @TheEconomist edition reports on how AI can turbocharge scientific progress and lead to a golden age of discovery, echoing key insights from our recent @Nature paper,

The Economist

@TheEconomist

1 year

Debate about AI often focuses on potential dangers: algorithmic bias, the mass destruction of jobs or even the extinction of humanity. But as some fret about dystopian scenarios, others are focusing on potential rewards

2

12

30

0

19

83

Marinka Zitnik

@marinkazitnik

11 months

Preparing for #NeurIPS2023 ! Nine from our group will attend, presenting papers, giving talks, and organizing workshops @michellemli , @AdaFang , @YEktefaie , @ZaixiZhang , @oq_35 , @TianlongChen4 , @GDasoulas , @YepHuang Find me giving four invited talks, I'm grateful for having a

1

12

82

Marinka Zitnik

@marinkazitnik

3 years

Many congratulations to co-authors @WangQianwenToo , @KexinHuang5 @payal_chandak @ngehlenborg for the best paper award at @icmlconf Interpretable ML in Healthcare. So happy to work with amazing students and collaborators @HarvardDBMI #ICML2021 #XAI #GNN

3

8

80

Marinka Zitnik

@marinkazitnik

3 years

Thanks for organizing this, @guadagonzalezzp @logml2021

Guadalupe Gonzalez

@justguadaa

3 years

Live now: “Graph Representation Learning for Biomedical Discovery” by @marinkazitnik at @logml2021 . Tune it to hear from an expert in the field how geometric deep learning is powering breakthroughs in biomedical discovery. Stream: #MachineLearning

0

26

82

1

12

69

Marinka Zitnik

@marinkazitnik

6 years

#ISMB2018 #ISMB18 Tutorial PM6: Deep Learning for Network Biology -- All materials: See you in Grand Ballroom A at 2 pm today! w/ @jure

0

39

68

Marinka Zitnik

@marinkazitnik

4 years

Very excited to share this research where we use #graphML and #network #medicine to identify novel #therapeutic opportunities

Network medicine framework for identifying drug-repurposing opportunities for COVID-19 | PNAS

The COVID-19 pandemic has highlighted the need to quickly and reliably prioritize clinically approved compounds for their potential effectiveness f...

www.pnas.org

Deisy Gysi, PhD

@GysiDeisy

4 years

I’m proud and excited to share our work on drug repurposing opportunities for treating COVID-19, freshly published in PNAS ().

6

8

31

0

13

65

Marinka Zitnik

@marinkazitnik

5 years

We will present a tutorial on Machine Learning for Drug Development at #IJCAI2020 ! Materials to follow on our website: @IJCAIconf #drugs #networks #AI

1

26

67

Marinka Zitnik

@marinkazitnik

1 month

Thank you, @Forbes , for highlighting this ongoing drug repurposing research. The code, data, and model are all open-source!

AI Tool Speeds Drug Repurposing: And It’s Free

Harvard Zitnik lab released TxGNN, AI model to speed drug repurposing for unmet conditions

www.forbes.com

3

10

64

Marinka Zitnik

@marinkazitnik

1 year

Grateful for this collaboration with the brilliant minds @PetarV_93 and @pushmeet @GoogleDeepMind on how AI is reshaping the realm of science #AI4Science

Google DeepMind

@GoogleDeepMind

1 year

What could science at digital speed look like? 🚀 AI is poised to supercharge scientific discovery as we know it, by: 🔮 Exploring theories 🧪 Designing experiments 🔍 Analysing data Find out how in @Nature . ⬇️

13

106

473

1

7

63

Marinka Zitnik

@marinkazitnik

4 years

Mark your calendars for Nov 17-18! Join the discussion with leading experts in CS, bio, med, automation, and regulation about ways to innovate rapid therapeutics for future pandemics. Registration is free & open #futuretx20

2

11

60

Marinka Zitnik

@marinkazitnik

2 years

Excited for #NeurIPS2022 -- We'll present two papers, organize two workshops and give some invited talks and panel discussions #AI4Science #biomedicalAI [1/6]

