Search

Abstract One challenge that current de novo drug design models face is a disparity between the user’s expectations and the actual output of the model in practical applications. Tailoring models to better align with chemists’ implicit knowledge, expectation and preferences is key to overcoming this obstacle effectively. While interest in preference-based and human-in-the-loop machine learning in chemistry is continuously increasing, no tool currently exists that enables the collection of standardized and chemistry-specific feedback. Metis is a Python-based open-source graphical user interface (GUI), designed to solve this and enable the collection of chemists’ detailed feedback on molecular structures. The GUI enables chemists to explore and evaluate molecules, offering a user-friendly interface for annotating preferences and specifying desired or undesired structural features. By providing chemists the opportunity to give detailed feedback, allows researchers to capture more efficiently the chemist’s implicit knowledge and preferences. This knowledge is crucial to align the chemist’s idea with the de novo design agents. The GUI aims to enhance this collaboration between the human and the “machine” by providing an intuitive platform where chemists can interactively provide feedback on molecular structures, aiding in preference learning and refining de novo design strategies. Metis integrates with the existing de novo framework REINVENT, creating a closed-loop system where human expertise can continuously inform and refine the generative models. Scientific contribution We introduce a novel Graphical User Interface, that allows chemists/researchers to give detailed feedback on substructures and properties of small molecules. This tool can be used to learn the preferences of chemists in order to align de novo drug design models with the chemist’s ideas. The GUI can be customized to fit different needs and projects and enables direct integration into de novo REINVENT runs. We believe that Metis can facilitate the discussion and development of novel ways to integrate human feedback that goes beyond binary decisions of liking or disliking a molecule.

Abstract Background Consider a setting where multiple parties holding sensitive data aim to collaboratively learn population level statistics, but pooling the sensitive data sets is not possible due to privacy concerns and parties are unable to engage in centrally coordinated joint computation. We study the feasibility of combining privacy preserving synthetic data sets in place of the original data for collaborative learning on real-world health data from the UK Biobank. Methods We perform an empirical evaluation based on an existing prospective cohort study from the literature. Multiple parties were simulated by splitting the UK Biobank cohort along assessment centers, for which we generate synthetic data using differentially private generative modelling techniques. We then apply the original study’s Poisson regression analysis on the combined synthetic data sets and evaluate the effects of 1) the size of local data set, 2) the number of participating parties, and 3) local shifts in distributions, on the obtained likelihood scores. Results We discover that parties engaging in the collaborative learning via shared synthetic data obtain more accurate estimates of the regression parameters compared to using only their local data. This finding extends to the difficult case of small heterogeneous data sets. Furthermore, the more parties participate, the larger and more consistent the improvements become up to a certain limit. Finally, we find that data sharing can especially help parties whose data contain underrepresented groups to perform better-adjusted analysis for said groups. Conclusions Based on our results we conclude that sharing of synthetic data is a viable method for enabling learning from sensitive data without violating privacy constraints even if individual data sets are small or do not represent the overall population well. Lack of access to distributed sensitive data is often a bottleneck in biomedical research, which our study shows can be alleviated with privacy-preserving collaborative learning methods.

New scientific knowledge is needed more urgently than ever, to address global challenges such as climate change, sustainability, health, and societal well-being. Could artificial intelligence (AI) accelerate science to meet these global challenges in time? AI is already revolutionizing individual scientific disciplines, but we argue here that it could be more holistic and encompassing. We introduce the concept of virtual laboratories as a new perspective on scientific knowledge generation and a means to incentivize new AI research and development. Despite the often perceived domain-specific research practices and inherent tacit knowledge, we argue that many elements of the research process recur across scientific domains and that even common software platforms for serving different domains may be possible. We outline how virtual laboratories will make it easier for AI researchers to contribute to a broad range of scientific domains, and highlight the mutual benefits virtual laboratories offer to both AI and domain scientists.

