Deep learning transcriptomic model for prediction of pan-drug chemotherapeutic sensitivity

The emergence of precision oncology approaches has begun to inform clinical decision-making in diagnostic, prognostic, and treatment contexts. High-throughput technology has enabled machine learning algorithms to use the molecular characteristics of tumors to generate personalized therapies. However, precision oncology studies have yet to develop a predictive biomarker incorporating pan-cancer gene expression profiles to stratify tumors into similar drug sensitivity profiles. Here we show that a neural network with ten hidden layers accurately classifies pancancer cell lines into two distinct chemotherapeutic response groups based on a pan-drug dataset with 89.0% accuracy (AUC = 0.904). Using unsupervised clustering algorithms, we found a cohort of cell line gene expression data from the Genomics of Drug Sensitivity in Cancer could be clustered into two response groups with significant differences in pan-drug chemotherapeutic sensitivity. After applying the Boruta feature selection algorithm to this dataset, a deep learning model was developed to predict chemotherapeutic response groups. The model’s high classification efficacy validates our hypothesis that cell lines with similar gene expression profiles present similar pan-drug chemotherapeutic sensitivity. This finding provides evidence for the potential use of similar combinatorial biomarkers to select potent candidate drugs that maximize therapeutic response and minimize the cytotoxic burden. Future investigations should aim to recursively subcluster cell lines within the response clusters defined in this study to provide a higher resolution of potential patient response to chemotherapeutics.

Spatial Profiling Identifies Prognostic Features of Response to Adjuvant Therapy in Triple Negative Breast Cancer (TNBC)

Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer that has few effective treatment options due to its lack of targetable hormone receptors. Whilst the degree of tumour infiltrating lymphocytes (TILs) has been shown to associate with therapy response and prognosis, deeper characterization of the molecular diversity that may mediate chemotherapeutic response is lacking. Here we applied targeted proteomic analysis of both chemotherapy sensitive and resistant TNBC tissue samples by the Nanostring GeoMx Digital Spatial Platform (DSP). By quantifying 68 targets in the tumour and tumour microenvironment (TME) compartments and performing differential expression analysis between responsive and non-responsive tumours, we show that increased ER-alpha expression and decreased 4-1BB and MART1 within the stromal compartments is associated with adjuvant chemotherapy response. Similarly, higher expression of GZMA, STING and fibronectin and lower levels of CD80 were associated with response within tumour compartments. Univariate overall-survival (OS) analysis of stromal proteins supported these findings, with ER-alpha expression (HR=0.19, p=0.0012) associated with better OS while MART1 expression (HR=2.3, p=0.035) was indicative of poorer OS. Proteins within tumour compartments consistent with longer OS included PD-L1 (HR=0.53, p=0.023), FOXP3 (HR=0.5, p=0.026), GITR (HR=0.51, p=0.036), SMA (HR=0.59, p=0.043), while EPCAM (HR=1.7, p=0.045), and CD95 (HR=4.9, p=0.046) expression were associated with shorter OS. Our data provides early insights into the levels of these markers in the TNBC tumour microenvironment, and their association with chemotherapeutic response and patient survival.

SMARCB1 expression is a novel diagnostic and prognostic biomarker for osteosarcoma

Background: Although weak SMARCB1 expression is a known diagnostic and prognostic biomarker in several malignancies, its expression and clinical significance in osteosarcoma remain unknown. The aim of this study was to investigate SMARCB1 expression in osteosarcoma and its clinical significance with respect to chemosensitivity and prognosis. Methods: We obtained 114 specimens from 70 osteosarcoma patients to construct a tissue microarray (TMA) and assess SMARCB1 protein expression via immunohistochemistry. The mRNA expression of SMARCB1 was in silico analyzed using open-access RNA sequencing (RNA-Seq) and clinicopathological data provided by the Therapeutically Applicable Research to Generate Effective Treatments on Osteosarcoma (TARGET-OS) project. The correlations between SMARCB1 expression and clinical features were statistically analyzed. Results: Weak SMARCB1 expression occurred in 70% of the osteosarcoma patient specimens in the tissue microarray, and significantly correlated with poor neoadjuvant response as well as shorter overall and progression-free survival. In addition, mRNA in silico analysis confirmed SMARCB1 expression correlates with chemotherapeutic response and prognosis in osteosarcoma patients. Conclusion: To our knowledge, this study is the first to analyze SMARCB1 expression in osteosarcoma. SMARCB1 may serve as a novel diagnostic and prognostic biomarker in osteosarcoma.