1

4

57

Marinka Zitnik

@marinkazitnik

4 years

Submit your latest research to Graph Representation Learning Workshop at #ICML2020 Deadline: May 29 We encourage submissions on #graph representation learning, geometric deep learning, interdisciplinary applications, benchmarks, and research aiming to mitigate #COVID19

Google DeepMind

@GoogleDeepMind

4 years

Excited about Graph Representation Learning and its application across the sciences? Our Research Scientists @PetarV_93 and @jhamrick are co-organising an #icml2020 workshop on the topic -- consider submitting your latest research by 29 May! More information below:

1

35

115

0

12

57

Marinka Zitnik

@marinkazitnik

4 years

Great work, @_camiloruiz ! We develop a multiscale interactome approach to explain disease treatments. It predicts drug-disease treatments, identifies proteins and biological functions related to treatment, and identifies genes that alter treatment's efficacy & adverse reactions.

Lorenzo Righetto

@LorenzoRighett7

4 years

. @_camiloruiz , @marinkazitnik and @jure develop the multiscale interactome, a powerful approach to explain disease treatment. @StanfordBioE @StanfordEng @StanfordMed @czbiohub @HarvardDBMI

0

5

18

1

10

58

Marinka Zitnik

@marinkazitnik

3 years

Our new #AISTATS2022 paper introduces the first axiomatic framework for theoretically analyzing, evaluating, and comparing #GNN explainers. Check it out: w/ @hima_lakkaraju @_cagarwal (1/5) @aistats_conf

3

13

56

Marinka Zitnik

@marinkazitnik

2 years

Congrats to @payal_chandak and @KexinHuang5 on publishing PrimeKG, multimodal knowledge graph for precision medicine in @ScientificData 🔬 🎉 Stay ahead of the curve with PrimeKG as it's continually updated with the latest data

GitHub - mims-harvard/PrimeKG: Precision Medicine Knowledge Graph (PrimeKG)

Precision Medicine Knowledge Graph (PrimeKG). Contribute to mims-harvard/PrimeKG development by creating an account on GitHub.

github.com

Marinka Zitnik

@marinkazitnik

2 years

With @payal_chandak and @KexinHuang5 , we are excited to share PrimeKG, a precision medicine-oriented knowledge graph providing holistic and multimodal view of human disease (1/8)

4

48

223

1

19

56

Marinka Zitnik

@marinkazitnik

5 months

Many congratulations to @_michellemli for her successful PhD defense!

Ayush Noori

@ayushnoori

5 months

The inimitable @_michellemli is PhDone! Congratulations to my brilliant friend Michelle on her successful tour-de-force PhD defense in @marinkazitnik ’s lab. 🎉 Michelle is a leader, teacher, and mentor extraordinaire – she will change the world and uplift others with her!

5

3

30

4

3

55

Marinka Zitnik

@marinkazitnik

1 year

📢 1/7: Excited to share @NatMachIntell paper on language model pre-training and relational structure outside the realm of natural language Thankful for a star team @MattBMcDermott , B Yap, P Szolovits @HarvardDBMI @harvard_data @MIT

1

10

53

Marinka Zitnik

@marinkazitnik

10 months

Excited for the future of AI in medicine that @NEJM_AI will help create

NEJM AI

@NEJM_AI

10 months

Dr. @marinkazitnik is an Assistant Professor of Biomedical Informatics @harvardmed with additional appointments @harvard_data and @broadinstitute of Harvard and MIT. Dr. Zitnik works on infusing knowledge, structure, and geometry into machine learning models.

2

9

38

1

7

52

Marinka Zitnik

@marinkazitnik

3 years

Very excited about this project! We need to start opening graph neural nets to high-stakes domains #biomedicalAI Our approach can be used with any #GNN to learn provably fair and stable embeddings #graphML #trustworthyML @_cagarwal @hima_lakkaraju

Chirag Agarwal

@_cagarwal

3 years

We introduce and experiment with three new graph datasets comprising of high-stakes decision-making applications. Our results show that NIFTY improves the fairness and stability of SOTA GNNs by 92.01% and 60.87%, respectively, without sacrificing predictive performance [7/n]

