Joaquin Polonuer, Lucas Vittor, Iñaki Arango, Ayush Noori, David A. Clifton, Luciano Del Corro, Marinka Zitnik. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Graph Neural Networks (GNNs) have achieved significant success across various applications. However, their complex structures and inner workings can be challenging for non-AI experts to understand. To address this issue, this study presents GNN101, an educational visualization tool for interactive learning of GNNs. GNN101 introduces a set of animated visualizations that seamlessly integrates mathematical formulas with visualizations via multiple levels of abstraction, including a model overview, layer operations, and detailed calculations. Users can easily switch between two complementary views: a node-link view that offers an intuitive understanding of the graph data, and a matrix view that provides a space-efficient and comprehensive overview of all features and their transformations across layers. GNN101 was designed and developed based on close collaboration with four GNN experts and deployment in three GNN-related courses. We demonstrated the usability and effectiveness of GNN101 via use cases and user studies with both GNN teaching assistants and students. To ensure broad educational access, GNN101 is developed through modern web technologies and available directly in web browsers without requiring any installations.

Effective visualization is essential for interpreting genomics data, yet researchers often face challenges in finding relevant, reusable examples. Existing tools offer limited support for searching the vast landscape of genomics visualizations, making the process of authoring new visualizations time-consuming and inefficient. To address this gap, we introduce Geranium, a data visualization retrieval system for searching and authoring genomics visualizations. Geranium supports multimodal retrieval, enabling users to query with images, text, or grammar-based specifications. Retrieved examples serve as scaffolds for authoring, providing templates that researchers can adapt with their own data, thereby streamlining the mechanics of visualization construction. Geranium integrates three embedding methods to combine specialized and general knowledge: grammar-based embeddings tailored to genomics visualizations, multimodal embeddings from a biomedical vision-language foundation model, and text embeddings from a fine-tuned large language model. For each visualization, we construct a multimodal representation that includes a Gosling specification, a pixel-based rendering, and natural language descriptions. We evaluate embedding strategies to maximize top-$k$k retrieval accuracy and conduct user studies with domain collaborators to gather feedback on usability. Our collection comprises 3,200 visualizations across 50 categories, ranging from single-view to coordinated multi-view designs and supporting applications from single-cell epigenomics to structural variation analysis.

Biomedical reasoning integrates structured, codified knowledge with tacit, experience-driven insights. Depending on the context, quantity, and nature of available evidence, researchers and clinicians use diverse strategies, including rule-based, prototype-based, and case-based reasoning. Effective medical AI models must handle this complexity while ensuring reliability and adaptability. We introduce KGARevion, a knowledge graph-based agent that answers knowledge-intensive questions. Upon receiving a query, KGARevion generates relevant triplets by leveraging the latent knowledge embedded in a large language model. It then verifies these triplets against a grounded knowledge graph, filtering out errors and retaining only accurate, contextually relevant information for the final answer. This multi-step process strengthens reasoning, adapts to different models of medical inference, and outperforms retrieval-augmented generation-based approaches that lack effective verification mechanisms. Evaluations on medical QA benchmarks show that KGARevion improves accuracy by over 5.2% over 15 models in handling complex medical queries. To further assess its effectiveness, we curated three new medical QA datasets with varying levels of semantic complexity, where KGARevion improved accuracy by 10.4%. The agent integrates with different LLMs and biomedical knowledge graphs for broad applicability across knowledge-intensive tasks. We evaluated KGARevion on AfriMed-QA, a newly introduced dataset focused on African healthcare, demonstrating its strong zero-shot generalization to underrepresented medical contexts.

Test-time interventions for language models can enhance factual accuracy, mitigate harmful outputs, and improve model efficiency without costly retraining. But despite a flood of new methods, different types of interventions are largely developing independently. In practice, multiple interventions must be applied sequentially to the same model, yet we lack standardized ways to study how interventions interact. We fill this gap by introducing composable interventions, a framework to study the effects of using multiple interventions on the same language models, featuring new metrics and a unified codebase. Using our framework, we conduct extensive experiments and compose popular methods from three emerging intervention categories---knowledge editing, model compression, and machine unlearning. Our results over 417 different compositions uncover meaningful interactions: compression hinders editing and unlearning, composing interventions hinges on their order of application, and popular general-purpose metrics are inadequate for assessing composability. Taken together, our findings showcase clear gaps in composability, suggesting a need for new multi-objective interventions.

Foundation models trained on patient electronic health records (EHRs) require tokenizing medical data into sequences of discrete vocabulary items. Existing tokenizers treat medical codes from EHRs as isolated textual tokens. However, each medical code is defined by its textual description, its position in ontological hierarchies, and its relationships to other codes, such as disease co-occurrences and drug-treatment associations. Medical vocabularies contain more than 600,000 codes with critical information for clinical reasoning. We introduce MedTok, a multimodal medical code tokenizer that uses the text descriptions and relational context of codes. MedTok processes text using a language model encoder and encodes the relational structure with a graph encoder. It then quantizes both modalities into a unified token space, preserving modality-specific and cross-modality information. We integrate MedTok into five EHR models and evaluate it on operational and clinical tasks across in-patient and out-patient datasets, including outcome prediction, diagnosis classification, drug recommendation, and risk stratification. Swapping standard EHR tokenizers with MedTok improves AUPRC across all EHR models, by 4.10% on MIMIC-III, 4.78% on MIMIC-IV, and 11.32% on EHRShot, with the largest gains in drug recommendation. Beyond EHR modeling, we demonstrate using MedTok tokenizer with medical QA systems. Our results demonstrate the potential of MedTok as a unified tokenizer for medical codes, improving tokenization for medical foundation models.

