Research Project: Predicting Phenotype From Patterns Of Annotation - An Essay.

Develop and apply skills in research project design in order to construct a research proposal on a selected topic. The proposed project should be something that can be realistically conducted in a 9 month full time equivalent study period.  write a proposal that demonstrates their ability to consider the major factors and requirements in the design and management of a research project. Students are also required to demonstrate their ability to search current literature and use this as the basis and justification of their research proposal. In addition, students should also consider and describe external factors that could impact their research (e.g. social, political, organisational, environmental factors). 

Importance of developing decision trees for successful research

This research project depicts the role of predicted phenotype based on the patter of annotation. In order to predict the results based on some of the particular experiment the devoted resources for the experiment are needed. For gathering enough amounts of research contents this is mandatory for the researchers to develop a decision tree so that based on that the research can process forward (Gu, Eils and Schlesner 2016). With the successful usage of decision tree the phenotypes that are related to Saccharomyces Cerevisiae genes dependent on gene ontology can be functionally activated and implemented as well. From the cross validation of phenotype the research results can be successfully achieved rather the research work can be successfully conducted.

A research question has been developed based on the research topic and it is the role of the researcher to resolve the research question. The aim and objectives of the research are successfully developed and for the proposed research project the expected list of outcomes are also identified. Not only this but also, it is determined that, for this research topic a literature review has been conducted. The details of the research methodology is also elaborated in the below section and along with this the net time that will be approximate required for the successful conduction of the research are also elaborated in this research project.

Design and management of the project

If the research work is successfully conducted then the researcher will be able to understand the rate of growth which is related to a particular medium like either mutant strain or something else. This particular method can be successfully achieved by following three different methods such as cross functional validation, literature research or literature review or else deletion of strains for experimental access of 61 based on predicted gene phenotype but the association of this specific gene phenotype is not listed among the MIPS (Becker et al 2015). However, as much numbers of deletion will take place that much the rate of the abnormal growth will also enhance accordingly.

Whenever the genome of any particular organism is being sequenced and their genes of that organism identified another role for the researcher arises which deals with the role of each and every individual genes. The role of the genes include their molecular functionalities at the same time the phenotypes that are related to the disruption of the genes. According to Chicco, Sadowski and Baldi (2014) there is a complimentary relationship between the phenotypic attributes as well as functional attributes. Each of the attribute exchanges information about each other. Jaouachi et al. (2015) stated that the review of phenotypes of Saccharomyces Cerevisiae and the interplay relationship between the phenotypes will help to realize the relationship between their functions. The researchers are required to deliver huge efforts for the standardization of the vocabulary of the functionalities as well as phenotypes. The phenotype and the functions will collectively facilitate the usability of different statistical methods to understand the inter functions basically from the phenotypes.

Understanding gene functionality through phenotype prediction

In order to take out all the functions in Saccharomyces Cerevisiae decision tree plays active role. From the function of Saccharomyces Cerevisiae by building a decision tree based on the phenotypes the research project can be conducted. Different type of approaches are available and based on the most suitable approach the functional annotation scan be predicted accordingly (Letunic and Bork 2017). However, based on other functional annotations this prediction can be successfully conducted. Single annotated functional is not functionally successful rather it can be said that, with the informative patterns between the annotations the multiple functional annotation can be successfully identified. In order to conduct such research project gene ontology related information collection and analysis are much helpful.

External factors

With the enhancing knowledge and abilities in biotechnology the potential benefits associated to the project topic also increases simultaneously. As per the intension of biotechnology it is more focused on giving positive impact to society. The external factors can impact the social, environmental, organizational as well as political factors and their impact are all determined in the below section.

Social factor

Massive rate of technologies are incorporating with the biological application to make sure that in the future trend the risks are getting reduced. As huge numbers of ethical issues are rising regarding the application of the biotechnology massive controversy are being rising. The government should design and develop legislation and regulations so that the functionalities can be successfully operated (Guo 2016). These new biotechnology based discoveries can regulate and manage the social risks. These factors are also defined as the social cultural factor and the sub factors consider for this specific research project include population growth, age, health consciousness, career attitudes as well as distribution.

