ZCZongqing Chen

Zongqing Chen

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Zongqing Chen has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Information regimes in population-graph neuroimaging: cohort context and implementation-dependent evaluation sensitivity

    by Zongqing Chen, Biantian Yu, Keliang Wan, Qian Zhang, Fanghong Zhang, Ning Zhong, Hongzhi Kuai

    Population-graph models aggregate a query subject with an unlabeled cohort, so their reported performance can depend on the evaluation regime rather than on predictive information alone. Evaluation context has two separable axes: cohort visibility during training and the context available at inference . We study the training-time axis on an ABIDE-I cohort of 871 subjects (20 acquisition sites), comparing two population-graph implementations: a learned/adaptive graph (EV-GCN) and a static weighted graph (Parisot-GCN). Within each implementation the cohort, connectivity features, outer splits and training and selection rules are held fixed, and only the information available to the graph varies. The primary estimand is the implementation-by-training-context interaction, the difference between the P0-to-P1 AUC changes of the two implementations (ΔΔAUC). Across the two preselected outer splits (1024 and 2024), whose training and selection rules were fixed before the run, the direction is consistent and positive, with observed inter-action range 0.06285–0.11967; the earlier audited split 666 shows the same direction and is reported as historical support, because its execution identity cannot be established to the same standard. Uncertainty is assessed within each split by paired subject and site-cluster bootstrap resampling; the intervals are conditional on the fixed partitions and the trained checkpoints. Splits are replication units: they are not pooled and no cross-split average is reported. These findings tie reported performance to the evaluation information regime in the two implementations compared, and motivate explicit reporting of cohort visibility.

  • Open Access

    Reliable Evaluation of Transductive Population Graph Neural Networks for Multisite Autism fMRI

    by Keliang Wan, Zongqing Chen, Guixian Liu, Biantian Yu, Qian Zhang, Fanghong Zhang, Ning Zhong, Hongzhi Kuai

    Reliable population-graph evaluation requires separating cohort-conditioned discrimination from performance at an unseen site. We evaluate a recovered site-aware graph neural network in ABIDE-I (871 participants, 20 sites), distinguishing archived intervention results from newly recomputed controls. Archived cohort AUC was approximately 0.94, with high discrimination retained by site-only connectivity. A reconstructed ten-fold empirical site-prior classifier achieved pooled out-of-fold AUC 0.506 (95% site-resampling interval [0.418, 0.546]); simple site proportions therefore did not reproduce the high cohort result. In a budget-matched support-location experiment, the across-site mean AUC difference was +0.252 [0.184, 0.322] with directed edges but −0.003 [−0.020, 0.015] after symmetrisation, demonstrating implementation sensitivity rather than a stable support-location advantage. A supplementary leave-one-site-out analysis compared scoring-time population-edge access after the same source-site training procedure. Mean site-macro AUC was 0.577 with access and 0.580 without it; the paired difference was −0.0037 [−0.0179, 0.0111]. These observations do not establish equivalence or a complete mechanism. Explicit access contracts, compatible estimators and run-level provenance are necessary to interpret high transductive cohort performance.


  • Open Access

    Interpretable feature extraction and dimensionality reduction in ESM2 for protein localization prediction

    by Zeyu Luo, Rui Wang, Yawen Sun, Junhao Liu, Zongqing Chen, Yu-Juan Zhang

    As the application of large language models (LLMs) has broadened into the realm of biological predictions, leveraging their capacity for self-supervised learning to create feature representations of amino acid sequences, these models have set a new benchmark in tackling downstream challenges, such as subcellular localization. However, previous studies have primarily focused on either the structural design of models or differing strategies for fine-tuning, largely overlooking investigations into the nature of the features derived from LLMs. In this research, we propose different ESM2 representation extraction strategies, considering both the character type and position within the ESM2 input sequence. Using model dimensionality reduction, predictive analysis and interpretability techniques, we have illuminated potential associations between diverse feature types and specific subcellular localizations. Particularly, the prediction of Mitochondrion and Golgi apparatus prefer segments feature closer to the N-terminal, and phosphorylation site-based features could mirror phosphorylation properties. We also evaluate the prediction performance and interpretability robustness of Random Forest and Deep Neural Networks with varied feature inputs. This work offers novel insights into maximizing LLMs’ utility, understanding their mechanisms, and extracting biological domain knowledge. Furthermore, we have made the code, feature extraction API, and all relevant materials available at https://github.com/yujuan-zhang/feature-representation-for-LLMs.


  • Open Access

    On universal partial words

    by Herman Z. Q. Chen, Sergey Kitaev, Torsten Mütze, Brian Y. Sun

    A universal word for a finite alphabet $A$ and some integer $n\geq 1$ is a word over $A$ such that every word in $A^n$ appears exactly once as a subword (cyclically or linearly). It is well-known and easy to prove that universal words exist for any $A$ and $n$. In this work we initiate the systematic study of universal partial words. These are words that in addition to the letters from $A$ may contain an arbitrary number of occurrences of a special `joker' symbol $\Diamond\notin A$, which can be substituted by any symbol from $A$. For example, $u=0\Diamond 011100$ is a linear partial word for the binary alphabet $A=\{0,1\}$ and for $n=3$ (e.g., the first three letters of $u$ yield the subwords $000$ and $010$). We present results on the existence and non-existence of linear and cyclic universal partial words in different situations (depending on the number of $\Diamond$s and their positions), including various explicit constructions. We also provide numerous examples of universal partial words that we found with the help of a computer.