A probabilistic graphical model is proposed, modeling the joint model parameter and multiplier evolution, with a hypervolume based likelihood, promoting multi-objective descent in structural risk minimization. We address multi-objective model parameter optimization via a surrogate single objective penalty loss with time-varying multipliers, equivalent to online scheduling of loss landscape. The multi-objective descent goal is dispatched hierarchically into a series of constraint optimization sub-problems with shrinking bounds according to Pareto dominance. The bound serves as setpoint for the low-level multiplier controller to schedule loss landscapes via output feedback of each loss term. Our method forms closed loop of model parameter dynamic, circumvents excessive memory requirements and extra computational burden of existing multi-objective deep learning methods, and is robust against controller hyperparameter variation, demonstrated on domain generalization tasks.

Multi-epitope vaccines (EVs) represent a versatile and promising approach for combating a wide range of diseases, including viral and bacterial infections, parasitic diseases, and cancer. A critical aspect of EV design is ensuring efficient proteasomal cleavage of the synthetic polypeptide to recover therapeutic epitopes for presentation to$\mathbf{T}$cells. This process is influenced by the selection and arrangement of epitopes, as well as the design of linkers joining them. Modern EV design frameworks leverage proteasomal cleavage predictors to optimize epitope recovery and vaccine efficacy. However, the predictive power of these tools remains a limiting factor, particularly for challenging cleavage sites such as N -terminals. In this work, we systematically review and benchmark recent advances in proteasomal cleavage prediction, focusing on deep learning-based methods. We evaluate a range of architectures, including MLPs, CNNs, LSTMs, and Transformers, alongside simpler baselines such as logistic regression. Our results demonstrate that while complex models achieve marginally higher predictive performance, simpler models remain competitive and offer significant computational efficiency. We also explore the impact of dataset size, window size, and training techniques, finding diminishing returns from increasingly larger datasets and more complex models. Notably, our benchmarking highlights substantial improvements in predicting N-terminal cleavage sites, which are often overlooked but critical for EV design. Our findings provide practical guidance for the development of nextgeneration proteasomal cleavage predictors and underscore the importance of considering the probabilistic nature of cleavage in EV design. By consolidating the state of the art and introducing efficient baselines, this work aims to advance the field of multiepitope vaccine design and support the development of more effective and personalized immunotherapies.11Code for all experiments is available at this repository: https://github.com/ziegleringo/cleavage_benchmark.

Neural network representations of simple models, such as linear regression, are being studied increasingly to better understand the underlying principles of deep learning algorithms. However, neural representations of distributional regression models, such as the Cox model, have received little attention so far. We close this gap by proposing a framework for distributional regression using inverse flow transformations (DRIFT), which includes neural representations of the aforementioned models. We empirically demonstrate that the neural representations of models in DRIFT can serve as a substitute for their classical statistical counterparts in several applications involving continuous, ordered, time-series, and survival outcomes. We confirm that models in DRIFT empirically match the performance of several statistical methods in terms of estimation of partial effects, prediction, and aleatoric uncertainty quantification. DRIFT covers both interpretable statistical models and flexible neural networks opening up new avenues in both statistical modeling and deep learning.

Semi-structured regression (SSR) models jointly learn the effect of structured (tabular) and unstructured (non-tabular) data through additive predictors and deep neural networks (DNNs), respectively. Inference in SSR models aims at deriving confidence intervals for the structured predictor, although current approaches ignore the variance of the DNN estimation of the unstructured effects. This results in an underestimation of the variance of the structured coefficients and, thus, an increase of Type-I error rates. To address this shortcoming, we present here a theoretical framework for structured inference in SSR models that incorporates the variance of the DNN estimate into confidence intervals for the structured predictor. By treating this estimate as a random offset with known variance, our formulation is agnostic to the specific deep uncertainty quantification method employed. Through numerical experiments and a practical application on a medical dataset, we show that our approach results in increased coverage of the true structured coefficients and thus a reduction in Type-I error rate compared to ignoring the variance of the neural network, naive ensembling of SSR models, and a variational inference baseline.

Deep learning has enabled outstanding progress on bioinformatics datasets and a variety of tasks, such as protein structure prediction, identification of regulatory regions, genome annotation, and interpretation of the noncoding genome. The layout and configuration of neural networks used for these tasks have mostly been developed manually by human experts, which is a time-consuming and error-prone process. Therefore, there is growing interest in automated neural architecture search (NAS) methods in bioinformatics. In this paper, we present a novel search space for NAS algorithms that operate on genome data, thus creating extensions for existing NAS algorithms for sequence data that we name Genome-DARTS, Genome-P-DARTS, Genome-BONAS, Genome-SH, and Genome-RS. Moreover, we introduce two novel NAS algorithms, CWP-DARTS and EDPDARTS, that build on and extend the idea of P-DARTS. We evaluate the presented methods and compare them to manually designed neural architectures on a widely used genome sequence machine learning task to show that NAS methods can be adapted well for bioinformatics sequence datasets. Our experiments show that architectures optimized by our NAS methods outperform manually developed architectures while having significantly fewer parameters.

Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). This selection often depends on the initial model fit on labeled data. Early overfitting might thus be propagated to the final model by selecting instances with overconfident but erroneous predictions, often referred to as confirmation bias. This paper introduces BPLS, a Bayesian framework for PLS that aims to mitigate this issue. At its core lies a criterion for selecting instances to label: an analytical approximation of the posterior predictive of pseudo-samples. We derive this selection criterion by proving Bayes-optimality of the posterior predictive of pseudo-samples. We further overcome computational hurdles by approximating the criterion analytically. Its relation to the marginal likelihood allows us to come up with an approximation based on Laplace’s method and the Gaussian integral. We empirically assess BPLS on simulated and real-world data. When faced with high-dimensional data prone to overfitting, BPLS outperforms traditional PLS methods.

MOTIVATION: Conceptually, epitope-based vaccine design poses two distinct problems: (i) selecting the best epitopes to elicit the strongest possible immune response and (ii) arranging and linking them through short spacer sequences to string-of-beads vaccines, so that their recovery likelihood during antigen processing is maximized. Current state-of-the-art approaches solve this design problem sequentially. Consequently, such approaches are unable to capture the inter-dependencies between the two design steps, usually emphasizing theoretical immunogenicity over correct vaccine processing, thus resulting in vaccines with less effective immunogenicity in vivo. RESULTS: In this work, we present a computational approach based on linear programming, called JessEV, that solves both design steps simultaneously, allowing to weigh the selection of a set of epitopes that have great immunogenic potential against their assembly into a string-of-beads construct that provides a high chance of recovery. We conducted Monte Carlo cleavage simulations to show that a fixed set of epitopes often cannot be assembled adequately, whereas selecting epitopes to accommodate proper cleavage requirements substantially improves their recovery probability and thus the effective immunogenicity, pathogen and population coverage of the resulting vaccines by at least 2-fold. AVAILABILITY AND IMPLEMENTATION: The software and the data analyzed are available at https://github.com/SchubertLab/JessEV. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Epitope-based vaccines have revolutionized vaccine research in the last decades. Due to their complex nature, bioinformatics plays a pivotal role in their development. However, existing algorithms address only specific parts of the design process or are unable to provide formal guarantees on the quality of the solution. We present a unifying formalism of the general epitope vaccine design problem that tackles all phases of the design process simultaneously and combines all prevalent design principles. We then demonstrate how to formulate the developed formalism as an integer linear program, which guarantees optimality of the designs. This makes it possible to explore new regions of the vaccine design space, analyze the trade-offs between the design phases, and balance the many requirements of vaccines.