Machine learning methods in the computational biology of cancer

Cancer-associated fibroblast-secreted FGF7 as an ovarian cancer progression promoter

BACKGROUND

Ovarian cancer (OC) is distinguished by its aggressive nature and the limited efficacy of current treatment strategies. Recent studies have emphasized the significant role of cancer-associated fibroblasts (CAFs) in OC development and progression.

METHODS

Employing sophisticated machine learning techniques on bulk transcriptomic datasets, we identified fibroblast growth factor 7 (FGF7), derived from CAFs, as a potential oncogenic factor. We investigated the relationship between FGF7 expression and various clinical parameters. A series of in vitro experiments were undertaken to evaluate the effect of CAFs-derived FGF7 on OC cell activities, such as proliferation, migration, and invasion. Single-cell transcriptomic analysis was also conducted to elucidate the interaction between FGF7 and its receptor. Detailed mechanistic investigations sought to clarify the pathways through which FGF7 fosters OC progression.

RESULTS

Our findings indicate that higher FGF7 levels correlate with advanced tumor stages, increased vascular invasion, and poorer prognosis. CAFs-derived FGF7 significantly enhanced OC cell proliferation, migration, and invasion. Single-cell analysis and in vitro studies revealed that CAFs-derived FGF7 inhibits the ubiquitination and degradation of hypoxia-inducible factor 1 alpha (HIF-1α) via FGFR2 interaction. Activation of the FGF7/HIF-1α pathway resulted in the upregulation of mesenchymal markers and downregulation of epithelial markers. Importantly, in vivo treatment with neutralizing antibodies targeting CAFs-derived FGF7 substantially reduced tumor growth.

CONCLUSION

Neutralizing FGF7 in the medium or inhibiting HIF-1α signaling reversed the effects of FGF7-mediated EMT, emphasizing the dependence of FGF7-mediated EMT on HIF-1α activation. These findings suggest that targeting the FGF7/HIF-1α/EMT axis may offer new therapeutic opportunities to intervene in OC progression.

Prognostic and immunological implications of paraptosis-related genes in lung adenocarcinoma: Comprehensive analysis and functional verification of hub gene

BACKGROUND

Lung adenocarcinoma (LUAD) poses significant clinical challenges due to its inherent heterogeneity and variable response to treatment. Recent research has specifically focused on elucidating the role of Paraptosis-related genes (PRGs) in the progression of cancer and the prognosis of patients.

METHODS

We conducted a comprehensive analysis of the differential expression of PRGs in LUAD. Additionally, univariate Cox regression analysis was utilized to determine the prognostic significance of these genes. Furthermore, consensus clustering was employed to differentiate molecular subtypes within LUAD, while immune heterogeneity was assessed. To evaluate treatment outcomes, the expression of immune checkpoint inhibitors was examined, and the sensitivity of LUAD patients to chemotherapy drugs was assessed. Moreover, machine learning algorithms were employed to construct a Paraptosis-related risk score with prognostic and immunological indicators. Finally, to validate the findings, in vitro experiments were performed to verify the regulatory effect of key PRGs on Paraptosis.

RESULTS

Our analysis identified 24 PRGs that exhibited differential expression, with CDKN3, TP53, and PHB emerging as the most prominently upregulated genes in tumor tissues. Among these genes, seven were identified as prognostic markers, with HSPB8 being the sole protective factor. Notably, our analysis also revealed the existence of two distinct molecular subtypes within LUAD, each characterized by unique prognoses and immune responses. Specifically, Subtype B displayed a poorer prognosis but demonstrated increased sensitivity to both chemotherapy and immunotherapy. In addition, our development of a Paraptosis-Associated Risk Score yielded a significant prognostic value in predicting patient outcomes. Furthermore, we found regulatory effect of CDKN3 on Paraptosis in two cell lines.

CONCLUSIONS

Our study highlights the importance of PRGs in LUAD, particularly in prognosis and treatment response. The identified molecular subtypes and Paraptosis-Associated Risk Score offer valuable insights for personalized treatment strategies.

Sparse Group Lasso: Optimal Sample Complexity, Convergence Rate, and Statistical Inference

We study sparse group Lasso for high-dimensional double sparse linear regression, where the parameter of interest is simultaneously element-wise and group-wise sparse. This problem is an important instance of the simultaneously structured model - an actively studied topic in statistics and machine learning. In the noiseless case, matching upper and lower bounds on sample complexity are established for the exact recovery of sparse vectors and for stable estimation of approximately sparse vectors, respectively. In the noisy case, upper and matching minimax lower bounds for estimation error are obtained. We also consider the debiased sparse group Lasso and investigate its asymptotic property for the purpose of statistical inference. Finally, numerical studies are provided to support the theoretical results.