Existing biomedical benchmarks do not provide end-to-end infrastructure for training, evaluation, and inference of models that integrate multimodal biological data and a broad range of machine learning tasks in therapeutics. We present PyTDC, an open-source machine-learning platform providing streamlined training, evaluation, and inference software for multimodal biological AI models. PyTDC unifies distributed, heterogeneous, continuously updated data sources and model weights and standardizes benchmarking and inference endpoints. This paper discusses the components of PyTDC's architecture and, to our knowledge, the first-of-its-kind case study on the introduced single-cell drug-target nomination ML task. We find state-of-the-art methods in graph representation learning and domain-specific methods from graph theory perform poorly on this task. Though we find a context-aware geometric deep learning method that outperforms the evaluated SoTA and domain-specific baseline methods, the model is unable to generalize to unseen cell types or incorporate additional modalities, highlighting PyTDC's capacity to facilitate an exciting avenue of research developing multimodal, context-aware, foundation models for open problems in biomedical AI.

Protein language models (PLMs) are often assumed to capture evolutionary information by training on large protein sequence datasets. Yet it remains unclear whether PLMs can reason about evolution—that is, infer evolutionary relationships between sequences. We test this capability by evaluating whether standard PLM usage, frozen or fine-tuned embeddings with distance-based comparison, supports evolutionary reasoning. Existing PLMs consistently fail to recover phylogenetic structure, despite strong performance on sequence-level tasks such as masked-token and contact prediction. We present Phyla, a hybrid state-space and transformer model that jointly processes multiple sequences and is trained using a tree-based objective across 3,000 phylogenies spanning diverse protein families. Phyla outperforms the next-best PLM by 9\% on tree reconstruction and 23\% on taxonomic clustering while remaining alignment- and guide-tree-free. Although classical alignment pipelines achieve higher absolute accuracy, Phyla narrows the gap and achieves markedly lower end-to-end runtime. Applied to real data, Phyla reconstructs biologically accurate clades in the tree of life and resolves genome-scale relationships among Mycobacterium tuberculosis isolates. These findings suggest that, under standard usage, evolutionary reasoning does not reliably emerge from large-scale sequence modeling. Instead, Phyla shows that models trained with phylogenetic supervision can reason about evolution more effectively, offering a biologically grounded path toward evolutionary foundation models.

Biomedical research data portals are essential resources for scientific inquiry, and interactive exploratory visualizations are an integral component for querying such data repositories. Increasingly, machine learning is being integrated into visualization systems to create natural language interfaces where questions about data can be answered with visualizations, and follow-up questions can build on the previous state. This paper introduces a framework that takes abstract low-level questions about data and a visualization grammar specification that can answer such a question, reifies them with data entities and fields that meet certain constraints, and paraphrases the question language to produce the final collection of realized data-question-visualization triplets. Furthermore, we can link these foundational elements together to construct chains of queries, visualizations, and follow-up queries. We developed an open-source review interface for evaluating the results of these datasets. We applied this framework to five biomedical research data repositories, resulting in DQVis, a dataset of 1.08 million data-question-visualization triplets and 11.4 thousand two-step question samples. Five visualization experts provided feedback on the generated dataset through our review interface. We present a summary of their input and publish the full reviews as an additional resource alongside the dataset.The DQVis dataset and generation code are available at https://huggingface.co/datasets/HIDIVE/DQVis and https://github.com/hms-dbmi/DQVis-Generation.

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game-a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern multimodal LLMs and benefits from a rich repository of high-quality, human-annotated creative responses, making it an ideal platform for studying LLM creativity. Next, beyond using the Oogiri game for standard evaluations like ranking and selection, we propose LoTbench, an interactive, causality-aware evaluation framework, to further address some intrinsic risks in standard evaluations, such as information leakage and limited interpretability. The proposed LoTbench not only quantifies LLM creativity more effectively but also visualizes the underlying creative thought processes. Our results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable. Furthermore, we observe a strong correlation between results from the multimodal cognition benchmark MMMU and LoTbench, but only a weak connection with traditional creativity metrics. This suggests that LoTbench better aligns with human cognitive theories, highlighting cognition as a critical foundation in the early stages of creativity and enabling the bridging of diverse concepts. Project Page.

Chain-of-Thought (CoT) [2], [3] guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logi-cal tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs - a non-sequential, creative paradigm involving strong associations and knowledge leaps. 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. Then to investi-gate LLMs' LoT ability in the Oogiri game, we first build a multimodal and multilingual Oogiri-GO dataset which contains over 130,000 samples from the Oogiri game, and observe the insufficient LoT ability or failures of most existing LLMs on the Oogiri game. Accordingly, we introduce a creative Leap-of-Thought (CLoT) paradigm to improve LLM's LoT ability. CLoT first formulates the Oogiri-GO dataset into LoT-oriented instruction tuning data to train pre-trained LLM for achieving certain LoT humor generation and discrimination abilities. Then CLoT designs an ex-plorative self-refinement that encourages the LLM to gener-ate more creative LoT data via exploring parallels between seemingly unrelated concepts and selects high-quality data to train itself for self-refinement. CLoT not only excels in humor generation in the Oogiri game as shown in Fig. 1 but also boosts creative abilities in various tasks like “cloud guessing game” and “divergent association task”. These findings advance our understanding and offer a pathway to improve LLMs' creative capacities for innovative applications across domains. The dataset, code, and models have been released online: https://zhongshsh.github.io/CLoT.

Large language models (LLMs) have gained considerable attention for their excellent natural language processing capabilities. Nonetheless, these LLMs present many challenges, particularly in the realm of trustworthiness. This paper introduces TrustLLM, a comprehensive study of trustworthiness in LLMs, including principles for different dimensions of trustworthiness, established benchmark, evaluation, and analysis of trustworthiness for mainstream LLMs, and discussion of open challenges and future directions. Specifically, we first propose a set of principles for trustworthy LLMs that span eight different dimensions. Based on these principles, we further establish a benchmark across six dimensions including truthfulness, safety, fairness, robustness, privacy, and machine ethics. We then present a study evaluating 16 mainstream LLMs in TrustLLM, consisting of over 30 datasets. Our findings firstly show that in general trustworthiness and capability (i.e., functional effectiveness) are positively related. Secondly, our observations reveal that proprietary LLMs generally outperform most open-source counterparts in terms of trustworthiness, raising concerns about the potential risks of widely accessible open-source LLMs. However, a few open-source LLMs come very close to proprietary ones, suggesting that open-source models can achieve high levels of trustworthiness without additional mechanisms like moderator, offering valuable insights for developers in this field. Thirdly, it is important to note that some LLMs may be overly calibrated towards exhibiting trustworthiness, to the extent that they compromise their utility by mistakenly treating benign prompts as harmful and consequently not responding. Besides these observations, we’ve uncovered key insights into the multifaceted trustworthiness in LLMs. We emphasize the importance of ensuring transparency not only in the models themselves but also in the technologies that underpin trustworthiness. We advocate that the establishment of an AI alliance between industry, academia, the open-source community to foster collaboration is imperative to advance the trustworthiness of LLMs.

