The recent proliferation of foundation models calls for a paradigm shift from Data Science to Model Science. Unlike data-centric approaches, Model Science places the trained model at the core of analysis, aiming to interact, verify, explain, and control its behavior across diverse operational contexts. This paper introduces a conceptual framework for a new discipline called Model Science, along with the proposal for its four key pillars: Verification, which requires strict, context-aware evaluation protocols; Explanation, which is understood as various approaches to explore of internal model operations; Control, which integrates alignment techniques to steer model behavior; and Interface, which develops interactive and visual explanation tools to improve human calibration and decision-making. The proposed framework aims to guide the development of credible, safe, and human-aligned AI systems.

We discover a theoretical connection between explanation estimation and distribution compression that significantly improves the approximation of feature attributions, importance, and effects. While the exact computation of various machine learning explanations requires numerous model inferences and becomes impractical, the computational cost of approximation increases with an ever-increasing size of data and model parameters. We show that the standard i.i.d. sampling used in a broad spectrum of algorithms for post-hoc explanation leads to an approximation error worthy of improvement. To this end, we introduce Compress Then Explain (CTE), a new paradigm of sample-efficient explainability. It relies on distribution compression through kernel thinning to obtain a data sample that best approximates its marginal distribution. CTE significantly improves the accuracy and stability of explanation estimation with negligible computational overhead. It often achieves an on-par explanation approximation error 2-3x faster by using fewer samples, i.e. requiring 2-3x fewer model evaluations. CTE is a simple, yet powerful, plug-in for any explanation method that now relies on i.i.d. sampling.

Visual counterfactual explanations (VCEs) have recently gained immense popularity as a tool for clarifying the decision-making process of image classifiers. This trend is largely motivated by what these explanations promise to deliver -- indicate semantically meaningful factors that change the classifier's decision. However, we argue that current state-of-the-art approaches lack a crucial component -- the region constraint -- whose absence prevents from drawing explicit conclusions, and may even lead to faulty reasoning due to phenomenons like confirmation bias. To address the issue of previous methods, which modify images in a very entangled and widely dispersed manner, we propose region-constrained VCEs (RVCEs), which assume that only a predefined image region can be modified to influence the model's prediction. To effectively sample from this subclass of VCEs, we propose Region-Constrained Counterfactual Schrödinger Bridge (RCSB), an adaptation of a tractable subclass of Schrödinger Bridges to the problem of conditional inpainting, where the conditioning signal originates from the classifier of interest. In addition to setting a new state-of-the-art by a large margin, we extend RCSB to allow for exact counterfactual reasoning, where the predefined region contains only the factor of interest, and incorporating the user to actively interact with the RVCE by predefining the regions manually.

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable features, SAEs are particularly valuable for analyzing vision-language models (e.g., CLIP and SigLIP), which are fundamental building blocks in modern large-scale systems yet remain challenging to interpret and control. However, current SAE methods are limited by optimizing both reconstruction quality and sparsity simultaneously, as they rely on either activation suppression or rigid sparsity constraints. To this end, we introduce Matryoshka SAE (MSAE), a new architecture that learns hierarchical representations at multiple granularities simultaneously, enabling a direct optimization of both metrics without compromise. MSAE establishes a state-of-the-art Pareto frontier between reconstruction quality and sparsity for CLIP, achieving 0.99 cosine similarity and less than 0.1 fraction of variance unexplained while maintaining 80% sparsity. Finally, we demonstrate the utility of MSAE as a tool for interpreting and controlling CLIP by extracting over 120 semantic concepts from its representation to perform concept-based similarity search and bias analysis in downstream tasks like CelebA. We make the codebase available at https://github.com/WolodjaZ/MSAE.

