Change search
Link to record
Permanent link

Direct link
BETA
Publications (4 of 4) Show all publications
Ahmed, L. (2019). Scalable Analysis of Large Datasets in Life Sciences. (Doctoral dissertation). KTH Royal Institute of Technology
Open this publication in new window or tab >>Scalable Analysis of Large Datasets in Life Sciences
2019 (English)Doctoral thesis, monograph (Other academic)
Abstract [en]

We are experiencing a deluge of data in all fields of scientific and business research, particularly in the life sciences, due to the development of better instrumentation and the rapid advancements that have occurred in information technology in recent times. There are major challenges when it comes to handling such large amounts of data. These range from the practicalities of managing these large volumes of data, to understanding the meaning and practical implications of the data.

In this thesis, I present parallel methods to efficiently manage, process, analyse and visualize large sets of data from several life sciences fields at a rapid rate, while building and utilizing various machine learning techniques in a novel way. Most of the work is centred on applying the latest Big Data Analytics frameworks for creating efficient virtual screening strategies while working with large datasets. Virtual screening is a method in cheminformatics used for Drug discovery by searching large libraries of molecule structures. I also present a method for the analysis of large Electroencephalography data in real time. Electroencephalography is one of the main techniques used to measure the brain electrical activity.

First, I evaluate the suitability of Spark, a parallel framework for large datasets, for performing parallel ligand-based virtual screening. As a case study, I classify molecular library using prebuilt classification models to filter out the active molecules. I also demonstrate a strategy to create cloud-ready pipelines for structure-based virtual screening. The major advantages of this strategy are increased productivity and high throughput. In this work, I show that Spark can be applied to virtual screening, and that it is, in general, an appropriate solution for large-scale parallel pipelining. Moreover, I illustrate how Big Data analytics are valuable in working with life sciences datasets.

Secondly, I present a method to further reduce the overall time of the structured-based virtual screening strategy using machine learning and a conformal-prediction-based iterative modelling strategy. The idea is to only dock those molecules that have a better than average chance of being an inhibitor when searching for molecules that could potentially be used as drugs. Using machine learning models from this work, I built a web service to predict the target profile of multiple compounds against ready-made models for a list of targets where 3D structures are available. These target predictions can be used to understand off-target effects, for example in the early stages of drug discovery projects.

Thirdly, I present a method to detect seizures in long term Electroencephalography readings - this method works in real time taking the ongoing readings in as live data streams. The method involves tackling the challenges of real-time decision-making, storing large datasets in memory and updating the prediction model with newly produced data at a rapid rate. The resulting algorithm not only classifies seizures in real time, it also learns the threshold in real time. I also present a new feature "top-k amplitude measure" for classifying which parts of the data correspond to seizures. Furthermore, this feature helps to reduce the amount of data that needs to be processed in the subsequent steps.

Abstract [sv]

Vi upplever just nu en flodvåg av data inom både vetenskaplig forskning och färetagsdriven utveckling. Detta gäller framfärallt inom livsvetenskap på grund av utveckling av bättre instrument och framsteg inom informationsteknologin under de senaste åren. Det finns dock betydande utmaningar med hanteringen av sådana datamängder som sträcker sig från praktisk hantering av de stora datavolymerna till färståelse av betydelsen och de praktiska implikationerna av dessa data.

I den här avhandlingen presenterar jag metoder fär att snabbt och effektivt hantera, behandla, analysera och visualisera stora biovetenskapliga datamängder. Stärre delen av arbetet är fokuserat på att tillämpa de senaste Big Data ramverken fär att på så sätt skapa effektiva verktyg fär virtuell screening, vilket är en metod som används fär att säka igenom stora mängder kemiska strukturer fär läkemedelsutvecklings. Vidare presenterar jag en metod fär analys av stora mängder elektroencefalografidata (EEG) i realtid, vilken är en av de huvudsakliga metoderna fär att mäta elektrisk hjärnaktivitet.

Färst utvärderar jag lämpligheten att med Spark (ett parallellt ramverk fär stora datamängder) genomfära parallell ligand-baserad virtuell screening. Jag applicerar metoden fär att klassificera samlingar med molekyler med hjälp av färtränade modeller fär att selektera de aktiva molekylerna. Jag demonstrerar även en strategi fär att skapa molnanpassade fläden fär strukturbaserad virtuell screening. Den huvudsakliga färdelen med den här strategin är äkad produktivitet och häg hastighet i analysen. I det här arbetet visar jag att Spark kan användas fär virtuell screening och att det även i allmänhet är en lämplig läsning fär parallell analys av stora mängder data. Dessutom visar jag genom ett exempel att Big Data analys kan vara värdefull vid arbete med biovetenskapliga data.