More than 10 million Europeans show signs of mild cognitive impairment (MCI), a transitional stage between normal brain aging and dementia stage memory disorder. The path MCI takes can be divergent; while some maintain stability or even revert to cognitive norms, alarmingly, up to half of the cases progress to dementia within 5 years. Current diagnostic practice lacks the necessary screening tools to identify those at risk of progression. The European patient experience often involves a long journey from the initial signs of MCI to the eventual diagnosis of dementia. The trajectory is far from ideal. Here, we introduce the AI-Mind project, a pioneering initiative with an innovative approach to early risk assessment through the implementation of advanced artificial intelligence (AI) on multimodal data. The cutting-edge AI-based tools developed in the project aim not only to accelerate the diagnostic process but also to deliver highly accurate predictions regarding an individual's risk of developing dementia when prevention and intervention may still be possible. AI-Mind is a European Research and Innovation Action (RIA H2020-SC1-BHC-06-2020, No. 964220) financed between 2021 and 2026. First, the AI-Mind Connector identifies dysfunctional brain networks based on high-density magneto- and electroencephalography (M/EEG) recordings. Second, the AI-Mind Predictor predicts dementia risk using data from the Connector, enriched with computerized cognitive tests, genetic and protein biomarkers, as well as sociodemographic and clinical variables. AI-Mind is integrated within a network of major European initiatives, including The Virtual Brain, The Virtual Epileptic Patient, and EBRAINS AISBL service for sensitive data, HealthDataCloud, where big patient data are generated for advancing digital and virtual twin technology development. AI-Mind's innovation lies not only in its early prediction of dementia risk, but it also enables a virtual laboratory scenario for hypothesis-driven personalized intervention research. This article introduces the background of the AI-Mind project and its clinical study protocol, setting the stage for future scientific contributions.

Abstract A de novo molecular design workflow can be used together with technologies such as reinforcement learning to navigate the chemical space. A bottleneck in the workflow that remains to be solved is how to integrate human feedback in the exploration of the chemical space to optimize molecules. A human drug designer still needs to design the goal, expressed as a scoring function for the molecules that captures the designer’s implicit knowledge about the optimization task. Little support for this task exists and, consequently, a chemist usually resorts to iteratively building the objective function of multi-parameter optimization (MPO) in de novo design. We propose a principled approach to use human-in-the-loop machine learning to help the chemist to adapt the MPO scoring function to better match their goal. An advantage is that the method can learn the scoring function directly from the user’s feedback while they browse the output of the molecule generator, instead of the current manual tuning of the scoring function with trial and error. The proposed method uses a probabilistic model that captures the user’s idea and uncertainty about the scoring function, and it uses active learning to interact with the user. We present two case studies for this: In the first use-case, the parameters of an MPO are learned, and in the second use-case a non-parametric component of the scoring function to capture human domain knowledge is developed. The results show the effectiveness of the methods in two simulated example cases with an oracle, achieving significant improvement in less than 200 feedback queries, for the goals of a high QED score and identifying potent molecules for the DRD2 receptor, respectively. We further demonstrate the performance gains with a medicinal chemist interacting with the system. Graphical Abstract

Abstract Background A deep understanding of carcinogenesis at the DNA level underpins many advances in cancer prevention and treatment. Mutational signatures provide a breakthrough conceptualisation, as well as an analysis framework, that can be used to build such understanding. They capture somatic mutation patterns and at best identify their causes. Most studies in this context have focused on an inherently additive analysis, e.g. by non-negative matrix factorization, where the mutations within a cancer sample are explained by a linear combination of independent mutational signatures. However, other recent studies show that the mutational signatures exhibit non-additive interactions. Results We carefully analysed such additive model fits from the PCAWG study cataloguing mutational signatures as well as their activities across thousands of cancers. Our analysis identified systematic and non-random structure of residuals that is left unexplained by the additive model. We used hierarchical clustering to identify cancer subsets with similar residual profiles to show that both systematic mutation count overestimation and underestimation take place. We propose an extension to the additive mutational signature model—multiplicatively acting modulatory processes—and develop a maximum-likelihood framework to identify such modulatory mutational signatures. The augmented model is expressive enough to almost fully remove the observed systematic residual patterns. Conclusion We suggest the modulatory processes biologically relate to sample specific DNA repair propensities with cancer or tissue type specific profiles. Overall, our results identify an interesting direction where to expand signature analysis.

An open-source framework combines deep learning and permutations of gene interaction neural networks to detect complex gene–gene interactions and their significance in contributions to phenotypes.

Modeling has actively tried to take the human out of the loop, originally for objectivity and recently also for automation. We argue that an unnecessary side effect has been that modeling workflows and machine learning pipelines have become restricted to only well-specified problems. Putting the humans back into the models would enable modeling a broader set of problems, through iterative modeling processes in which AI can offer collaborative assistance. However, this requires advances in how we scope our modeling problems, and in the user models. In this perspective article, we characterize the required user models and the challenges ahead for realizing this vision, which would enable new interactive modeling workflows, and human-centric or human-compatible machine learning pipelines.

