{"data":{"event":{"id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","slug":"novel-two-stage-deep-learning-based-approach-applied-to-gene-expression--78553cf366","title":"\n\nNovel two-stage deep learning-based approach applied to gene expression data pertaining to esophageal adenocarcinoma boosting biological knowledge discovery \n\n","short_summary":"Esophageal cancer (EC) is characterized by complex transcriptional alterations and therapeutic resistance, posing challenges for traditional computational methods. In this study, we propose a deep learning (DL)-based computational framework to identify important genes and biologically relevant pathways in bulk cell RNA-seq data (GSE234304 and GSE273848), which comprise tumor and non-tumor esophageal tissue samples. A fully connected feedforward neural network was trained for binary classification, and two feature selection strategies were implemented: Neural Network followed by Support Vector ","full_description":"Esophageal cancer (EC) is characterized by complex transcriptional alterations and therapeutic resistance, posing challenges for traditional computational methods. In this study, we propose a deep learning (DL)-based computational framework to identify important genes and biologically relevant pathways in bulk cell RNA-seq data (GSE234304 and GSE273848), which comprise tumor and non-tumor esophageal tissue samples. A fully connected feedforward neural network was trained for binary classification, and two feature selection strategies were implemented: Neural Network followed by Support Vector Regression (NN+SVR) and Integrated Gradients combined with SVR (IG+SVR). The genes were then ranked according to their weights in SVR deriving the importance scores, and the top 100 genes were subjected to enrichment analysis using Enrichr and Metascape. The proposed DL-based approaches identified a greater number of expressed genes across established esophageal cancer cell lines than LIMMA, SAM, and the t-test did. Specifically, in the GSE234304 dataset, IG + SVR, our best method, identified a total of 9 expressed genes while the best baseline method, LIMMA, identified a total of 3 expressed genes. In terms of GSE273848 dataset, IG + SVR was also the best identifying a total of 11 expressed genes while the best baseline method, t-test, had a total of 7 expressed genes. The key genes identified included CEBPB, SUMO1, RORA, STAT1, GATA, OCT1, RUNX1, and NR3C1, as well as pathways related to nucleoprotein maturation, collagen fibril organization, the immunoglobulin-mediated immune response, immune regulation, and insulin signaling. These results show that combining neural networks and attribution-based regression creates an effective and interpretable framework for selecting genes in esophageal cancer research.\n\nUpdate (2026-09-18): \n\nPep-PU-GAN: Positive-Unlabeled Adversarial Learning for Peptide Function Prediction \n\n. Peptide classification remains challenging in bioinformatics because of limited labeled data, particularly the scarcity of verified negative examples, and the complex relationship between amino acid sequences and biological functions. This study introduces Pep-PU-GAN, a deep learning framework that combines positive-unlabeled (PU) learning, generative adversarial networks (GANs), and graph neural networks (GNNs) for peptide classification. Peptides are represented as sequence-derived residue graphs, with amino acids as nodes and edges connecting adjacent residues, enabling attention-based message passing over local neighborhoods. The architecture includes a generator that produces synthetic peptide embeddings in encoder space and a dual-function discriminator that distinguishes real from synthetic embeddings while performing PU classification. Training uses a custom loss integrating non-negative PU (nnPU) risk estimation with adversarial objectives. A self-training mechanism further incorporates high-confidence synthetic positive embeddings to augment the training set an\n\nUpdate (2026-09-21): \n\nIndividual-level expression deconvolution and assessment of cross-sample variation \n\n. Recovering cell-type-specific gene expression from bulk RNA sequencing would facilitate the study of transcriptional variation among individuals. However, accuracy can differ substantially among genes and cell types. We describe a reference-informed Bayesian deconvolution framework and a score that identifies gene--cell-type pairs likely to have more accurate estimates of cross-sample variation. The score uses bulk counts, reference expression profiles, and estimated RNA proportions. Known component expression is used to train and evaluate the score, but is not needed to calculate predictions