Language-image pre-training (LIP) enables the development of vision-language models capable of zero-shot classification, localization, multimodal retrieval, and semantic understanding. Various explanation methods have been proposed to visualize the importance of input image-text pairs on the model's similarity outputs. However, popular saliency maps are limited by capturing only first-order attributions, overlooking the complex cross-modal interactions intrinsic to such encoders. We introduce faithful interaction explanations of LIP models (FIxLIP) as a unified approach to decomposing the similarity in vision-language encoders. FIxLIP is rooted in game theory, where we analyze how using the weighted Banzhaf interaction index offers greater flexibility and improves computational efficiency over the Shapley interaction quantification framework. From a practical perspective, we propose how to naturally extend explanation evaluation metrics, such as the pointing game and area between the insertion/deletion curves, to second-order interaction explanations. Experiments on the MS COCO and ImageNet-1k benchmarks validate that second-order methods, such as FIxLIP, outperform first-order attribution methods. Beyond delivering high-quality explanations, we demonstrate the utility of FIxLIP in comparing different models, e.g. CLIP vs. SigLIP-2.

Solving inverse problems—recovering signals from incomplete or noisy measurements—is fundamental in science and engineering. Score-based generative models (SGMs) have recently emerged as a powerful framework for this task. Two main paradigms have formed: unsupervised approaches that adapt pretrained generative models to inverse problems, and supervised bridge methods that train stochastic processes conditioned on paired clean and corrupted data. While the former typically assume knowledge of the measurement model, the latter have largely overlooked this structural information. We introduce System-embedded Diffusion Bridge Models (SDBs), a new class of supervised bridge methods that explicitly embed the known linear measurement system into the coefficients of a matrix-valued SDE. This principled integration yields consistent improvements across diverse linear inverse problems and demonstrates robust generalization under system misspecification between training and deployment, offering a promising solution to real-world applications.

Abstract Counterfactual explanations provide an intuitive way to understand model decisions by identifying minimal changes required to alter an outcome. However, applying counterfactual methods to time series models remains challenging due to temporal dependencies, high dimensionality, and the lack of an intuitive human-interpretable representation. We introduce MASCOTS, a method that leverages the Bag-of-Receptive-Fields representation alongside symbolic transformations inspired by Symbolic Aggregate Approximation. By operating in a symbolic feature space, it enhances interpretability while preserving fidelity to the original data and model. Unlike existing approaches that either depend on model structure or autoencoder-based sampling, MASCOTS directly generates meaningful and diverse counterfactual observations in a model-agnostic manner, operating on both univariate and multivariate data. We evaluate MASCOTS on univariate and multivariate benchmark datasets, demonstrating comparable validity, proximity, and plausibility to state-of-the-art methods, while significantly improving interpretability and sparsity. Its symbolic nature allows for explanations that can be expressed visually, in natural language, or through semantic representations, making counterfactual reasoning more accessible and actionable.

Analysis of 3D segmentation models, especially in the context of medical imaging, is often limited to segmentation performance metrics that overlook the crucial aspect of explainability and bias. Currently, effectively explaining these models with saliency maps is challenging due to the high dimensions of input images multiplied by the ever-growing number of segmented class labels. To this end, we introduce AGG2Exp, a methodology for aggregating fine-grained voxel attributions of the segmentation model's pre-dictions. Unlike classical explanation methods that primar-ily focus on the local feature attribution, Agg2 Exr enables a more comprehensive global view on the importance of predicted segments in 3D images. Our benchmarking exper-iments show that gradient-based voxel attributions are more faithful to the model's predictions than perturbation-based explanations. As a concrete use-case, we apply AGG2Exp to discover knowledge acquired by the Swin UNEt TRans-former model trained on the TotalSegmentator v2 dataset for segmenting anatomical structures in computed tomogra-phy medical images. AGG2Exp facilitates the explanatory analysis of large segmentation models beyond their predictive performance. The source code is publicly available at https://github.com/mi2datalab/agg2exp.