Different neuroimaging methods can yield different views of task-dependent neural engagement. Studies examining the relationship between electromagnetic and hemodynamic measures have revealed correlated patterns across brain regions but the role of the applied stimulation or experimental tasks in these correlation patterns is still poorly understood. Here, we evaluated the across-tasks variability of MEG-fMRI relationship using data recorded during three distinct naming tasks (naming objects and actions from action images, and objects from object images), from the same set of participants. Our results demonstrate that the MEG-fMRI correlation pattern varies according to the performed task, and that this variability shows distinct spectral profiles across brain regions. Notably, analysis of the MEG data alone did not reveal modulations across the examined tasks in the time-frequency windows emerging from the MEG-fMRI correlation analysis. Our results suggest that the electromagnetic-hemodynamic correlation could serve as a more sensitive proxy for task-dependent neural engagement in cognitive tasks than isolated within-modality measures.

Summary: Differential privacy allows quantifying privacy loss resulting from accession of sensitive personal data. Repeated accesses to underlying data incur increasing loss. Releasing data as privacy-preserving synthetic data would avoid this limitation but would leave open the problem of designing what kind of synthetic data. We propose formulating the problem of private data release through probabilistic modeling. This approach transforms the problem of designing the synthetic data into choosing a model for the data, allowing also the inclusion of prior knowledge, which improves the quality of the synthetic data. We demonstrate empirically, in an epidemiological study, that statistical discoveries can be reliably reproduced from the synthetic data. We expect the method to have broad use in creating high-quality anonymized data twins of key datasets for research. The bigger picture: Open data are a key component of open science. Unrestricted access to datasets would be necessary for the transparency and reproducibility that the scientific method requires. So far, openness has been at odds with privacy requirements, which has prohibited the opening up of sensitive data even after pseudonymization, which does not protect against privacy breaches using side information. A recent solution for the data-sharing problem is to release synthetic data drawn from privacy-preserving generative models. We propose to interpret privacy-preserving data sharing as a modeling task, allowing us to incorporate prior knowledge of the data-generation process into the generator model using modern probabilistic modeling methods. We demonstrate that this can significantly increase the utility of the generated data.

Abstract Background Users of a personalised recommendation system face a dilemma: recommendations can be improved by learning from data, but only if other users are willing to share their private information. Good personalised predictions are vitally important in precision medicine, but genomic information on which the predictions are based is also particularly sensitive, as it directly identifies the patients and hence cannot easily be anonymised. Differential privacy has emerged as a potentially promising solution: privacy is considered sufficient if presence of individual patients cannot be distinguished. However, differentially private learning with current methods does not improve predictions with feasible data sizes and dimensionalities. Results We show that useful predictors can be learned under powerful differential privacy guarantees, and even from moderately-sized data sets, by demonstrating significant improvements in the accuracy of private drug sensitivity prediction with a new robust private regression method. Our method matches the predictive accuracy of the state-of-the-art non-private lasso regression using only 4x more samples under relatively strong differential privacy guarantees. Good performance with limited data is achieved by limiting the sharing of private information by decreasing the dimensionality and by projecting outliers to fit tighter bounds, therefore needing to add less noise for equal privacy. Conclusions The proposed differentially private regression method combines theoretical appeal and asymptotic efficiency with good prediction accuracy even with moderate-sized data. As already the simple-to-implement method shows promise on the challenging genomic data, we anticipate rapid progress towards practical applications in many fields. Reviewers This article was reviewed by Zoltan Gaspari and David Kreil.

Abstract Background Dispersed biomedical databases limit user exploration to generate structured knowledge. Linked Data unifies data structures and makes the dispersed data easy to search across resources, but it lacks supporting human cognition to achieve insights. In addition, potential errors in the data are difficult to detect in their free formats. Devising a visualization that synthesizes multiple sources in such a way that links between data sources are transparent, and uncertainties, such as data conflicts, are salient is challenging. Results To investigate the requirements and challenges of uncertainty-aware visualizations of linked data, we developed MediSyn, a system that synthesizes medical datasets to support drug treatment selection. It uses a matrix-based layout to visually link drugs, targets (e.g., mutations), and tumor types. Data uncertainties are salient in MediSyn; for example, (i) missing data are exposed in the matrix view of drug-target relations; (ii) inconsistencies between datasets are shown via overlaid layers; and (iii) data credibility is conveyed through links to data provenance. Conclusions Through the synthesis of two manually curated datasets, cancer treatment biomarkers and drug-target bioactivities, a use case shows how MediSyn effectively supports the discovery of drug-repurposing opportunities. A study with six domain experts indicated that MediSyn benefited the drug selection and data inconsistency discovery. Though linked publication sources supported user exploration for further information, the causes of inconsistencies were not easy to find. Additionally, MediSyn could embrace more patient data to increase its informativeness. We derive design implications from the findings.