This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing perturbations to the graph structure based on Laplacian distance and then minimize the overall loss of the GSD. By solving the min-max optimization problem, we derive a new variant of the Graph Diffusion Convolution (GDC) architecture, called Graph Adversarial Diffusion Convolution (GADC). GADC differs from GDC by incorporating an additional term that enhances robustness against adversarial attacks on the graph structure and noise in node features. Moreover, GADC improves the performance of GDC on heterophilic graphs. Extensive experiments demonstrate the effectiveness of GADC across various datasets. Code is available at https://github.com/SongtaoLiu0823/GADC.

Although pre-trained transformers and reprogrammed text-based LLMs have shown strong performance on time series tasks, the best-performing architectures vary widely across tasks, with most models narrowly focused on specific areas, such as time series forecasting. Unifying predictive and generative time series tasks within a single model remains challenging. We introduce UniTS, a unified multi-task time series model that utilizes task tokenization to integrate predictive and generative tasks into a single framework. UniTS employs a modified transformer block to capture universal time series representations, enabling transferability from a heterogeneous, multi-domain pre-training dataset—characterized by diverse dynamic patterns, sampling rates, and temporal scales—to a wide range of downstream datasets with varied task specifications and data domains. Tested on 38 datasets across human activity sensors, healthcare, engineering, and finance, UniTS achieves superior performance compared to 12 forecasting models, 20 classification models, 18 anomaly detection models, and 16 imputation models, including adapted text-based LLMs. UniTS also demonstrates strong few-shot and prompt capabilities when applied to new domains and tasks. In single-task settings, UniTS outperforms competitive task-specialized time series models. Code and datasets are available at https://github.com/mims-harvard/UniTS.

We consider the problem of crystal materials generation using language models (LMs). A key step is to convert 3D crystal structures into 1D sequences to be processed by LMs. Prior studies used the crystallographic information framework (CIF) file stream, which fails to ensure SE(3) and periodic invariance and may not lead to unique sequence representations for a given crystal structure. Here, we propose a novel method, known as Mat2Seq, to tackle this challenge. Mat2Seq converts 3D crystal structures into 1D sequences and ensures that different mathematical descriptions of the same crystal are represented in a single unique sequence, thereby provably achieving SE(3) and periodic invariance. Experimental results show that, with language models, Mat2Seq achieves promising performance in crystal structure generation as compared with prior methods.

Designing ligand-binding proteins, such as enzymes and biosensors, is essential in bioengineering and protein biology. One critical step in this process involves designing protein pockets, the protein interface binding with the ligand. Current approaches to pocket generation often suffer from time-intensive physical computations or template-based methods, as well as compromised generation quality due to the overlooking of domain knowledge. To tackle these challenges, we propose PocketFlow, a generative model that incorporates protein-ligand interaction priors based on flow matching. During training, PocketFlow learns to model key types of protein-ligand interactions, such as hydrogen bonds. In the sampling, PocketFlow leverages multi-granularity guidance (overall binding affinity and interaction geometry constraints) to facilitate generating high-affinity and valid pockets. Extensive experiments show that PocketFlow outperforms baselines on multiple benchmarks, e.g., achieving an average improvement of 1.29 in Vina Score and 0.05 in scRMSD. Moreover, modeling interactions make PocketFlow a generalized generative model across multiple ligand modalities, including small molecules, peptides, and RNA.

Unsupervised domain adaptation (UDA) enables the transfer of models trained on source domains to unlabeled target domains. However, transferring complex time series models presents challenges due to the dynamic temporal structure variations across domains. This leads to feature shifts in the time and frequency representations. 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. Effectively transferring complex time series models remains a formidable problem. We present RAINCOAT, the first model for both closed-set and universal domain adaptation on complex time series. RAINCOAT addresses feature and label shifts by considering both temporal and frequency features, aligning them across domains, and correcting for misalignments to facilitate the detection of private labels. Additionally, RAINCOAT improves transferability by identifying label shifts in target domains. Our experiments with 5 datasets and 13 state-of-the-art UDA methods demonstrate that RAINCOAT can improve transfer learning performance by up to 16.33% and can handle both closed-set and universal domain adaptation.

Recent years have witnessed a surge of research interest in graph machine learning. However, the benchmark datasets available to the field are rather limited in both quantity and diversity, an issue particularly notable given the immense potential applications of graph learning. The lack of diverse benchmark datasets may have biased the development of graph machine learning techniques towards narrow directions. By crowdsourcing novel tasks and datasets, this workshop aims to increase the diversity of graph learning benchmarks, identify new demands of graph machine learning in general, and gain a better synergy of how concrete techniques perform on these benchmarks. Moreover, this workshop offers a platform for discussions of best practices in curating graph learning benchmarks and data-centric approaches for graph learning.

Interpreting time series models is uniquely challenging because it requires identifying both the location of time series signals that drive model predictions and their matching to an interpretable temporal pattern. While explainers from other modalities can be applied to time series, their inductive biases do not transfer well to the inherently challenging interpretation of time series. We present TimeX, a time series consistency model for training explainers. TimeX trains an interpretable surrogate to mimic the behavior of a pretrained time series model. It addresses the issue of model faithfulness by introducing model behavior consistency, a novel formulation that preserves relations in the latent space induced by the pretrained model with relations in the latent space induced by TimeX. TimeX provides discrete attribution maps and, unlike existing interpretability methods, it learns a latent space of explanations that can be used in various ways, such as to provide landmarks to visually aggregate similar explanations and easily recognize temporal patterns. We evaluate TimeX on eight synthetic and real-world datasets and compare its performance against state-of-the-art interpretability methods. We also conduct case studies using physiological time series. Quantitative evaluations demonstrate that TimeX achieves the highest or second-highest performance in every metric compared to baselines across all datasets. Through case studies, we show that the novel components of TimeX show potential for training faithful, interpretable models that capture the behavior of pretrained time series models.

