MLW-gcForest: a multi-weighted gcForest model towards the staging of lung adenocarcinoma based on multi-modal genetic data

CAMR: cross-aligned multimodal representation learning for cancer survival prediction

MOTIVATION

Accurately predicting cancer survival is crucial for helping clinicians to plan appropriate treatments, which largely improves the life quality of cancer patients and spares the related medical costs. Recent advances in survival prediction methods suggest that integrating complementary information from different modalities, e.g. histopathological images and genomic data, plays a key role in enhancing predictive performance. Despite promising results obtained by existing multimodal methods, the disparate and heterogeneous characteristics of multimodal data cause the so-called modality gap problem, which brings in dramatically diverse modality representations in feature space. Consequently, detrimental modality gaps make it difficult for comprehensive integration of multimodal information via representation learning and therefore pose a great challenge to further improvements of cancer survival prediction.

RESULTS

To solve the above problems, we propose a novel method called cross-aligned multimodal representation learning (CAMR), which generates both modality-invariant and -specific representations for more accurate cancer survival prediction. Specifically, a cross-modality representation alignment learning network is introduced to reduce modality gaps by effectively learning modality-invariant representations in a common subspace, which is achieved by aligning the distributions of different modality representations through adversarial training. Besides, we adopt a cross-modality fusion module to fuse modality-invariant representations into a unified cross-modality representation for each patient. Meanwhile, CAMR learns modality-specific representations which complement modality-invariant representations and therefore provides a holistic view of the multimodal data for cancer survival prediction. Comprehensive experiment results demonstrate that CAMR can successfully narrow modality gaps and consistently yields better performance than other survival prediction methods using multimodal data.

AVAILABILITY AND IMPLEMENTATION

CAMR is freely available at https://github.com/wxq-ustc/CAMR.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

miR-17-5p/HOXA7 Is a Potential Driver for Brain Metastasis of Lung Adenocarcinoma Related to Ferroptosis Revealed by Bioinformatic Analysis

Objectives

Present study aims to identify the essential mRNAs responsible for the development of brain neurovascular-related metastases (BNM) among lung adenocarcinoma (LUAD) patients. Further, we attempted to predict brain metastases more accurately and prevent their development in LUAD patients.

Methods

Transcriptome data analysis was used to identify differentially expressed mRNAs (DEMs) associated with brain metastasis, and thereby the ferroptosis index (FPI) is calculated using a computational model. Meanwhile, the DEmRNAs linked with FPI, and brain metastasis were derived by the intersection of these two groups of DEMs. We also constructed a ceRNA network containing these DEmRNAs, identifying the HCP5 /hsa-miR-17-5p/HOXA7 axis for analysis. Further, a clinical cohort was employed to validate the regulatory roles of molecules involved in the ceRNA regulatory axis.

Results

Here we report the development of a ceRNA network based on BNM-associated DEMs and FPI-associated DEmRNAs which includes three core miRNAs (hsa-miR-338-3p, hsa-miR-429, and hsa-miR-17-5p), three mRNAs (HOXA7, TBX5, and TCF21), and five lncRNAs (HCP5, LINC00460, TP53TG1). Using gene set enrichment analysis (GSEA) and survival analysis, the potential axis of HCP5 /hsa-miR-17-5p/HOXA7 was further investigated. It is found that HOXA7 and ferroptosis index are positively correlated while inhibiting tumor brain metastasis. It may be that HCP5 binds competitively with miR-17-5p and upregulates HOXA7 to increase iron death limiting brain cancer metastases.

Conclusions

The expression of both HOXA7 and HCP5 is positively correlated with FPI, indicating a possible link between ferroptosis and BNM. According to the results of our study, the ferroptosis-related ceRNA HCP5 /hsa-miR-17-5p/HOXA7 axis may contribute to the development of BNM in LUAD patients.

Machine-Learning-Based Late Fusion on Multi-Omics and Multi-Scale Data for Non-Small-Cell Lung Cancer Diagnosis

Differentiation between the various non-small-cell lung cancer subtypes is crucial for providing an effective treatment to the patient. For this purpose, machine learning techniques have been used in recent years over the available biological data from patients. However, in most cases this problem has been treated using a single-modality approach, not exploring the potential of the multi-scale and multi-omic nature of cancer data for the classification. In this work, we study the fusion of five multi-scale and multi-omic modalities (RNA-Seq, miRNA-Seq, whole-slide imaging, copy number variation, and DNA methylation) by using a late fusion strategy and machine learning techniques. We train an independent machine learning model for each modality and we explore the interactions and gains that can be obtained by fusing their outputs in an increasing manner, by using a novel optimization approach to compute the parameters of the late fusion. The final classification model, using all modalities, obtains an F1 score of 96.81±1.07, an AUC of 0.993±0.004, and an AUPRC of 0.980±0.016, improving those results that each independent model obtains and those presented in the literature for this problem. These obtained results show that leveraging the multi-scale and multi-omic nature of cancer data can enhance the performance of single-modality clinical decision support systems in personalized medicine, consequently improving the diagnosis of the patient.