Predicting the hepatotoxic effects of new drugs is still a challenge. Using toxicogenomics data, the authors here define a predictive toxicogenomic space (PTGS), the component gene space capturing dose-dependent cytotoxicity, and demonstrate that it can be used to accurately predict drug-induced liver pathology, including human drug-induced liver injury fromin vitrodata.

Earlier research has suggested that approximate Bayesian computation (ABC) makes it possible to fit simulator-based intractable birth–death models to investigate communicable disease outbreak dynamics with accuracy comparable to that of exact Bayesian methods. However, recent findings have indicated that key parameters, such as the reproductive number R, may remain poorly identifiable with these models. Here we show that this identifiability issue can be resolved by taking into account disease-specific characteristics of the transmission process in closer detail. Using tuberculosis (TB) in the San Francisco Bay area as a case study, we consider a model that generates genotype data from a mixture of three stochastic processes, each with its own distinct dynamics and clear epidemiological interpretation. We show that our model allows for accurate posterior inferences about outbreak dynamics from aggregated annual case data with genotype information. As a byproduct of the inference, the model provides an estimate of the infectious population size at the time the data were collected. The acquired estimate is approximately two orders of magnitude smaller than assumed in earlier related studies, and it is much better aligned with epidemiological knowledge about active TB prevalence. Similarly, the reproductive number R related to the primary underlying transmission process is estimated to be nearly three times larger than previous estimates, which has a substantial impact on the interpretation of the fitted outbreak model.

Rheumatoid arthritis patients respond differently to anti-TNF treatment. Using community-based challenge, the authors show that currently available data does not reveal meaningful genetic predictors of response to anti-TNF therapy, thus confirming clinical observations.

Abstract Little is known about the human intra‐individual metabolic profile changes over an extended period of time. Here, we introduce a novel concept suggesting that children even at a very young age can be categorized in terms of metabolic state as they advance in development. The hidden Markov models were used as a method for discovering the underlying progression in the metabolic state. We applied the methodology to study metabolic trajectories in children between birth and 4 years of age, based on a series of samples selected from a large birth cohort study. We found multiple previously unknown age‐ and gender‐related metabolome changes of potential medical significance. Specifically, we found that the major developmental state differences between girls and boys are attributed to sphingolipids. In addition, we demonstrated the feasibility of state‐based alignment of personal metabolic trajectories. We show that children have different development rates at the level of metabolome and thus the state‐based approach may be advantageous when applying metabolome profiling in search of markers for subtle (patho)physiological changes.

A main challenge of data-driven sciences is how to make maximal use of the progressively expanding databases of experimental datasets in order to keep research cumulative. We introduce the idea of a modeling-based dataset retrieval engine designed for relating a researcher's experimental dataset to earlier work in the field. The search is (i) data-driven to enable new findings, going beyond the state of the art of keyword searches in annotations, (ii) modeling-driven, to include both biological knowledge and insights learned from data, and (iii) scalable, as it is accomplished without building one unified grand model of all data. Assuming each dataset has been modeled beforehand, by the researchers or automatically by database managers, we apply a rapidly computable and optimizable combination model to decompose a new dataset into contributions from earlier relevant models. By using the data-driven decomposition, we identify a network of interrelated datasets from a large annotated human gene expression atlas. While tissue type and disease were major driving forces for determining relevant datasets, the found relationships were richer, and the model-based search was more accurate than the keyword search; moreover, it recovered biologically meaningful relationships that are not straightforwardly visible from annotations-for instance, between cells in different developmental stages such as thymocytes and T-cells. Data-driven links and citations matched to a large extent; the data-driven links even uncovered corrections to the publication data, as two of the most linked datasets were not highly cited and turned out to have wrong publication entries in the database.