MHANet: A hybrid attention mechanism for retinal diseases classification

With the increase of patients with retinopathy, retinopathy recognition has become a research hotspot. In this article, we describe the etiology and symptoms of three kinds of retinal diseases, including drusen(DRUSEN), choroidal neovascularization(CNV) and diabetic macular edema(DME). In addition, we also propose a hybrid attention mechanism to classify and recognize different types of retinopathy images. In particular, the hybrid attention mechanism proposed in this paper includes parallel spatial attention mechanism and channel attention mechanism. It can extract the key features in the channel dimension and spatial dimension of retinopathy images, and reduce the negative impact of background information on classification results. The experimental results show that the hybrid attention mechanism proposed in this paper can better assist the network to focus on extracting thr fetures of the retinopathy area and enhance the adaptability to the differences of different data sets. Finally, the hybrid attention mechanism achieved 96.5% and 99.76% classification accuracy on two public OCT data sets of retinopathy, respectively.

Deep Learning of Markov Model-Based Machines for Determination of Better Treatment Option Decisions for Infertile Women

In this technical article, we are proposing ideas, that we have been developing on how machine learning and deep learning techniques can potentially assist obstetricians/gynecologists in better clinical decision-making, using infertile women in their treatment options in combination with mathematical modeling in pregnant women as examples.

Exclusive Sparsity Norm Minimization With Random Groups via Cone Projection

Many practical applications such as gene expression analysis, multitask learning, image recognition, signal processing, and medical data analysis pursue a sparse solution for the feature selection purpose and particularly favor the nonzeros evenly distributed in different groups. The exclusive sparsity norm has been widely used to serve to this purpose. However, it still lacks systematical studies for exclusive sparsity norm optimization. This paper offers two main contributions from the optimization perspective: 1) we provide several efficient algorithms to solve exclusive sparsity norm minimization with either smooth loss or hinge loss (nonsmooth loss). All algorithms achieve the optimal convergence rate . ( is the iteration number.) To the best of our knowledge, this is the first time to guarantee such convergence rate for the general exclusive sparsity norm minimization and 2) when the group information is unavailable to define the exclusive sparsity norm, we propose to use the random grouping scheme to construct groups and prove that if the number of groups is appropriately chosen, the nonzeros (true features) would be grouped in the ideal way with high probability. Empirical studies validate the efficiency of the proposed algorithms, and the effectiveness of random grouping scheme on the proposed exclusive support vector machine formulation.

RNA-seq assistant: machine learning based methods to identify more transcriptional regulated genes

BACKGROUND

Although different quality controls have been applied at different stages of the sample preparation and data analysis to ensure both reproducibility and reliability of RNA-seq results, there are still limitations and bias on the detectability for certain differentially expressed genes (DEGs). Whether the transcriptional dynamics of a gene can be captured accurately depends on experimental design/operation and the following data analysis processes. The workflow of subsequent data processing, such as reads alignment, transcript quantification, normalization, and statistical methods for ultimate identification of DEGs can influence the accuracy and sensitivity of DEGs analysis, producing a certain number of false-positivity or false-negativity. Machine learning (ML) is a multidisciplinary field that employs computer science, artificial intelligence, computational statistics and information theory to construct algorithms that can learn from existing data sets and to make predictions on new data set. ML-based differential network analysis has been applied to predict stress-responsive genes through learning the patterns of 32 expression characteristics of known stress-related genes. In addition, the epigenetic regulation plays critical roles in gene expression, therefore, DNA and histone methylation data has been shown to be powerful for ML-based model for prediction of gene expression in many systems, including lung cancer cells. Therefore, it is promising that ML-based methods could help to identify the DEGs that are not identified by traditional RNA-seq method.

RESULTS

We identified the top 23 most informative features through assessing the performance of three different feature selection algorithms combined with five different classification methods on training and testing data sets. By comprehensive comparison, we found that the model based on InfoGain feature selection and Logistic Regression classification is powerful for DEGs prediction. Moreover, the power and performance of ML-based prediction was validated by the prediction on ethylene regulated gene expression and the following qRT-PCR.

CONCLUSIONS

Our study shows that the combination of ML-based method with RNA-seq greatly improves the sensitivity of DEGs identification.

Sparse Supervised Classification Methods Predict and Characterize Nanomaterial Exposures: Independent Markers of MWCNT Exposures

Recent experimental evidence indicates significant pulmonary toxicity of multiwalled carbon nanotubes (MWCNTs), such as inflammation, interstitial fibrosis, granuloma formation, and carcinogenicity. Although numerous studies explored the adverse potential of various CNTs, their comparability is often limited. This is due to differences in administered dose, physicochemical characteristics, exposure methods, and end points monitored. Here, we addressed the problem through sparse classification method, a supervised machine learning approach that can reduce the noise contained in redundant variables for discriminating among MWCNT-exposed and MWCNT-unexposed groups. A panel of proteins measured from bronchoalveolar lavage fluid (BAL) samples was used to predict exposure to various MWCNT and determine markers that are attributable to MWCNT exposure and toxicity in mice. Using sparse support vector machine-based classification technique, we identified a small subset of proteins clearly distinguishing each exposure. Macrophage-derived chemokine (MDC/CCL22), in particular, was associated with various MWCNT exposures and was independent of exposure method employed, that is, oropharyngeal aspiration versus inhalation exposure. Sustained expression of some of the selected protein markers identified also suggests their potential role in MWCNT-induced toxicity and proposes hypotheses for future mechanistic studies. Such approaches can be used more broadly for nanomaterial risk profiling studies to evaluate decisions related to dose/time-response relationships that could delineate experimental variables from exposure markers.

