oncoPredict: an R package for predicting in vivo or cancer patient drug response and biomarkers from cell line screening data

Briefings in Bioinformatics, Journal Year: 2021, Volume and Issue: 22(6)

Published: June 21, 2021

Cell line drug screening datasets can be utilized for a range of different discovery applications from biomarker to building translational models response. Previously, we described three separate methodologies (1) correct general levels sensitivity enable drug-specific discovery, (2) predict clinical response in patients and (3) associate these predictions with features perform vivo discovery. Here, unite update into one R package (oncoPredict) facilitate the development adoption tools. This new OncoPredict applied various vitro contexts

Language: Английский

---

Deep learning in cancer diagnosis, prognosis and treatment selection

Genome Medicine, Journal Year: 2021, Volume and Issue: 13(1)

Published: Sept. 27, 2021

Abstract Deep learning is a subdiscipline of artificial intelligence that uses machine technique called neural networks to extract patterns and make predictions from large data sets. The increasing adoption deep across healthcare domains together with the availability highly characterised cancer datasets has accelerated research into utility in analysis complex biology cancer. While early results are promising, this rapidly evolving field new knowledge emerging both learning. In review, we provide an overview techniques how they being applied oncology. We focus on applications for omics types, including genomic, methylation transcriptomic data, as well histopathology-based genomic inference, perspectives different types can be integrated develop decision support tools. specific examples may diagnosis, prognosis treatment management. also assess current limitations challenges application precision oncology, lack phenotypically rich need more explainable models. Finally, conclude discussion obstacles overcome enable future clinical utilisation

Language: Английский

---

SynergyFinder Plus: Toward Better Interpretation and Annotation of Drug Combination Screening Datasets

Genomics Proteomics & Bioinformatics, Journal Year: 2022, Volume and Issue: 20(3), P. 587 - 596

Published: Jan. 25, 2022

Abstract Combinatorial therapies have been recently proposed to improve the efficacy of anticancer treatment. The SynergyFinder R package is a software used analyze pre-clinical drug combination datasets. Here, we report major updates for improved interpretation and annotation screening results. Unlike existing implementations, updated includes five main innovations. 1) We extend mathematical models higher-order data analysis implement dimension reduction techniques visualizing synergy landscape. 2) provide statistical sensitivity with confidence intervals P values. 3) incorporate barometer harmonize multiple scoring methods consensus metric synergy. 4) evaluate an unbiased clinical potential. 5) enable fast drugs cell lines, including their chemical target information. These annotations will mechanisms action combinations. To facilitate use within discovery community, also web server at www.synergyfinderplus.org as user-friendly interface more flexible versatile data.

Language: Английский

---

Artificial intelligence aids in development of nanomedicines for cancer management

Seminars in Cancer Biology, Journal Year: 2023, Volume and Issue: 89, P. 61 - 75

Published: Jan. 20, 2023

Language: Английский

---

Predicting cellular responses to complex perturbations in high‐throughput screens

Molecular Systems Biology, Journal Year: 2023, Volume and Issue: 19(6)

Published: May 8, 2023

Abstract Recent advances in multiplexed single‐cell transcriptomics experiments facilitate the high‐throughput study of drug and genetic perturbations. However, an exhaustive exploration combinatorial perturbation space is experimentally unfeasible. Therefore, computational methods are needed to predict, interpret, prioritize Here, we present compositional autoencoder (CPA), which combines interpretability linear models with flexibility deep‐learning approaches for response modeling. CPA learns silico predict transcriptional at level unseen dosages, cell types, time points, species. Using newly generated combination data, validate that can combinations while outperforming baseline models. Additionally, architecture's modularity enables incorporating chemical representation drugs, allowing prediction cellular completely drugs. Furthermore, also applicable screens. We demonstrate this by imputing 5,329 missing (97.6% all possibilities) a Perturb‐seq experiment diverse interactions. envision will efficient experimental design hypothesis generation enabling thus accelerate therapeutic applications using technologies.

