Machine Learning Reveals Impacts of Smoking on Gene Profiles of Different Cell Types in Lung.

Smoking significantly elevates the risk of lung diseases such as chronic obstructive pulmonary disease (COPD) and lung cancer. This risk is attributed to the harmful chemicals in tobacco smoke that damage lung tissue and impair lung function. Current research on the impact of smoking on gene expression in specific lung cells is limited. This study addresses this gap by analyzing gene expression profiles at the single-cell level from 43,539 lung endothelial cells, 234,349 lung epithelial cells, 189,843 lung immune cells, and 16,031 lung stromal cells using advanced machine learning techniques. The data, categorized by different lung cell types, were classified into three smoking states: active smoker, former smoker, and never smoker. Each cell sample encompassed 28,024 feature genes. Employing an incremental feature selection method within a computational framework, several specific genes have been identified as potential markers of smoking status in different lung cell types. These include B2M, EEF1A1, and TPT1 in lung endothelial cells; FTL and MT-ATP8 in lung epithelial cells; HLA-B and HLA-C in lung immune cells; and HSP90B1 and LCN2 in lung stroma cells. Additionally, this study developed quantitative rules for representing the gene expression patterns related to smoking. This research highlights the potential of machine learning in oncology, enhancing our molecular understanding of smoking's harm and laying the groundwork for future mechanism-based studies.

Exploring Prognostic Gene Factors in Breast Cancer via Machine Learning.

Breast cancer remains the most prevalent cancer in women. To date, its underlying molecular mechanisms have not been fully uncovered. The determination of gene factors is important to improve our understanding on breast cancer, which can correlate the specific gene expression and tumor staging. However, the knowledge in this regard is still far from complete. Thus, this study aimed to explore these knowledge gaps by analyzing existing gene expression profile data from 3149 breast cancer samples, where each sample was represented by the expression of 19,644 genes and classified into Nottingham histological grade (NHG) classes (Grade 1, 2, and 3). To this end, a machine learning-based framework was designed. First, the profile data were analyzed by using seven feature ranking algorithms to evaluate the importance of features (genes). Seven feature lists were generated, each of which sorted features in accordance with feature importance evaluated from a special aspect. Then, the incremental feature selection method was applied to each list to determine essential features for classification and building efficient classifiers. Consequently, overlapping genes, such as AURKA, CBX2, and MYBL2, were deemed as potentially related to breast cancer malignancy and prognosis, indicating that such genes were identified to be important by multiple feature ranking algorithms. In addition, the study formulated classification rules to reflect special gene expression patterns for three NHG classes. Some genes and rules were analyzed and supported by recent literature, providing new references for studying breast cancer.

Identifying genes associated with resistance to KRAS G12C inhibitors via machine learning methods.

BACKGROUND: Targeted therapy has revolutionized cancer treatment, greatly improving patient outcomes and quality of life. Lung cancer, specifically non-small cell lung cancer, is frequently driven by the G12C mutation at the KRAS locus. The development of KRAS inhibitors has been a breakthrough in the field of cancer research, given the crucial role of KRAS mutations in driving tumor growth and progression. However, over half of patients with cancer bypass inhibition show limited response to treatment. The mechanisms underlying tumor cell resistance to this treatment remain poorly understood. METHODS: To address above gap in knowledge, we conducted a study aimed to elucidate the differences between tumor cells that respond positively to KRAS (G12C) inhibitor therapy and those that do not. Specifically, we analyzed single-cell gene expression profiles from KRAS G12C-mutant tumor cell models (H358, H2122, and SW1573) treated with KRAS G12C (ARS-1620) inhibitor, which contained 4297 cells that continued to proliferate under treatment and 3315 cells that became quiescent. Each cell was represented by the expression levels on 8687 genes. We then designed an innovative machine learning based framework, incorporating seven feature ranking algorithms and four classification algorithms to identify essential genes and establish quantitative rules. RESULTS: Our analysis identified some top-ranked genes, including H2AFZ, CKS1B, TUBA1B, RRM2, and BIRC5, that are known to be associated with the progression of multiple cancers. CONCLUSION: Above genes were relevant to tumor cell resistance to targeted therapy. This study provides important insights into the molecular mechanisms underlying tumor cell resistance to KRAS inhibitor treatment.