Political factor

The successful research will allow the users if Application programming interface for defining the different kinds of class that are nominated as to be defined by the researchers. According to the success criteria not all the classes available rather some of the classes are only acceptable. In order to differentiate all the different classes the information that are considered include name, interface, packages etc.

Organizational factor

From the past 15 years the businesses are giving their strict focus on the environmental factors. Population target, raw material scarcities are the reasons for which the environmental factors analysis has become as one of the most essential factor. Annotation is an important factor that has to be analyzed to imply that only sustainable sources are being adopted and analyzed accordingly.

Potential benefits of biotechnology

Environmental factor

A comprehensive atlas should have to be created so that the patterns can be successfully implemented and analyzed accordingly (Kolesnikov and Lampert 2016.). The genetic features flow from the parents to next generation and also the features also flow. Experimental phenotypes can assist the system to operate successfully.

Research question

How the phenotypes associated to Saccharomyces Cerevisiae can be predicted from the pattern of annotation mechanism?

Research aim

The aim of the research project is to demonstrate the role of predicting phenotype from patterns of annotation. The usages of the predicting prototype are the other constraints that are to be identified by the researchers. It is defined that, all the deletion strains are obtainable as well as the phenotypes assay are also all described. Among these different methods the most suitable method is required to be conducted by the researcher to reach the aim and objectives.

It can be said that, if the research work is successfully conducted then the most useful model that is essential for demonstrating the roles of cross validation as well as decision tree will become clear to the readers. The crucial necessities of identifying gene phenotypes are very much essential that can also be demonstrated successfully with the help of experimental phenotype assay with the usage of the deletion strain.

Research plan

Code annotation is also referred to as an attribute rather simple annotation that is based on application programming interface. It is the feature language that allows custom metadata. Some of these annotations can be used by the researchers to conduct the research work. Popular computing programming languages such as java, C++ can be applied for the development of the project framework.

Methodology

Methods

In order to conduct the research project on “Predicting Phenotype from Patterns of Annotation” training data are required. The SGD GO annotation and the MIPS phenotype annotations are downloaded from the specific resources for gathering needful information. In order to specify the phenotypes, the MIPS phenotypes are to be all organize hierarchically considering a descending order (Miñarro-Giménez et al. 2017). More specifically it can be said that, for each of the j phenotype if the  random variable indicator is Xj then the value of Xj(i) will be equal to 1 (when for the gene in the annotation is j) on the other hand the value if Xj(i) will be equal to 0 (for all other cases). Alike hierarchy the GO attribute are all well organized with the help of the Directed Acyclic Graph (DAG) (Kanehisa et al. 2015). For this specific case there may present multiple numbers of patterns for a single attribute. The Directed Acyclic Graph is comprises of three different braches such as unknown molecular functions, biological processes and cellular components. Simultaneously it is also determined that, the GO attribute is comprises of approximately 13000 terms.

Impact of external factors on biotechnology

Among the total 13,000 terms 3051 terms are related to the yeast genes. However, for three of the attributes respectively biological unknown process, unknown cellular components and unknown molecular components the annotations are all excluded. According to Zhang et al (2018), the composition of MIPS and GO attributes are explicit annotations. In order to define the value of Xj specific level of literature are to be reviewed and analyzed accordingly. Not only this but also, for determining the value of Xj the logical structure should have to be prepared professionally by the researchers (Burghardt 2014). The vectors for all the random variables are necessary for conducting the research successfully for all the individual genes (Shin et al. 2016). For those organism where the rates of mutant strains are less, is recognized that the phenotype prediction approach is more suitable.

Decision tree

Decision Tree (DT) is another method that may also help the researchers to successfully conduct the research work and to meet the research aims and objectives. Only with the proper application of the decision tree the appropriate outcome from the research project can be obtained. Not only overview but also the applications of such tree are very much crucial to be understood by the researcher to gain the expected outcome (Burghardt 2014). The test sequence can be successfully prescribed for all the phenotypes so that it can be applied for all the genes. The successful application of the decision tree will help to measure whether the gene is annotated while having the prototype j (Kächele et al. 2015). The statistical assumption for this specific case deals with whether the gees are annotated as having k phenotype.