1

4

0

7

51

Marinka Zitnik

@marinkazitnik

23 days

Exciting times for @AI_for_Science and everyone working in the field🏅🏅🏅

The Nobel Prize

@NobelPrize

24 days

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”

537

9K

20K

2

4

51

Marinka Zitnik

@marinkazitnik

2 years

ML track @iscb #ISMB2022 starts on Wed at 10:30am CDT Speakers @DrAnneCarpenter @suinleelab @s_brunak N. Beerenwinkel @cbg_ethz @GreeneScientist @markowetzlab @FertigLab G. Rustici @AstraZeneca and many more Excited to chair this track w/ @CataVallejosM

0

12

51

Marinka Zitnik

@marinkazitnik

17 days

Next in @NeurIPSConf 2024 series is PocketFlow. This generative model uses flow matching to learn critical protein-ligand interactions like hydrogen bonds It combines overall binding affinity with interaction geometry constraints to ensure high affinity and valid pocket

Biology+AI Daily

@BiologyAIDaily

1 month

Generalized Protein Pocket Generation with Prior-Informed Flow Matching - The paper introduces PocketFlow, a generative model that revolutionizes protein pocket design by incorporating protein-ligand interaction priors using a flow matching approach. - PocketFlow significantly

2

10

54

0

13

51

Marinka Zitnik

@marinkazitnik

2 years

First talk in the session is David Kelley @drklly on sequence‐based modeling of single‐cell ATAC‐seq using convolutional neural networks #biodata22

scBasset: sequence-based modeling of single-cell ATAC-seq using convolutional neural networks

Nature Methods - Using a sequence-based deep neural network, scBasset facilitates various tasks of single-cell ATAC-seq analysis in a unified framework.

www.nature.com

3

6

50

Marinka Zitnik

@marinkazitnik

1 year

It's an exciting double conference week, #ISMBECCB2023 and #ICML2023 . If you're attending, these talks and presentations are not to be missed! At @iscb , @_michellemli will talk about her work with @Emily_Alsentzer on SHEPHERD, which is our latest zero-shot deep learning model

1

6

50

Marinka Zitnik

@marinkazitnik

2 years

Excited about the future of #multimodal #AI using #graphs to bring diverse modalities together Check our preprint on graph-centric multimodal representation learning 👇 Led by fantastic students @YEktefaie @GDasoulas @ayushnoori collab w @MahaFarhat @HarvardDBMI @harvard_data

Yasha Ektefaie

@YEktefaie

2 years

Excited to present our new preprint on geometric multimodal representation learning! Keep reading for more details 👀. [1/6]

5

29

110

0

14

47

Marinka Zitnik

@marinkazitnik

3 years

Genes can participate in multiple independent biological functions, a foundational genetic principle known as pleiotropy. We show how sparse approximation & learning can decipher pleiotropy in high-dim gene perturb datasets. Great work, @joshbiology ! #MLCB2021

Joshua Pan

@joshbiology

3 years

Ever felt your favorite gene has *more than one function* after perturbing it in many cell contexts? Today at #MLCB2021 , I'll discuss automatic genotype-phenotype inference from high-dimensional gene perturbation data using sparse approximation: [a 🧵]

6

82

350

0

9

48

Marinka Zitnik

@marinkazitnik

5 years

Excited to share a new preprint on predicting molecular #interactions with skip-graph networks Skip- #GNN uses 2nd-order interactions, which proved incredibly useful in #bionets over the last decade Led by a fantastic student @KexinHuang5 @harvard_data

SkipGNN: Predicting Molecular Interactions with Skip-Graph Networks

Molecular interaction networks are powerful resources for the discovery. They are increasingly used with machine learning methods to predict biologically meaningful interactions. While deep...

arxiv.org

0

7

49

Marinka Zitnik

@marinkazitnik

2 years

Join us tomorrow @iscb #ISMB2022 ! How #graph #AI can help advance precision medicine? Advances in methods and key areas in #disease #therapeutics & #patients , and demos, practical tips, and hands-on exercises With star student @_michellemli @HarvardDBMI