from a trained model. We evaluated the approach in a ROSMAP-derived simulation with 40 target donors, 2,000 genes, and seven cell types. Median gene-wise correlation was 0.801 for raw allocated counts and 0.296 after normalization within each donor and cell type. To evaluate the score, we divided genes into five sets, kept linked genes together, and scored each set using a model trained on the other four. Retaining approximately 20% of pairs within each cell type increased the median\n\nUpdate (2026-09-22): \n\nStackHPpred: A Stacking-based ensemble learning framework for the identification of peptide hormones using multi-view feature representations \n\n. Peptide hormones are important signaling molecules that regulate diverse physiological processes and have substantial therapeutic relevance. However, their experimental identification can be challenging because of low abundance, limited stability, and complex post-translational processing, highlighting the need for reliable computational approaches. Here, we present StackHPpred, a stacking-based ensemble framework for accurate identification of hormone peptides (HPs) from amino acid sequences. We systematically evaluated 56 feature representations, comprising 35 conventional sequence descriptors and 21 PLM/NLP-based embeddings, across 10 machine-learning classifiers, generating 560 baseline models. Prediction-level correlation analysis was subsequently employed to identify 14 complementary, non-redundant feature representations, which were integrated through feature- and classifier-level stacking strategies using out-of-fold predicted probabilities. The final StackHPpred model, based on the top three feature repre\n\nUpdate (2026-09-24): \n\nSingle-Sample Network Topology Unveils Pathogenic Hubs in Sjögren's Disease \n\n. Sjogren's disease (SD) is a systemic autoimmune condition characterized by extensive clinical and biological heterogeneity, complicating the development of targeted therapies. To better describe the personalized molecular rewiring driving SD pathogenesis, we utilized bulk RNA-sequencing data from whole blood samples of the PRECISESADS IMI consortium to construct sample-specific gene interaction networks by applying the LIONESS algorithm integrated with experimental protein-protein interaction evidence. Comparing SD patients against healthy controls, we identified an absolute total of 647 Differentially Interacting Genes (DIGs) representing structural shifts in network connectivity. Topological clustering of these DIGs revealed four major functional macro-modules underlying disease pathology: defense response to virus, B cell activation, DNA replication, and positive regulation of protein catabolic process. Central topological hubs, such as ISG15, OASL, UBE2L6, and LGALS3BP, were identified as drivers of this reorganization, a fact supported by integrating network topology with ","ledger_type":"benefit","primary_domain_id":"8f1af1b9-7302-4b51-aae9-fdfac04d158a","event_status":"provisional","event_date":"2026-09-18T00:00:00.000Z","discovery_date":"2026-09-18T00:00:00.000Z","first_published_date":"2026-09-18T00:00:00.000Z","last_reviewed_date":"2026-09-24T00:00:00.000Z","geographic_scope":"International","affected_population":null,"base_impact_tier":1,"base_score":"1.00","attribution_multiplier":"0.5000","evidence_multiplier":"0.5000","realization_multiplier":"0.4000","durability_multiplier":"0.5000","current_event_score":"0.050000","confidence_level":"low","score_explanation":"Ingest update: raised attribution; independent source raised evidence; raised realization; added a follow-up source. Score remains provisional until review. Follow-up ingest: independent source raised evidence; added a follow-up source. Follow-up ingest: independent source raised evidence; added a follow-up source. Follow-up ingest: added a follow-up source.","methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","original_methodology_version_id":"8745541b-0f8e-4d5a-9b47-5291d3813a8d","published_at":"2026-09-19T00:01:53.216Z","created_at":"2026-09-19T00:01:53.216Z","updated_at":"2026-09-24T17:01:04.095Z","flags":[],"domain_name":"Biology","domain_slug":"biology","methodology_version":"0.2"},"contributions":[{"id":"ca1a439a-96e3-4a27-8a84-97ac52c2a04b","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","model_id":"535014f7-c941-4d39-aa9b-8f9c1d3d07b7","role_description":"Unspecified system mentioned or implied by a news item. Remap to a named release when identified.","attribution_multiplier":"0.5000","credit_share":"1.0000","contribution_score":"0.050000","attribution_rationale":"News ingest does not infer a named model from the publisher alone. Attribution stays unspecified until a