The discovery of dynamical systems is crucial across a range of fields, including pharmacology, epidemiology, and physical sciences. *Accurate* and *interpretable* modeling of these systems is essential for understanding complex temporal processes, optimizing interventions, and minimizing adverse effects. In pharmacology, for example, precise modeling of drug dynamics is vital to maximize therapeutic efficacy while minimizing patient harm, as in chemotherapy. However, current models, often developed by human experts, are limited by high cost, lack of scalability, and restriction to existing human knowledge. In this paper, we present the **Data-Driven Discovery (D3)** framework, a novel approach leveraging Large Language Models (LLMs) to iteratively discover and refine interpretable models of dynamical systems, demonstrated here with pharmacological applications. Unlike traditional methods, D3 enables the LLM to propose, acquire, and integrate new features, validate, and compare dynamical systems models, uncovering new insights into pharmacokinetics. Experiments on a pharmacokinetic Warfarin dataset reveal that D3 identifies a new plausible model that is well-fitting, highlighting its potential for precision dosing in clinical applications.

The state of clinical data is a barrier to the development of machine learning models to improve healthcare. Uncontrolled clinical freetext is common in both the patient and clinical trials: the resulting spelling, grammatical errors, phrasing variation, and other resulting variability results in difficult-to-leverage data. As part of our effort to harmonize the Aggregate Analysis of ClinicalTrials.gov (AACT) drop-withdrawal reasons to a controlled vocabulary, we explored two solutions. Elastic's fuzzy matching capability matched entries in the AACT Drop-Withdrawal table to a list of user-specified terms (74.6% coverage). The second approach was a custom pipeline employing NLP preprocessing, Levenshtein Distance (Fuzzy Matching), and semantic similarity mapping using a pre-trained FastText Model (98% coverage). Although manual oversight is still required, the amount of effort to harmonize with a controlled vocabulary is notably reduced. This work enables the rapid harmonization of clinical databases, allowing them to be leveraged for machine learning and analytics.

Information theoretic feature selection methods quantify the importance of each feature by estimating mutual information terms to capture: the relevancy, the redundancy and the complementarity. These terms are commonly estimated by maximum likelihood, while an under-explored area of research is how to use shrinkage methods instead. Our work suggests a novel shrinkage method for data-efficient estimation of information theoretic terms. The small sample behaviour makes it particularly suitable for estimation of discrete distributions with large number of categories (bins). Using our novel estimators we derive a framework for generating feature selection criteria that capture any high-order feature interaction for redundancy and complementarity. We perform a thorough empirical study across datasets from diverse sources and using various evaluation measures. Our first finding is that our shrinkage based methods achieve better results, while they keep the same computational cost as the simple maximum likelihood based methods. Furthermore, under our framework we derive efficient novel high-order criteria that outperform state-of-the-art methods in various tasks.

Motivation: The identification of biomarkers to support decision-making is central to personalized medicine, in both clinical and research scenarios. The challenge can be seen in two halves: identifying predictive markers, which guide the development/use of tailored therapies; and identifying prognostic markers, which guide other aspects of care and clinical trial planning, i.e. prognostic markers can be considered as covariates for stratification. Mistakenly assuming a biomarker to be predictive, when it is in fact largely prognostic (and vice-versa) is highly undesirable, and can result in financial, ethical and personal consequences. We present a framework for data-driven ranking of biomarkers on their prognostic/predictive strength, using a novel information theoretic method. This approach provides a natural algebra to discuss and quantify the individual predictive and prognostic strength, in a self-consistent mathematical framework. Results: Our contribution is a novel procedure, INFO+, which naturally distinguishes the prognostic versus predictive role of each biomarker and handles higher order interactions. In a comprehensive empirical evaluation INFO+ outperforms more complex methods, most notably when noise factors dominate, and biomarkers are likely to be falsely identified as predictive, when in fact they are just strongly prognostic. Furthermore, we show that our methods can be 1-3 orders of magnitude faster than competitors, making it useful for biomarker discovery in 'big data' scenarios. Finally, we apply our methods to identify predictive biomarkers on two real clinical trials, and introduce a new graphical representation that provides greater insight into the prognostic and predictive strength of each biomarker. Availability and implementation: R implementations of the suggested methods are available at https://github.com/sechidis. Supplementary information: Supplementary data are available at Bioinformatics online.

Bioinformatics, (2018) https://doi.org/10.1093/bioinformatics/bty357 The author wishes to apologize for a mistake in Figure 2 in the above manuscript. The figure appears correctly below: When biomarkers have both prognostic/predictive strength (M-1) VT achieves higher TPR, otherwise (M-2) the gains in TPR are vanishing. In terms of FNRProg.⁠, VT always has very high error rate on selecting solely prognostic biomarkers as predictive, and it performs worse than random selection. This is the average TPR/FNRProg. over 200 simulated datasets for three different values of the predictive strength θ: 1/5 means a strongly prognostic signal, 1 means equal strength between prognostic and predictive signals, and 5 means a strongly predictive signal. The sample size is 2000, and the dimensionality p = 30 biomarkers. Dashed lines show the TPR/FNRProg. if we were ranking the biomarkers at random. (a) M-1: Biomarkers can be both prognostic and predictive. (b) M-2: Biomarkers are solely either prognostic or predictive The paper has been corrected online.

Background: In contrast to efficacy, safety hypotheses of clinical trials are not always pre-specified, and therefore, the safety interpretation work of a trial tends to be more exploratory, often reactive, and the analysis more statistically and graphically challenging. Methods: We introduce a new means of visualizing the adverse event data across an entire clinical trial. Results: The approach overcomes some of the current limitations of adverse event analysis and streamlines the way safety data can be explored, interpreted and analyzed. Using a phase II study, we describe and exemplify how the tendril plot effectively summarizes the time-resolved safety profile of two treatment arms in a single plot and how that can provide scientists with a trial safety overview that can support medical decision making. Conclusion: To our knowledge, the tendril plot is the only way to graphically show important treatment differences with preserved temporal information, across an entire clinical trial, in a single view.