Abstract A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs have not been comprehensively verified, and growing evidence casts doubt on them. In this paper, we highlight the risks related to overreliance and susceptibility to adversarial manipulation of these so-called “intrinsically (aka inherently) interpretable” models by design. We introduce two strategies for adversarial analysis with prototype manipulation and backdoor attacks against prototype-based networks, and discuss how concept bottleneck models defend against these attacks. Fooling the model’s reasoning by exploiting its use of latent prototypes manifests the inherent uninterpretability of deep neural networks, leading to a false sense of security reinforced by a visual confirmation bias. The reported limitations of part-prototype networks put their trustworthiness and applicability into question, motivating further work on the robustness and alignment of (deep) interpretable models.

Abstract Explainable AI (XAI) is an increasingly important area of machine learning research, which aims to make black-box models transparent and interpretable. In this paper, we propose a novel approach to XAI that uses the so-called counterfactual paths for model-agnostic global explanations. The algorithm measures feature importance by identifying sequential permutations of features that most influence changes in model predictions. It is particularly suitable for generating explanations based on counterfactual paths in knowledge graphs incorporating domain knowledge. Counterfactual paths introduce an additional graph dimension to current XAI methods in both explaining and visualizing black-box models. Experiments with synthetic and bio-medical data demonstrate the practical applicability of our approach.

If AI is the new electricity, what should we do to keep ourselves from getting electrocuted? In this work, we explore factors related to the potential of large language models (LLMs) to manipulate human decisions. We describe the results of two experiments designed to determine what characteristics of humans are associated with their susceptibility to LLM manipulation, and what characteristics of LLMs are associated with their manipulativeness potential. We explore human factors by conducting user studies in which participants answer general knowledge questions using LLM-generated hints, whereas LLM factors by provoking language models to create manipulative statements. Then, we analyze their obedience, the persuasion strategies used, and the choice of vocabulary. Based on these experiments, we discuss two actions that can protect us from LLM manipulation. In the long term, we put AI literacy at the forefront, arguing that educating society would minimize the risk of manipulation and its consequences. We also propose an ad hoc solution, a classifier that detects LLM manipulation – a Manipulation Fuse.

Explainable Artificial Intelligence (XAI) is a young but very promising field of research. Unfortunately, the progress in this field is currently slowed down by divergent and incompatible goals. We separate various threads tangled within the area of XAI into two complementary cultures of human/value-oriented explanations (BLUE XAI) and model/validation-oriented explanations (RED XAI). This position paper argues that the area of RED XAI is currently under-explored, i.e., more methods for explainability are desperately needed to question models (e.g., extract knowledge from well-performing models as well as spotting and fixing bugs in faulty models), and the area of RED XAI hides great opportunities and potential for important research necessary to ensure the safety of AI systems. We conclude this paper by presenting promising challenges in this area.

Does the stethoscope in the picture make the adjacent person a doctor or a patient? This, of course, depends on the contextual relationship of the two objects. If it’s obvious, why don’t explanation methods for vision models use contextual information? In this paper, we (1) review the most popular methods of explaining computer vision models by pointing out that they do not take into account context information, (2) show examples of failures of popular XAI methods, (3) provide examples of real-world use cases where spatial context plays a significant role, (4) propose new research directions that may lead to better use of context information in explaining computer vision models, (5) argue that a change in approach to explanations is needed from *where* to *how*.

Abstract The growing need for in-depth analysis of predictive models leads to a series of new methods for explaining their local and global properties. Which of these methods is the best? It turns out that this is an ill-posed question. One cannot sufficiently explain a black-box machine learning model using a single method that gives only one perspective. Isolated explanations are prone to misunderstanding, leading to wrong or simplistic reasoning. This problem is known as the Rashomon effect and refers to diverse, even contradictory, interpretations of the same phenomenon. Surprisingly, most methods developed for explainable and responsible machine learning focus on a single-aspect of the model behavior. In contrast, we showcase the problem of explainability as an interactive and sequential analysis of a model. This paper proposes how different Explanatory Model Analysis (EMA) methods complement each other and discusses why it is essential to juxtapose them. The introduced process of Interactive EMA (IEMA) derives from the algorithmic side of explainable machine learning and aims to embrace ideas developed in cognitive sciences. We formalize the grammar of IEMA to describe human-model interaction. It is implemented in a widely used human-centered open-source software framework that adopts interactivity, customizability and automation as its main traits. We conduct a user study to evaluate the usefulness of IEMA, which indicates that an interactive sequential analysis of a model may increase the accuracy and confidence of human decision making.