The design of \emph{de novo} functional proteins that bind with specific ligand molecules is crucial in various domains like therapeutics and bio-engineering. One vital yet challenging step is to design the protein pocket, the cavity region of protein where the ligand binds with. Existing methods suffer from inefficient generation, insufficient context modeling (ligand molecule), and incapability of generating sidechain atoms. To overcome the limitations, we propose a \textbf{F}ull-\textbf{A}tom \textbf{I}terative \textbf{R}efinement framework (\textbf{FAIR}) for protein pocket sequence (i.e., residue types) and 3D structure co-design. Generally, FAIR consists of two steps that follow a coarse-to-fine pipeline (backbone atoms to full atoms including sidechain) for full-atom generation. For efficiency, all residue types and structures are updated together in each round (i.e., full-shot refinement). In the first step, the residue types and backbone coordinates are updated with a hierarchical context encoder and two structure refinement modules capturing inter-residue and pocket-ligand interactions. The second step further models the sidechain atoms of pockets and updates residue types to achieve sequence-structure consistency. The structure of the binding ligand is also updated along with the above refinement iterations accounting for its flexibility. Finally, extensive evaluations show that FAIR outperforms baselines in efficiently designing high-quality pocket sequences and structures. Specifically, the average improvements on AAR and RMSD are over 10$\%$.

SUMMARY: Heterogeneous knowledge graphs (KGs) have enabled the modeling of complex systems, from genetic interaction graphs and protein-protein interaction networks to networks representing drugs, diseases, proteins, and side effects. Analytical methods for KGs rely on quantifying similarities between entities, such as nodes, in the graph. However, such methods must consider the diversity of node and edge types contained within the KG via, for example, defined sequences of entity types known as meta-paths. We present metapaths, the first R software package to implement meta-paths and perform meta-path-based similarity search in heterogeneous KGs. The metapaths package offers various built-in similarity metrics for node pair comparison by querying KGs represented as either edge or adjacency lists, as well as auxiliary aggregation methods to measure set-level relationships. Indeed, evaluation of these methods on an open-source biomedical KG recovered meaningful drug and disease-associated relationships, including those in Alzheimer's disease. The metapaths framework facilitates the scalable and flexible modeling of network similarities in KGs with applications across KG learning. AVAILABILITY AND IMPLEMENTATION: The metapaths R package is available via GitHub at https://github.com/ayushnoori/metapaths and is released under MPL 2.0 (Zenodo DOI: 10.5281/zenodo.7047209). Package documentation and usage examples are available at https://www.ayushnoori.com/metapaths.

MOTIVATION: Predicting molecule-disease indications and side effects is important for drug development and pharmacovigilance. Comprehensively mining molecule-molecule, molecule-disease and disease-disease semantic dependencies can potentially improve prediction performance. METHODS: We introduce a Multi-Modal REpresentation Mapping Approach to Predicting molecular-disease relations (M2REMAP) by incorporating clinical semantics learned from electronic health records (EHR) of 12.6 million patients. Specifically, M2REMAP first learns a multimodal molecule representation that synthesizes chemical property and clinical semantic information by mapping molecule chemicals via a deep neural network onto the clinical semantic embedding space shared by drugs, diseases and other common clinical concepts. To infer molecule-disease relations, M2REMAP combines multimodal molecule representation and disease semantic embedding to jointly infer indications and side effects. RESULTS: We extensively evaluate M2REMAP on molecule indications, side effects and interactions. Results show that incorporating EHR embeddings improves performance significantly, for example, attaining an improvement over the baseline models by 23.6% in PRC-AUC on indications and 23.9% on side effects. Further, M2REMAP overcomes the limitation of existing methods and effectively predicts drugs for novel diseases and emerging pathogens. AVAILABILITY AND IMPLEMENTATION: The code is available at https://github.com/celehs/M2REMAP, and prediction results are provided at https://shiny.parse-health.org/drugs-diseases-dev/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Disease knowledge graphs have emerged as a powerful tool for artificial intelligence to connect, organize, and access diverse information about diseases. Relations between disease concepts are often distributed across multiple datasets, including unstructured plain text datasets and incomplete disease knowledge graphs. Extracting disease relations from multimodal data sources is thus crucial for constructing accurate and comprehensive disease knowledge graphs. We introduce REMAP, a multimodal approach for disease relation extraction. The REMAP machine learning approach jointly embeds a partial, incomplete knowledge graph and a medical language dataset into a compact latent vector space, aligning the multimodal embeddings for optimal disease relation extraction. Additionally, REMAP utilizes a decoupled model structure to enable inference in single-modal data, which can be applied under missing modality scenarios. We apply the REMAP approach to a disease knowledge graph with 96,913 relations and a text dataset of 1.24 million sentences. On a dataset annotated by human experts, REMAP improves language-based disease relation extraction by 10.0% (accuracy) and 17.2% (F1-score) by fusing disease knowledge graphs with language information. Furthermore, REMAP leverages text information to recommend new relationships in the knowledge graph, outperforming graph-based methods by 8.4% (accuracy) and 10.4% (F1-score). REMAP is a flexible multimodal approach for extracting disease relations by fusing structured knowledge and language information. This approach provides a powerful model to easily find, access, and evaluate relations between disease concepts.

