Browse
Submit Data
Databases
API
Help

Dataset Information

0 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Machine learning from large-scale proteomics accurately ranks anti-cancer drugs based on efficacy

ABSTRACT: We present an approach, named Drug Ranking Using ML (DRUML), which uses omics data to produce ordered lists of > 400 drugs based on their effectiveness in decreasing cancer cell proliferation. We trained and validated DRUML using in-house proteomics and phosphoproteomics data from a panel of 26 AML, 10 esophageal and 12 hepatocellular carcinoma cell lines in triplicate (three independent cultures per cell line) by LC-MS/MS

INSTRUMENT(S): Q Exactive Plus

ORGANISM(S): Homo Sapiens (human)

TISSUE(S): Myeloblast, Hepatocyte, Epithelial Cell Of Esophagus, Peripheral Blood, Epithelial Cell, Esophageal Epithelial Cell

DISEASE(S): Acute Myeloid Leukemia,Esophageal Cancer,Hepatocellular Carcinoma

SUBMITTER: Maruan Hijazi

LAB HEAD: Pedro Cutillas

PROVIDER: PXD019591 | Pride | 2021-02-22

REPOSITORIES: pride

ACCESS DATA

Json Xml

Dataset's files

Source:

			Action	DRS
	F001926.mzid.gz	Mzid
	F001927.mzid.gz	Mzid
	F001928.mzid.gz	Mzid
	F001929.mzid.gz	Mzid
	F001930.mzid.gz	Mzid

Items per page:

1 - 5 of 864

Publications

Drug ranking using machine learning systematically predicts the efficacy of anti-cancer drugs.

Gerdes Henry H Casado Pedro P Dokal Arran A Hijazi Maruan M Akhtar Nosheen N Osuntola Ruth R Rajeeve Vinothini V Fitzgibbon Jude J Travers Jon J Britton David D Khorsandi Shirin S Cutillas Pedro R PR

Nature communications 20210325 1

Artificial intelligence and machine learning (ML) promise to transform cancer therapies by accurately predicting the most appropriate therapies to treat individual patients. Here, we present an approach, named Drug Ranking Using ML (DRUML), which uses omics data to produce ordered lists of >400 drugs based on their anti-proliferative efficacy in cancer cells. To reduce noise and increase predictive robustness, instead of individual features, DRUML uses internally normalized distance metrics of d ...[more]

PMID: 33767176

Similar Datasets

LipidOA: A Machine-Learning and Prior-Knowledge-Based Tool for Structural Annotation of Glycerophospholipids

Project description:The Paternò-Büchi (PB) reaction is a carbon-carbon double bond (C═C)-specific derivatization reaction that can be used to pinpoint the location(s) of C═C(s) in unsaturated lipids and quantitate the location of isomers when coupled with tandem mass spectrometry (MS/MS). As the data of PB-MS/MS are increasingly generated, the establishment of a corresponding data analysis tool is highly needed. Herein, LipidOA, a machine-learning and prior-knowledge-based data analysis tool, is developed to analyze PB-MS/MS data generated by liquid chromatography-mass spectrometry workflows. LipidOA consists of four key functional modules to realize an annotation of glycerophospholipid (GPL) structures at the fatty acyl-specific C═C location level. These include (1) data preprocessing, (2) picking C═C diagnostic ions, (3) <i>de novo</i> annotation, and (4) result ranking. Importantly, in the result-ranking module, the reliability of structural annotation is sorted via the use of a machine learning classifier and comparison to the total fatty acid database generated from the same sample. LipidOA is trained and validated by four PB-MS/MS data sets acquired using different PB reagents on mass spectrometers of different resolutions and of different biological samples. Overall, LipidOA provides high precision (higher than 0.9) and a wide coverage for structural annotations of GPLs. These results demonstrate that LipidOA can be used as a robust and flexible tool for annotating PB-MS/MS data collected under different experimental conditions using different lipidomic workflows.

