Evaluation and optimization of sequence-based gene regulatory deep learning models
Ontology highlight
ABSTRACT:
PROVIDER: PRJNA1070665 | ENA |
REPOSITORIES: ENA
Dataset's files
| Action | DRS | |||
|---|---|---|---|---|
| SRR27765223_1.fastq.gz | Fastqsanger.gz | |||
| SRR27765223_2.fastq.gz | Fastqsanger.gz | |||
| SRR27765224_1.fastq.gz | Fastqsanger.gz | |||
| SRR27765224_2.fastq.gz | Fastqsanger.gz | |||
| SRR27765225_1.fastq.gz | Fastqsanger.gz |
Items per page: 5 1 - 5 of 72 |
Similar Datasets
Project description:As training dataset for Random Promoter DREAM Challenge 2022, we generated ~6.7 million synthetic promoters (in yeast) comprised of random DNA (N80) and measured their expression by FACS (sorting into 18 bins). As test dataset for Random Promoter DREAM Challenge 2022, we generated ~71k synthetic promoters (in yeast) comprised of designed DNA (NBT) and measured their expression by FACS (sorting into 18 bins).
2024-02-03 | GSE254493 | GEO
Project description:Neural networks have emerged as immensely powerful tools in predicting functional genomic regions, notably evidenced by recent successes in deciphering gene regulatory logic. However, a systematic evaluation of how model architectures and training strategies impact genomics model performance is lacking. To address this gap, we held a DREAM Challenge where competitors trained models on a dataset of millions of random promoter DNA sequences and corresponding expression levels, experimentally determined in yeast, to best capture the relationship between regulatory DNA and gene expression. For a robust evaluation of the models, we designed a comprehensive suite of benchmarks encompassing various sequence types. While some benchmarks produced similar results across the top-performing models, others differed substantially. All top-performing models used neural networks, but diverged in architectures and novel training strategies, tailored to genomics sequence data. To dissect how architectural and training choices impact performance, we developed the Prix Fixe framework to divide any given model into logically equivalent building blocks. We tested all possible combinations for the top three models and observed performance improvements for each. The DREAM Challenge models not only achieved state-of-the-art results on our comprehensive yeast dataset but also consistently surpassed existing benchmarks on Drosophila and human genomic datasets. Overall, we demonstrate that high-quality gold-standard genomics datasets can drive significant progress in model development.
| S-EPMC10888977 | biostudies-literature
Project description:Accurate prediction of cell cycle phases is important in understanding how certain diseases (e.g. cancer) develop and respond to treatment. It is also essential for reducing the confounding effects in single-cell RNA sequencing (scRNA-Seq) data analysis. We evaluated both traditional machine learning techniques and deep learning approaches for predicting cell cycle phases from scRNA-seq data. Models were trained on consensus predictions from four popular cell cycle analysis tools, namely, CellCycleScore, ccAF, Revelio, and Tricycle, then applied to unlabeled scRNA-seq data generated from human leukemia cell lines. We evaluated model performance using publicly available datasets, GSE146773 (human leukemia cells, 1,151 cells) and GSE64016 (human embryonic stem cells, 213 cells), both labeled with their respective cell cycle phases through experiments. In addition to the four tools, we assessed traditional machine learning models (AdaBoost, Random Forest, and LightGBM), deep learning models including multiple dense networks DNN (2-5), CNN, Hybrid CNN-Dense, Feature embedding, and ensemble models. DNN 3 achieved the highest accuracy, reaching 75.16% on the GSE146773 dataset and 70.85% on GSE64016. This outperformed existing tools such as Revelio (68.34% on GSE146773, 68.2% on GSE64016), CellCycleScore (66.54% on GSE146773, 53.84% on GSE64016), ccAF (45% on GSE146773, 40% on GSE64016), ccAFv2 (47.23% on GSE146773, 43.72% on GSE64016), Tricycle (53.23% on GSE146773, 58.7% on GSE64016), and Cyclum (38.52% on GSE146773, 26.3% for GSE64016). These results signify the potential of deep learning models for robust cell cycle phase prediction in scRNA-seq data.