I den andra delen av mitt arbete presenterar jag en metod som ytterligare minskar tiden fär den strukturbaserade virtuella screening genom användning av maskininlärning och en iterativ modelleringsstrategi baserad på Conformal Prediction. Syftet är att endast docka de molekyler som har en hägre sannolikhet att binda till ett målprotein, vid säkning efter molekyler som potentiellt kan användas som läkemedelskandidater. Med användning av maskininlärningsmodellerna från detta arbete har jag byggt en webbtjänst fär att färutsäga en profil av en molekyls olika interaktioner med olika målprotein. Dessa prediktioner kan användas fär att indikera sekundära interaktioner i tidiga skeden av läkemedelsutvecklingen.

I den tredje delen presenterar jag metoder fär att detektera anfall med långtidsEEG - den här metoden fungerar i realtid genom att ta pågående mätningar som datasträmmar. Metoden mäter utmaningarna med att fatta beslut i realtid att lagra stora mängder data i datorns minne och uppdatera färutsägelsemodellen ny data som produceras i snabb takt. Den resulterande algoritmen klassificerar inte bara anfall i realtid, den lär sig också gränsvärdet i realtid. Jag presenterar också ett nytt mått, “topp-k amplitudmått” fär att klassificera vilka delar of data som motsvarar anfall. Utäver detta hjälper måttet till att minska mängden data som behäver behandlas i efterfäljande steg.

Place, publisher, year, edition, pages
KTH Royal Institute of Technology, 2019. p. 134
Series
TRITA-EECS-AVL ; 2019:69
Keywords
Big Data, Apache Spark, Virtual Screening, EEG, Cloud Computing, Life Sciences, Machine Learning
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
urn:nbn:se:kth:diva-261683 (URN)978-91-7873-309-5 (ISBN)
Public defence
2019-12-03, Kollegiesalen, Brinellvägen 8, 114 28, Stockholm, 10:00 (English)
Opponent
Supervisors
Note

QC 20191011

Available from: 2019-10-11 Created: 2019-10-09 Last updated: 2019-11-07Bibliographically approved
Ahmed, L., Georgiev, V., Capuccini, M., Toor, S., Schaal, W., Laure, E. & Spjuth, O. (2018). Efficient iterative virtual screening with Apache Spark and conformal prediction. Journal of Cheminformatics, 10, Article ID 8.
Open this publication in new window or tab >>Efficient iterative virtual screening with Apache Spark and conformal prediction
Show others...
2018 (English)In: Journal of Cheminformatics, ISSN 1758-2946, E-ISSN 1758-2946, Vol. 10, article id 8Article in journal (Refereed) Published
Abstract [en]

Background: Docking and scoring large libraries of ligands against target proteins forms the basis of structure-based virtual screening. The problem is trivially parallelizable, and calculations are generally carried out on computer clusters or on large workstations in a brute force manner, by docking and scoring all available ligands. Contribution: In this study we propose a strategy that is based on iteratively docking a set of ligands to form a training set, training a ligand-based model on this set, and predicting the remainder of the ligands to exclude those predicted as 'low-scoring' ligands. Then, another set of ligands are docked, the model is retrained and the process is repeated until a certain model efficiency level is reached. Thereafter, the remaining ligands are docked or excluded based on this model. We use SVM and conformal prediction to deliver valid prediction intervals for ranking the predicted ligands, and Apache Spark to parallelize both the docking and the modeling. Results: We show on 4 different targets that conformal prediction based virtual screening (CPVS) is able to reduce the number of docked molecules by 62.61% while retaining an accuracy for the top 30 hits of 94% on average and a speedup of 3.7. The implementation is available as open source via GitHub (https://github.com/laeeq80/spark-cpvs) and can be run on high-performance computers as well as on cloud resources.

