To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus is suitable for LoT study.
With diverse data -- from patient records to imaging -- GNNs process data holistically by viewing modalities as nodes interconnected by their relationships.
In the initial stage, the residue types and backbone coordinates are refined using a hierarchical context encoder, complemented by two structure refinement modules that capture both inter-residue and pocket-ligand interactions.
no code implementations • 15 Sep 2023 • Marinka Zitnik, Michelle M. Li, Aydin Wells, Kimberly Glass, Deisy Morselli Gysi, Arjun Krishnan, T. M. Murali, Predrag Radivojac, Sushmita Roy, Anaïs Baudot, Serdar Bozdag, Danny Z. Chen, Lenore Cowen, Kapil Devkota, Anthony Gitter, Sara Gosline, Pengfei Gu, Pietro H. Guzzi, Heng Huang, Meng Jiang, Ziynet Nesibe Kesimoglu, Mehmet Koyuturk, Jian Ma, Alexander R. Pico, Nataša Pržulj, Teresa M. Przytycka, Benjamin J. Raphael, Anna Ritz, Roded Sharan, Yang shen, Mona Singh, Donna K. Slonim, Hanghang Tong, Xinan Holly Yang, Byung-Jun Yoon, Haiyuan Yu, Tijana Milenković
As such, it is expected to help shape short- and long-term vision for future computational and algorithmic research in network biology.
1 code implementation • 17 Jul 2023 • Xuan Zhang, Limei Wang, Jacob Helwig, Youzhi Luo, Cong Fu, Yaochen Xie, Meng Liu, Yuchao Lin, Zhao Xu, Keqiang Yan, Keir Adams, Maurice Weiler, Xiner Li, Tianfan Fu, Yucheng Wang, Haiyang Yu, Yuqing Xie, Xiang Fu, Alex Strasser, Shenglong Xu, Yi Liu, Yuanqi Du, Alexandra Saxton, Hongyi Ling, Hannah Lawrence, Hannes Stärk, Shurui Gui, Carl Edwards, Nicholas Gao, Adriana Ladera, Tailin Wu, Elyssa F. Hofgard, Aria Mansouri Tehrani, Rui Wang, Ameya Daigavane, Montgomery Bohde, Jerry Kurtin, Qian Huang, Tuong Phung, Minkai Xu, Chaitanya K. Joshi, Simon V. Mathis, Kamyar Azizzadenesheli, Ada Fang, Alán Aspuru-Guzik, Erik Bekkers, Michael Bronstein, Marinka Zitnik, Anima Anandkumar, Stefano Ermon, Pietro Liò, Rose Yu, Stephan Günnemann, Jure Leskovec, Heng Ji, Jimeng Sun, Regina Barzilay, Tommi Jaakkola, Connor W. Coley, Xiaoning Qian, Xiaofeng Qian, Tess Smidt, Shuiwang Ji
Advances in artificial intelligence (AI) are fueling a new paradigm of discoveries in natural sciences.
Recent developments in geometric deep learning, focusing on the integration and processing of 3D geometric data, coupled with the availability of accurate protein 3D structure predictions from tools like AlphaFold, have greatly advanced the field of structure-based drug design.
Deleted Edge Consistency ensures that the influence of deleted elements is removed from both model weights and neighboring representations, while Neighborhood Influence guarantees that the remaining model knowledge is preserved after deletion.
Additionally, the label distributions of tasks in the source and target domains can differ significantly, posing difficulties in addressing label shifts and recognizing labels unique to the target domain.
Artificial intelligence for graphs has achieved remarkable success in modeling complex systems, ranging from dynamic networks in biology to interacting particle systems in physics.
As post hoc explanations are increasingly used to understand the behavior of graph neural networks (GNNs), it becomes crucial to evaluate the quality and reliability of GNN explanations.
OpenXAI comprises of the following key components: (i) a flexible synthetic data generator and a collection of diverse real-world datasets, pre-trained models, and state-of-the-art feature attribution methods, (ii) open-source implementations of twenty-two quantitative metrics for evaluating faithfulness, stability (robustness), and fairness of explanation methods, and (iii) the first ever public XAI leaderboards to benchmark explanations.
