Biology subjects

Sriswasdi, S.

Publications and source records attributed to Sriswasdi, S..

7 recordsLinked to original sources

bioRxiv2026

Do Symptoms Matter? Investigating Symptom-Based Lesion Network Mapping.

Lesion network mapping (LNM) describes a group of methods using normative functional connectivity data to map disparate brain lesions and stimulation sites onto common brain networks. Van den Heuvel and colleagues recently showed that these methods lack disease specificity, instead producing maps that converge toward intrinsic properties of the normative connectome dataset. Here, we investigate symptom LNM (sLNM), a recent advancement in the method which attempts to increase the robustness of results by incorporating symptom severity and incorporating replication across multiple datasets and prediction of clinical outcomes. Using clinical datasets of depression and Brocas aphasia, we show that sLNM maps from unrelated disorders nonetheless converge despite using null models which break the specific lesion-symptom structure in the datasets. Using simulated datasets with a known ground-truth disease network, we show that sLNM results are systematically biased towards the normative connectomes first principal component (PC1), which drives spurious convergence across unrelated datasets. We further show that the apparent clinical predictive capability of these maps are non-specific: network maps derived from unrelated disorders such as migraine and aphasia predict brain stimulation improvement in depression as well as -- or better than -- the cohorts own sLNM map. However, controlling for PC1 reduces spurious convergence across unrelated datasets and improves clinical prediction specificity, supporting the notion that disease-specific signal exists within sLNM but is confounded by the globally present PC1 signal in the normative connectome. These findings offer a practical correction applicable to existing and future sLNM studies.

neuroscience↗

bioRxiv2026

Mass Spectrometry-Based Profiling of Personalized Immunopeptidomes in Thai Renal Cell Carcinoma

This study profiles the personalized immunopeptidomes of 13 Thai patients with renal cell carcinoma (RCC), addressing a critical knowledge gap in Southeast Asian populations characterized by distinct HLA allele distributions. We combined whole-exome sequencing (WES)-based personalized proteome construction with liquid chromatography-tandem mass spectrometry (LC-MS/MS), using both database-driven searches and de novo peptide sequencing. HLA typing identified seven alleles not previously represented in major immunopeptidome databases, with HLA-A*11:01 being the most frequent (69%). Database-based analysis identified a single tumor-specific neoantigen derived from a mutant JADE2 peptide in the patient with the highest tumor mutational burden, which was validated by a mutant-specific ELISPOT response. In contrast, de novo sequencing revealed numerous non-canonical peptides, a subset of which were supported by proteogenomic validation using PepQuery and detected exclusively in cancer proteomes but not in normal tissue datasets, indicating their potential as tumor-associated antigens. Together, these results establish an integrated and scalable framework for identifying HLA-presented tumor-derived peptides and provide a foundational immunopeptidome resource to support personalized cancer immunotherapy development in Southeast Asia.

systems biology↗

bioRxiv2023

Label-free tumor cells classification using deep learning and high-content imaging

Many studies have shown that cellular morphology can be used to distinguish spiked-in tumor cells in blood sample background. However, most validation experiments included only homogeneous cell lines and inadequately captured the broad morphological heterogeneity of cancer cells. Further-more, normal, non-blood cells could be erroneously classified as cancer because their morphology differ from blood cells. Here, we constructed a database of microscopic images of organoid-derived cancer and normal cell with diverse morphology and developed a proof-of-concept deep learning model that can distinguish cancer cells from normal cells within an unlabeled microscopy image. In total, more than 75,000 organoid-drived cells from 3 cholangiocarcinoma patients were collected. The model achieved an area under the receiver operating characteristics curve (AUROC) of 0.78 and can generalize to cell images from an unseen patient. These resources serve as a foundation for an automated, robust platform for circulating tumor cell detection.

bioinformatics↗

bioRxiv2021

An explainable self-attention deep neural network for detecting mild cognitive impairment using multi-inputbdigital drawing tasks