Determination of adulteration in wheat flour using multi-grained cascade forest-related models coupled with the fusion information of hyperspectral imaging

Wheat flour (WF) is a common ingredient in staple foods. However, the presence of intentional or unintentional adulterants makes it difficult to guarantee WF quality. Multi-grained cascade forest (gcForest) model, a non-neural network deep learning structure, fused with image-spectra features from hyperspectral imaging (HSI) was employed for detecting adulterant type (peanut, walnut, or benzoyl peroxide) and the corresponding concentration (0.03%, 0.05%, 0.1%, 0.5%, 1%, and 2%). Based on the spectra of full wavelength and effective wavelength (EW) from hyperspectral images of WF samples, the gcForest-related models exhibited high performance (lowest ACC_P = 92.45%) and stability (lowest area under the curve = 0.9986). Furthermore, the fusion of the EW and the image features extracted by the symmetric all convolutional neural network (SACNN) was used to establish the gcForest-related models. The maximum accuracy improvement of the fusion feature model relative to the single spectral model and the image model was 2.45% and 44.37%, respectively. The results indicate that the gcForest-related model, combined with the image-spectra fusion feature of HSI, provides an effective tool for detection in food and agriculture.

High-dimensional role of AI and machine learning in cancer research

The role of Artificial Intelligence and Machine Learning in cancer research offers several advantages, primarily scaling up the information processing and increasing the accuracy of the clinical decision-making. The key enabling tools currently in use in Precision, Digital and Translational Medicine, here named as 'Intelligent Systems' (IS), leverage unprecedented data volumes and aim to model their underlying heterogeneous influences and variables correlated with patients' outcomes. As functionality and performance of IS are associated with complex diagnosis and therapy decisions, a rich spectrum of patterns and features detected in high-dimensional data may be critical for inference purposes. Many challenges are also present in such discovery task. First, the generation of interpretable model results from a mix of structured and unstructured input information. Second, the design, and implementation of automated clinical decision processes for drawing disease trajectories and patient profiles. Ultimately, the clinical impacts depend on the data effectively subjected to steps such as harmonisation, integration, validation, etc. The aim of this work is to discuss the transformative value of IS applied to multimodal data acquired through various interrelated cancer domains (high-throughput genomics, experimental biology, medical image processing, radiomics, patient electronic records, etc.).

A narrative review of artificial intelligence-assisted histopathologic diagnosis and decision-making for non-small cell lung cancer: achievements and limitations

Objective

To summarize the current evidence regarding the applications, workflow, and limitations of artificial intelligence (AI) in the management of patients pathologically-diagnosed with lung cancer.

Background

Lung cancer is one of the most common cancers and the leading cause of cancer-related deaths worldwide. AI technologies have been applied to daily medical workflow and have achieved an excellent performance in predicting histopathologic subtypes, analyzing gene mutation profiles, and assisting in clinical decision-making for lung cancer treatment. More advanced deep learning for classifying pathologic images with minimal human interactions has been developed in addition to the conventional machine learning scheme.

Methods

Studies were identified by searching databases, including PubMed, EMBASE, Web of Science, and Cochrane Library, up to February 2021 without language restrictions.

Conclusions

A number of studies have evaluated AI pipelines and confirmed that AI is robust and efficacious in lung cancer diagnosis and decision-making, demonstrating that AI models are a useful tool for assisting oncologists in health management. Although several limitations that pose an obstacle for the widespread use of AI schemes persist, the unceasing refinement of AI techniques is poised to overcome such problems. Thus, AI technology is a promising tool for use in diagnosing and managing lung cancer.

An autonomous hybrid brain-computer interface system combined with eye-tracking in virtual environment

BACKGROUND

Brain-computer interface (BCI) has become an effective human-machine interactive way. However, the performance of the traditional BCI system needs to be further improved, such as flexibility, robustness, and accuracy. We aim to develop an autonomous hybrid BCI system combined with eye-tracking for the control tasks in the virtual environment.

NEW METHOD

This work developed an autonomous control strategy and proposed an effective fusion method for electroencephalogram (EEG) and eye tracking. For the autonomous control, the sliding window method was adopted to analyze the user's eye-gaze data. When the variance of eye-gaze data was less than the threshold, target recognition was triggered. EEG and eye-gaze data were synchronously collected and fused for classification. In addition, a fusion method based on particle swarm optimization (PSO) was proposed, which can find the best fusion weights to adapt to the differences of single modalities.

RESULTS

EEG data and eye-gaze data of 15 subjects in steady-state visual evoked potentials (SSVEP) tasks were collected to evaluate the effectiveness of the hybrid BCI system. The results showed that the PSO fusion method performed best in all fusion methods. And the proposed hybrid BCI system obtained higher accuracy and information transfer rate (ITR) than the single-modality.