Abstract The increased interest in deep learning applications, and their hard-to-detect biases result in the need to validate and explain complex models. However, current explanation methods are limited as far as both the explanation of the reasoning process and prediction results are concerned. They usually only show the location in the image that was important for model prediction. The lack of possibility to interact with explanations makes it difficult to verify and understand exactly how the model works. This creates a significant risk when using the model. The risk is compounded by the fact that explanations do not take into account the semantic meaning of the explained objects. To escape from the trap of static and meaningless explanations, we propose a tool and a process called LIMEcraft. LIMEcraft enhances the process of explanation by allowing a user to interactively select semantically consistent areas and thoroughly examine the prediction for the image instance in case of many image features. Experiments on several models show that our tool improves model safety by inspecting model fairness for image pieces that may indicate model bias. The code is available at: http://github.com/MI2DataLab/LIMEcraft .

Abstract For many machine learning models, a choice of hyperparameters is a crucial step towards achieving high performance. Prevalent meta-learning approaches focus on obtaining good hyperparameter configurations with a limited computational budget for a completely new task based on the results obtained from the prior tasks. This paper proposes a new formulation of the tuning problem, called consolidated learning, more suited to practical challenges faced by model developers, in which a large number of predictive models are created on similar datasets. In such settings, we are interested in the total optimization time rather than tuning for a single task. We show that a carefully selected static portfolio of hyperparameter configurations yields good results for anytime optimization, while maintaining the ease of use and implementation. Moreover, we point out how to construct such a portfolio for specific domains. The improvement in the optimization is possible due to the more efficient transfer of hyperparameter configurations between similar tasks. We demonstrate the effectiveness of this approach through an empirical study for the XGBoost algorithm and the newly created metaMIMIC benchmarks of predictive tasks extracted from the MIMIC-IV medical database. In the paper, we show that the potential of consolidated learning is considerably greater due to its compatibility with many machine learning application scenarios.

The machine learning modeling process conventionally results in selecting a single model that maximizes a selected performance metric. However, this approach leads to abandoning a more profound analysis of slightly inferior models. Particularly in medical and healthcare studies, where the objective extends beyond predictions to generation of valuable insights, relying solely on a single model can result in misleading or incomplete conclusions. This problem is particularly pertinent when dealing with a set of models known asRashomon set, with performance close to maximum one. Such a set can be numerous and may contain models describing the data in a different way, which calls for comprehensive analysis. This paper introduces a novel method to explore models in the Rashomon set, extending the conventional modeling approach. We propose theRashomon_DETECTalgorithm to detect models with different behavior. It is based on recent developments in the eXplainable Artificial Intelligence (XAI) field. To quantify differences in variable effects among models, we introduce the Profile Disparity Index (PDI) based on measures from functional data analysis. To illustrate the effectiveness of our approach, we showcase its application on real-world medical problem: predicting survival among hemophagocytic lymphohistiocytosis (HLH) patients – a foundational case study. Additionally, we benchmark our approach on other medical data sets, demonstrating its versatility and utility in various contexts. If differently behaving models are detected in the Rashomon set, their combined analysis leads to more trustworthy conclusions, which is of vital importance for high-stakes applications such as medical applications.

