Sparse group selection and analysis of function-related residue for protein-state recognition.

Machine learning methods have helped to advance wide range of scientific and technological field in recent years, including computational chemistry. As the chemical systems could become complex with high dimension, feature selection could be critical but challenging to develop reliable machine learning based prediction models, especially for proteins as bio-macromolecules. In this study, we applied sparse group lasso (SGL) method as a general feature selection method to develop classification model for an allosteric protein in different functional states. This results into a much improved model with comparable accuracy (Acc) and only 28 selected features comparing to 289 selected features from a previous study. The Acc achieves 91.50% with 1936 selected feature, which is far higher than that of baseline methods. In addition, grouping protein amino acids into secondary structures provides additional interpretability of the selected features. The selected features are verified as associated with key allosteric residues through comparison with both experimental and computational works about the model protein, and demonstrate the effectiveness and necessity of applying rigorous feature selection and evaluation methods on complex chemical systems.

PCAT6 mediates cellular biological functions in gastrointestinal stromal tumor via upregulation of PRDX5 and activation of Wnt pathway.

Gastrointestinal stromal tumor (GIST) is a common mesenchymal tumor in the gastrointestinal tract. Prostate cancer associated transcript 6 (PCAT6) is a long noncoding RNA (lncRNA) and plays a pivotal role in tumor formation. Present study was designed to explore the function of PCAT6 in GIST. Ki67 staining, colony formation and trypan blue staining assays revealed that PCAT6 boosted GIST cell proliferation but inhibited cell apoptosis. Also, sphere formation assay and Western blot uncovered the promoting role of PCAT6 in GIST stemness. Then, we identified that PCAT6 could activate Wnt/ß-catenin pathway. And the tumor facilitator role of Wnt/ß-catenin pathway was validated in the rescue assays. Next, miR-143-3p was identified as the downstream microRNA of PCAT6. Moreover, miR-143-3p itself served as a tumor suppressor in GIST. Subsequently, peroxiredoxin 5 (PRDX5) was verified as the target of miR-143-3p. PCAT6 promoted GIST cell proliferation and stemness via sponging miR-143-3p to upregulate PRDX5. In a word, PCAT6 promoted GIST cell proliferation and stemness but inhibited cell apoptosis via competing endogenous RNA pattern and activation of Wnt pathway, which might contribute to GIST treatment.

GWO+RuleFit: rule-based explainable machine-learning combined with heuristics to predict mid-treatment FDG PET response to chemoradiation for locally advanced non-small cell lung cancer.

Objective.Vital rules learned from fluorodeoxyglucose positron emission tomography (FDG-PET) radiomics of tumor subregional response can provide clinical decision support for precise treatment adaptation. We combined a rule-based machine learning (ML) model (RuleFit) with a heuristic algorithm (gray wolf optimizer, GWO) for mid-chemoradiation FDG-PET response prediction in patients with locally advanced non-small cell lung cancer.Approach.Tumors subregions were identified using K-means clustering. GWO+RuleFit consists of three main parts: (i) a random forest is constructed based on conventional features or radiomic features extracted from tumor regions or subregions in FDG-PET images, from which the initial rules are generated; (ii) GWO is used for iterative rule selection; (iii) the selected rules are fit to a linear model to make predictions about the target variable. Two target variables were considered: a binary response measure (ΔSUVmean ⩾ 20% decline) for classification and a continuous response measure (ΔSUVmean) for regression. GWO+RuleFit was benchmarked against common ML algorithms and RuleFit, with leave-one-out cross-validated performance evaluated by the area under the receiver operating characteristic curve (AUC) in classification and root-mean-square error (RMSE) in regression.Main results.GWO+RuleFit selected 15 rules from the radiomic feature dataset of 23 patients. For treatment response classification, GWO+RuleFit attained numerically better cross-validated performance than RuleFit across tumor regions and sets of features (AUC: 0.58-0.86 vs. 0.52-0.78,p= 0.170-0.925). GWO+Rulefit also had the best or second-best performance numerically compared to all other algorithms for all conditions. For treatment response regression prediction, GWO+RuleFit (RMSE: 0.162-0.192) performed better numerically for low-dimensional models (p= 0.097-0.614) and significantly better for high-dimensional models across all tumor regions except one (RMSE: 0.189-0.219,p< 0.004).Significance. The GWO+RuleFit selected rules were interpretable, highlighting distinct radiomic phenotypes that modulated treatment response. GWO+Rulefit achieved parsimonious models while maintaining utility for treatment response prediction, which can aid clinical decisions for patient risk stratification, treatment selection, and biologically driven adaptation. Clinical trial: NCT02773238.

Sensitivity analysis of FDG PET tumor voxel cluster radiomics and dosimetry for predicting mid-chemoradiation regional response of locally advanced lung cancer.