Lack of PRAME Expression in Cutaneous T-Cell Lymphomas

Cutaneous T-cell lymphomas (CTCLs) are rare tumors with no established markers that can reliably distinguish between benign and malignant lesions. Preferentially Expressed Antigen in Melanoma (PRAME) is a cancer/testis antigen that is found in many solid and hematologic malignancies. PRAME overexpression typically portends a poor prognosis and lower chemotherapeutic response. To date, no studies have established a role for PRAME in CTCL. An analysis was performed on 47 cases definitively diagnosed as CTCL: 25 cases of mycosis fungoides, 2 of Sezary syndrome, 5 of CD30+ lymphoproliferative disorder, 7 of primary cutaneous anaplastic large T-cell lymphoma, 3 of primary cutaneous CD4+ small/medium T-cell lymphoproliferative disorder, 1 of subcutaneous panniculitis-like T-cell lymphoma, and 4 of angiocentric T-cell lymphoma. PRAME immunohistochemistry was completely negative in all cases. PRAME expression was not found in any CTCL subtypes, suggesting that the pathogenesis of CTCL is not mediated by PRAME. Further study is required to identify biomarkers that might aid in the diagnosis and prognostication of CTCLs.

The Relationship Between Gut Microbiome Features and Chemotherapy Response in Gastrointestinal Cancer

ObjectiveThe prognosis of advanced gastrointestinal cancer is poor. There are studies indicating that gut microbes might have the predictive ability to evaluate the outcome of cancer therapy, especially immunotherapy. There is limited evidence to date on the influence of microbes on chemotherapeutic response.DesignIn total, 130 patients with advanced or metastatic esophageal (n=40), gastric (n=46), and colorectal cancer (n=44) were enrolled. We included 147 healthy people as controls and used 16S rRNA sequencing to analyze the fecal microbiota.ResultsSignificant differences in the abundance of fecal microbiota between patients with gastrointestinal cancer and controls were identified. The abundance of Bacteroides fragilis, Escherichia coli, Akkermansia muciniphila, Clostridium hathewayi, and Alistipes finegoldii were significantly increased in the patient group. Faecalibacterium prausnitzii, Roseburia faecis, Clostridium clostridioforme, Blautia producta, Bifidobacterium adolescent, and Butyricicoccus pullicaecorum taxa were significantly more abundant in the controls. The amount of R. faecis in non-responders (NR) was more likely to decrease significantly after chemotherapy, while the amount mostly increased in responders (R) (P=0.040). The optimal abundance variation of R. faecis may be a predictor for distinguishing patients with PD from those with non-PD in all patients with gastrointestinal cancer, with a sensitivity of 75.0% and a specificity of 93.9%.ConclusionThe gut microbiome of patients with esophageal cancer, gastric cancer, and colorectal cancer differs from those of healthy people. The abundance alteration of R. faecis in patients with GI cancer might be a predictor of chemotherapy efficacy.

SPDR-2 Histopathological investigation of the oligodendroglial tumors resected following alkylating agent chemotherapy

Oligodendrogliomas, i.e., lower grade gliomas with 1p/19q codeletion, are often responsive to chemotherapy, however, those tumors eventually recur and life-limiting in the majority of patients despite initial chemotherapeutic response. We have been treating those patients with upfront chemotherapy and subsequent resection following tumor volume decrease since 2006. This study aimed to elucidate the histological changes and the mechanism of recurrence after alkylating agent chemotherapy in oligodendrogliomas. Fifteen oligodendrogliomas (Grade 2: 12, Grade 3: 3) resected following tumor volume decrease after alkylating agent chemotherapy were included and compared with their pre-chemotherapy specimens. Histological changes were investigated using hematoxylin-eosin staining, and changes in proliferative activity, status of glioma stem cells (GSCs), and tumor-infiltrating macrophages were assessed using immunohistochemistry. The frequent histological findings following chemotherapy included a sparse glial background, abundant foamy cell infiltration, gliosis, calcification, and nuclear degradation. The Ki-67/MIB-1 index decreased and the number of macrophages increased after chemotherapy. Moreover, the ratio of GSCs to total tumor cells increased after chemotherapy. GSCs and macrophages constitute the mechanism of resistance to and recurrence after alkylating agent chemotherapy in oligodendrogliomas.