SUMMARY: Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to explain their internal operations and prediction rationales. To tackle this issue, we introduce the survex R package, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques. The capabilities of the proposed software encompass understanding and diagnosing survival models, which can lead to their improvement. By revealing insights into the decision-making process, such as variable effects and importances, survex enables the assessment of model reliability and the detection of biases. Thus, transparency and responsibility may be promoted in sensitive areas, such as biomedical research and healthcare applications. AVAILABILITY AND IMPLEMENTATION: survex is available under the GPL3 public license at https://github.com/modeloriented/survex and on CRAN with documentation available at https://modeloriented.github.io/survex.

Machine and deep learning survival models demonstrate similar or even improved time-to-event prediction capabilities compared to classical statistical learning methods yet are too complex to be interpreted by humans. Several model-agnostic explanations are available to overcome this issue; however, none directly explain the survival function prediction. In this paper, we introduce SurvSHAP(t), the first time-dependent explanation that allows for interpreting survival black-box models. It is based on SHapley Additive exPlanations with solid theoretical foundations and a broad adoption among machine learning practitioners. The proposed methods aim to enhance precision diagnostics and support domain experts in making decisions. Experiments on synthetic and medical data confirm that SurvSHAP(t) can detect variables with a time-dependent effect, and its aggregation is a better determinant of the importance of variables for a prediction than SurvLIME. SurvSHAP(t) is model-agnostic and can be applied to all models with functional output. We provide an accessible implementation of time-dependent explanations in Python at https://github.com/MI2DataLab/survshap.

We introduce a model-agnostic algorithm for manipulating SHapley Additive exPlanations (SHAP) with perturbation of tabular data. It is evaluated on predictive tasks from healthcare and financial domains to illustrate how crucial is the context of data distribution in interpreting machine learning models. Our method supports checking the stability of the explanations used by various stakeholders apparent in the domain of responsible AI; moreover, the result highlights the explanations' vulnerability that can be exploited by an adversary.

The expected goal provides a more representative measure of the team and player performance which also suit the low-scoring nature of football instead of score in modern football. The score of a match involves randomness and often may not represent the performance of the teams and players, therefore it has been popular to use the alternative statistics in recent years such as shots on target, ball possessions, and drills. To measure the probability of a shot being a goal by the expected goal, several features are used to train an expected goal model which is based on the event and tracking football data. The selection of these features, the size and date of the data, and the model which are used as the parameters that may affect the performance of the model. Using black-box machine learning models for increasing the predictive performance of the model decreases its interpretability that causes the loss of information that can be gathered from the model. This paper proposes an accurate expected goal model trained consisting of 315,430 shots from seven seasons between 2014-15 and 2020-21 of the top-five European football leagues. Moreover, this model is explained by using explainable artificial intelligence tool to obtain an explainable expected goal model for evaluating a team or player performance. To the best of our knowledge, this is the first paper that demonstrates a practical application of an explainable artificial intelligence tool aggregated profiles to explain a group of observations on an accurate expected goal model for monitoring the team and player performance. Moreover, these methods can be generalized to other sports branches.

Abstract Many methods have been developed to understand complex predictive models and high expectations are placed on post-hoc model explainability. It turns out that such explanations are not robust nor trustworthy, and they can be fooled. This paper presents techniques for attacking Partial Dependence (plots, profiles, PDP), which are among the most popular methods of explaining any predictive model trained on tabular data. We showcase that PD can be manipulated in an adversarial manner, which is alarming, especially in financial or medical applications where auditability became a must-have trait supporting black-box machine learning. The fooling is performed via poisoning the data to bend and shift explanations in the desired direction using genetic and gradient algorithms. We believe this to be the first work using a genetic algorithm for manipulating explanations, which is transferable as it generalizes both ways: in a model-agnostic and an explanation-agnostic manner.

For high-stakes prediction making, the Responsible Artificial Intelligence (RAI) is more important than ever. It builds upon Explainable Artificial Intelligence (XAI) to advance the efforts in providing fairness, model explainability, and accountability to the AI systems. During the literature review of COVID-19 related prognosis and diagnosis, we found out that most of the predictive models are not faithful to the RAI principles, which can lead to biassed results and wrong reasoning. To solve this problem, we show how novel XAI techniques boost transparency, reproducibility and quality of models.