Mild cognitive impairment (MCI) is an early stage of age-inappropriate cognitive decline, which could develop into dementia - an untreatable neurodegenerative disorder. An early detection of MCI is a crucial step for timely prevention and intervention. To tackle this problem, recent studies have developed deep learning models to detect MCI and various types of dementia using data obtained from the classic clock-drawing test (CDT), a popular neuropsychological screening tool that can be easily and rapidly implemented for assessing cognitive impairments in an aging population. While these models succeed at distinguishing severe forms of dementia, it is still difficult to predict the early stage of the disease using the CDT data alone. Also, the state-of-the-art deep learning techniques still face the black-box challenges, making it questionable to implement them in the clinical setting. Here, we propose a novel deep learning modeling framework that incorporates data from multiple drawing tasks including the CDT, cube-copying, and trail-making tasks obtained from a digital platform. Using self-attention and soft-label methods, our model achieves much higher classification performance at detecting MCI compared to those of a well-established convolutional neural network model. Moreover, our model can highlight features of the MCI data that considerably deviate from those of the healthy aging population, offering accurate predictions for detecting MCI along with visual explanation that aids the interpretation of the deep learning model.

neuroscience↗

bioRxiv2021

Unsupervised mining of HLA-I peptidomes reveals new binding motifs and substantial false positives in community database

Modern vaccine designs and studies of human leukocyte antigen (HLA)-mediated immune responses rely heavily on the knowledge of HLA allele-specific binding motifs and computational prediction of HLA-peptide binding affinity. Breakthroughs in HLA peptidomics have considerably expanded the databases of natural HLA ligands and enabled detailed characterizations of HLA-peptide binding specificity. However, cautions must be made when analyzing HLA peptidomics data because identified peptides may be contaminants in mass spectrometry or may weakly bind to the HLA molecules. Here, a hybrid de novo peptide sequencing approach was applied to large-scale mono-allelic HLA peptidomics datasets to uncover new ligands and refine current knowledge of HLA binding motifs. Up to 12-40% of the peptidomics data were low-binding affinity peptides with an arginine or a lysine at the C-terminus and likely to be tryptic peptide contaminants. Thousands of these peptides have been reported in a community database as legitimate ligands and might be erroneously used for training prediction models. Furthermore, unsupervised clustering of identified ligands revealed additional binding motifs for several HLA class I alleles and effectively isolated outliers that were experimentally confirmed to be false positives. Overall, our findings expanded the knowledge of HLA binding specificity and advocated for more rigorous interpretation of HLA peptidomics data that will ensure the high validity of community HLA ligandome databases.

immunology↗

bioRxiv2019

Uncovering thousands of new HLA antigens and phosphopeptides with deep learning-based sequence-mask-search de novo peptide sequencing framework

Typical analyses of mass spectrometry data only identify amino acid sequences that exist in reference databases. This restricts the possibility of discovering new peptides such as those that contain uncharacterized mutations or originate from unexpected processing of RNAs and proteins. De novo peptide sequencing approaches address this limitation but often suffer from low accuracy and require extensive validation by experts. Here, we develop SMSNet, a deep learning-based hybrid de novo peptide sequencing framework that achieves >95% amino acid accuracy while retaining good identification coverage. Applications of SMSNet on landmark proteomics and peptideomics studies reveal over 10,000 previously uncharacterized HLA antigens and phosphopeptides and in conjunction with database-search methods, expand the coverage of peptide identification by almost 30%. The power to accurately identify new peptides of SMSNet would make it an invaluable tool for any future proteomics and peptidomics studies - especially cancer neoantigen discovery and proteome characterization of non-model organisms.

bioinformatics↗

bioRxiv2018

Universal MHC binding prediction

Immunotherapy is an emerging approach in cancer treatment that activates the host immune system to destroy cancer cells that express unique peptide signatures (neoepitopes). Administrations of cancer-specific neoepitopes in the form of synthetic peptide vaccine have been proven effective in both mouse models and human patients. Because only a tiny fraction of cancer-specific neoepitopes actually elicit immune response, selection of potent, immunogenic neoepitopes remains a challenging step in cancer vaccine development. A basic approach for immunogenicity prediction is based on the premise that effective neoepitope should bind with the Major Histocompatibility Complex (MHC) with high affinity. In this study, we developed MHCSeqNet, an open-source deep learning model, which not only competes favorably with state-of-the-art predictors but also exhibits promising generalization to new MHC class I and class II alleles. MHCSeqNet employed neural network architectures developed for natural language processing to model amino acid sequence representations of MHC allele and epitope peptide as sentences with amino acids as individual words. This consideration allows MHCSeqNet to accept new MHC alleles as well as peptides of any length. The flexibility offered by MHCSeqNet should make it a valuable tool for screening effective neoepitopes in cancer vaccine development.\n\nAvailability and implementationhttps://github.com/cmbcu/MHCSeqNet

bioinformatics↗