Machine Learning Classification of Time since BNT162b2 COVID-19 Vaccination Based on Array-Measured Antibody Activity.

Vaccines trigger an immunological response that includes B and T cells, with B cells producing antibodies. SARS-CoV-2 immunity weakens over time after vaccination. Discovering key changes in antigen-reactive antibodies over time after vaccination could help improve vaccine efficiency. In this study, we collected data on blood antibody levels in a cohort of healthcare workers vaccinated for COVID-19 and obtained 73 antigens in samples from four groups according to the duration after vaccination, including 104 unvaccinated healthcare workers, 534 healthcare workers within 60 days after vaccination, 594 healthcare workers between 60 and 180 days after vaccination, and 141 healthcare workers over 180 days after vaccination. Our work was a reanalysis of the data originally collected at Irvine University. This data was obtained in Orange County, California, USA, with the collection process commencing in December 2020. British variant (B.1.1.7), South African variant (B.1.351), and Brazilian/Japanese variant (P.1) were the most prevalent strains during the sampling period. An efficient machine learning based framework containing four feature selection methods (least absolute shrinkage and selection operator, light gradient boosting machine, Monte Carlo feature selection, and maximum relevance minimum redundancy) and four classification algorithms (decision tree, k-nearest neighbor, random forest, and support vector machine) was designed to select essential antibodies against specific antigens. Several efficient classifiers with a weighted F1 value around 0.75 were constructed. The antigen microarray used for identifying antibody levels in the coronavirus features ten distinct SARS-CoV-2 antigens, comprising various segments of both nucleocapsid protein (NP) and spike protein (S). This study revealed that S1 + S2, S1.mFcTag, S1.HisTag, S1, S2, Spike.RBD.His.Bac, Spike.RBD.rFc, and S1.RBD.mFc were most highly ranked among all features, where S1 and S2 are the subunits of Spike, and the suffixes represent the tagging information of different recombinant proteins. Meanwhile, the classification rules were obtained from the optimal decision tree to explain quantitatively the roles of antigens in the classification. This study identified antibodies associated with decreased clinical immunity based on populations with different time spans after vaccination. These antibodies have important implications for maintaining long-term immunity to SARS-CoV-2.

Identification of Phase-Separation-Protein-Related Function Based on Gene Ontology by Using Machine Learning Methods.

Phase-separation proteins (PSPs) are a class of proteins that play a role in the process of liquid-liquid phase separation, which is a mechanism that mediates the formation of membranelle compartments in cells. Identifying phase separation proteins and their associated function could provide insights into cellular biology and the development of diseases, such as neurodegenerative diseases and cancer. Here, PSPs and non-PSPs that have been experimentally validated in earlier studies were gathered as positive and negative samples. Each protein's corresponding Gene Ontology (GO) terms were extracted and used to create a 24,907-dimensional binary vector. The purpose was to extract essential GO terms that can describe essential functions of PSPs and build efficient classifiers to identify PSPs with these GO terms at the same time. To this end, the incremental feature selection computational framework and an integrated feature analysis scheme, containing categorical boosting, least absolute shrinkage and selection operator, light gradient-boosting machine, extreme gradient boosting, and permutation feature importance, were used to build efficient classifiers and identify GO terms with classification-related importance. A set of random forest (RF) classifiers with F1 scores over 0.960 were established to distinguish PSPs from non-PSPs. A number of GO terms that are crucial for distinguishing between PSPs and non-PSPs were found, including GO:0003723, which is related to a biological process involving RNA binding; GO:0016020, which is related to membrane formation; and GO:0045202, which is related to the function of synapses. This study offered recommendations for future research aimed at determining the functional roles of PSPs in cellular processes by developing efficient RF classifiers and identifying the representative GO terms related to PSPs.

Using Machine Learning Methods in Identifying Genes Associated with COVID-19 in Cardiomyocytes and Cardiac Vascular Endothelial Cells.