release is identified.","attribution_confidence":"medium","first_used_date":"2026-09-18T00:00:00.000Z","model_version_if_known":null,"review_status":"approved","created_at":"2026-09-19T00:01:53.253Z","model_slug":"unspecified-ai-system","model_name":"Unspecified AI system","identity_class":"unknown","is_internal":false,"family_name":"Unspecified","family_slug":"unknown-unspecified","organization_name":"Unknown","organization_slug":"unknown"}],"sources":[{"id":"c7cec50b-78f0-4c32-8abc-d43e3cad9464","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.12.751181v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.12.751181v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-18T00:00:00.000Z","retrieved_at":"2026-09-19T00:01:53.267Z","title":"\n\nNovel two-stage deep learning-based approach applied to gene expression data pertaining to esophageal adenocarcinoma boosting biological knowledge discovery \n\n","excerpt":"Esophageal cancer (EC) is characterized by complex transcriptional alterations and therapeutic resistance, posing challenges for traditional computational methods. In this study, we propose a deep learning (DL)-based computational framework to identify important genes and biologically relevant pathways in bulk cell RNA-seq data (GSE234304 and GSE273848), which comprise tumor and non-tumor esophageal tissue samples. A fully connected feedforward neural network was trained for binary classificatio","content_hash":null,"source_reliability_class":"medium","is_primary_source":true,"is_independent":true,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-19T00:01:53.267Z"},{"id":"b83d8dc4-dc83-462a-8bcf-a8a57c19107d","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.13.751209v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.13.751209v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-18T00:00:00.000Z","retrieved_at":"2026-09-19T00:01:53.556Z","title":"\n\nPep-PU-GAN: Positive-Unlabeled Adversarial Learning for Peptide Function Prediction \n\n","excerpt":"Peptide classification remains challenging in bioinformatics because of limited labeled data, particularly the scarcity of verified negative examples, and the complex relationship between amino acid sequences and biological functions. This study introduces Pep-PU-GAN, a deep learning framework that combines positive-unlabeled (PU) learning, generative adversarial networks (GANs), and graph neural networks (GNNs) for peptide classification. Peptides are represented as sequence-derived residue gra","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-19T00:01:53.556Z"},{"id":"95febdb0-f4a1-4011-8a83-cdb28dc45bbd","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.14.751599v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.14.751599v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-21T00:00:00.000Z","retrieved_at":"2026-09-21T15:01:00.425Z","title":"\n\nIndividual-level expression deconvolution and assessment of cross-sample variation \n\n","excerpt":"Recovering cell-type-specific gene expression from bulk RNA sequencing would facilitate the study of transcriptional variation among individuals. However, accuracy can differ substantially among genes and cell types. We describe a reference-informed Bayesian deconvolution framework and a score that identifies gene--cell-type pairs likely to have more accurate estimates of cross-sample variation. The score uses bulk counts, reference expression profiles, and estimated RNA proportions. Known compo","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-21T15:01:00.425Z"},{"id":"feed48d8-a9f0-4b5a-ab98-66a94228e3a3","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.16.751134v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.16.751134v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-22T00:00:00.000Z","retrieved_at":"2026-09-22T21:01:01.159Z","title":"\n\nStackHPpred: A Stacking-based ensemble learning framework for the identification of peptide hormones using multi-view feature representations \n\n","excerpt":"Peptide hormones are important signaling molecules that regulate diverse physiological processes and have substantial therapeutic relevance. However, their experimental identification can be challenging because of low abundance, limited stability, and complex post-translational processing, highlighting the need for reliable computational approaches. Here, we present StackHPpred, a stacking-based ensemble framework for accurate identification of hormone peptides (HPs) from amino acid