2022-11-23 | MTBLS6075 | MetaboLights

Machine learning for grading and prognosis of esophageal dysplasia using mass spectrometry and histological imaging

Project description:Background: Barrett’s esophagus (BE) is a precursor lesion of esophageal adenocarcinoma and may progress from non-dysplastic through low-grade dysplasia (LGD) to high-grade dysplasia (HGD) and cancer. Grading BE is of crucial prognostic value and is currently based on the subjective evaluation of biopsies. This study aims to investigate the potential of machine learning (ML) using spatially resolved molecular data from mass spectrometry imaging (MSI) and histological data from microscopic haematoxylin and eosin (H&E)-stained imaging for computer-aided diagnosis and prognosis of BE. Methods: Biopsies from 57 patients were considered, divided into non-dysplastic (n=15), LGD non-progressive (n=14), LGD progressive (n=14), and HGD (n=14). MSI experiments were conducted at 50x50 μm spatial resolution per pixel corresponding to a tile size of 96x96 pixels in the co-registered H&E images, making a total of 144,823 tiles for the whole dataset. Results: ML models were trained to distinguish epithelial tissue from stroma with area-under-the-curve (AUC) values of 0.89 (MSI) and 0.95 (H&E)) and dysplastic grade (AUC of 0.97 (MSI) and 0.85 (H&E)) on a tile level, and low-grade progressors from non-progressors on a patient level (accuracies of 0.72 (MSI) and 0.48 (H&E)). Conclusions: In summary, while the H&E-based classifier was best at distinguishing tissue types, the MSI-based model was more accurate at distinguishing dysplastic grades and patients at progression risk, which demonstrates the complementarity of both approaches.

2021-11-15 | PXD028949 | Pride

Machine learning for discovery: deciphering RNA splicing logic

Project description:Machine learning methods, particularly neural networks trained on large datasets, are transforming how scientists approach scientific discovery and experimental design. However, current state-of-the-art neural networks are limited by their uninterpretability: despite providing accurate predictions, they cannot describe how they arrived at their predictions. Here, using an ``interpretable-by-design'' approach, we present a neural network model that provides insights into RNA splicing, a fundamental process in the transfer of genomic information into functional biochemical products. Although we designed our model to emphasize interpretability, its predictive accuracy is on par with state-of-the-art models. To demonstrate the model's interpretability, we introduce a visualization that, for any given exon, allows us to trace and quantify the entire decision process from input sequence to output splicing prediction. Importantly, the model revealed novel components of the splicing logic, which we experimentally validated. This study highlights how interpretable machine learning can advance scientific discovery.

2022-10-01 | GSE200096 | GEO

Machine learning-optimized targeted detection of alternative splicing

Project description:RNA-sequencing (RNA-seq) is widely used for analysis of alternative splicing, but in practice, has inherent biases which hinder its ability to detect and quantify splicing events. To address this, we present a targeted RNA-seq method that specifically enriches for splicing-informative junction-spanning reads. Local Splicing Variation sequencing (LSV-seq) utilizes multiplexed reverse transcription from highly scalable pools of primers anchored near splice junctions of interest. Primers are designed using Optimal Prime, a novel dedicated machine learning algorithm trained on the performance of thousands of primer sequences. LSV-seq achieves high on-target capture rates and concordance with RNA-seq, while requiring several-fold lower sequencing depth. We use LSV-seq to target events with low coverage in GTEx RNA-seq data and discover hundreds of previously hidden tissue-specific splicing events. Our results demonstrate the ability of LSV-seq to capture alternative splicing with exceptional sensitivity and highlight its potential to improve the detection of other RNA features of interest.

2024-12-27 | GSE246294 | GEO

Drug ranking using machine learning systematically predicts the efficacy of anti-cancer drugs.

