Biology subjects

Minhas, F. u. A. A.

Publications and source records attributed to Minhas, F. u. A. A..

4 recordsLinked to original sources

bioRxiv2023

Cancer drug sensitivity prediction from routine histology images

Drug sensitivity prediction models can aid in personalising cancer therapy, biomarker discovery, and drug design. Such models require survival data from randomized controlled trials which can be time consuming and expensive. In this proof-of-concept study, we demonstrate for the first time that deep learning can link histological patterns in whole slide images (WSIs) of Haematoxylin & Eosin (H&E) stained breast cancer sections with drug sensitivities inferred from cell lines. We employ patient-wise drug sensitivities imputed from gene expression based mapping of drug effects on cancer cell lines to train a deep learning model that predicts sensitivity to multiple drugs from WSIs. We show that it is possible to use routine WSIs to predict the drug sensitivity profile of a cancer patient for a number of approved and experimental drugs. We also show that the proposed approach can identify cellular and histological patterns associated with drug sensitivity profiles of cancer patients. HighlightsO_LIPredicting drug sensitivity from routine histology images and cell lines C_LIO_LIDiscovery of histology image patterns linked to drug sensitivity C_LIO_LIA novel deep learning pipeline for analysing drug sensitivity profiles C_LI

cancer biology↗

bioRxiv2023

Data-Driven Modelling of Gene Expression States in Breast Cancer and their Prediction from Routine Whole Slide Images

Identification of gene expression state of a cancer patient from routine pathology imaging and characterization of its phenotypic effects have significant clinical and therapeutic implications. However, prediction of expression of individual genes from whole slide images (WSIs) is challenging due to co-dependent or correlated expression of multiple genes. Here, we use a purely data-driven approach to first identify groups of genes with co-dependent expression and then predict their status from (WSIs) using a bespoke graph neural network. These gene groups allow us to capture the gene expression state of a patient with a small number of binary variables that are biologically meaningful and carry histopathological insights for clinically and therapeutic use cases. Prediction of gene expression state based on these gene groups allows associating histological phenotypes (cellular composition, mitotic counts, grading, etc.) with underlying gene expression patterns and opens avenues for gaining significant biological insights from routine pathology imaging directly. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=139 SRC="FIGDIR/small/536756v1_ufig1.gif" ALT="Figure 1"> View larger version (57K): org.highwire.dtl.DTLVardef@74d0dcorg.highwire.dtl.DTLVardef@13c2708org.highwire.dtl.DTLVardef@26a6dborg.highwire.dtl.DTLVardef@194b076_HPS_FORMAT_FIGEXP M_FIG C_FIG HighlightsO_LIData-driven discovery of co-expressing gene groups in breast caner C_LIO_LIHistological imaging based prediction of gene groups via deep learning C_LIO_LIIdentification of phenotypic correlates of gene-expression in histological imaging C_LIO_LIClinical and therapeutic impact of gene groups and their visual patterns identified C_LI

pathology↗

bioRxiv2019

Machine Learning Predicts New Anti-CRISPR Proteins

The increasing use of CRISPR-Cas9 in medicine, agriculture and synthetic biology has accelerated the drive to discover new CRISPR-Cas inhibitors as potential mechanisms of control for gene editing applications. Many such anti-CRISPRs have been found in mobile genetic elements that disable the CRISPR-Cas adaptive immune system. However, comparing all currently known anti-CRISPRs does not reveal a shared set of properties that can be used for facile bioinformatic identification of new anti-CRISPR families. Here, we describe AcRanker, a machine learning based method for identifying new potential anti-CRISPRs directly from proteomes using protein sequence information only. Using a training set of known anti-CRISPRs, we built a model based on XGBoost ranking and extensively benchmarked it through non-redundant cross-validation and external validation. We then applied AcRanker to predict candidate anti-CRISPRs from self-targeting bacterial genomes and discovered two previously unknown anti-CRISPRs: AcrllA16 (ML1) and AcrIIA17 (ML8). We show that AcrIIA16 strongly inhibits Streptococcus iniae Cas9 (SinCas9) and weakly inhibits Streptococcus pyogenes Cas9 (SpyCas9). We also show that AcrIIA17 inhibits both SpyCas9 and SauCas9 with low potency. The addition of AcRanker to the anti-CRISPR discovery toolkit allows researchers to directly rank potential anti-CRISPR candidate genes for increased speed in testing and validation of new anti-CRISPRs. A web server implementation for AcRanker is available online at http://acranker.pythonanywhere.com/.

biochemistry↗

bioRxiv2017

Quadratic Programming Data Descriptors for Abnormal Beat Detection in ECG Recordings

This paper analyzes the efficacy of applying one class classifiers (OCCs) to the problem of abnormal beat detection in ECG. It also proposes a novel OCC called Quadratic Programming Dissimilarity representation based Data Descriptor (QPDDD). A comparison of the proposed classification technique with existing classifiers over the MIT-BIH arrhythmia database is presented. Results show that OCCs coupled with wavelet domain features present a practical, robust and scalable solution for handling inter-individual variability in ECG patterns of different types of cardiac beats. An equal error rate of 90-95% was obtained for the MIT-BIH arrhythmia database depending upon the amount of training data used. A major advantage of the proposed scheme is that it requires only normal beats during its training. Another advantage is that it is able to handle inter-individual differences in ECG morphologies as the training takes place separately for each individual.

bioinformatics↗