2025-10-22 | GSE293316 | GEO
Project description:Generating and analyzing overlapping peptides through multienzymatic digestion is an efficient procedure for de novo protein using from bottom-up mass spectrometry (MS). Despite improved instrumentation and software, de novo MS data analysis remains challenging. In recent years, deep learning models have represented a performance breakthrough. Incorporating that technology into de novo protein sequencing workflows require machine-learning models capable of handling highly diverse MS data. In this study, we analyzed the requirements for assembling such generalizable deep learning models by systematically varying the composition and size of the training set. We assessed the generated models' performances using two test sets composed of peptides originating from the multienzyme digestion of samples from various species. The peptide recall values on the test sets showed that the deep learning models generated from a collection of highly N- and C-termini diverse peptides generalized 76% more over the termini-restricted ones. Moreover, expanding the training set's size by adding peptides from the multienzymatic digestion with five proteases of several species samples led to a 2-3 fold generalizability gain. Furthermore, we tested the applicability of these multienzyme deep learning (MEM) models by fully de novo sequencing the heavy and light monomeric chains of five commercial antibodies (mAbs). MEMs extracted over 10000 matching and overlapped peptides across six different proteases mAb samples, achieving a 100% sequence coverage for 8 of the ten polypeptide chains. We foretell that the MEMs' proven improvements to de novo analysis will positively impact several applications, such as analyzing samples of high complexity, unknown nature, or the peptidomics field.
2023-01-16 | PXD037803 | Pride
Project description:Evaluation of animal models of AD
| PRJNA408065 | ENA
Project description:Functional Optimization of Designer Cardiac Organoids Enabled by Machine Learning Techniques
| PRJNA1111511 | ENA
Project description:Drug-induced cardiotoxicity and hepatotoxicity are major causes of drug attrition. To decrease late-stage drug attrition, pharmaceutical and biotechnology industries need to establish biologically relevant models that use phenotypic screening to detect drug-induced toxicity in vitro. In this study, we sought to rapidly detect patterns of cardiotoxicity using high-content image analysis with deep learning and induced pluripotent stem cell-derived cardiomyocytes (iPSC-CMs). We screened a library of 1280 bioactive compounds and identified those with potential cardiotoxic liabilities in iPSC-CMs using a single-parameter score based on deep learning. Compounds demonstrating cardiotoxicity in iPSC-CMs included DNA intercalators, ion channel blockers, epidermal growth factor receptor, cyclin-dependent kinase, and multi-kinase inhibitors. We also screened a diverse library of molecules with unknown targets and identified chemical frameworks that show cardiotoxic signal in iPSC-CMs. By using this screening approach during target discovery and lead optimization, we can de-risk early-stage drug discovery. We show that the broad applicability of combining deep learning with iPSC technology is an effective way to interrogate cellular phenotypes and identify drugs that may protect against diseased phenotypes and deleterious mutations.
2021-07-07 | GSE172181 | GEO
Project description:The coronavirus disease of 2019 pandemic has catalyzed the rapid development of mRNA vaccines, whereas, how to optimize the mRNA sequence of exogenous gene such as severe acute respiratory syndrome coronavirus 2 spike to fit human cells remains a critical challenge. A new algorithm, iDRO (integrated deep-learning-based mRNA optimization), is developed to optimize multiple components of mRNA sequences based on given amino acid sequences of target protein. Considering the biological constraints, we divided iDRO into two steps: open reading frame (ORF) optimization and 5' untranslated region (UTR) and 3'UTR generation. In ORF optimization, BiLSTM-CRF (bidirectional long-short-term memory with conditional random field) is employed to determine the codon for each amino acid. In UTR generation, RNA-Bart (bidirectional auto-regressive transformer) is proposed to output the corresponding UTR. The results show that the optimized sequences of exogenous genes acquired the pattern of human endogenous gene sequence. In experimental validation, the mRNA sequence optimized by our method, compared with conventional method, shows higher protein expression. To the best of our knowledge, this is the first study by introducing deep-learning methods to integrated mRNA sequence optimization, and these results may contribute to the development of mRNA therapeutics.
| S-EPMC9851294 | biostudies-literature
Project description:Improved Prediction of Smoking Status via Isoform-Aware RNA-seq Deep Learning Models
| PRJNA666220 | ENA
Project description:HydRA: Deep-learning models for predicting RNA-binding capacity from protein interaction association context and protein sequence
| PRJNA916520 | ENA