Place, publisher, year, edition, pages
BioMed Central, 2018
Keywords
Virtual screening, Docking, Conformal prediction, Cloud computing, Apache Spark
National Category
Chemical Sciences Computer Sciences
Identifiers
urn:nbn:se:kth:diva-224683 (URN)10.1186/s13321-018-0265-z (DOI)000426699400001 ()29492726 (PubMedID)2-s2.0-85042857389 (Scopus ID)
Funder
Swedish e‐Science Research CenterSwedish National Infrastructure for Computing (SNIC)
Note

QC 20180323

Available from: 2018-03-23 Created: 2018-03-23 Last updated: 2018-03-23Bibliographically approved
Capuccini, M., Ahmed, L., Schaal, W., Laure, E. & Spjuth, O. (2017). Large-scale virtual screening on public cloud resources with Apache Spark. Journal of Cheminformatics, 9, Article ID 15.
Open this publication in new window or tab >>Large-scale virtual screening on public cloud resources with Apache Spark
Show others...
2017 (English)In: Journal of Cheminformatics, ISSN 1758-2946, E-ISSN 1758-2946, Vol. 9, article id 15Article in journal (Refereed) Published
Abstract [en]

Background: Structure-based virtual screening is an in-silico method to screen a target receptor against a virtual molecular library. Applying docking-based screening to large molecular libraries can be computationally expensive, however it constitutes a trivially parallelizable task. Most of the available parallel implementations are based on message passing interface, relying on low failure rate hardware and fast network connection. Google's MapReduce revolutionized large-scale analysis, enabling the processing of massive datasets on commodity hardware and cloud resources, providing transparent scalability and fault tolerance at the software level. Open source implementations of MapReduce include Apache Hadoop and the more recent Apache Spark. Results: We developed a method to run existing docking-based screening software on distributed cloud resources, utilizing the MapReduce approach. We benchmarked our method, which is implemented in Apache Spark, docking a publicly available target receptor against similar to 2.2 M compounds. The performance experiments show a good parallel efficiency (87%) when running in a public cloud environment. Conclusion: Our method enables parallel Structure-based virtual screening on public cloud resources or commodity computer clusters. The degree of scalability that we achieve allows for trying out our method on relatively small libraries first and then to scale to larger libraries.

Place, publisher, year, edition, pages
BioMed Central, 2017
Keywords
Virtual screening, Docking, Cloud computing, Apache Spark
National Category
Computer Systems
Identifiers
urn:nbn:se:kth:diva-205469 (URN)10.1186/s13321-017-0204-4 (DOI)000396830300001 ()28316653 (PubMedID)2-s2.0-85014678539 (Scopus ID)
Note

QC 20170523

Available from: 2017-05-23 Created: 2017-05-23 Last updated: 2017-05-23Bibliographically approved
Ahmed, L., Edlund, Å., Laure, E. & Spjuth, O. (2013). Using iterative MapReduce for parallel virtual screening. In: 2013 IEEE 5th International Conference on Cloud Computing Technology and Science (CloudCom): . Paper presented at 5th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2013; Bristol; United Kingdom; 2 December 2013 through 5 December 2013 (pp. 27-32). IEEE Computer Society
Open this publication in new window or tab >>Using iterative MapReduce for parallel virtual screening
2013 (English)In: 2013 IEEE 5th International Conference on Cloud Computing Technology and Science (CloudCom), IEEE Computer Society, 2013, p. 27-32Conference paper, Published paper (Refereed)
Abstract [en]

Virtual Screening is a technique in chemo informatics used for Drug discovery by searching large libraries of molecule structures. Virtual Screening often uses SVM, a supervised machine learning technique used for regression and classification analysis. Virtual screening using SVM not only involves huge datasets, but it is also compute expensive with a complexity that can grow at least up to O(n2). SVM based applications most commonly use MPI, which becomes complex and impractical with large datasets. As an alternative to MPI, MapReduce, and its different implementations, have been successfully used on commodity clusters for analysis of data for problems with very large datasets. Due to the large libraries of molecule structures in virtual screening, it becomes a good candidate for MapReduce. In this paper we present a MapReduce implementation of SVM based virtual screening, using Spark, an iterative MapReduce programming model. We show that our implementation has a good scaling behaviour and opens up the possibility of using huge public cloud infrastructures efficiently for virtual screening.

Place, publisher, year, edition, pages
IEEE Computer Society, 2013
Keywords
Big Data, Chemoinformatics, MapReduce, Parallel SVM, Spark
National Category
Computer Sciences
Identifiers
urn:nbn:se:kth:diva-146956 (URN)10.1109/CloudCom.2013.99 (DOI)000352079100005 ()2-s2.0-84899736110 (Scopus ID)978-0-7695-5095-4 (ISBN)
Conference
5th IEEE International Conference on Cloud Computing Technology and Science, CloudCom 2013; Bristol; United Kingdom; 2 December 2013 through 5 December 2013
Note

QC 20140619

Available from: 2014-06-19 Created: 2014-06-18 Last updated: 2018-01-11Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0001-6877-3702

Search in DiVA

Show all publications