Antimicrobial peptides emerge as compounds that can alleviate the global health hazard of antimicrobial resistance, prompting a need for novel computational approaches to peptide generation. Here, we propose HydrAMP, a conditional variational autoencoder that learns lower-dimensional, continuous representation of peptides and captures their antimicrobial properties. The model disentangles the learnt representation of a peptide from its antimicrobial conditions and leverages parameter-controlled creativity. HydrAMP is the first model that is directly optimized for diverse tasks, including unconstrained and analogue generation and outperforms other approaches in these tasks. An additional preselection procedure based on ranking of generated peptides and molecular dynamics simulations increases experimental validation rate. Wet-lab experiments on five bacterial strains confirm high activity of nine peptides generated as analogues of clinically relevant prototypes, as well as six analogues of an inactive peptide. HydrAMP enables generation of diverse and potent peptides, making a step towards resolving the antimicrobial resistance crisis.

Machine learning algorithms hold the promise to effectively automate the analysis of histopathological images that are routinely generated in clinical practice. Any machine learning method used in the clinical diagnostic process has to be extremely accurate and, ideally, provide a measure of uncertainty for its predictions. Such accurate and reliable classifiers need enough labelled data for training, which requires time-consuming and costly manual annotation by pathologists. Thus, it is critical to minimise the amount of data needed to reach the desired accuracy by maximising the efficiency of training. We propose an accurate, reliable and active (ARA) image classification framework and introduce a new Bayesian Convolutional Neural Network (ARA-CNN) for classifying histopathological images of colorectal cancer. The model achieves exceptional classification accuracy, outperforming other models trained on the same dataset. The network outputs an uncertainty measurement for each tested image. We show that uncertainty measures can be used to detect mislabelled training samples and can be employed in an efficient active learning workflow. Using a variational dropout-based entropy measure of uncertainty in the workflow speeds up the learning process by roughly 45%. Finally, we utilise our model to segment whole-slide images of colorectal tissue and compute segmentation-based spatial statistics.

ConspectusThe escalating threat of antimicrobial resistance (AMR) poses a significant global health crisis, potentially surpassing cancer as a leading cause of death by 2050. Traditional antibiotic discovery methods have not kept pace with the rapidly evolving resistance mechanisms of pathogens, highlighting the urgent need for novel therapeutic strategies. In this context, antimicrobial peptides (AMPs) represent a promising class of therapeutics due to their selectivity toward bacteria and slower induction of resistance compared to classical, small molecule antibiotics. However, designing effective AMPs remains challenging because of the vast combinatorial sequence space and the need to balance efficacy with low toxicity. Addressing this issue is of paramount importance for chemists and researchers dedicated to developing next-generation antimicrobial agents.Artificial intelligence (AI) presents a powerful tool to revolutionize AMP discovery. By leveraging AI, we can navigate the immense sequence space more efficiently, identifying peptides with optimal therapeutic properties. This Account explores the emerging application of AI in AMP discovery, focusing on two primary strategies: AMP mining, and AMP generation, as well as the use of discriminative methods as a valuable toolbox.AMP mining involves scanning biological sequences to identify potential AMPs. Discriminative models are then used to predict the activity and toxicity of these peptides. This approach has successfully identified numerous promising candidates, which were subsequently validated experimentally, demonstrating the potential of AI in AMP design and discovery.AMP generation, on the other hand, creates novel peptide sequences by learning from existing data through generative modeling. This class of models optimizes for desired properties, such as increased activity and reduced toxicity, potentially producing synthetic peptides that surpass naturally occurring ones. Despite the risk of generating unrealistic sequences, generative models hold the promise of accelerating the discovery of highly effective and highly novel and diverse AMPs.In this Account, we describe the technical challenges and advancements in these AI-based approaches. We discuss the importance of integrating various data sources and the role of advanced algorithms in refining peptide predictions. Additionally, we highlight the future potential of AI to not only expedite the discovery process but also to uncover peptides with unprecedented properties, paving the way for next-generation antimicrobial therapies.In conclusion, the synergy between AI and AMP discovery opens new frontiers in the fight against AMR. By harnessing the power of AI, we can design novel peptides that are both highly effective and safe, offering hope for a future where AMR is no longer a looming threat. Our paper underscores the transformative potential of AI in drug discovery, advocating for its continued integration into biomedical research.