Nature Communications 7: Article number: 12460 (2016); Published: 23 August 2016; Updated: 10 October 2016. The HTML version of this Article incorrectly duplicated the authors S. Louis Bridges, Lindsey Criswell, Larry Moreland, Lars Klareskog, Saedis Saevarsdottir, Leonid Padyukov, Peter K. Gregersen, Stephen Friend, Robert Plenge, Gustavo Stolovitzky, Baldo Oliva, Yuanfang Guan and Lara M.

Recent evidence from serum metabolomics indicates that specific metabolic disturbances precede β-cell autoimmunity in humans and can be used to identify those children who subsequently progress to type 1 diabetes. The mechanisms behind these disturbances are unknown. Here we show the specificity of the pre-autoimmune metabolic changes, as indicated by their conservation in a murine model of type 1 diabetes. We performed a study in non-obese prediabetic (NOD) mice which recapitulated the design of the human study and derived the metabolic states from longitudinal lipidomics data. We show that female NOD mice who later progress to autoimmune diabetes exhibit the same lipidomic pattern as prediabetic children. These metabolic changes are accompanied by enhanced glucose-stimulated insulin secretion, normoglycemia, upregulation of insulinotropic amino acids in islets, elevated plasma leptin and adiponectin, and diminished gut microbial diversity of the Clostridium leptum group. Together, the findings indicate that autoimmune diabetes is preceded by a state of increased metabolic demands on the islets resulting in elevated insulin secretion and suggest alternative metabolic related pathways as therapeutic targets to prevent diabetes.

In a recent FIELD study the fenofibrate therapy surprisingly failed to achieve significant benefit over placebo in the primary endpoint of coronary heart disease events. Increased levels of atherogenic homocysteine were observed in some patients assigned to fenofibrate therapy but the molecular mechanisms behind this are poorly understood. Herein we investigated HDL lipidomic profiles associated with fenofibrate treatment and the drug-induced Hcy levels in the FIELD substudy. We found that fenofibrate leads to complex HDL compositional changes including increased apoA-II, diminishment of lysophosphatidylcholines and increase of sphingomyelins. Ethanolamine plasmalogens were diminished only in a subgroup of fenofibrate-treated patients with elevated homocysteine levels. Finally we performed molecular dynamics simulations to qualitatively reconstitute HDL particles in silico. We found that increased number of apoA-II excludes neutral lipids from HDL surface and apoA-II is more deeply buried in the lipid matrix than apoA-I. In conclusion, a detailed molecular characterization of HDL may provide surrogates for predictors of drug response and thus help identify the patients who might benefit from fenofibrate treatment.

BACKGROUND: Retroviral LTRs, paired or single, influence the transcription of both retroviral and non-retroviral genomic sequences. Vertebrate genomes contain many thousand endogenous retroviruses (ERVs) and their LTRs. Single LTRs are difficult to detect from genomic sequences without recourse to repetitiveness or presence in a proviral structure. Understanding of LTR structure increases understanding of LTR function, and of functional genomics. Here we develop models of orthoretroviral LTRs useful for detection in genomes and for structural analysis. PRINCIPAL FINDINGS: Although mutated, ERV LTRs are more numerous and diverse than exogenous retroviral (XRV) LTRs. Hidden Markov models (HMMs), and alignments based on them, were created for HML- (human MMTV-like), general-beta-, gamma- and lentiretroviruslike LTRs, plus a general-vertebrate LTR model. Training sets were XRV LTRs and RepBase LTR consensuses. The HML HMM was most sensitive and detected 87% of the HML LTRs in human chromosome 19 at 96% specificity. By combining all HMMs with a low cutoff, for screening, 71% of all LTRs found by RepeatMasker in chromosome 19 were found. HMM consensus sequences had a conserved modular LTR structure. Target site duplications (TG-CA), TATA (occasionally absent), an AATAAA box and a T-rich region were prominent features. Most of the conservation was located in, or adjacent to, R and U5, with evidence for stem loops. Several of the long HML LTRs contained long ORFs inserted after the second A rich module. HMM consensus alignment allowed comparison of functional features like transcriptional start sites (sense and antisense) between XRVs and ERVs. CONCLUSION: The modular conserved and redundant orthoretroviral LTR structure with three A-rich regions is reminiscent of structurally relaxed Giardia promoters. The five HMMs provided a novel broad range, repeat-independent, ab initio LTR detection, with prospects for greater generalisation, and insight into LTR structure, which may aid development of LTR-targeted pharmaceuticals.