T cells are at the centre of adaptive immunity, protecting the organism against infection and cancer. T-cell receptors (TCRs), expressed on the surface of T cells, enable the recognition of target cells through interactions with peptides presented by major histocompatibility complex (pMHC) molecules. Reliable, large-scale mapping of TCRs to their cognate pMHCs remains a holy grail of modern systems immunology, with far-reaching implications for cancer immunotherapy, vaccine development, and the understanding and treatment of autoimmune diseases. While exhaustive experimental mapping remains intractable due to the enormous combinatorial sequence space of TCRs and pMHCs, computational approaches offer a promising alternative. Consequently, we have witnessed increasingly sophisticated computational models of TCR–antigen specificity, from small neural networks to deep generative models and large protein language models. However, several independent benchmarks have shown that these models, despite their size and sophistication, largely fail to generalise to TCRs or pMHCs not present in the data available during model development. Here, we investigate possible reasons for this and suggest a path forward to generalisable TCR–pMHC prediction. First, our analysis of the largest public repositories of TCR–pMHC data reveals significant biases towards a small number of antigens and MHC molecules, sparse sampling of TCR sequence space per pMHC, as well as inconsistencies and inaccuracies in data collation. Second, we show the importance of carefully setting up model evaluation to measure discrimination based on antigen specificity instead of confounding factors present in the evaluation data. Finally, we highlight the need for and propose how best to match the evaluation metric with the specific downstream application of the predictions. Our investigation suggests that we, as a community, need more representative and better curated data, and a robust set of metrics and benchmarks to guide future model development towards generalisable TCR–pMHC specificity prediction.
Supporting data, adapters, predictions and code for the article *Low-Cost LoRA Fine-Tuning of Small Language Models for Multi-Step Arithmetic Reasoning* by Jake O'Grady, Asena Isik Gürhan, Chee Fong Ting and Effirul Ramlan (University of Galway). We generated 20,000 GSM8K-derived arithmetic problems with step-by-step s...
O'Grady, Jake, Gürhan, Asena Isik, Chee, Fong Ting et al.· Zenodo (CERN European Organi...· 465 citations
The results are packaged in the Greenfield Startup Model (GSM), which explains the priority of startups to release the product as quickly as possible, and the need to shorten time-to-market, by speeding up the development through low-precision engineering activities.
Carmine Giardino, Nicolò Paternoster, M. Unterkalmsteiner et al.· IEEE Transactions on Softwar...· 178 citations· ⚡14
Software startup companies develop innovative, software-intensive products within limited timeframes and with few resources, searching for sustainable and scalable business models.
M. Unterkalmsteiner, P. Abrahamsson, Xiaofeng Wang et al.· e-Informatica Software Engin...· 157 citations· ⚡17
This study conducts a case survey study based on the secondary data of the major pivots happened in 49 software startups, and demonstrates that customer need pivot is the most common among all pivot types.
Sohaib Shahid Bajwa, Xiaofeng Wang, Anh Nguyen-Duc et al.· Empirical Software Engineeri...· 127 citations· ⚡15
The comparison of adopter and non-adopter sample reveals three potential adoption inhibitor, security, data privacy, and portability, which underlines the importance of the technical and security perspectives for research investigating the adoption of technology.
Nattakarn Phaphoom, Xiaofeng Wang, S. Samuel et al.· Journal of Systems and Softw...· 111 citations· ⚡8
Objective There is dearth of information on the timeliness of antenatal care (ANC) uptake. This study aimed to determine the timely ANC uptake by a medically trained provider (MTP) as per the World Health Organization (WHO) recommendations and the country guideline. Methods Cross-sectional survey was done with 2,731 wo...
B. Sarker, Musfikur Rahman, T. Rahman et al.· PLoS ONE· 89 citations· ⚡7
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Senior Research Scientist Jim Glass discusses how his MIT-IBM Computing Research Lab collaboration connects perception and language, and addresses the shortcoming of current models.
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
Enforcing physics-based constraints prevents AI models from generating unreliable predictions for complex nonlinear systems in weather, climate, and turbulent flows.
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.