Whether AI explanations can help users achieve specific tasks efficiently (i.e., usable explanations) is significantly influenced by their visual presentation. While many techniques exist to generate explanations, it remains unclear how to select and visually present AI explanations based on the characteristics of domain users. This paper aims to understand this question through a multidisciplinary design study for a specific problem: explaining graph neural network (GNN) predictions to domain experts in drug repurposing, i.e., reuse of existing drugs for new diseases. Building on the nested design model of visualization, we incorporate XAI design considerations from a literature review and from our collaborators' feedback into the design process. Specifically, we discuss XAI-related design considerations for usable visual explanations at each design layer: target user, usage context, domain explanation, and XAI goal at the domain layer; format, granularity, and operation of explanations at the abstraction layer; encodings and interactions at the visualization layer; and XAI and rendering algorithm at the algorithm layer. We present how the extended nested model motivates and informs the design of DrugExplorer, an XAI tool for drug repurposing. Based on our domain characterization, DrugExplorer provides path-based explanations and presents them both as individual paths and meta-paths for two key XAI operations, why and what else. DrugExplorer offers a novel visualization design called MetaMatrix with a set of interactions to help domain users organize and compare explanation paths at different levels of granularity to generate domain-meaningful insights. We demonstrate the effectiveness of the selected visual presentation and DrugExplorer as a whole via a usage scenario, a user study, and expert interviews. From these evaluations, we derive insightful observations and reflections that can inform the design of XAI visualizations for other scientific applications.

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. However, there has been little to no work on systematically analyzing the reliability of these methods. Here, we introduce the first-ever theoretical analysis of the reliability of state-of-the-art GNN explanation methods. More specifically, we theoretically analyze the behavior of various state-of-the-art GNN explanation methods with respect to several desirable properties (e.g., faithfulness, stability, and fairness preservation) and establish upper bounds on the violation of these properties. We also empirically validate our theoretical results using extensive experimentation with nine real-world graph datasets. Our empirical results further shed light on several interesting insights about the behavior of state-of-the-art GNN explanation methods.

While several types of post hoc explanation methods have been proposed in recent literature, there is very little work on systematically benchmarking these methods. Here, we introduce OpenXAI, a comprehensive and extensible open-source framework for evaluating and benchmarking post hoc explanation methods. 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 readily compare several explanation methods across a wide variety of metrics, models, and datasets. OpenXAI is easily extensible, as users can readily evaluate custom explanation methods and incorporate them into our leaderboards. Overall, OpenXAI provides an automated end-to-end pipeline that not only simplifies and standardizes the evaluation of post hoc explanation methods, but also promotes transparency and reproducibility in benchmarking these methods. While the first release of OpenXAI supports only tabular datasets, the explanation methods and metrics that we consider are general enough to be applicable to other data modalities. OpenXAI datasets and data loaders, implementations of state-of-the-art explanation methods and evaluation metrics, as well as leaderboards are publicly available at https://open-xai.github.io/. OpenXAI will be regularly updated to incorporate text and image datasets, other new metrics and explanation methods, and welcomes inputs from the community.

Pre-training on time series poses a unique challenge due to the potential mismatch between pre-training and target domains, such as shifts in temporal dynamics, fast-evolving trends, and long-range and short-cyclic effects, which can lead to poor downstream performance. While domain adaptation methods can mitigate these shifts, most methods need examples directly from the target domain, making them suboptimal for pre-training. To address this challenge, methods need to accommodate target domains with different temporal dynamics and be capable of doing so without seeing any target examples during pre-training. Relative to other modalities, in time series, we expect that time-based and frequency-based representations of the same example are located close together in the time-frequency space. To this end, we posit that time-frequency consistency (TF-C) --- embedding a time-based neighborhood of an example close to its frequency-based neighborhood --- is desirable for pre-training. Motivated by TF-C, we define a decomposable pre-training model, where the self-supervised signal is provided by the distance between time and frequency components, each individually trained by contrastive estimation. We evaluate the new method on eight datasets, including electrodiagnostic testing, human activity recognition, mechanical fault detection, and physical status monitoring. 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. The source code and datasets are available at https://github.com/mims-harvard/TFC-pretraining.

The rapid increase of interest in, and use of, artificial intelligence (AI) in computer applications has raised a parallel concern about its ability (or lack thereof) to provide understandable, or explainable, output to users. This concern is especially legitimate in biomedical contexts, where patient safety is of paramount importance. This position paper brings together seven researchers working in the field with different roles and perspectives, to explore in depth the concept of explainable AI, or XAI, offering a functional definition and conceptual framework or model that can be used when considering XAI. This is followed by a series of desiderata for attaining explainability in AI, each of which touches upon a key domain in biomedicine.

As the representations output by Graph Neural Networks (GNNs) are increasingly employed in real-world applications, it becomes important to ensure that these representations are fair and stable. 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. We introduce a novel objective function that simultaneously accounts for fairness and stability and develop a layer-wise weight normalization using the Lipschitz constant to enhance neural message passing in GNNs. In doing so, we enforce fairness and stability both in the objective function as well as in the GNN architecture. Further, we show theoretically that our layer-wise weight normalization promotes counterfactual fairness and stability in the resulting representations. We introduce three new graph datasets comprising of high-stakes decisions in criminal justice and financial lending domains. Extensive experimentation with the above datasets demonstrates the efficacy of our framework.

SUMMARY: Accurate prediction of drug-target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use DL library for DTI prediction. DeepPurpose supports training of customized DTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. We demonstrate state-of-the-art performance of DeepPurpose on several benchmark datasets. AVAILABILITY AND IMPLEMENTATION: https://github.com/kexinhuang12345/DeepPurpose. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Deep learning methods for graphs achieve remarkable performance on many node-level and graph-level prediction tasks. However, despite the proliferation of the methods and their success, prevailing Graph Neural Networks (GNNs) neglect subgraphs, rendering subgraph prediction tasks challenging to tackle in many impactful applications. Further, subgraph prediction tasks present several unique challenges: subgraphs can have non-trivial internal topology, but also carry a notion of position and external connectivity information relative to the underlying graph in which they exist. Here, we introduce SubGNN, a subgraph neural network to learn disentangled subgraph representations. We propose a novel subgraph routing mechanism that propagates neural messages between the subgraph’s components and randomly sampled anchor patches from the underlying graph, yielding highly accurate subgraph representations. SubGNN specifies three channels, each designed to capture a distinct aspect of subgraph topology, and we provide empirical evidence that the channels encode their intended properties. We design a series of new synthetic and real-world subgraph datasets. Empirical results for subgraph classification on eight datasets show that SubGNN achieves considerable performance gains, outperforming strong baseline methods, including node-level and graph-level GNNs, by 19.8% over the strongest baseline. SubGNN performs exceptionally well on challenging biomedical datasets, where subgraphs have complex topology and even comprise multiple disconnected components.