0

12

48

Marinka Zitnik

@marinkazitnik

8 months

📢 New @Harvard Seminar Series on Efficient ML! 👇 Thanks @schwarzjn_ for spearheading this effort! @HarvardDBMI @KempnerInst @harvard_data @harvardmed @zakkohane @ShamKakade6 🎓 Check out a phenomenal speaker lineup with an opening by LLM superstars @sarahookr @cohere and

Jonathan Richard Schwarz

@schwarzjn_

8 months

🚨 Excited to announce our new @Harvard seminar series on Efficient ML! Please join LLM superstars @sarahookr ( @cohere ) & @valentina__py ( @allen_ai ) for our kick-off meeting next Monday! Open to everyone! 📅 🔗 @harvard_data @harvardmed @KempnerInst

4

34

155

0

7

48

Marinka Zitnik

@marinkazitnik

3 years

So excited about this new venue! Submit your finest work in graph representation learning, geometric deep learning, graph AI

Learning on Graphs Conference 2024

@LogConference

3 years

Here it is: the first Learning on Graphs Conference! 🎊 We think this new venue will be valuable for the Graph/Geometric Machine Learning community. What makes it so important+unique? See our blog post! 1/6

4

301

888

0

7

47

Marinka Zitnik

@marinkazitnik

6 years

How do biological #networks change with #evolution ? Our study just published in @PNASNews shows that evolution leads to resilient protein interactomes, which, in turn, are beneficial for organisms w/ @jure , M.W. Feldman et al.

1

16

47

Marinka Zitnik

@marinkazitnik

2 years

Excited about this #NeurIPS2022 paper on broadly generalizable self-supervised learning Congrats to fantastic students @xiangzhang1015 Z. Zhao @HarvardDBMI @harvard_data and collab w T. Tsiligkaridis @MITLL project page: code:

GitHub - mims-harvard/TFC-pretraining: Self-supervised contrastive learning for time series via...

Self-supervised contrastive learning for time series via time-frequency consistency - mims-harvard/TFC-pretraining

github.com

Marinka Zitnik

@marinkazitnik

2 years

Can we infuse #structure into a time series ( #TS ) model from a diverse dataset so as to greatly improve #generalization on new TS coming from different datasets? Yes, via a new principle called #Representational Time-Frequency Consistency (TF-C) 1/3

3

102

516

1

8

44

Marinka Zitnik

@marinkazitnik

2 years

Looking forward to meeting you all @kdd_news #KDD2022 - On Monday I will give keynotes on: Infusing Structure and Knowledge into Biomedical AI (10:45am) Graph-Guided Networks for Complex Time Series (14:20am)

0

6

45

Marinka Zitnik

@marinkazitnik

5 years

New preprint: Meta-learning for identifying and naming cell types, even cell types that have never been seen before and do not exist in the training data #MetaLearning #TabulaMuris #TabulaMurisSenis #aging

bioRxiv

@biorxivpreprint

5 years

Discovering novel cell types across heterogeneous single-cell experiments #bioRxiv

0

7

8

1

6

44

Marinka Zitnik

@marinkazitnik

4 years

So excited and honored that our research is recognized by the @Bayer Early Excellence in Science Award

Patrick Cramer

@mpgpresident

4 years

Congratulations to Ruth Ley for obtaining the Otto Bayer Award 2020! Congratulations to Julia Mahamid, Josep Cornella, Nikolai Franzmeier and Marinka Zitnik for obtaining the Early Excellence in Science Awards 2020! @CornellaLab @nfranzme @marinkazitnik

2

1

17

5

2

45

Marinka Zitnik

@marinkazitnik

2 years

We are hiring postdocs in graph AI for cancer drug discovery #AI4Science #graphs #ML

Harvard Data Science Initiative

@harvard_data

2 years

🔍 Join Professor @marinkazitnik 's lab as a Postdoc #Research Fellow in #AI for Cancer Drug Discovery at @Harvard ! Apply to lead the design, development, and implementation of novel AI methods for the analysis of clinical and biomarker #data in oncology:

0

2

5

0

9

45

Marinka Zitnik

@marinkazitnik

5 years

Excited about our new work accepted to #ICLR2020 as full paper with spotlight! @iclr_conf TL;DR: We develop strategies for pre-training Graph Neural Networks and study their effectiveness on multiple datasets, GNN architectures, and diverse downstream tasks #molecules #proteins