How will the coronavirus disease 2019 (COVID-19) pandemic develop in the coming months and years? Based on an expert survey, we examine key aspects that are likely to influence the COVID-19 pandemic in Europe. The challenges and developments will strongly depend on the progress of national and global vaccination programs, the emergence and spread of variants of concern (VOCs), and public responses to non-pharmaceutical interventions (NPIs). In the short term, many people remain unvaccinated, VOCs continue to emerge and spread, and mobility and population mixing are expected to increase. Therefore, lifting restrictions too much and too early risk another damaging wave. This challenge remains despite the reduced opportunities for transmission given vaccination progress and reduced indoor mixing in summer 2021. In autumn 2021, increased indoor activity might accelerate the spread again, whilst a necessary reintroduction of NPIs might be too slow. The incidence may strongly rise again, possibly filling intensive care units, if vaccination levels are not high enough. A moderate, adaptive level of NPIs will thus remain necessary. These epidemiological aspects combined with economic, social, and health-related consequences provide a more holistic perspective on the future of the COVID-19 pandemic.

In large collections of tumor samples, it has been observed that sets of genes that are commonly involved in the same cancer pathways tend not to occur mutated together in the same patient. Such gene sets form mutually exclusive patterns of gene alterations in cancer genomic data. Computational approaches that detect mutually exclusive gene sets, rank and test candidate alteration patterns by rewarding the number of samples the pattern covers and by punishing its impurity, i.e., additional alterations that violate strict mutual exclusivity. However, the extant approaches do not account for possible observation errors. In practice, false negatives and especially false positives can severely bias evaluation and ranking of alteration patterns. To address these limitations, we develop a fully probabilistic, generative model of mutual exclusivity, explicitly taking coverage, impurity, as well as error rates into account, and devise efficient algorithms for parameter estimation and pattern ranking. Based on this model, we derive a statistical test of mutual exclusivity by comparing its likelihood to the null model that assumes independent gene alterations. Using extensive simulations, the new test is shown to be more powerful than a permutation test applied previously. When applied to detect mutual exclusivity patterns in glioblastoma and in pan-cancer data from twelve tumor types, we identify several significant patterns that are biologically relevant, most of which would not be detected by previous approaches. Our statistical modeling framework of mutual exclusivity provides increased flexibility and power to detect cancer pathways from genomic alteration data in the presence of noise. A summary of this paper appears in the proceedings of the RECOMB 2014 conference, April 2–5. Tumor DNA carries multiple alterations, including somatic point mutations, amplifications, and deletions. It is challenging to identify the disease-causing alterations from the plethora of random ones, and to delineate their functional relations and involvement in common pathways. One solution for this task is inspired by the observation that genes from the same cancer pathway tend not to be altered together in each patient, and thus form patterns of mutually exclusive alterations across patients. Mutual exclusivity may arise, because alteration of only one pathway component is sufficient to deregulate the entire process. Detecting such patterns is an important step in de novo identification of cancerous pathways and potential treatment targets. However, the task is complicated by errors in the data, due to measurement noise, false mutation calls and their misinterpretation. Here, we propose a fully probabilistic, generative model of mutually exclusive patterns accounting for observation errors, with interpretable parameters that allow proper evaluation of patterns, free of error bias. Within our statistical framework, we develop efficient algorithms for parameter estimation and pattern ranking, together with a statistical test for mutual exclusivity, providing more flexibility and power than procedures applied previously.