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 datasets are large-scale, encompass multiple important graph ML tasks, and cover a diverse range of domains, ranging from social and information networks to biological networks, molecular graphs, source code ASTs, and knowledge graphs. For each dataset, we provide a unified evaluation protocol using meaningful application-specific data splits and evaluation metrics. In addition to building the datasets, we also perform extensive benchmark experiments for each dataset. Our experiments suggest that OGB datasets present significant challenges of scalability to large-scale graphs and out-of-distribution generalization under realistic data splits, indicating fruitful opportunities for future research. Finally, OGB provides an automated end-to-end graph ML pipeline that simplifies and standardizes the process of graph data loading, experimental setup, and model evaluation. OGB will be regularly updated and welcomes inputs from the community. OGB datasets as well as data loaders, evaluation scripts, baseline code, and leaderboards are publicly available at https://ogb.stanford.edu .

Prevailing methods for graphs require abundant label and edge information for learning. When data for a new task are scarce, meta-learning can learn from prior experiences and form much-needed inductive biases for fast adaption to new tasks. Here, we introduce G-Meta, a novel meta-learning algorithm for graphs. G-Meta uses local subgraphs to transfer subgraph-specific information and learn transferable knowledge faster via meta gradients. 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. G-Meta is theoretically justified as we show that the evidence for a prediction can be found in the local subgraph surrounding the target node or edge. Experiments on seven datasets and nine baseline methods show that G-Meta outperforms existing methods by up to 16.3%. Unlike previous methods, G-Meta successfully learns in challenging, few-shot learning settings that require generalization to completely new graphs and never-before-seen labels. Finally, G-Meta scales to large graphs, which we demonstrate on a new Tree-of-Life dataset comprising of 1,840 graphs, a two-orders of magnitude increase in the number of graphs used in prior work.

Deep learning methods for graphs achieve remarkable performance on many tasks. However, despite the proliferation of such methods and their success, recent findings indicate that small, unnoticeable perturbations of graph structure can catastrophically reduce performance of even the strongest and most popular Graph Neural Networks (GNNs). Here, we develop GNNGuard, a general defense approach against a variety of training-time attacks that perturb the discrete graph structure. GNNGuard can be straightforwardly incorporated into any GNN. Its core principle is to detect and quantify the relationship between the graph structure and node features, if one exists, and then exploit that relationship to mitigate the negative effects of the attack. GNNGuard learns how to best assign higher weights to edges connecting similar nodes while pruning edges between unrelated nodes. The revised edges then allow the underlying GNN to robustly propagate neural messages in the graph. GNNGuard introduces two novel components, the neighbor importance estimation, and the layer-wise graph memory, and we show empirically that both components are necessary for a successful defense. Across five GNNs, three defense methods, and four datasets, including a challenging human disease graph, experiments show that GNNGuard outperforms existing defense approaches by 15.3% on average. Remarkably, GNNGuard can effectively restore state-of-the-art performance of GNNs in the face of various adversarial attacks, including targeted and non-targeted attacks, and can defend against attacks on heterophily graphs.

Graph Neural Networks (GNNs) are a powerful tool for machine learning on graphs.GNNs combine node feature information with the graph structure by recursively passing neural messages along edges of the input graph. However, incorporating both graph structure and feature information leads to complex models, and explaining predictions made by GNNs remains unsolved. Here we propose GNNExplainer, the first general, model-agnostic approach for providing interpretable explanations for predictions of any GNN-based model on any graph-based machine learning task. Given an instance, GNNExplainer identifies a compact subgraph structure and a small subset of node features that have a crucial role in GNN's prediction. Further, GNNExplainer can generate consistent and concise explanations for an entire class of instances. We formulate GNNExplainer as an optimization task that maximizes the mutual information between a GNN's prediction and distribution of possible subgraph structures. Experiments on synthetic and real-world graphs show that our approach can identify important graph structures as well as node features, and outperforms baselines by 17.1% on average. GNNExplainer provides a variety of benefits, from the ability to visualize semantically relevant structures to interpretability, to giving insights into errors of faulty GNNs.

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. Although recent studies explored using neural network models for BioNER to free experts from manual feature engineering, the performance remains limited by the available training data for each entity type. RESULTS: We propose a multi-task learning framework for BioNER to collectively use the training data of different types of entities and improve the performance on each of them. In experiments on 15 benchmark BioNER datasets, our multi-task model achieves substantially better performance compared with state-of-the-art BioNER systems and baseline neural sequence labeling models. Further analysis shows that the large performance gains come from sharing character- and word-level information among relevant biomedical entities across differently labeled corpora. AVAILABILITY AND IMPLEMENTATION: Our source code is available at https://github.com/yuzhimanhua/lm-lstm-crf. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Nodes residing in different parts of a graph can have similar structural roles within their local network topology. The identification of such roles provides key insight into the organization of networks and can be used for a variety of machine learning tasks. However, learning structural representations of nodes is a challenging problem, and it has typically involved manually specifying and tailoring topological features for each node. In this paper, we develop GraphWave, a method that represents each node's network neighborhood via a low-dimensional embedding by leveraging heat wavelet diffusion patterns. Instead of training on hand-selected features, GraphWave learns these embeddings in an unsupervised way. We mathematically prove that nodes with similar network neighborhoods will have similar GraphWave embeddings even though these nodes may reside in very different parts of the network, and our method scales linearly with the number of edges. Experiments in a variety of different settings demonstrate GraphWave's real-world potential for capturing structural roles in networks, and our approach outperforms existing state-of-the-art baselines in every experiment, by as much as 137%.