Weihua Hu

@weihua916

5 years

(1) Strategies for Pre-training GNNs (spotlight) joint work with @liubowen16 @marinkazitnik @vijaypande @percyliang @jure

2

3

41

0

4

43

Marinka Zitnik

@marinkazitnik

4 years

Subgraph Neural Networks GNNGuard: Defending GNNs against Adversarial Attacks Graph Meta Learning via Local Subgraphs Open Graph Benchmark: Datasets for ML on Graphs

Open Graph Benchmark: Datasets for Machine Learning on Graphs

We present the Open Graph Benchmark (OGB), a diverse set of challenging and realistic benchmark datasets to facilitate scalable, robust, and reproducible graph machine learning (ML) research. OGB...

arxiv.org

1

7

41

Marinka Zitnik

@marinkazitnik

4 months

It was great to discuss with @cziscience ’s tech team on accelerating the digital age of biology and sharing our research @HarvardDBMI @KempnerInst

Exploring The Digital Age of Biology

Advances in AI can answer the biggest questions about human biology

chanzuckerberg.com

1

6

40

Marinka Zitnik

@marinkazitnik

2 years

Exciting news for biomedical AI world!

NEJM AI

@NEJM_AI

2 years

Coming soon: NEJM AI, a new journal from NEJM Group. NEJM AI aims to identify and evaluate state-of-the-art applications of artificial intelligence to clinical medicine. Learn more about the new journal:

12

113

335

2

41

Marinka Zitnik

@marinkazitnik

5 years

We are guest-editing special issue on Graph Embeddings and Deep Learning for Network Biology @ComputerSociety @TheOfficialACM IEEE/ACM TCBB Call: Submit your finest work by July 30, 2020! Spread the word! #machinelearning #graphs #compbio #medicine

0

12

38

Marinka Zitnik

@marinkazitnik

3 years

Excited to see this published: We examined 10,443,476 #adverse #drug event reports, spanning 19,193 adverse events and 3,624 drugs, to extract insights into safe #medication use & how adverse events vary across #patient groups Detailed tweetorial to follow shortly #data #AI

Nature Computational Science

@NatComputSci

3 years

In a recent Article, @xiangzhang1015 , @marissa_sumathi and @marinkazitnik analyze large-scale patient safety data to reveal demographic disparities of drug safety and identify at-risk patients during a pandemic.

1

3

25

1

8

40

Marinka Zitnik

@marinkazitnik

8 months

Thank you @BiswasFamilyFdn for your vision and generosity Learn more about our project CURE-Bench to build and evaluate all-disease foundation models for identifying clinically relevant drug repurposing hits Thankful to @BiswasFamilyFdn for supporting

4

10

41

Marinka Zitnik

@marinkazitnik

1 year

AI and science: @Richvn @Nature polled 1,600 researchers around the world about their views on the rise of AI in science, including machine learning and generative AI #AI4Science @AI_for_Science Among those who used AI in their research, more than 25% felt that AI tools would

1

8

38

Marinka Zitnik

@marinkazitnik

4 years

Excited to present a tutorial on #ML for drug development and discovery at @IJCAIconf . Jan 6, 7-10pm EST / Jan 7, 9am-12pm JST w/ @jimeng and Danica Xiao @IQVIA_global

0

7

40

Marinka Zitnik

@marinkazitnik

4 years

We are thrilled to release the Open Graph Benchmark! OGB contains numerous biomedical datasets, including protein interaction nets, cross-species graphs, drug-drug interaction nets, and biomedical knowledge graphs #ML #graphs #networks

Weihua Hu

@weihua916

4 years

Super excited to share Open Graph Benchmark (OGB)! OGB provides large-scale, diverse graph datasets to catalyze graph ML research. The datasets are easily accessible via OGB Python package with unified evaluation protocols and public leaderboards. Paper:

