MOTIVATION: Reliable TCR-epitope binding prediction models are essential for development of adoptive T cell therapy and vaccine design. These models often struggle with false positives, which can be attributed to the limited data coverage in existing negative sample datasets. Common strategies for generating negative samples, such as pairing with background T cell receptors (TCRs) or shuffling within pairs, fail to account for model-specific vulnerabilities or biologically implausible sequences. RESULTS: To address these challenges, we propose an iterative attack-and-defend framework that systematically identifies and mitigates weaknesses in TCR-epitope prediction models. During the attack phase, a reinforcement learning from AI feedback (RLAIF) framework is used to attack a prediction model by generating biologically implausible sequences that can easily deceive the model. During the defense phase, these identified false positives are incorporated into fine-tuning dataset, enhancing the model's ability to detect false positives. A comprehensive adversarial negative dataset can be obtained by iteratively attacking and defending the model. This dataset can be directly used to improve model robustness, eliminating the need for users to conduct their own attack-and-defend cycles. We apply our framework to five existing binding prediction models, spanning diverse architectures and embedding strategies to show its efficacy. Experimental results show that our approach significantly improves these models' ability to detect adversarial false positives. The combined dataset constructed from these experiments also provides a benchmarking tool to evaluate and refine prediction models. Our framework offers a new approach for improving model robustness in other biological tasks where negative sampling is inherently limited. AVAILABILITY AND IMPLEMENTATION: The curated dataset and code are available at a public repository (https://github.com/Lee-CBG/BAP_Attack_n_Defend).

T cell receptors (TCRs) are critical components of adaptive immune systems, responsible for responding to threats by recognizing epitope sequences presented on host cell surface. Computational prediction of binding affinity between TCRs and epitope sequences using machine/deep learning has attracted intense attention recently. However, its success is hindered by the lack of large collections of annotated TCR-epitope pairs. Annotating their binding affinity requires expensive and time-consuming wet-lab evaluation. To reduce annotation cost, we present ActiveTCR, a framework that incorporates active learning and TCR-epitope binding affinity prediction models. Starting with a small set of labeled training pairs, ActiveTCR iteratively searches for unlabeled TCR-epitope pairs that are "worthy" for annotation. It aims to maximize performance gains while minimizing the cost of annotation. We compared four query strategies with a random sampling baseline and demonstrated that ActiveTCR reduces annotation costs by approximately 40%. Furthermore, we showed that providing ground truth labels of TCR-epitope pairs to query strategies can help identify and reduce more than 40% redundancy among already annotated pairs without compromising model performance, enabling users to train equally powerful prediction models with less training data. Our work is the first systematic investigation of data optimization for TCR-epitope binding affinity prediction.

Interpretable machine learning has gained much attention recently. Briefness and comprehensiveness are necessary in order to provide a large amount of information concisely when explaining a black-box decision system. However, existing interpretable machine learning methods fail to consider briefness and comprehensiveness simultaneously, leading to redundant explanations. We propose the variational information bottleneck for interpretation, VIBI, a system-agnostic interpretable method that provides a brief but comprehensive explanation. VIBI adopts an information theoretic principle, information bottleneck principle, as a criterion for finding such explanations. For each instance, VIBI selects key features that are maximally compressed about an input (briefness), and informative about a decision made by a black-box system on that input (comprehensive). We evaluate VIBI on three datasets and compare with state-of-the-art interpretable machine learning methods in terms of both interpretability and fidelity evaluated by human and quantitative metrics.

While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those relations. Most recent studies rely on black-box models, which are not as linguistically insightful as desired. On the other hand, earlier studies use rather simple lexical features, missing logical relations between statements. To overcome these limitations, our work classifies argumentative relations based on four logical and theory-informed mechanisms between two statements, namely, (i) factual consistency, (ii) sentiment coherence, (iii) causal relation, and (iv) normative relation. We demonstrate that our operationalization of these logical mechanisms classifies argumentative relations without directly training on data labeled with the relations, significantly better than several unsupervised baselines. We further demonstrate that these mechanisms also improve supervised classifiers through representation learning.

Finding attackable sentences in an argument is the first step toward successful refutation in argumentation.We present a first large-scale analysis of sentence attackability in online arguments.We analyze driving reasons for attacks in argumentation and identify relevant characteristics of sentences.We demonstrate that a sentence's attackability is associated with many of these characteristics regarding the sentence's content, proposition types, and tone, and that an external knowledge source can provide useful information about attackability.Building on these findings, we demonstrate that machine learning models can automatically detect attackable sentences in arguments, significantly better than several baselines and comparably well to laypeople. 1

Heterogeneity of complex human diseases makes it difficult to control and treat diseases effectively. Recent clinical efforts involve redefining subtypes of the diseases using cluster analysis. However, follow-up studies for the new clusters/subtypes identified from these efforts have been limited by the fact that clinical datasets collected from different times and cohorts often have different subjects and variables. A typical way to address this problem is to use only the common subjects and the variables among the datasets for analysis, which will inevitably result in loss of power and information. In this work, we developed a supervised learning strategy and a new classification algorithm called Naïve Bayes ensemble, which can classify unlabeled subjects from a new dataset into the clusters/subtypes previously identified from an earlier dataset so that one can make full use of the new dataset for further analysis. The Naïve Bayes ensemble employs a probability framework to summarize votes from single classifiers and take into account misclassification rates of each class predicted by each single classifier. We also propose a procedure to automatically select single classifiers to be included in the ensemble, which are based on both classification performance and the diversity of the single classifiers. The Naïve Bayes ensemble outperforms 7 single classifiers and other ensemble methods when we evaluated their performance using leave-one-out cross validation (LOOCV) on our asthma clinical datasets. Furthermore, using biological functional validation, our results show that the supervised learning strategy and the Naïve Bayes ensemble we proposed can indeed greatly increase the power of the downstream analysis and help yield biologically/clinically meaningful results.