Learning low-dimensional embeddings of knowledge graphs is a powerful approach used to predict unobserved or missing edges between entities. However, an open challenge in this area is developing techniques that can go beyond simple edge prediction and handle more complex logical queries, which might involve multiple unobserved edges, entities, and variables. For instance, given an incomplete biological knowledge graph, we might want to predict "em what drugs are likely to target proteins involved with both diseases X and Y?" -- a query that requires reasoning about all possible proteins that might interact with diseases X and Y. Here we introduce a framework to efficiently make predictions about conjunctive logical queries -- a flexible but tractable subset of first-order logic -- on incomplete knowledge graphs. In our approach, we embed graph nodes in a low-dimensional space and represent logical operators as learned geometric operations (e.g., translation, rotation) in this embedding space. By performing logical operations within a low-dimensional embedding space, our approach achieves a time complexity that is linear in the number of query variables, compared to the exponential complexity required by a naive enumeration-based approach. We demonstrate the utility of this framework in two application studies on real-world datasets with millions of relations: predicting logical relationships in a network of drug-gene-disease interactions and in a graph-based representation of social interactions derived from a popular web forum.

Motivation: The use of drug combinations, termed polypharmacy, is common to treat patients with complex diseases or co-existing conditions. However, a major consequence of polypharmacy is a much higher risk of adverse side effects for the patient. Polypharmacy side effects emerge because of drug-drug interactions, in which activity of one drug may change, favorably or unfavorably, if taken with another drug. The knowledge of drug interactions is often limited because these complex relationships are rare, and are usually not observed in relatively small clinical testing. Discovering polypharmacy side effects thus remains an important challenge with significant implications for patient mortality and morbidity. Results: Here, we present Decagon, an approach for modeling polypharmacy side effects. 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. Decagon is developed specifically to handle such multimodal graphs with a large number of edge types. Our approach develops a new graph convolutional neural network for multirelational link prediction in multimodal networks. Unlike approaches limited to predicting simple drug-drug interaction values, Decagon can predict the exact side effect, if any, through which a given drug combination manifests clinically. Decagon accurately predicts polypharmacy side effects, outperforming baselines by up to 69%. We find that it automatically learns representations of side effects indicative of co-occurrence of polypharmacy in patients. Furthermore, Decagon models particularly well polypharmacy side effects that have a strong molecular basis, while on predominantly non-molecular side effects, it achieves good performance because of effective sharing of model parameters across edge types. Decagon opens up opportunities to use large pharmacogenomic and patient population data to flag and prioritize polypharmacy side effects for follow-up analysis via formal pharmacological studies. Availability and implementation: Source code and preprocessed datasets are at: http://snap.stanford.edu/decagon.

MOTIVATION: Understanding functions of proteins in specific human tissues is essential for insights into disease diagnostics and therapeutics, yet prediction of tissue-specific cellular function remains a critical challenge for biomedicine. RESULTS: Here, we present OhmNet , a hierarchy-aware unsupervised node feature learning approach for multi-layer networks. We build a multi-layer network, where each layer represents molecular interactions in a different human tissue. OhmNet then automatically learns a mapping of proteins, represented as nodes, to a neural embedding-based low-dimensional space of features. OhmNet encourages sharing of similar features among proteins with similar network neighborhoods and among proteins activated in similar tissues. The algorithm generalizes prior work, which generally ignores relationships between tissues, by modeling tissue organization with a rich multiscale tissue hierarchy. We use OhmNet to study multicellular function in a multi-layer protein interaction network of 107 human tissues. In 48 tissues with known tissue-specific cellular functions, OhmNet provides more accurate predictions of cellular function than alternative approaches, and also generates more accurate hypotheses about tissue-specific protein actions. We show that taking into account the tissue hierarchy leads to improved predictive power. Remarkably, we also demonstrate that it is possible to leverage the tissue hierarchy in order to effectively transfer cellular functions to a functionally uncharacterized tissue. Overall, OhmNet moves from flat networks to multiscale models able to predict a range of phenotypes spanning cellular subsystems. AVAILABILITY AND IMPLEMENTATION: Source code and datasets are available at http://snap.stanford.edu/ohmnet . CONTACT: [email protected].

MOTIVATION: RNA binding proteins (RBPs) play important roles in post-transcriptional control of gene expression, including splicing, transport, polyadenylation and RNA stability. To model protein-RNA interactions by considering all available sources of information, it is necessary to integrate the rapidly growing RBP experimental data with the latest genome annotation, gene function, RNA sequence and structure. Such integration is possible by matrix factorization, where current approaches have an undesired tendency to identify only a small number of the strongest patterns with overlapping features. Because protein-RNA interactions are orchestrated by multiple factors, methods that identify discriminative patterns of varying strengths are needed. RESULTS: We have developed an integrative orthogonality-regularized nonnegative matrix factorization (iONMF) to integrate multiple data sources and discover non-overlapping, class-specific RNA binding patterns of varying strengths. The orthogonality constraint halves the effective size of the factor model and outperforms other NMF models in predicting RBP interaction sites on RNA. We have integrated the largest data compendium to date, which includes 31 CLIP experiments on 19 RBPs involved in splicing (such as hnRNPs, U2AF2, ELAVL1, TDP-43 and FUS) and processing of 3'UTR (Ago, IGF2BP). We show that the integration of multiple data sources improves the predictive accuracy of retrieval of RNA binding sites. In our study the key predictive factors of protein-RNA interactions were the position of RNA structure and sequence motifs, RBP co-binding and gene region type. We report on a number of protein-specific patterns, many of which are consistent with experimentally determined properties of RBPs. AVAILABILITY AND IMPLEMENTATION: The iONMF implementation and example datasets are available at https://github.com/mstrazar/ionmf CONTACT: : [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

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. Often, any pair of objects-such as a gene and a disease-can be related in different ways, for example, directly via gene-disease associations or indirectly via functional annotations, chemicals and pathways. Different ways of relating these objects carry different semantic meanings However, traditional methods disregard these semantics and thus cannot fully exploit their value in data modeling. RESULTS: We present Medusa, an approach to detect size-k modules of objects that, taken together, appear most significant to another set of objects. Medusa operates on large-scale collections of heterogeneous datasets and explicitly distinguishes between diverse data semantics. It advances research along two dimensions: it builds on collective matrix factorization to derive different semantics, and it formulates the growing of the modules as a submodular optimization program. Medusa is flexible in choosing or combining semantic meanings and provides theoretical guarantees about detection quality. In a systematic study on 310 complex diseases, we show the effectiveness of Medusa in associating genes with diseases and detecting disease modules. We demonstrate that in predicting gene-disease associations Medusa compares favorably to methods that ignore diverse semantic meanings. We find that the utility of different semantics depends on disease categories and that, overall, Medusa recovers disease modules more accurately when combining different semantics. AVAILABILITY AND IMPLEMENTATION: Source code is at http://github.com/marinkaz/medusa CONTACT: [email protected], [email protected].