Corona Virus Disease 2019 (COVID-19) not only causes respiratory system damage, but also imposes strain on the cardiovascular system. Vascular endothelial cells and cardiomyocytes play an important role in cardiac function. The aberrant expression of genes in vascular endothelial cells and cardiomyocytes can lead to cardiovascular diseases. In this study, we sought to explain the influence of respiratory syndrome coronavirus 2 (SARS-CoV-2) infection on the gene expression levels of vascular endothelial cells and cardiomyocytes. We designed an advanced machine learning-based workflow to analyze the gene expression profile data of vascular endothelial cells and cardiomyocytes from patients with COVID-19 and healthy controls. An incremental feature selection method with a decision tree was used in building efficient classifiers and summarizing quantitative classification genes and rules. Some key genes, such as MALAT1, MT-CO1, and CD36, were extracted, which exert important effects on cardiac function, from the gene expression matrix of 104,182 cardiomyocytes, including 12,007 cells from patients with COVID-19 and 92,175 cells from healthy controls, and 22,438 vascular endothelial cells, including 10,812 cells from patients with COVID-19 and 11,626 cells from healthy controls. The findings reported in this study may provide insights into the effect of COVID-19 on cardiac cells and further explain the pathogenesis of COVID-19, and they may facilitate the identification of potential therapeutic targets.

Immune responses of different COVID-19 vaccination strategies by analyzing single-cell RNA sequencing data from multiple tissues using machine learning methods.

Multiple types of COVID-19 vaccines have been shown to be highly effective in preventing SARS-CoV-2 infection and in reducing post-infection symptoms. Almost all of these vaccines induce systemic immune responses, but differences in immune responses induced by different vaccination regimens are evident. This study aimed to reveal the differences in immune gene expression levels of different target cells under different vaccine strategies after SARS-CoV-2 infection in hamsters. A machine learning based process was designed to analyze single-cell transcriptomic data of different cell types from the blood, lung, and nasal mucosa of hamsters infected with SARS-CoV-2, including B and T cells from the blood and nasal cavity, macrophages from the lung and nasal cavity, alveolar epithelial and lung endothelial cells. The cohort was divided into five groups: non-vaccinated (control), 2*adenovirus (two doses of adenovirus vaccine), 2*attenuated (two doses of attenuated virus vaccine), 2*mRNA (two doses of mRNA vaccine), and mRNA/attenuated (primed by mRNA vaccine, boosted by attenuated vaccine). All genes were ranked using five signature ranking methods (LASSO, LightGBM, Monte Carlo feature selection, mRMR, and permutation feature importance). Some key genes that contributed to the analysis of immune changes, such as RPS23, DDX5, PFN1 in immune cells, and IRF9 and MX1 in tissue cells, were screened. Afterward, the five feature sorting lists were fed into the feature incremental selection framework, which contained two classification algorithms (decision tree [DT] and random forest [RF]), to construct optimal classifiers and generate quantitative rules. Results showed that random forest classifiers could provide relative higher performance than decision tree classifiers, whereas the DT classifiers provided quantitative rules that indicated special gene expression levels under different vaccine strategies. These findings may help us to develop better protective vaccination programs and new vaccines.

Identification of genes related to immune enhancement caused by heterologous ChAdOx1-BNT162b2 vaccines in lymphocytes at single-cell resolution with machine learning methods.

The widely used ChAdOx1 nCoV-19 (ChAd) vector and BNT162b2 (BNT) mRNA vaccines have been shown to induce robust immune responses. Recent studies demonstrated that the immune responses of people who received one dose of ChAdOx1 and one dose of BNT were better than those of people who received vaccines with two homologous ChAdOx1 or two BNT doses. However, how heterologous vaccines function has not been extensively investigated. In this study, single-cell RNA sequencing data from three classes of samples: volunteers vaccinated with heterologous ChAdOx1-BNT and volunteers vaccinated with homologous ChAd-ChAd and BNT-BNT vaccinations after 7 days were divided into three types of immune cells (3654 B, 8212 CD4+ T, and 5608 CD8+ T cells). To identify differences in gene expression in various cell types induced by vaccines administered through different vaccination strategies, multiple advanced feature selection methods (max-relevance and min-redundancy, Monte Carlo feature selection, least absolute shrinkage and selection operator, light gradient boosting machine, and permutation feature importance) and classification algorithms (decision tree and random forest) were integrated into a computational framework. Feature selection methods were in charge of analyzing the importance of gene features, yielding multiple gene lists. These lists were fed into incremental feature selection, incorporating decision tree and random forest, to extract essential genes, classification rules and build efficient classifiers. Highly ranked genes include PLCG2, whose differential expression is important to the B cell immune pathway and is positively correlated with immune cells, such as CD8+ T cells, and B2M, which is associated with thymic T cell differentiation. This study gave an important contribution to the mechanistic explanation of results showing the stronger immune response of a heterologous ChAdOx1-BNT vaccination schedule than two doses of either BNT or ChAdOx1, offering a theoretical foundation for vaccine modification.