The relevance of the Key Information Extraction (KIE) task is increasingly important in natural language processing problems. But there are still only a few well-defined problems that serve as benchmarks for solutions in this area. To bridge this gap, we introduce two new datasets (Kleister NDA and Kleister Charity). They involve a mix of scanned and born-digital long formal English-language documents. In these datasets, an NLP system is expected to find or infer various types of entities by employing both textual and structural layout features. The Kleister Charity dataset consists of 2,788 annual financial reports of charity organizations, with 61,643 unique pages and 21,612 entities to extract. The Kleister NDA dataset has 540 Non-disclosure Agreements, with 3,229 unique pages and 2,160 entities to extract. We provide several state-of-the-art baseline systems from the KIE domain (Flair, BERT, RoBERTa, LayoutLM, LAMBERT), which show that our datasets pose a strong challenge to existing models. The best model achieved an 81.77% and an 83.57% F1-score on respectively the Kleister NDA and the Kleister Charity datasets. We share the datasets to encourage progress on more in-depth and complex information extraction tasks.

Machine learning has proved to generate useful predictive models that can and should support decision makers in many areas. The availability of tools for AutoML makes it possible to quickly create an effective but complex predictive model. However, the complexity of such models is often a major obstacle in applications, especially in terms of high-stake decisions. We are experiencing a growing number of examples where the use of black boxes leads to decisions that are harmful, unfair or simply wrong. In this paper, we show that very often we can simplify complex models without compromising their performance; however, with the benefit of much needed transparency. We propose a framework that uses elastic black boxes as supervisor models to create simpler, less opaque, yet still accurate and interpretable glass box models. The new models were created using newly engineered features extracted with the help of a supervisor model. We supply the analysis using a large-scale benchmark on several tabular data sets from the OpenML database. There are tree main results of this paper: 1) we show that extracting information from complex models may improve the performance of simpler models, 2) we question a common myth that complex predictive models outperform simpler predictive models, 3) we present a real-life application of the proposed method.

In modern machine learning, we observe the phenomenon of opaqueness debt, which manifests itself by an increased risk of discrimination, lack of reproducibility, and deflated performance due to data drift. An increasing amount of available data and computing power results in the growing complexity of black-box predictive models. To manage these issues, good MLOps practice asks for better validation of model performance and fairness, higher explainability, and continuous monitoring. The necessity for deeper model transparency comes from both scientific and social domains and is also caused by emerging laws and regulations on artificial intelligence. To facilitate the responsible development of machine learning models, we introduce dalex, a Python package which implements a model-agnostic interface for interactive explainability and fairness. It adopts the design crafted through the development of various tools for explainable machine learning; thus, it aims at the unification of existing solutions. This library's source code and documentation are available under open license at https://python.drwhy.ai.

The sudden outbreak and uncontrolled spread of COVID-19 disease is one of the most important global problems today. In a short period of time, it has led to the development of many deep neural network models for COVID-19 detection with modules for explainability. In this work, we carry out a systematic analysis of various aspects of proposed models. Our analysis revealed numerous mistakes made at different stages of data acquisition, model development, and explanation construction. In this work, we overview the approaches proposed in the surveyed Machine Learning articles and indicate typical errors emerging from the lack of deep understanding of the radiography domain. We present the perspective of both: experts in the field - radiologists and deep learning engineers dealing with model explanations. The final result is a proposed checklist with the minimum conditions to be met by a reliable COVID-19 diagnostic model.