2

112

407

0

13

39

Marinka Zitnik

@marinkazitnik

11 months

Phenomenal resource with ready-to-use embeddings and models through @cziscience Cell Census 🚀 Congrats to @JCoolScience @Paedugar and the #CELLxGENE team 👏 Thanks for showcasing PINNACLE, our contextual AI model for single-cell protein biology, and scCIPHER, our multimodal AI

Jonah Cool

@JCoolScience

11 months

🚨1/ New to CZ #CELLxGENE : models & embeddings that integrate up to 36M cells in the Census corpus. Use embeddings to explore the corpus directly, or download the models to run your own data through them to enable direct comparisons to the reference. 🧵

4

48

186

0

8

38

Marinka Zitnik

@marinkazitnik

4 years

So glad to see this! We started to tackle this challenge through Therapeutics Data Commons, an ecosystem of AI/ML-ready datasets for therapeutics, together with tools, leaderboards and community resources like meaningful data splits

Therapeutics Data Commons

Artificial intelligence foundation for therapeutic science

tdcommons.ai

Michael F. Chiang, MD

@NEIDirector

4 years

ICYMI: if you have interest in dataset generation for #AI , check out the new @NIH_CommonFund Bridge2AI program. Details here: … @NLMdirector @NHGRI_Director @NCCIH_Director @NIBIBgov @aao_ophth @aaopt @AMIAinformatics @ARVOinfo @SfNtweets

0

13

22

0

8

37

Marinka Zitnik

@marinkazitnik

3 years

Submit your papers to our Graph Learning Benchmarks @GLB_Workshop @TheWebConf #TheWebConf Call for contributions to establish novel ML tasks and novel graph-structured data @Jiaqi_Ma_ @jiong971 @epsiloncorrect @danaikoutra @meiqzh

Workshop on Graph Learning Benchmarks (GLB 2022)

Apr. 26, 2022, Virtual

graph-learning-benchmarks.github.io

Workshop on Graph Learning Benchmarks

@GLB_Workshop

3 years

Hello Twitter! This is the official Twitter account for the Workshop on Graph Learning Benchmarks ( #GLB ). We are pleased to announce that the 2nd GLB workshop will be held with the #WebConf 2022. The CfP is out! The submission due is Feb 28, 2022. More at

1

14

51

0

13

38

Marinka Zitnik

@marinkazitnik

1 year

Exciting new resources to power openly available AI models of human cells and catalyze medical research

Chan Zuckerberg Initiative

@ChanZuckerberg

1 year

AI is catalyzing scientific discovery into health and disease. To accelerate progress, we’re building one of the world’s largest computing systems dedicated to non-profit life science research that we’ll leverage to create predictive models of whole cells

32

118

468

1

7

37

Marinka Zitnik

@marinkazitnik

1 year

Such an excellent thread on AlphaMissense by @simocristea

Simona Cristea

@simocristea

1 year

The human genome is gradually unravelling its secrets 🎁 AlphaMissense model @ScienceMagazine : one more path lit up by deep learning in exploring the code of life 🧬 We now know with high confidence if 89% of ALL missense variants are benign or pathogenic Key contributions🧵🧵

11

176

734

2

6

38

Marinka Zitnik

@marinkazitnik

6 months

Exciting new partnership with key priorities, including AI, to accelerate progress in biology through models that leverage data about genetics, patient outcomes, and protein shapes and use these models to provide deep insights into drug design Focus on deployment & delivery: 💊

Gates Foundation

@gatesfoundation

6 months

Our new 3-year, $300 million partnership with @NovoNordiskFond & @WellcomeTrust will support researchers around the world working to develop next-generation solutions to the world’s more pressing global health challenges. Read more:

8

48

174

0

4

37

Marinka Zitnik

@marinkazitnik

16 days

Back in Boston today! Full house @harvard PQG Conference on AI in Genomics and Health, . This theme couldn't be more timely! @harvardmed @HarvardDBMI Next is the first Abstract Winner Platform Talk by F. Hormozdiari on using multimodal AI with

0

1

37

Marinka Zitnik

@marinkazitnik

9 months

Grateful for the chance to discuss AI's 2024 prospects with @NatMachIntell . We covered LLM progress, multimodal AI, multi-task agents, and the crucial issue of bridging the digital divide across communities and world regions Appreciating the insightful exchange, @LCVenema !