Identification of Smoking-Associated Transcriptome Aberration in Blood with Machine Learning Methods.

Long-term cigarette smoking causes various human diseases, including respiratory disease, cancer, and gastrointestinal (GI) disorders. Alterations in gene expression and variable splicing processes induced by smoking are associated with the development of diseases. This study applied advanced machine learning methods to identify the isoforms with important roles in distinguishing smokers from former smokers based on the expression profile of isoforms from current and former smokers collected in one previous study. These isoforms were deemed as features, which were first analyzed by the Boruta to select features highly correlated with the target variables. Then, the selected features were evaluated by four feature ranking algorithms, resulting in four feature lists. The incremental feature selection method was applied to each list for obtaining the optimal feature subsets and building high-performance classification models. Furthermore, a series of classification rules were accessed by decision tree with the highest performance. Eventually, the rationality of the mined isoforms (features) and classification rules was verified by reviewing previous research. Features such as isoforms ENST00000464835 (expressed by LRRN3), ENST00000622663 (expressed by SASH1), and ENST00000284311 (expressed by GPR15), and pathways (cytotoxicity mediated by natural killer cell and cytokine-cytokine receptor interaction) revealed by the enrichment analysis, were highly relevant to smoking response, suggesting the robustness of our analysis pipeline.

Adsorption-Hydration Sequence Method for Methane Storage in Porous Material Slurry.

Porous materials are deemed to be capable for promoting hydrate formation, while for the purpose of hydrate-based gas storage, those systems containing porous materials often cannot meet the requirement of high storage density. To increase the storage density, an adsorption-hydration sequence method was designed and systematically examined in this study. Methane storage and release in ZIF-8 slurries and fixed beds were investigated. The ZIF-8 retained 98.62%, while the activated carbon lost 62.17% of their adsorption capacities in slurry. In ZIF-8 fixed beds, methane storage density of 127.41 V/Vbed was acquired, while the gas loss during depressurization accounted for 21.50% of the gas uptake. In the ZIF-8 slurry, the storage density was effectively increased with the adsorption-hydration sequence method, and the gas loss during depressurization was much smaller than that in fixed beds. In the slurry, the gas uptake and gas loss decreased with the decrease of the chilling temperature. The largest gas uptake and storage density of 78.84 mmol and 133.59 V/Vbed were acquired in the slurry with ZIF-8 content of 40 wt.% at 268.15 K, meanwhile, the gas loss just accounted for 14.04% of the gas uptake. Self-preservation effect was observed in the slurry, and the temperature for the slowest gas release was found to be 263.15 K, while the release ratio at 10 h reached to 43.42%. By increasing the back pressure, the gas release rate could be effectively controlled. The gas release ratio at 1.1 MPa at 10 h was just 11.08%. The results showed that the application of adsorption-hydration sequence method in ZIF-8 slurry is a prospective manner for gas transportation.

Self-Assembled Vanadium Oxide Nanoflakes for p-Type Ammonia Sensors at Room Temperature.

VO2(B), VO2(M), and V2O5 are the most famous compounds in the vanadium oxide family. Here, their gas-sensing properties were investigated and compared. VO2(B) nanoflakes were first self-assembled via a hydrothermal method, and then VO2(M) and V2O5 nanoflakes were obtained after a heat-phase transformation in nitrogen and air, respectively. Their microstructures were evaluated using X-ray diffraction and scanning and transmission electron microscopies, respectively. Gas sensing measurements indicated that VO2(M) nanoflakes were gas-insensitive, while both VO2(B) and V2O5 nanoflakes were highly selective to ammonia at room temperature. As ammonia sensors, both VO2(B) and V2O5 nanoflakes showed abnormal p-type sensing characteristics, although vanadium oxides are generally considered as n-type semiconductors. Moreover, V2O5 nanoflakes exhibited superior ammonia sensing performance compared to VO2(B) nanoflakes, with one order of magnitude higher sensitivity, a shorter response time of 14⁻22 s, and a shorter recovery time of 14⁻20 s. These characteristics showed the excellent potential of V2O5 nanostructures as ammonia sensors.

