Announcements

We had the pleasure of speaking with Dr. Gang Wang, who is the corresponding author of the cover article published in Volume 33, Issue 1 of Current Oncology (ISSN: 1718-7729). Here, he will share insights into his academic journey, research focus, and the motivation behind his recent work.

“Machine Learning in Biomarker-Driven Precision Oncology: Automated Immunohistochemistry Scoring and Emerging Directions in Genitourinary Cancers”
by Matthew Yap, Ioana-Maria Mihai and Gang Wang
Curr. Oncol. 2026, 33(1), 31; https://doi.org/10.3390/curroncol33010031
Available online: https://www.mdpi.com/1718-7729/33/1/31

Dr. Gang Wang is a clinical pathologist at BC Cancer and a Clinical Professor at the Department of Pathology and Laboratory Medicine at the University of British Columbia. His clinical and research work focuses on genitourinary malignancies, with an emphasis on biomarker development and precision oncology.

Dr. Wang’s research program centers on identifying and validating tissue-based biomarkers that predict disease progression and treatment response, particularly in bladder, prostate, and renal cancers. His work increasingly integrates digital pathology and artificial intelligence to enable quantitative, reproducible biomarker assessment and to support personalized treatment strategies. He has led and collaborated on multiple funded projects, including AI-driven approaches for biomarker discovery and prediction of therapy response.

The following is an interview with Dr. Wang:

1. Could you please briefly introduce the main research content of the published paper?

This review really focuses on a very practical problem in pathology—how we can make biomarker assessment more consistent and quantitative. Immunohistochemistry is something we rely on every day in clinical practice, but it does have well-known limitations, especially around variability between observers and across laboratories.

In the paper, we look at how machine learning, particularly within digital pathology, can help address these issues by enabling automated and reproducible scoring of biomarkers on whole-slide images. We first discuss areas where this is already quite mature—such as ER/PR, HER2, PD-L1, and Ki-67—and then shift toward emerging applications in genitourinary cancers.

A big part of the message is that while the technology is clearly promising and increasingly robust, there’s still a gap between technical capability and clinical implementation. Bridging that gap—through validation, standardization, and workflow integration—is really the next step.

2. Could you tell us a little bit about your current research?

My work is broadly in precision oncology, with a particular focus on genitourinary cancers. I’m very interested in how we can better use the data we already generate—whether it’s pathology slides, imaging, or clinical information—to improve prediction of treatment response and outcomes.

A large part of my research involves digital pathology and AI, especially around quantitative biomarker assessment. At the same time, I’ve been increasingly working on integrating different data types—for example, combining pathology with imaging or clinical data—to build more comprehensive, clinically relevant models.

Because I’m also actively involved in clinical service and departmental leadership; I tend to approach research with a strong emphasis on translation. The goal is not just to develop models, but to make sure they can actually be used in practice and improve patient care.

3. How do you evaluate research trends in this field, and what advice would you give to early career researchers who are interested in this research area?

The field has evolved quite a bit over the past few years. Earlier work was often focused on developing algorithms and demonstrating performance, but now there’s a clear shift toward clinical applicability—things like reproducibility, external validation, and integration into real workflows.

There’s also a growing recognition that no single data type is sufficient. The future is really in multimodal approaches—bringing together pathology, imaging, and molecular data to better reflect the biology of the disease.

For early career researchers, I think one of the most important things is to stay grounded in clinically meaningful questions. It’s easy to get drawn into technical aspects, but the most impactful work usually comes from addressing real clinical needs. Building strong collaborations is also essential because this is inherently a multidisciplinary field. And finally, paying attention to data quality and validation is critical—those are often the hardest parts, but also the most important.

4. Why did you choose Current Oncology as a platform for publishing your work, and how was your experience? Would you consider publishing your future research in Current Oncology?

We chose Current Oncology mainly because of its clinical focus and broad audience. Our work sits at the intersection of pathology, oncology, and AI, so it was important to publish somewhere that reaches clinicians as well as researchers.

The experience was very positive. The review process was efficient, and the feedback was constructive. Overall, it felt like a supportive environment for this type of translational work. I would certainly consider publishing there again, especially for projects that have a strong clinical component.

5. How do you think open access way of publishing impacts authors?

I think open access has had a very positive impact overall. It allows research to be accessed much more widely, which is particularly important in fields like oncology where findings can have direct clinical implications.

From an author’s perspective, it definitely helps with visibility and dissemination. At the same time, there are practical considerations around publication costs, which can be a barrier for some groups. So while the model is very beneficial in terms of access, there’s still work to be done to make it equitable.

6. In your opinion, which research topics will be of particular interest to the research community in the coming years?

I think we’ll continue to see strong interest in multimodal approaches that combine different types of data to better understand disease biology and predict outcomes. Digital pathology and computational analysis of tissue will remain a major area, especially as we move toward more quantitative and standardized assessments.

Another important direction is the tumor microenvironment and spatial biology—understanding not just what biomarkers are present, but how they are organized and interact within tissue.

But perhaps, most importantly, there will be increasing focus on implementation—how to take these tools and actually use them in clinical practice. That includes validation, regulation, and workflow integration. In the end, the real impact will come from tools that can reliably support clinical decision-making and improve patient outcomes.