We investigated the sensitivity of regional tumor response prediction to variability in voxel clustering techniques, imaging features, and machine learning algorithms in 25 patients with locally advanced non-small cell lung cancer (LA-NSCLC) enrolled on the FLARE-RT clinical trial. Metabolic tumor volumes (MTV) from pre-chemoradiation (PETpre) and mid-chemoradiation fluorodeoxyglucose-positron emission tomography (FDG PET) images (PETmid) were subdivided into K-means or hierarchical voxel clusters by standardized uptake values (SUV) and 3D-positions. MTV cluster separability was evaluated by CH index, and morphologic changes were captured by Dice similarity and centroid Euclidean distance. PETpre conventional features included SUVmean, MTV/MTV cluster size, and mean radiation dose. PETpre radiomics consisted of 41 intensity histogram and 3D texture features (PET Oncology Radiomics Test Suite) extracted from MTV or MTV clusters. Machine learning models (multiple linear regression, support vector regression, logistic regression, support vector machines) of conventional features or radiomic features were constructed to predict PETmid response. Leave-one-out-cross-validated root-mean-squared-error (RMSE) for continuous response regression (ΔSUVmean) and area-under-receiver-operating-characteristic-curve (AUC) for binary response classification were calculated. K-means MTV 2-clusters (MTVhi, MTVlo) achieved maximum CH index separability (Friedman p < 0.001). Between PETpre and PETmid, MTV cluster pairs overlapped (Dice 0.70-0.87) and migrated 0.6-1.1 cm. PETmid ΔSUVmean response prediction was superior in MTV and MTVlo (RMSE = 0.17-0.21) compared to MTVhi (RMSE = 0.42-0.52, Friedman p < 0.001). PETmid ΔSUVmean response class prediction performance trended higher in MTVlo (AUC = 0.83-0.88) compared to MTVhi (AUC = 0.44-0.58, Friedman p = 0.052). Models were more sensitive to MTV/MTV cluster regions (Friedman p = 0.026) than feature sets/algorithms (Wilcoxon signed-rank p = 0.36). Top-ranked radiomic features included GLZSM-LZHGE (large-zone-high-SUV), GTSDM-CP (cluster-prominence), GTSDM-CS (cluster-shade) and NGTDM-CNT (contrast). Top-ranked features were consistent between MTVhi and MTVlo cluster pairs but varied between MTVhi-MTVlo clusters, reflecting distinct regional radiomic phenotypes. Variability in tumor voxel cluster response prediction can inform robust radiomic target definition for risk-adaptive chemoradiation in patients with LA-NSCLC. FLARE-RT trial: NCT02773238.

Dysregulated microRNA expression profiles in gastric cancer cells with high peritoneal metastatic potential.

Despite significant developments in its clinical treatment, the reported incidence and mortality of gastric cancer have exhibited marked increases. The molecular mechanisms of gastric cancer initiation and progression remain to be fully elucidated. The aim of the present study was to identify novel microRNAs (miRNAs/miRs) with a role in the peritoneal metastasis of gastric cancer by comparing the miRNA expression in the gastric cancer cell line GC9811 with that in its variant GC9811-P, a sub-cell line with a high potential for peritoneal metastasis. A miRNA microarray analysis identified 153 dysregulated miRNAs, including 74 upregulated and 79 downregulated miRNAs. Of these, four significantly upregulated miRNAs (miR-181a-5p, miR-106b-5p, miR-199a-3p and miR-148a-3p) and four downregulated miRNAs (miR-146a-5p, miR-21-5p, miR-222-3p and miR-221-3p) were selected and further confirmed by reverse transcription-quantitative polymerase chain reaction analysis. Furthermore, knockdown of miR-21-5p promoted the migration and invasion of GC9811 cells. Collectively, the results suggested that the miRNA expression profile in GC9811-P vs. GC9811 cells was altered to favor disease progression, and the dysregulated miRNAs, including miR-21-5p, may therefore provide novel biomarkers and potential therapeutic targets for gastric cancer metastasis.

MicroRNA-214 promotes peritoneal metastasis through regulating PTEN negatively in gastric cancer.

BACKGROUND AND OBJECTIVE: We aimed to investigate the effects of microRNA-214 (miR-214) on peritoneal metastasis as well as to elucidate its regulatory mechanism in gastric cancer (GC). METHODS: The expression levels of miR-214 in human GC cell lines MKN-28NM, MKN-28M, GC9811 and GC9811-P were analyzed by quantitative real-time PCR. Lentiviral miR-214, lentiviral miR-214 inhibitor, and empty lentiviral vector were transfected to GC cell lines, respectively. The roles of miR-214 in cell invasion, migration, proliferation and colony-forming ability were then analyzed. Besides, the expression levels of PTEN in different transfected cells were determined by western blot analysis. RESULTS: We found that miR-214 was up-regulated in GC9811-P cells with high metastatic potential to the peritoneum compared with that in GC9811 cells. In addition, in vitro overexpression of miR-214 promoted cell invasion, migration, proliferation and colony-forming ability of GC9811 cells, while down-regulation of miR-214 had opposite effects in GC9811-P cells. Besides, overexpression of miR-214 in GC9811 cells markedly down-regulated PTEN expression, whereas down-regulation of miR-214 in GC9811-P cells significantly increased PTEN expression. CONCLUSIONS: Our findings indicate that miR-214 may promote peritoneal metastasis of GC cells via down-regulation of PTEN, thus leading to the progression of GC.