MOTIVATION: Markov networks are undirected graphical models that are widely used to infer relations between genes from experimental data. Their state-of-the-art inference procedures assume the data arise from a Gaussian distribution. High-throughput omics data, such as that from next generation sequencing, often violates this assumption. Furthermore, when collected data arise from multiple related but otherwise nonidentical distributions, their underlying networks are likely to have common features. New principled statistical approaches are needed that can deal with different data distributions and jointly consider collections of datasets. RESULTS: We present FuseNet, a Markov network formulation that infers networks from a collection of nonidentically distributed datasets. Our approach is computationally efficient and general: given any number of distributions from an exponential family, FuseNet represents model parameters through shared latent factors that define neighborhoods of network nodes. In a simulation study, we demonstrate good predictive performance of FuseNet in comparison to several popular graphical models. We show its effectiveness in an application to breast cancer RNA-sequencing and somatic mutation data, a novel application of graphical models. Fusion of datasets offers substantial gains relative to inference of separate networks for each dataset. Our results demonstrate that network inference methods for non-Gaussian data can help in accurate modeling of the data generated by emergent high-throughput technologies. AVAILABILITY AND IMPLEMENTATION: Source code is at https://github.com/marinkaz/fusenet.

BACKGROUND: Relation extraction is an essential procedure in literature mining. It focuses on extracting semantic relations between parts of text, called mentions. Biomedical literature includes an enormous amount of textual descriptions of biological entities, their interactions and results of related experiments. To extract them in an explicit, computer readable format, these relations were at first extracted manually from databases. Manual curation was later replaced with automatic or semi-automatic tools with natural language processing capabilities. The current challenge is the development of information extraction procedures that can directly infer more complex relational structures, such as gene regulatory networks. RESULTS: We develop a computational approach for extraction of gene regulatory networks from textual data. Our method is designed as a sieve-based system and uses linear-chain conditional random fields and rules for relation extraction. With this method we successfully extracted the sporulation gene regulation network in the bacterium Bacillus subtilis for the information extraction challenge at the BioNLP 2013 conference. To enable extraction of distant relations using first-order models, we transform the data into skip-mention sequences. We infer multiple models, each of which is able to extract different relationship types. Following the shared task, we conducted additional analysis using different system settings that resulted in reducing the reconstruction error of bacterial sporulation network from 0.73 to 0.68, measured as the slot error rate between the predicted and the reference network. We observe that all relation extraction sieves contribute to the predictive performance of the proposed approach. Also, features constructed by considering mention words and their prefixes and suffixes are the most important features for higher accuracy of extraction. Analysis of distances between different mention types in the text shows that our choice of transforming data into skip-mention sequences is appropriate for detecting relations between distant mentions. CONCLUSIONS: Linear-chain conditional random fields, along with appropriate data transformations, can be efficiently used to extract relations. The sieve-based architecture simplifies the system as new sieves can be easily added or removed and each sieve can utilize the results of previous ones. Furthermore, sieves with conditional random fields can be trained on arbitrary text data and hence are applicable to broad range of relation extraction tasks and data domains.

For most problems in science and engineering we can obtain data sets that describe the observed system from various perspectives and record the behavior of its individual components. Heterogeneous data sets can be collectively mined by data fusion. Fusion can focus on a specific target relation and exploit directly associated data together with contextual data and data about system's constraints. In the paper we describe a data fusion approach with penalized matrix tri-factorization (DFMF) that simultaneously factorizes data matrices to reveal hidden associations. The approach can directly consider any data that can be expressed in a matrix, including those from feature-based representations, ontologies, associations and networks. We demonstrate the utility of DFMF for gene function prediction task with eleven different data sources and for prediction of pharmacologic actions by fusing six data sources. Our data fusion algorithm compares favorably to alternative data integration approaches and achieves higher accuracy than can be obtained from any single data source alone.

Data integration procedures combine heterogeneous data sets into predictive models, but they are limited to data explicitly related to the target object type, such as genes. Collage is a new data fusion approach to gene prioritization. It considers data sets of various association levels with the prediction task, utilizes collective matrix factorization to compress the data, and chaining to relate different object types contained in a data compendium. Collage prioritizes genes based on their similarity to several seed genes. We tested Collage by prioritizing bacterial response genes in Dictyostelium as a novel model system for prokaryote-eukaryote interactions. Using 4 seed genes and 14 data sets, only one of which was directly related to the bacterial response, Collage proposed 8 candidate genes that were readily validated as necessary for the response of Dictyostelium to Gram-negative bacteria. These findings establish Collage as a method for inferring biological knowledge from the integration of heterogeneous and coarsely related data sets.

MOTIVATION: Epistasis analysis is an essential tool of classical genetics for inferring the order of function of genes in a common pathway. Typically, it considers single and double mutant phenotypes and for a pair of genes observes whether a change in the first gene masks the effects of the mutation in the second gene. Despite the recent emergence of biotechnology techniques that can provide gene interaction data on a large, possibly genomic scale, few methods are available for quantitative epistasis analysis and epistasis-based network reconstruction. RESULTS: We here propose a conceptually new probabilistic approach to gene network inference from quantitative interaction data. The approach is founded on epistasis analysis. Its features are joint treatment of the mutant phenotype data with a factorized model and probabilistic scoring of pairwise gene relationships that are inferred from the latent gene representation. The resulting gene network is assembled from scored pairwise relationships. In an experimental study, we show that the proposed approach can accurately reconstruct several known pathways and that it surpasses the accuracy of current approaches. AVAILABILITY AND IMPLEMENTATION: Source code is available at http://github.com/biolab/red.