Martin Loza

Mr. Martin Loza

orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 January 2025 in Nature Communications
Verified
Journal Article
Open access
PDF file
YYYitao Yang
Yitao Yang
YCYang Cui
Yang Cui
XZXin Zeng
Xin Zeng
YZYubo Zhang
Yubo Zhang
MLMartin Loza
Martin Loza
Kenta NakaiKenta Nakai
Kenta Nakai
Spatial transcriptomics is an essential application for investigating cellular structures and interactions and requires multimodal information to precisely study spatial domains. Here, we propose STAIG, a deep-learning model that integrates gene expression, spatial coordinates, and histological images using graph-contrastive learning coupled with high-performance feature extraction. STAIG can integrate tissue slices without prealignment and remove batch effects. Moreover, it is designed to accept data acquired from various platforms, with or without histological images. By performing extensive benchmarks, we demonstrate the capability of STAIG to recognize spatial regions with high precision and uncover new insights into tumor microenvironments, highlighting its promising potential in deciphering spatial biological intricates.

15 March 2022 in NAR Genomics and Bioinformatics
Verified
Journal Article
Open access
PDF file
MLMartin Loza
Martin Loza
STShunsuke Teraguchi
Shunsuke Teraguchi
DSDaron Standley
Daron Standley
DDDiego Diez
Diego Diez
Single cell transcriptomic approaches are becoming mainstream, with replicate experiments commonly performed with the same single cell technology. Methods that enable integration of these datasets by removing batch effects while preserving biological information are required for unbiased data interpretation. Here, we introduce Canek for this purpose. Canek leverages information from mutual nearest neighbor to combine local linear corrections with cell-specific non-linear corrections within a fuzzy logic framework. Using a combination of real and synthetic datasets, we show that Canek corrects batch effects while introducing the least amount of bias compared with competing methods. Canek is computationally efficient and can easily integrate thousands of single-cell transcriptomes from replicated experiments.

12 December 2023 in Nucleic Acids Research
Verified
Journal Article
Open access
PDF file
MLMartin Loza
Martin Loza
AVAlexis Vandenbon
Alexis Vandenbon
Kenta NakaiKenta Nakai
Kenta Nakai
In this research, we elucidate the presence of around 11,000 housekeeping cis-regulatory elements (HK-CREs) and describe their main characteristics. Besides the trivial promoters of housekeeping genes, most HK-CREs reside in promoter regions and are involved in a broader role beyond housekeeping gene regulation. HK-CREs are conserved regions rich in unmethylated CpG sites. Their distribution highly correlates with that of protein-coding genes, and they interact with many genes over long distances. We observed reduced activity of a subset of HK-CREs in diverse cancer subtypes due to aberrant methylation, particularly those located in chromosome 19 and associated with zinc finger genes. Further analysis of samples from 17 cancer subtypes showed a significantly increased survival probability of patients with higher expression of these genes, suggesting them as housekeeping tumor suppressor genes. Overall, our work unravels the presence of housekeeping CREs indispensable for the maintenance and stability of cells.

28 September 2024 in NAR Genomics and Bioinformatics
Verified
Journal Article
Open access
XZXin Zeng
Xin Zeng
FGFuki Gyoja
Fuki Gyoja
YCYang Cui
Yang Cui
MLMartin Loza
Martin Loza
TKTakehiro G Kusakabe
Takehiro G Kusakabe
Kenta NakaiKenta Nakai
Kenta Nakai
Despite known single-cell expression profiles in vertebrate retinas, understanding of their developmental and evolutionary expression patterns among homologous cell classes remains limited. We examined and compared approximately 240 000 retinal cells from four species and found significant similarities among homologous cell classes, indicating inherent regulatory patterns. To understand these shared patterns, we constructed gene regulatory networks for each developmental stage for three of these species. We identified 690 regulons governed by 530 regulators across three species, along with 10 common cell class-specific regulators and 16 highly preserved regulons. RNA velocity analysis pinpointed conserved putative driver genes and regulators to retinal cell differentiation in both mouse and zebrafish. Investigation of the origins of retinal cells by examining conserved expression patterns between vertebrate retinal cells and invertebrate Ciona intestinalis photoreceptor-related cells implied functional similarities in light transduction mechanisms. Our findings offer insights into the evolutionarily conserved regulatory frameworks and differentiation drivers of vertebrate retinal cells.

19 December 2023 in bioRxiv
Verified
Preprint
Open access
PDF file
YYYitao Yang
Yitao Yang
YCYang Cui
Yang Cui
XZXin Zeng
Xin Zeng
YZYubo Zhang
Yubo Zhang
MLMartin Loza
Martin Loza
Kenta NakaiKenta Nakai
Kenta Nakai
Spatial transcriptomics is an essential application for investigating cellular structures and interactions and requires multimodal information to precisely study spatial domains. Here, we propose STAIG, a novel deep-learning model that integrates gene expression, spatial coordinates, and histological images using graph-contrastive learning coupled with high-performance feature extraction. STAIG can integrate tissue slices without prealignment and remove batch effects. Moreover, it was designed to accept data acquired from various platforms, with or without histological images. By performing extensive benchmarks, we demonstrated the capability of STAIG to recognize spatial regions with high precision and uncover new insights into tumor microenvironments, highlighting its promising potential in deciphering spatial biological intricates.

27 March 2024 in Briefings in Bioinformatics
Verified
Journal Article
Open access
PDF file
WZWeihang Zhang
Weihang Zhang
YCYang Cui
Yang Cui
BLBowen Liu
Bowen Liu
MLMartin Loza
Martin Loza
SPSung-Joon Park
Sung-Joon Park
Kenta NakaiKenta Nakai
Kenta Nakai
Reliable cell type annotations are crucial for investigating cellular heterogeneity in single-cell omics data. Although various computational approaches have been proposed for single-cell RNA sequencing (scRNA-seq) annotation, high-quality cell labels are still lacking in single-cell sequencing assay for transposase-accessible chromatin (scATAC-seq) data, because of extreme sparsity and inconsistent chromatin accessibility between datasets. Here, we present a novel automated cell annotation method that transfers cell type information from a well-labeled scRNA-seq reference to an unlabeled scATAC-seq target, via a parallel graph neural network, in a semi-supervised manner. Unlike existing methods that utilize only gene expression or gene activity features, HyGAnno leverages genome-wide accessibility peak features to facilitate the training process. In addition, HyGAnno reconstructs a reference–target cell graph to detect cells with low prediction reliability, according to their specific graph connectivity patterns. HyGAnno was assessed across various datasets, showcasing its strengths in precise cell annotation, generating interpretable cell embeddings, robustness to noisy reference data and adaptability to tumor tissues.