Role of Surviving in Bladder Cancer: Issues to Be Overcome When Designing an Efficient Dual Nano-Therapy

Bladder cancer is the 10th most diagnosed cancer, with almost 10 M cancer deaths last year worldwide. Currently, chemotherapy is widely used as adjuvant therapy after surgical transurethral resection. Paclitaxel (PTX) is one of the most promising drugs, but cancer cells acquire resistance, causing failure of this treatment and increasing the recurrence of the disease. This poor chemotherapeutic response has been associated with the overexpression of the protein survivin. In this work, we present a novel dual nano-treatment for bladder cancer based on the hypothesis that the inhibition of survivin in cancer cells, using a siRNA gene therapy strategy, could decrease their resistance to PTX. For this purpose, two different polymeric nanoparticles were developed to encapsulate PTX and survivin siRNA independently. PTX nanoparticles showed sizes around 150 nm, with a paclitaxel loading of around 1.5%, that produced sustained tumor cell death. In parallel, siRNA nanoparticles, with similar sizes and loading efficiency of around 100%, achieved the oligonucleotide transfection and knocking down of survivin expression that also resulted in tumor cell death. However, dual treatment did not show the synergistic effect expected. The root cause of this issue was found to be the cell cycle arrest produced by nuclear survivin silencing, which is incompatible with PTX action. Therefore, we concluded that although the vastly reported role of survivin in bladder cancer, its silencing does not sensitize cells to currently applied chemotherapies.

METTL3 promotes homologous recombination repair and modulates chemotherapeutic response by regulating the EGF/Rad51 axis

METTL3 and N6-methyladenosine (m6A) are involved in many types of biological and pathological processes, including DNA repair. However, the function and mechanism of METTL3 in DNA repair and chemotherapeutic response remain largely unknown. In present study, we identified that METTL3 participates in the regulation of homologous recombination repair (HR), which further influences chemotherapeutic response in breast cancer (BC) cells. Knockdown of METTL3 sensitized BC cells to Adriamycin (ADR) treatment and increased accumulation of DNA damage. Mechanically, we demonstrated that inhibition of METTL3 impaired HR efficiency and increased ADR-induced DNA damage by regulating m6A modification of EGF/RAD51 axis. METTL3 promoted EGF expression through m6A modification, which further upregulated RAD51 expression, resulting in enhanced HR activity. We further demonstrated that the m6A "reader," YTHDC1, bound to the m6A modified EGF transcript and promoted EGF synthesis, which enhanced HR and cell survival during ADR treatment. Our findings reveal a pivotal mechanism of METTL3-mediated HR and chemotherapeutic drug response, which may contribute to cancer therapy.

Exploiting convergent evolution to derive a pan-cancer cisplatin sensitivity gene expression signature

Precision medicine offers remarkable potential for the treatment of cancer, but is largely focused on tumors that harbor actionable mutations. Gene expression signatures can expand the scope of precision medicine by predicting response to traditional(cytotoxic) chemotherapy agents without relying on changes in mutational status. We present a novel signature extraction method, inspired by the principle of convergent evolution, which states that tumors with disparate genetic backgrounds may evolve similar phenotypes independently. This evolutionary-informed method can be utilized to produce signatures predictive of response to over 200 chemotherapeutic drugs found in the Genomics of Drug Sensitivity in Cancer Database. Here, we demonstrate its use by extracting the Cisplatin Response Signature, CisSig, for use in predicting a common trait (sensitivity to cisplatin) across disparate tumor subtypes (epithelial-origin tumors). CisSig is predictive of cisplatin response within the cell lines and clinical trends in independent datasets of tumor samples. This novel methodology can be used to produce robust signatures for the prediction of traditional chemotherapeutic response, dramatically increasing the reach of personalized medicine in cancer.