Abstract Medical free-text records store a lot of useful information that can be exploited in developing computer-supported medicine. However, extracting the knowledge from the unstructured text is difficult and depends on the language. In the paper, we apply Natural Language Processing methods to process raw medical texts in Polish and propose a new methodology for clustering of patients’ visits. We (1) extract medical terminology from a corpus of free-text clinical records, (2) annotate data with medical concepts, (3) compute vector representations of medical concepts and validate them on the proposed term analogy tasks, (4) compute visit representations as vectors, (5) introduce a new method for clustering of patients’ visits and (6) apply the method to a corpus of 100,000 visits. We use several approaches to visual exploration that facilitate interpretation of segments. With our method, we obtain stable and separated segments of visits which are positively validated against final medical diagnoses. In this paper we show how algorithm for segmentation of medical free-text records may be used to aid medical doctors. In addition to this, we share implementation of described methods with examples as open-source package .

SUMMARY: Krüppel-associated box domain zinc finger protein (KRAB ZNF) explorer is a web-based tool for comprehensive characterization of the mRNA expression status of KRAB-ZNF transcription factors in the data from The Cancer Genome Atlas study. Key functionalities cover a comparative analysis of KRAB-ZNF expression between normal and cancer tissues, an association of KRAB-ZNF expression with various pathological features, including survival analysis, association with global DNA methylation status, analyses of KRAB-ZNF isoform expressions and analysis of KRAB-ZNF levels in normal tissues. AVAILABILITY AND IMPLEMENTATION: KRAB ZNF explorer is available at http://mi2.mini.pw.edu.pl: 8080/KRAB_ZNF/. The source code for shiny application is available at: https://github.com/MI2DataLab/KRAB_ZNF/tree/master/app and the source code for analyses and precalculations are available at: https://github.com/MI2DataLab/KRAB_ZNF/tree/master/work.

Nie dotyczy

Predictive modeling is invaded by elastic, yet complex methods such as neural networks or ensembles (model stacking, boosting or bagging). Such methods are usually described by a large number of parameters or hyper parameters - a price that one needs to pay for elasticity. The very number of parameters makes models hard to understand. This paper describes a consistent collection of explainers for predictive models, a.k.a. black boxes. Each explainer is a technique for exploration of a black box model. Presented approaches are model-agnostic, what means that they extract useful information from any predictive method irrespective of its internal structure. Each explainer is linked with a specific aspect of a model. Some are useful in decomposing predictions, some serve better in understanding performance, while others are useful in understanding importance and conditional responses of a particular variable. Every explainer presented here works for a single model or for a collection of models. In the latter case, models can be compared against each other. Such comparison helps to find strengths and weaknesses of different models and gives additional tools for model validation. Presented explainers are implemented in the DALEX package for R. They are based on a uniform standardized grammar of model exploration which may be easily extended.

BACKGROUND: Deregulation between two different cell populations manifests itself in changing gene expression patterns and changing regulatory interactions. Accumulating knowledge about biological networks creates an opportunity to study these changes in their cellular context. RESULTS: We analyze re-wiring of regulatory networks based on cell population-specific perturbation data and knowledge about signaling pathways and their target genes. We quantify deregulation by merging regulatory signal from the two cell populations into one score. This joint approach, called JODA, proves advantageous over separate analysis of the cell populations and analysis without incorporation of knowledge. JODA is implemented and freely available in a Bioconductor package 'joda'. CONCLUSIONS: Using JODA, we show wide-spread re-wiring of gene regulatory networks upon neocarzinostatin-induced DNA damage in Human cells. We recover 645 deregulated genes in thirteen functional clusters performing the rich program of response to damage. We find that the clusters contain many previously characterized neocarzinostatin target genes. We investigate connectivity between those genes, explaining their cooperation in performing the common functions. We review genes with the most extreme deregulation scores, reporting their involvement in response to DNA damage. Finally, we investigate the indirect impact of the ATM pathway on the deregulated genes, and build a hypothetical hierarchy of direct regulation. These results prove that JODA is a step forward to a systems level, mechanistic understanding of changes in gene regulation between different cell populations.