Experiments against eight state-of-the-art methods show that TF-C outperforms baselines by 15. 4% (F1 score) on average in one-to-one settings (e. g., fine-tuning an EEG-pretrained model on EMG data) and by 8. 4% (precision) in challenging one-to-many settings (e. g., fine-tuning an EEG-pretrained model for either hand-gesture recognition or mechanical fault prediction), reflecting the breadth of scenarios that arise in real-world applications.
On a dataset annotated by human experts, REMAP improves text-based disease relation extraction by 10. 0% (accuracy) and 17. 2% (F1-score) by fusing disease knowledge graphs with text information.
As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are stable, e. g., robust to infinitesimal perturbations to an input.
no code implementations • 22 Dec 2021 • Ryan T. Scott, Erik L. Antonsen, Lauren M. Sanders, Jaden J. A. Hastings, Seung-min Park, Graham Mackintosh, Robert J. Reynolds, Adrienne L. Hoarfrost, Aenor Sawyer, Casey S. Greene, Benjamin S. Glicksberg, Corey A. Theriot, Daniel C. Berrios, Jack Miller, Joel Babdor, Richard Barker, Sergio E. Baranzini, Afshin Beheshti, Stuart Chalk, Guillermo M. Delgado-Aparicio, Melissa Haendel, Arif A. Hamid, Philip Heller, Daniel Jamieson, Katelyn J. Jarvis, John Kalantari, Kia Khezeli, Svetlana V. Komarova, Matthieu Komorowski, Prachi Kothiyal, Ashish Mahabal, Uri Manor, Hector Garcia Martin, Christopher E. Mason, Mona Matar, George I. Mias, Jerry G. Myers, Jr., Charlotte Nelson, Jonathan Oribello, Patricia Parsons-Wingerter, R. K. Prabhu, Amina Ann Qutub, Jon Rask, Amanda Saravia-Butler, Suchi Saria, Nitin Kumar Singh, Frank Soboczenski, Michael Snyder, Karthik Soman, David Van Valen, Kasthuri Venkateswaran, Liz Warren, Liz Worthey, Jason H. Yang, Marinka Zitnik, Sylvain V. Costes
Human space exploration beyond low Earth orbit will involve missions of significant distance and duration.
no code implementations • 22 Dec 2021 • Lauren M. Sanders, Jason H. Yang, Ryan T. Scott, Amina Ann Qutub, Hector Garcia Martin, Daniel C. Berrios, Jaden J. A. Hastings, Jon Rask, Graham Mackintosh, Adrienne L. Hoarfrost, Stuart Chalk, John Kalantari, Kia Khezeli, Erik L. Antonsen, Joel Babdor, Richard Barker, Sergio E. Baranzini, Afshin Beheshti, Guillermo M. Delgado-Aparicio, Benjamin S. Glicksberg, Casey S. Greene, Melissa Haendel, Arif A. Hamid, Philip Heller, Daniel Jamieson, Katelyn J. Jarvis, Svetlana V. Komarova, Matthieu Komorowski, Prachi Kothiyal, Ashish Mahabal, Uri Manor, Christopher E. Mason, Mona Matar, George I. Mias, Jack Miller, Jerry G. Myers Jr., Charlotte Nelson, Jonathan Oribello, Seung-min Park, Patricia Parsons-Wingerter, R. K. Prabhu, Robert J. Reynolds, Amanda Saravia-Butler, Suchi Saria, Aenor Sawyer, Nitin Kumar Singh, Frank Soboczenski, Michael Snyder, Karthik Soman, Corey A. Theriot, David Van Valen, Kasthuri Venkateswaran, Liz Warren, Liz Worthey, Marinka Zitnik, Sylvain V. Costes
Space biology research aims to understand fundamental effects of spaceflight on organisms, develop foundational knowledge to support deep space exploration, and ultimately bioengineer spacecraft and habitats to stabilize the ecosystem of plants, crops, microbes, animals, and humans for sustained multi-planetary life.