sequences. W","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-22T21:01:01.159Z"},{"id":"b51b37b9-2bd4-4053-ab37-762fc69cfcb7","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.16.752113v1?rss=1\n","canonical_url":"\nhttps://www.biorxiv.org/content/10.64898/2026.09.16.752113v1?rss=1\n","source_type":"preprint","publisher":"bioRxiv","author":null,"publication_date":"2026-09-24T00:00:00.000Z","retrieved_at":"2026-09-24T17:01:04.087Z","title":"\n\nSingle-Sample Network Topology Unveils Pathogenic Hubs in Sjögren's Disease \n\n","excerpt":"Sjogren's disease (SD) is a systemic autoimmune condition characterized by extensive clinical and biological heterogeneity, complicating the development of targeted therapies. To better describe the personalized molecular rewiring driving SD pathogenesis, we utilized bulk RNA-sequencing data from whole blood samples of the PRECISESADS IMI consortium to construct sample-specific gene interaction networks by applying the LIONESS algorithm integrated with experimental protein-protein interaction ev","content_hash":null,"source_reliability_class":"medium","is_primary_source":false,"is_independent":false,"is_peer_reviewed":false,"archived_url":null,"created_at":"2026-09-24T17:01:04.087Z"}],"claims":[{"id":"088b29aa-fda1-4aa3-8352-f9c3ff57fafd","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","claim_text":"\n\nNovel two-stage deep learning-based approach applied to gene expression data pertaining to esophageal adenocarcinoma boosting biological knowledge discovery \n\n","claim_type":"outcome","claim_status":"supported","confidence_score":null,"created_at":"2026-09-19T00:01:53.275Z","updated_at":"2026-09-19T00:01:53.275Z"}],"revisions":[{"id":"3a736b1f-ec76-46ea-b452-386faee89bad","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","model_id":null,"previous_score":"0.000000","new_score":"0.001000","previous_factors":{},"new_factors":{"tier":1,"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"change_reason":"Auto-published from news ingest.","trigger_type":"news_ingest","trigger_source_ids":null,"reviewer_id":null,"review_status":"published","created_at":"2026-09-19T00:01:53.291Z"},{"id":"bd56e26d-498f-4bfe-a78b-e74ef89007a3","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","model_id":null,"previous_score":"0.001000","new_score":"0.035000","previous_factors":{"tier":1,"evidence":0.1,"base_score":1,"durability":0.5,"attribution":0.1,"realization":0.2},"new_factors":{"tier":1,"models":["535014f7-c941-4d39-aa9b-8f9c1d3d07b7"],"evidence":0.35,"base_score":1,"durability":0.5,"attribution":0.5,"realization":0.4},"change_reason":"Ingest update: raised attribution; independent source raised evidence; raised realization; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["b83d8dc4-dc83-462a-8bcf-a8a57c19107d"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-19T00:01:53.585Z"},{"id":"77ab70a1-a97b-4551-84ef-08b5c87a5d40","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","model_id":null,"previous_score":"0.035000","new_score":"0.045000","previous_factors":{"tier":1,"evidence":0.35,"base_score":1,"durability":0.5,"attribution":0.5,"realization":0.4},"new_factors":{"tier":1,"models":["535014f7-c941-4d39-aa9b-8f9c1d3d07b7"],"evidence":0.45,"base_score":1,"durability":0.5,"attribution":0.5,"realization":0.4},"change_reason":"Ingest update: independent source raised evidence; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["95febdb0-f4a1-4011-8a83-cdb28dc45bbd"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-21T15:01:00.448Z"},{"id":"7c0e2084-e750-4ab8-899f-1a3899a1002c","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","model_id":null,"previous_score":"0.045000","new_score":"0.050000","previous_factors":{"tier":1,"evidence":0.45,"base_score":1,"durability":0.5,"attribution":0.5,"realization":0.4},"new_factors":{"tier":1,"models":["535014f7-c941-4d39-aa9b-8f9c1d3d07b7"],"evidence":0.5,"base_score":1,"durability":0.5,"attribution":0.5,"realization":0.4},"change_reason":"Ingest update: independent source raised evidence; added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["feed48d8-a9f0-4b5a-ab98-66a94228e3a3"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-22T21:01:01.190Z"},{"id":"3be440b7-e09a-4381-80e2-b5f89b75a4cd","event_id":"55a1e92b-e6fa-47bb-89f0-95b02135de54","model_id":null,"previous_score":"0.050000","new_score":"0.050000","previous_factors":{"tier":1,"evidence":0.5,"base_score":1,"durability":0.5,"attribution":0.5,"realization":0.4},"new_factors":{"tier":1,"models":["535014f7-c941-4d39-aa9b-8f9c1d3d07b7"],"evidence":0.5,"base_score":1,"durability":0.5,"attribution":0.5,"realization":0.4},"change_reason":"Ingest update: added a follow-up source.","trigger_type":"ingest_update","trigger_source_ids":["b51b37b9-2bd4-4053-ab37-762fc69cfcb7"],"reviewer_id":null,"review_status":"published","created_at":"2026-09-24T17:01:04.103Z"}],"secondary":[]},"methodology_version":"0.1"}