COMPARISON WITH EXISTING METHODS

The PSO fusion method was compared with average weighting fusion, prior weighting fusion, support vector machine, decision tree, random forest, and extreme random tree.

CONCLUSION

The proposed methods of autonomous control and dual-modal fusion can improve the flexibility, robustness and classification performance of the hybrid BCI system.

Computational detection of a genome instability-derived lncRNA signature for predicting the clinical outcome of lung adenocarcinoma

Evidence has been emerging of the importance of long non-coding RNAs (lncRNAs) in genome instability. However, no study has established how to classify such lncRNAs linked to genomic instability, and whether that connection poses a therapeutic significance. Here, we established a computational frame derived from mutator hypothesis by combining profiles of lncRNA expression and those of somatic mutations in a tumor genome, and identified 185 candidate lncRNAs associated with genomic instability in lung adenocarcinoma (LUAD). Through further studies, we established a six lncRNA-based signature, which assigned patients to the high- and low-risk groups with different prognosis. Further validation of this signature was performed in a number of separate cohorts of LUAD patients. In addition, the signature was found closely linked to genomic mutation rates in patients, indicating it could be a useful way to quantify genomic instability. In summary, this research offered a novel method by through which more studies may explore the function of lncRNAs and presented a possible new way for detecting biomarkers associated with genomic instability in cancers.

Synergistic Effects of Different Levels of Genomic Data for the Staging of Lung Adenocarcinoma: An Illustrative Study

Lung adenocarcinoma (LUAD) is a common and very lethal cancer. Accurate staging is a prerequisite for its effective diagnosis and treatment. Therefore, improving the accuracy of the stage prediction of LUAD patients is of great clinical relevance. Previous works have mainly focused on single genomic data information or a small number of different omics data types concurrently for generating predictive models. A few of them have considered multi-omics data from genome to proteome. We used a publicly available dataset to illustrate the potential of multi-omics data for stage prediction in LUAD. In particular, we investigated the roles of the specific omics data types in the prediction process. We used a self-developed method, Omics-MKL, for stage prediction that combines an existing feature ranking technique Minimum Redundancy and Maximum Relevance (mRMR), which avoids redundancy among the selected features, and multiple kernel learning (MKL), applying different kernels for different omics data types. Each of the considered omics data types individually provided useful prediction results. Moreover, using multi-omics data delivered notably better results than using single-omics data. Gene expression and methylation information seem to play vital roles in the staging of LUAD. The Omics-MKL method retained 70 features after the selection process. Of these, 21 (30%) were methylation features and 34 (48.57%) were gene expression features. Moreover, 18 (25.71%) of the selected features are known to be related to LUAD, and 29 (41.43%) to lung cancer in general. Using multi-omics data from genome to proteome for predicting the stage of LUAD seems promising because each omics data type may improve the accuracy of the predictions. Here, methylation and gene expression data may play particularly important roles.

Non-small-cell lung cancer classification via RNA-Seq and histology imaging probability fusion

BACKGROUND

Adenocarcinoma and squamous cell carcinoma are the two most prevalent lung cancer types, and their distinction requires different screenings, such as the visual inspection of histology slides by an expert pathologist, the analysis of gene expression or computer tomography scans, among others. In recent years, there has been an increasing gathering of biological data for decision support systems in the diagnosis (e.g. histology imaging, next-generation sequencing technologies data, clinical information, etc.). Using all these sources to design integrative classification approaches may improve the final diagnosis of a patient, in the same way that doctors can use multiple types of screenings to reach a final decision on the diagnosis. In this work, we present a late fusion classification model using histology and RNA-Seq data for adenocarcinoma, squamous-cell carcinoma and healthy lung tissue.

RESULTS

The classification model improves results over using each source of information separately, being able to reduce the diagnosis error rate up to a 64% over the isolate histology classifier and a 24% over the isolate gene expression classifier, reaching a mean F1-Score of 95.19% and a mean AUC of 0.991.

CONCLUSIONS

These findings suggest that a classification model using a late fusion methodology can considerably help clinicians in the diagnosis between the aforementioned lung cancer cancer subtypes over using each source of information separately. This approach can also be applied to any cancer type or disease with heterogeneous sources of information.

Deep learning in systems medicine

Systems medicine (SM) has emerged as a powerful tool for studying the human body at the systems level with the aim of improving our understanding, prevention and treatment of complex diseases. Being able to automatically extract relevant features needed for a given task from high-dimensional, heterogeneous data, deep learning (DL) holds great promise in this endeavour. This review paper addresses the main developments of DL algorithms and a set of general topics where DL is decisive, namely, within the SM landscape. It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine. Several key challenges have been highlighted including delivering clinical impact and improving interpretability. We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease. The review offers valuable insights and informs the research in DL and SM.