1 code implementation • 11 Nov 2021 • Joshua Pan, Jason J. Kwon, Jessica A. Talamas, Ashir A. Borah, Francisca Vazquez, Jesse S. Boehm, Aviad Tsherniak, Marinka Zitnik, James M. McFarland, William C. Hahn
In high-throughput functional genomic screens, each gene product is commonly assumed to exhibit a singular biological function within a defined protein complex or pathway.
Here, we introduce RAINDROP, a graph neural network that embeds irregularly sampled and multivariate time series while also learning the dynamics of sensors purely from observational data.
Single cell technologies are rapidly generating large amounts of data that enables us to understand biological systems at single-cell resolution.
As Graph Neural Networks (GNNs) are increasingly being employed in critical real-world applications, several methods have been proposed in recent literature to explain the predictions of these models.
We construct a multi-scale network of the Human Cell Atlas and apply AWARE to learn protein, cell type, and tissue embeddings that uphold cell type and tissue hierarchies.
Biomedical networks (or graphs) are universal descriptors for systems of interacting elements, from molecular interactions and disease co-morbidity to healthcare systems and scientific knowledge.
Based on this review, we introduce a descriptive framework for pre-training that allows for a granular, comprehensive understanding of how relational structure can be induced.
In this work, we establish a key connection between counterfactual fairness and stability and leverage it to propose a novel framework, NIFTY (uNIfying Fairness and stabiliTY), which can be used with any GNN to learn fair and stable representations.
Here, we introduce Therapeutics Data Commons (TDC), the first unifying platform to systematically access and evaluate machine learning across the entire range of therapeutics.
no code implementations • 11 Jan 2021 • Tingyi Wanyan, Hossein Honarvar, Suraj K. Jaladanki, Chengxi Zang, Nidhi Naik, Sulaiman Somani, Jessica K. De Freitas, Ishan Paranjpe, Akhil Vaid, Riccardo Miotto, Girish N. Nadkarni, Marinka Zitnik, ArifulAzad, Fei Wang, Ying Ding, Benjamin S. Glicksberg
This has been a major issue for developing ML models for the coronavirus-disease 2019 (COVID-19) pandemic where data is highly imbalanced, particularly within electronic health records (EHR) research.
The efficacy of a drug depends on its binding affinity to the therapeutic target and pharmacokinetics.
G-Meta learns how to quickly adapt to a new task using only a handful of nodes or edges in the new task and does so by learning from data points in other graphs or related, albeit disjoint label sets.
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.
Ranked #1 on Link Property Prediction on ogbl-citation2
Accurate prediction of drug-target interactions (DTI) is crucial for drug discovery.
Ranked #2 on Drug Discovery on KIBA
2 code implementations • 15 Apr 2020 • Deisy Morselli Gysi, Ítalo Do Valle, Marinka Zitnik, Asher Ameli, Xiao Gan, Onur Varol, Susan Dina Ghiassian, JJ Patten, Robert Davey, Joseph Loscalzo, Albert-László Barabási
The current pandemic has highlighted the need for methodologies that can quickly and reliably prioritize clinically approved compounds for their potential effectiveness for SARS-CoV-2 infections.
There is a need of ensuring machine learning models that are interpretable.
Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training.
Ranked #2 on Drug Discovery on ClinTox
We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures.
In this Review, we describe the principles of data integration and discuss current methods and available implementations.
Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities.
Ranked #6 on Complex Query Answering on FB15k-237
Networks are ubiquitous in biology where they encode connectivity patterns at all scales of organization, from molecular to the biome.
Community detection identifies candidate modules as hypotheses, which then need to be validated through experiments, such as mutagenesis in a biological laboratory.
The approach constructs a multimodal graph of protein-protein interactions, drug-protein target interactions, and the polypharmacy side effects, which are represented as drug-drug interactions, where each side effect is an edge of a different type.
Ranked #1 on Link Prediction on Decagon
Motivation: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases.
However, we show that higher-order network structures, such as small subgraphs of the pathway, provide a promising direction for the development of new methods.
Motivation: The rapid growth of diverse biological data allows us to consider interactions between a variety of objects, such as genes, chemicals, molecular signatures, diseases, pathways and environmental exposures.