Efficient least angle regression for identification of linear-in-the-parameters models

Least angle regression, as a promising model selection method, differentiates itself from conventional stepwise and stagewise methods, in that it is neither too greedy nor too slow. It is closely related to L₁ norm optimization, which has the advantage of low prediction variance through sacrificing part of model bias property in order to enhance model generalization capability. In this paper, we propose an efficient least angle regression algorithm for model selection for a large class of linear-in-the-parameters models with the purpose of accelerating the model selection process. The entire algorithm works completely in a recursive manner, where the correlations between model terms and residuals, the evolving directions and other pertinent variables are derived explicitly and updated successively at every subset selection step. The model coefficients are only computed when the algorithm finishes. The direct involvement of matrix inversions is thereby relieved. A detailed computational complexity analysis indicates that the proposed algorithm possesses significant computational efficiency, compared with the original approach where the well-known efficient Cholesky decomposition is involved in solving least angle regression. Three artificial and real-world examples are employed to demonstrate the effectiveness, efficiency and numerical stability of the proposed algorithm.

Machine learning based detection of age-related macular degeneration (AMD) and diabetic macular edema (DME) from optical coherence tomography (OCT) images

Non-lethal macular diseases greatly impact patients' life quality, and will cause vision loss at the late stages. Visual inspection of the optical coherence tomography (OCT) images by the experienced clinicians is the main diagnosis technique. We proposed a computer-aided diagnosis (CAD) model to discriminate age-related macular degeneration (AMD), diabetic macular edema (DME) and healthy macula. The linear configuration pattern (LCP) based features of the OCT images were screened by the Correlation-based Feature Subset (CFS) selection algorithm. And the best model based on the sequential minimal optimization (SMO) algorithm achieved 99.3% in the overall accuracy for the three classes of samples.

Use of a Latent Topic Model for Characteristic Extraction from Health Checkup Questionnaire Data

OBJECTIVES

When patients complete questionnaires during health checkups, many of their responses are subjective, making topic extraction difficult. Therefore, the purpose of this study was to develop a model capable of extracting appropriate topics from subjective data in questionnaires conducted during health checkups.

METHODS

We employed a latent topic model to group the lifestyle habits of the study participants and represented their responses to items on health checkup questionnaires as a probability model. For the probability model, we used latent Dirichlet allocation to extract 30 topics from the questionnaires. According to the model parameters, a total of 4381 study participants were then divided into groups based on these topics. Results from laboratory tests, including blood glucose level, triglycerides, and estimated glomerular filtration rate, were compared between each group, and these results were then compared with those obtained by hierarchical clustering.

RESULTS

If a significant (p < 0.05) difference was observed in any of the laboratory measurements between groups, it was considered to indicate a questionnaire response pattern corresponding to the value of the test result. A comparison between the latent topic model and hierarchical clustering grouping revealed that, in the latent topic model method, a small group of participants who reported having subjective signs of urinary disorder were allocated to a single group.

CONCLUSIONS

The latent topic model is useful for extracting characteristics from a small number of groups from questionnaires with a large number of items. These results show that, in addition to chief complaints and history of past illness, questionnaire data obtained during medical checkups can serve as useful judgment criteria for assessing the conditions of patients.

Optimized Prediction of Extreme Treatment Outcomes in Ovarian Cancer

Ovarian cancer is the fifth leading cause of death among female cancers. Front-line therapy for ovarian cancer is platinum-based chemotherapy. However, the response of patients is highly nonuniform. The TCGA database of serous ovarian carcinomas shows that ~10% of patients respond poorly to platinum-based chemotherapy, with tumors relapsing in seven months or less. Another 10% or so enjoy disease-free survival of three years or more. The objective of the present research is to identify a small number of highly predictive biomarkers that can distinguish between the two extreme responders and then extrapolate to all patients. This is achieved using the lone star algorithm that is specifically developed for biological applications. Using this algorithm, we are able to identify biomarker panels of 25 genes (of 12,000 genes) that can be used to classify patients into one of the three groups: super responders, medium responders, and nonresponders. We are also able to determine a discriminant function that can divide the entire patient population into two classes, such that one group has a clear survival advantage over the other. These biomarkers are developed using the TCGA Agilent platform data and cross-validated on the TCGA Affymetrix platform data, as well as entirely independent data from Tothill et al. The P-values on the training data are extremely small, sometimes below machine zero, while the P-values on cross-validation are well below the widely accepted threshold of 0.05.

Data collection as a barrier to personalized medicine

Basic life science research holds the promise of personalizing medical care. However, translation steps from the laboratory to the bedside are not trivial. Results from clinical research are difficult to replicate in part because study cohorts are poorly defined phenotypically. Here, we discuss how computer technology can improve the collection of clinical data to enable translation of insights from basic science to validated clinical guidelines.