Project description:Artificial intelligence and machine learning (ML) promise to transform cancer therapies by accurately predicting the most appropriate therapies to treat individual patients. Here, we present an approach, named Drug Ranking Using ML (DRUML), which uses omics data to produce ordered lists of >400 drugs based on their anti-proliferative efficacy in cancer cells. To reduce noise and increase predictive robustness, instead of individual features, DRUML uses internally normalized distance metrics of drug response as features for ML model generation. DRUML is trained using in-house proteomics and phosphoproteomics data derived from 48 cell lines, and it is verified with data comprised of 53 cellular models from 12 independent laboratories. We show that DRUML predicts drug responses in independent verification datasets with low error (mean squared error < 0.1 and mean Spearman's rank 0.7). In addition, we demonstrate that DRUML predictions of cytarabine sensitivity in clinical leukemia samples are prognostic of patient survival (Log rank p < 0.005). Our results indicate that DRUML accurately ranks anti-cancer drugs by their efficacy across a wide range of pathologies.

| S-EPMC7994645 | biostudies-literature

Computational analysis of cholangiocarcinoma phosphoproteomes identifies patient-specific drug targets

Project description:We used mass-spectrometry based phosphoproteomics and computational methods to identify patient-specific drug targets in primary CCA and CCA-derived cell lines. We analyzed 13 primary CCA with matched background tissue and 8 different cell lines leading to the identification and quantification of >13,000 phosphorylation sites. Application of the Drug Ranking Using Machine Learning (DRUML) algorithm identified inhibitors of HDAC and PI3K pathway members as highly ranking in primary CCA relative to background. The accuracy of drug rankings based on predicted responses was confirmed using cell line models of CCA. Together, our study uncovers frequently overactive biochemical pathways in primary CCA and provides a proof-of-concept of the use of machine learning for ranking drugs based on efficacy within individual patient tumors.

2023-03-11 | PXD027329 | Pride

Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data [Transcriptomics]

Project description:We experimented how well various supervised machine learning methods such as decision tree, partial least squares discriminant analysis (PLSDA), support vector machine and random forest perform in classifying endometriosis from the control samples trained on both transcriptomics and methylomics data. The assessment was done from two different perspectives for improving classification performances: (a) implication of three different normalization techniques, and (b) implication of differential analysis using the generalized linear model (GLM). We concluded that an appropriate machine learning diagnostic pipeline for endometriosis should use TMM normalization for transcriptomics data, and quantile or voom normalization for methylomics data, GLM for feature space reduction and classification performance maximization.

2019-07-18 | GSE134056 | GEO

Machine Learning Classifiers for Endometriosis Using Transcriptomics and Methylomics Data [Methylomics]

2019-07-18 | GSE134052 | GEO

Machine learning predicts individual cancer patient responses to therapeutic drugs with high accuracy

Project description:Samples of primary tumors collected from 23 ovarian cancer patients

2018-04-07 | GSE112798 | GEO

Improved Prediction of Venetoclax and Azacitidine Efficacy in Acute Myeloid Leukemia through Machine Learning

Project description:Despite the transformative impact of venetoclax-azacitidine in treating acute myeloid leukemia (AML), reliable markers for accurately predicting patient responses remain urgently needed. To address this challenge, we employed a multidisciplinary approach that combined transcriptomic profiling, ex vivo drug sensitivity testing, functional assays, and clinical data to identify robust predictors of venetoclax-azacitidine response. We pinpointed a set of core genes linked to both ex vivo and in vivo drug responsiveness, validated through CRISPR-Cas9 screens in the setting of both venetoclax and azacitidine therapies. In particular, silencing BCL2L1 and PINK1 preferentially enhanced response to the venetoclax-azacitidine treatment. Building on these insights, we further developed and validated an 8-gene random forest model (RF8) that demonstrated high specificity and sensitivity in four independent cohorts comprising 498 patients. This model was capable of distilling downstream effects of genetic alterations to assist in predicting treatment response and outperformed existing genetic mutation-based signatures. Furthermore, the RF8 score demonstrated a nearly monotonic relationship with venetoclax-azacitidine response probabilities and patient outcomes, enabling precise stratification of patients. These findings illustrated the feasibility of translating integrated transcriptomic and drug-response profiling data into more refined risk stratification approaches, offering a new avenue for optimizing clinical decision-making in AML.

2025-02-18 | GSE289785 | GEO

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data