Drug-Homogeneity Index in Mass-Spectrometry Imaging

Artificial Intelligence-Driven Platform: Unveiling Critical Hepatic Molecular Alterations in Hepatocellular Carcinoma Development

Since most Hepatocellular Carcinoma (HCC) typically arises as a consequence of long-term liver damage, the hepatic molecular characteristics are closely related to the occurrence of HCC. Gaining comprehensive information about the location, morphology, and hepatic molecular alterations related to HCC is essential for accurate diagnosis. However, there is a dearth of technological advancements capable of concurrently providing precise HCC diagnosis and discerning the accompanying hepatic molecular alterations. In this study, an integrated information system is developed for the pathological-level diagnosis of HCC and the revelation of critical molecular alterations in the liver. This system utilizes computed tomography/Surface-enhanced Raman scattering combined with an artificial intelligence strategy to establish connections between the occurrence of HCC and alterations in hepatic biomolecules. Employing artificial intelligence techniques, the SERS spectra from both healthy and HCC groups are successfully classified into two distinct categories with a remarkable accuracy rate of 91.38%. Based on molecular profiling, it is identified that the nucleotide-to-lipid signal ratio holds significant potential as a reliable indicator for the occurrence of HCC, thereby serving as a promising tool for prevention and therapeutic surveillance.

Evaluation and comparison of unsupervised methods for the extraction of spatial patterns from mass spectrometry imaging data (MSI)

For the extraction of spatially important regions from mass spectrometry imaging (MSI) data, different clustering methods have been proposed. These clustering methods are based on certain assumptions and use different criteria to assign pixels into different classes. For high-dimensional MSI data, the curse of dimensionality also limits the performance of clustering methods which are usually overcome by pre-processing the data using dimension reduction techniques. In summary, the extraction of spatial patterns from MSI data can be done using different unsupervised methods, but the robust evaluation of clustering results is what is still missing. In this study, we have performed multiple simulations on synthetic and real MSI data to validate the performance of unsupervised methods. The synthetic data were simulated mimicking important spatial and statistical properties of real MSI data. Our simulation results confirmed that K-means clustering with correlation distance and Gaussian Mixture Modeling clustering methods give optimal performance in most of the scenarios. The clustering methods give efficient results together with dimension reduction techniques. From all the dimension techniques considered here, the best results were obtained with the minimum noise fraction (MNF) transform. The results were confirmed on both synthetic and real MSI data. However, for successful implementation of MNF transform the MSI data requires to be of limited dimensions.

PEGylated recombinant human hyaluronidase (PEGPH20) pre-treatment improves intra-tumour distribution and efficacy of paclitaxel in preclinical models

BACKGROUND

Scarce drug penetration in solid tumours is one of the possible causes of the limited efficacy of chemotherapy and is related to the altered tumour microenvironment. The abnormal tumour extracellular matrix (ECM) together with abnormal blood and lymphatic vessels, reactive stroma and inflammation all affect the uptake, distribution and efficacy of anticancer drugs.

METHODS

We investigated the effect of PEGylated recombinant human hyaluronidase PH20 (PEGPH20) pre-treatment in degrading hyaluronan (hyaluronic acid; HA), one of the main components of the ECM, to improve the delivery of antitumor drugs and increase their therapeutic efficacy. The antitumor activity of paclitaxel (PTX) in HA synthase 3-overexpressing and wild-type SKOV3 ovarian cancer model and in the BxPC3 pancreas xenograft tumour model, was evaluated by monitoring tumour growth with or without PEGPH20 pre-treatment. Pharmacokinetics and tumour penetration of PTX were assessed by HPLC and mass spectrometry imaging analysis in the same tumour models. Tumour tissue architecture and HA deposition were analysed by histochemistry.

RESULTS

Pre-treatment with PEGPH20 modified tumour tissue architecture and improved the antitumor activity of paclitaxel in the SKOV3/HAS3 tumour model, favouring its accumulation and more homogeneous intra-tumour distribution, as assessed by quantitative and qualitative analysis. PEGPH20 also reduced HA content influencing, though less markedly, PTX distribution and antitumor activity in the BxPC3 tumour model.

CONCLUSION

Remodelling the stroma of HA-rich tumours by depletion of HA with PEGPH20 pre-treatment, is a potentially successful strategy to improve the intra-tumour distribution of anticancer drugs, increasing their therapeutic efficacy, without increasing toxicity.

A methodological approach to correlate tumor heterogeneity with drug distribution profile in mass spectrometry imaging data

BACKGROUND

Drug mass spectrometry imaging (MSI) data contain knowledge about drug and several other molecular ions present in a biological sample. However, a proper approach to fully explore the potential of such type of data is still missing. Therefore, a computational pipeline that combines different spatial and non-spatial methods is proposed to link the observed drug distribution profile with tumor heterogeneity in solid tumor. Our data analysis steps include pre-processing of MSI data, cluster analysis, drug local indicators of spatial association (LISA) map, and ions selection.

RESULTS

The number of clusters identified from different tumor tissues. The spatial homogeneity of the individual cluster was measured using a modified version of our drug homogeneity method. The clustered image and drug LISA map were simultaneously analyzed to link identified clusters with observed drug distribution profile. Finally, ions selection was performed using the spatially aware method.

CONCLUSIONS

In this paper, we have shown an approach to correlate the drug distribution with spatial heterogeneity in untargeted MSI data. Our approach is freely available in an R package 'CorrDrugTumorMSI'.

Spatial Metabolomics and Imaging Mass Spectrometry in the Age of Artificial Intelligence

Spatial metabolomics is an emerging field of omics research that has enabled localizing metabolites, lipids, and drugs in tissue sections, a feat considered impossible just two decades ago. Spatial metabolomics and its enabling technology-imaging mass spectrometry-generate big hyper-spectral imaging data that have motivated the development of tailored computational methods at the intersection of computational metabolomics and image analysis. Experimental and computational developments have recently opened doors to applications of spatial metabolomics in life sciences and biomedicine. At the same time, these advances have coincided with a rapid evolution in machine learning, deep learning, and artificial intelligence, which are transforming our everyday life and promise to revolutionize biology and healthcare. Here, we introduce spatial metabolomics through the eyes of a computational scientist, review the outstanding challenges, provide a look into the future, and discuss opportunities granted by the ongoing convergence of human and artificial intelligence.

Unsupervised segmentation of mass spectrometric ion images characterizes morphology of tissues

MOTIVATION

Mass spectrometry imaging (MSI) characterizes the spatial distribution of ions in complex biological samples such as tissues. Since many tissues have complex morphology, treatments and conditions often affect the spatial distribution of the ions in morphology-specific ways. Evaluating the selectivity and the specificity of ion localization and regulation across morphology types is biologically important. However, MSI lacks algorithms for segmenting images at both single-ion and spatial resolution.

RESULTS

This article contributes spatial-Dirichlet Gaussian mixture model (DGMM), an algorithm and a workflow for the analyses of MSI experiments, that detects components of single-ion images with homogeneous spatial composition. The approach extends DGMMs to account for the spatial structure of MSI. Evaluations on simulated and experimental datasets with diverse MSI workflows demonstrated that spatial-DGMM accurately segments ion images, and can distinguish ions with homogeneous and heterogeneous spatial distribution. We also demonstrated that the extracted spatial information is useful for downstream analyses, such as detecting morphology-specific ions, finding groups of ions with similar spatial patterns, and detecting changes in chemical composition of tissues between conditions.

AVAILABILITY AND IMPLEMENTATION

The data and code are available at https://github.com/Vitek-Lab/IonSpattern.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.