Tunable integration of absorption-membrane-adsorption for efficiently separating low boiling gas mixtures near normal temperature.

Separation of low boiling gas mixtures is widely concerned in process industries. Now their separations heavily rely upon energy-intensive cryogenic processes. Here, we report a pseudo-absorption process for separating low boiling gas mixtures near normal temperature. In this process, absorption-membrane-adsorption is integrated by suspending suitable porous ZIF material in suitable solvent and forming selectively permeable liquid membrane around ZIF particles. Green solvents like water and glycol were used to form ZIF-8 slurry and tune the permeability of liquid membrane surrounding ZIF-8 particles. We found glycol molecules form tighter membrane while water molecules form looser membrane because of the hydrophobicity of ZIF-8. When using mixing solvents composed of glycol and water, the permeability of liquid membrane becomes tunable. It is shown that ZIF-8/water slurry always manifests remarkable higher separation selectivity than solid ZIF-8 and it could be tuned to further enhance the capture of light hydrocarbons by adding suitable quantity of glycol to water. Because of its lower viscosity and higher sorption/desorption rate, tunable ZIF-8/water-glycol slurry could be readily used as liquid absorbent to separate different kinds of low boiling gas mixtures by applying a multistage separation process in one traditional absorption tower, especially for the capture of light hydrocarbons.

Biological formation of 5-aminolevulinic acid by photosynthetic bacteria.

In this study, 7 stains of Rhodopseudomonas sp. were selected from 36 photosynthetic bacteria stains storied in our laboratory. Rhodopseudomonas sp. strain 99-28 has the highest 5-aminolevulinic acid(ALA) production ability in these 7 strains. Rhodopseudomonas sp. 99-28 strain was mutated using ultraviolet radiation and a mutant strain L-1, which ALA production is higher than wild strain 99-28 about one times, was obtained. The elements affecting ALA formation of strain 99-28 and L-1 were studied. Under the optimal condition( pH 7.5, supplement of ALA dehydratase(ALAD) inhibitor, levulinic acid(LA) and precursors of ALA synthesis, glycine and succinat, 3000 Ix of light density), ALA formation of mutant L-1 was up to 22.15 mg/L. Strain L-1 was used to treat wastewater to remove COD(Cr) and produce ALA. ALA production was 2.819 mg/L, 1.531 mg/L, 2.166 mg/L, and 2.424 mg/L in monosodium glutamate wastewater(MGW), succotash wastewater(SW), brewage wastewater(BW), and citric acid wastewater(CAW) respectively. More than 90% of COD(Cr) was removed in four kinds of wastewater. When LA, glycin and succinate were supplied, ALA production was dramatically increased, however, COD(Cr) could hardly be removed.

Experimental and modeling study on decomposition kinetics of methane hydrates in different media.

The decomposition kinetic behaviors of methane hydrates formed in 5 cm3 porous wet activated carbon were studied experimentally in a closed system in the temperature range of 275.8-264.4 K. The decomposition rates of methane hydrates formed from 5 cm3 of pure free water and an aqueous solution of 650 g x m(-3) sodium dodecyl sulfate (SDS) were also measured for comparison. The decomposition rates of methane hydrates in seven different cases were compared. The results showed that the methane hydrates dissociate more rapidly in porous activated carbon than in free systems. A mathematical model was developed for describing the decomposition kinetic behavior of methane hydrates below ice point based on an ice-shielding mechanism in which a porous ice layer was assumed to be formed during the decomposition of hydrate, and the diffusion of methane molecules through it was assumed to be one of the control steps. The parameters of the model were determined by correlating the decomposition rate data, and the activation energies were further determined with respect to three different media. The model was found to well describe the decomposition kinetic behavior of methane hydrate in different media.