Kecheng Lei

Glioblastomas are aggressive, heterogeneous tumors that present significant challenges in both diagnosis and treatment. Despite advances in surgical resection, radiotherapy, and chemotherapy with temozolomide (TMZ), the prognosis for glioblastoma patients remains poor, largely due to tumor heterogeneity and resistance mechanisms, such as genetic mutations in DNA repair pathways. To address these specific heterogenous qualities of glioblastoma, single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool for characterizing glioblastoma tumors, enabling the identification of subpopulations that respond differently to treatment. However, utilizing the vast amount of data generated by scRNA-seq poses challenges in clinical applications. To overcome this challenge, computational models have been introduced to more effectively process patient scRNA-seq data into more digestible information for clinicians. More specifically, advanced deep learning approaches show promise for processing and analyzing patient scRNA-seq data, enhancing informed treatment approaches for highly heterogenous glioblastoma. This review aims to explain how scRNA-seq can be used to identify important areas of glioblastoma treatment resistance, evaluate current glioblastoma scRNA-seq-based deep learning models, and outline relevant training datasets to overcome patient scRNA-seq data availability limitations. Ultimately, these deep learning models can be utilized by researchers and clinicians to provide more informed and precise treatment to glioblastoma patients.

Schwannomatosis (SWN) is a rare genetic condition characterized by the development of benign schwannomas along peripheral and spinal nerves, and this tumor

The blood-brain barrier (BBB), crucial for central nervous system (CNS) homeostasis, poses challenges for drug delivery in CNS diseases due to selective permeability. Because of this difficulty, there are limited treatments developed for CNS diseases. As a solution, computational models can be implemented in treatment development to enable rapid screening of drug permeability, saving time and resources. This study explores machine learning, deep learning, and transfer learning models to predict the BBB permeability of drug molecules, validated through an in vitro assay known as Parallel Artificial Membrane Permeability Assay-BBB (PAMPA-BBB). Using the Blood-Brain Barrier Database (B3DB) of ∼ 8,000 compounds of known BBB permeability, classification models including support vector machines (SVMs), deep neural networks (DNNs), direct message passing neural networks (D-MPNNs), and transfer learning with quantum chemical properties were developed. Experimental validation with 18 compounds from the Emory Enriched Bioactive Library (EEBL), a library containing 1,018 FDA-approved pharmacologically active compounds of known activity, highlighted PAMPA-BBB as a robust validation method. The SVM model with combined 2D RDKit and Morgan fingerprint molecular representation achieved high performance (accuracy: 89.08%) on the B3DB test set. The best-performing models for the 18 EEBL compounds were transfer learning models. In particular, the model trained on the QM9-extended polarizability property correctly classified 17 out of 18 compounds, while the model trained on the QM9-extended dipole moment property achieved correct classification across all 18 experimental compounds. Additional analyses demonstrated that QC-based transfer learning provides complementary predictive value beyond traditional molecular descriptors such as LogP and molecular weight. QC-pretrained models achieved higher accuracy and ROC-AUC on both the B3DB and external PAMPA test sets, with performance remaining robust even after descriptor ablation. Moreover, QC-pretrained models outperformed the baseline of P-glycoprotein (P-gp) inhibition, underscoring the unique contribution of quantum-derived representations to BBB permeability prediction. Therefore, this study motivates the synergy of computational and experimental methods in enabling faster, more cost-effective, and targeted identification of CNS-active or CNS-sparing drugs.

Schwannomatosis is a non‑cancerous disorder causing peripheral nerve sheath tumors (schwannomas), often leading to chronic pain. It is linked to loss of SWI/SNF related, matrix associated, actin dependent regulator of chromatin subfamily B member 1 (SMARCB1) or leucine zipper‑transcription regulator 1 (LTZR1) gene function, though some patients may initially show minor mutations or no clinical signs, resulting in misdiagnosis, missed assessments, increased recurrence risk, unawareness of malignancy and overlooked genetic counseling during pregnancy. The present study reports a patient with a sporadic synonymous mutation in the SMARCB1 gene [SNP c.1032 C>T (p.Gly344Gly {GGC>GGT}) in exon 8]. This patient, a 53‑year‑old female with an 8‑year history of schwannomatosis, presented to the neurosurgical department for recurrent tumor removal. Tumor tissue was analyzed using immunohistochemistry, hematoxylin and eosin staining, and enzyme‑linked immunosorbent assay. Initially, the clinical impact of the SMARCB1 mutation on schwannomatosis was unclear. However, resected schwannomas showed 10‑60% mosaic loss of nuclear SMARCB1 protein, with protein assays confirming low SMARCB1 levels, particularly in the distal thigh schwannoma. This case highlights the tumorigenic potential of SMARCB1 single nucleotide polymorphisms, emphasizing the need for multimodal diagnosis, long‑term follow‑up, awareness of recurrence and malignancy, and timely surgical planning in schwannomatosis patients.

Background: Spinal cord glioma (SCG) is considered an orphan disease that lacks effective treatment options with margins that are surgically inaccessible and an overall paucity of literature on the topic. The tumor microenvironment is a critical factor to consider in treatment and modeling design, especially with respect to the unresectable tumor edge. Recently, our group developed a high-grade spinal cord glioma (SCG) model in Göttingen minipigs. Methods: Immunofluorescence and ELISA were performed to explore the microenvironmental features and inflammation cytokines in this minipig SCG model. Protein carbonyl assay and GSH/GSSG assay were analyzed in the core and edge lesions in the minipig SCG model. The primary core and edge cells proliferation rate were shown in vitro, and the xenograft model in vivo. Results: We identified an elevated Ki-67 proliferative index, vascular and pericyte markers, CD31 and desmin in the tumor edge as compared to the tumor core. In addition, we found that the tumor edge demonstrated increased pro-inflammatory and gliomagenic cytokines including TNF-α, IL-1β, and IL-6. Furthermore, the mediation of oxidative stress is upregulated in the tumor edge. Hypoxic markers had statistically significant increased staining in the tumor core, but were notably still present in the tumor edge. The edge cells cultures derived from SCG biopsy also demonstrated an increased proliferative rate compared to core cell cultures in a xenotransplantation model. Conclusions: Our study demonstrates heterogeneity in microenvironmental features in our minipig model of high-grade SCG, with a phenotype at the edge showing increased oxidative stress, proliferation, inflammatory cytokines, neovascularization, and decreased but present staining for hypoxic markers. These findings support the utility of this model as a means for investigating therapeutic approaches targeting the more aggressive and surgically unresectable tumor border.