Nature Machine Intelligence

@NatMachIntell

9 months

Nature Machine Intelligence has turned 5! Many thanks to all colleagues, authors and referees for helping us shape the journal. Read our anniversary edition of AI Reflections - interviews with recent Comment and Perspective authors

1

10

55

0

2

37

Marinka Zitnik

@marinkazitnik

3 years

Excited for a day at the #AACR2022 ! Will be speaking on deep learning for interactomes, targeting disease-perturbed networks, and @ProjectTDC #AACR2022 #graphAI #drugdiscovery

0

3

36

Marinka Zitnik

@marinkazitnik

3 years

Excited about our @NeurIPSConf 2021 workshop on AI for Science: Mind the Gaps

AI for Science

ai4sciencecommunity.github.io

AI for Science

@AI_for_Science

3 years

Introducing AI for Science — a @NeurIPSConf 2021 Workshop! Our workshop focuses on bridging the gaps between machine learning and science. We have a stellar lineup of speakers! Submit your work and sign up for mentorship program now:

2

51

188

0

4

36

Marinka Zitnik

@marinkazitnik

1 year

Only 5% of 10,000+ #RareDiseases have FDA-approved treatments Excited about #XcelerateRARE data challenge to utilize patient-provided data and help solve these critical unknowns @GlobalGenes @RARE_X_

0

4

36

Marinka Zitnik

@marinkazitnik

4 years

We are looking forward to continuing our research on actionable artificial intelligence for finding cures for emerging diseases

Amazon Science

@AmazonScience

4 years

Congratulations to the 101 recipients of the 2020 #AmazonResearchAwards , who represent 59 universities in 13 countries. Each award supports the work of one to two graduate or postdoctoral students for one year, under the supervision of a faculty member.

0

14

81

3

35

Marinka Zitnik

@marinkazitnik

3 years

To hear highlights about our ongoing research you can find us at these 4 @icmlconf workshops - Socially Responsible ML - Theoretic Foundation, Criticism, Trends in Explainable AI - Interpretable ML in Healthcare - Computational Biology #icml2021 Schedule:

1

6

35

Marinka Zitnik

@marinkazitnik

2 years

Therapeutics Commons @ProjectTDC now has its own @huggingface 🤗 model hub

tdc (Therapeutics Data Commons)

huggingface.co

Therapeutic Data Commons

@ProjectTDC

2 years

📢📢1/ Thrilled to share @ProjectTDC Therapeutics Commons 0.4.0 We have a new interface allowing users to easily access and leverage large pre-trained models for direct prediction or fine-tuning on downstream tasks Check out our @huggingface Hub

2

18

44

0

3

35

Marinka Zitnik

@marinkazitnik

1 year

Excited to share how combining biological LLMs with knowledge graph AI enables zero-shot prediction in drug discovery 🎯💊 Thanks @HarvardCMSA for organizing this conference

Harvard CMSA

@HarvardCMSA

1 year

The CMSA will host the ninth annual Big Data Conference Aug. 31-Sep. 1, 2023

0

2

11

1

5

34

Marinka Zitnik

@marinkazitnik

2 years

Looking forward to an exciting program at @NSF workshop on future directions in #network #biology #NetBio @ProfMilenkovic @anthonygitter @haiyuanyu @ProfMonaSingh @sroyyors @compbiologist @benjraphael @xanderpico @GysiDeisy @bozdags @pedjagogue ++

2

10

35

Marinka Zitnik

@marinkazitnik

6 years

New preprint: Machine Learning for Integrating #Data in #Biology and #Medicine : Principles, Practice, and Opportunities - w/ Francis Nguyen, Bo Wang, @jure , Anna Goldenberg, @michaelhoffman

0

25

33

Marinka Zitnik

@marinkazitnik

3 years

Join us @NeurIPSConf 2021 "AI for Science" Workshop — Monday, Dec 13, 8a-6p ET @AI_for_Science Great day to celebrate AI achievements in scientific discovery and highlight open challenges that need to be addressed to move the field forward #AI4Science

0

7

35