Language: Английский

---

Machine learning in the prediction of cancer therapy

Computational and Structural Biotechnology Journal, Journal Year: 2021, Volume and Issue: 19, P. 4003 - 4017

Published: Jan. 1, 2021

Resistance to therapy remains a major cause of cancer treatment failures, resulting in many cancer-related deaths. can occur at any time during the treatment, even beginning. The current plan is dependent mainly on subtypes and presence genetic mutations. Evidently, mutation does not always predict therapeutic response vary for different subtypes. Therefore, there an unmet need predictive models match patient with specific drug or combination. Recent advancements using artificial intelligence have shown great promise preclinical settings. However, despite massive improvements computational power, building clinically useable challenging due lack meaningful pharmacogenomic data. In this review, we provide overview recent prediction machine learning, which most widely used branch intelligence. We describe basics learning algorithms, illustrate their use, highlight challenges clinical practice.

Language: Английский

---

Machine Learning for Lung Cancer Diagnosis, Treatment, and Prognosis

Genomics Proteomics & Bioinformatics, Journal Year: 2022, Volume and Issue: 20(5), P. 850 - 866

Published: Oct. 1, 2022

The recent development of imaging and sequencing technologies enables systematic advances in the clinical study lung cancer. Meanwhile, human mind is limited effectively handling fully utilizing accumulation such enormous amounts data. Machine learning-based approaches play a critical role integrating analyzing these large complex datasets, which have extensively characterized cancer through use different perspectives from accrued In this article, we provide an overview machine that strengthen varying aspects diagnosis therapy, including early detection, auxiliary diagnosis, prognosis prediction, immunotherapy practice. Moreover, highlight challenges opportunities for future applications learning

Language: Английский

---

Clinical application of advanced multi-omics tumor profiling: Shaping precision oncology of the future

Cancer Cell, Journal Year: 2022, Volume and Issue: 40(9), P. 920 - 938

Published: Sept. 1, 2022

Language: Английский

---

Gene expression based inference of cancer drug sensitivity

Nature Communications, Journal Year: 2022, Volume and Issue: 13(1)

Published: Sept. 27, 2022

Abstract Inter and intra-tumoral heterogeneity are major stumbling blocks in the treatment of cancer responsible for imparting differential drug responses patients. Recently, availability high-throughput screening datasets has paved way machine learning based personalized therapy recommendations using molecular profiles specimens. In this study, we introduce Precily, a predictive modeling approach to infer response cancers gene expression data. context, demonstrate benefits considering pathway activity estimates tandem with descriptors as features. We apply Precily on single-cell bulk RNA sequencing data associated hundreds cell lines. then assess predictability outcomes our in-house prostate line xenografts exposed conditions. Further, applicability patient from The Cancer Genome Atlas an independent clinical study describing journey three melanoma Our findings highlight importance chemo-transcriptomics approaches selection.

Language: Английский

---

Role of ctDNA in Breast Cancer

Cancers, Journal Year: 2022, Volume and Issue: 14(2), P. 310 - 310

Published: Jan. 9, 2022

Breast cancer is currently classified by immunohistochemistry. However, technological advances in the detection of circulating tumor DNA (ctDNA) have made new options available for diagnosis, classification, biological knowledge, and treatment selection. a heterogeneous disease ctDNA can accurately reflect this heterogeneity, allowing us to detect, monitor, understand evolution disease. patients higher levels than healthy subjects, be used different objectives at timepoints disease, ranging from screening early monitoring resistance mutations advanced In breast cancer, clearance has been associated with rates complete pathological response after neoadjuvant fewer recurrences radical treatments. metastatic help select optimal sequencing future, thanks bioinformatics tools, use will become more frequent, enhancing our knowledge biology tumors. Moreover, deep learning algorithms may also able predict or sensitivity. coming years, continued research improvement liquid biopsy techniques key implementation analysis routine clinical practice.

Language: Английский

---