It is defined that for some of the GO attribute (MIPS or k) phenotype the value of k and the value of j are not equal (where k is not an ancestor of j) (Hoff and Preminger 2015). Based on the previous test the new testing approach should be selected and applied by the researchers. For the phenotype j the decision tree should have to e pupated by those who are responsible to conduct the research work (Kairam and Heer 2016). Under the training set the decision tree will be started with gene (g) considering single node for the root. Then each of the nodes is to be splitted recursively through testing each of the attributes.   

Research philosophy

In order to conduct the research topic, among three of the different research philosophies positivism, realism and interpretivism the positivism philosophy should have to be followed by the researcher. It will help the researcher to identify the hidden facts associated to the research.

Research aim and objectives

Research approach

There are two different type of research approaches are available such as deductive and inductive. However, among two of these approaches the inductive approach should be avoided. On the other hand, the deductive research approach should be adopted for this topic to access the hidden facts and to ensure that the project is meeting its objectives.

Data collection method

There are two different types of data collection methods available such as primary and secondary. Based on the research project specifications it has been found that, in order to conduct this research project the secondary data collection method is adopted. Considering different secondary sources the research work is needed to be conducted as for this topic the primary data collection approach is not appropriate (Suzuki, Kato and Matsubara 2017). Besides raw data validated and verified data are more appropriate for this specific research topic. Though mainly quantitative data are considered to identify the predicting phenotype from the pattern of annotation but at the same time qualitative data are also considered for this research topic.

After analyzing the details of the research project and its specifications it has been found that in order to successfully conduct the research project a total time of approximately 10 months will be required. Based on the details of the total research specification a set of activities are designed and after considering the complexity of each the activity a time has been predicted. It is the role of the project developers and the project team members to accomplish the activities within the estimated time period. The details of the project timeline are demonstrated in the below section:

Task Name	Duration	Start	Finish	Predecessors
Schedule preparation for the research work	365 days	Fri 8/24/18	Thu 1/16/20
Project initiation	150 days	Fri 8/24/18	Thu 3/21/19
Selection of topic for the research project	1 day	Fri 8/24/18	Fri 8/24/18
Understanding requirements for the chosen research project topic	10 days	Mon 8/27/18	Fri 9/7/18	2
Budget estimation for conducting the research work	56 days	Mon 9/10/18	Mon 11/26/18	3
Resource identification	6 days	Tue 11/27/18	Tue 12/4/18	4
Resource analysis	15 days	Tue 11/27/18	Mon 12/17/18	4
Gathering data	20 days	Tue 12/18/18	Mon 1/14/19	5,6
Analyzing gathered data	30 days	Tue 1/15/19	Mon 2/25/19	7
Allocation of the research team	10 days	Tue 2/26/19	Mon 3/11/19	8
Analyzing role of biotechnology to predict phenotype for patter of annotation	8 days	Tue 3/12/19	Thu 3/21/19	9
Project planning	126 days	Fri 3/22/19	Fri 9/13/19
Contingency plan	10 days	Fri 3/22/19	Thu 4/4/19	10
Cost planning	10 days	Fri 4/5/19	Thu 4/18/19	12
Timeline planning	10 days	Fri 4/19/19	Thu 5/2/19	13
Planning of research methodology	15 days	Fri 5/3/19	Thu 5/23/19	14
Factors getting affected due to the research	30 days	Fri 5/3/19	Thu 6/13/19	14
Research project formulation	30 days	Fri 6/14/19	Thu 7/25/19	15,16
Secondary source identification	15 days	Fri 7/26/19	Thu 8/15/19	10,17
Data collection from secondary sources	14 days	Fri 8/16/19	Wed 9/4/19	18
Analysis of secondary data	6 days	Fri 8/16/19	Fri 8/23/19	18
Developing research layouts	2 days	Thu 9/5/19	Fri 9/6/19	19,20
Developing rest of the research planning	5 days	Mon 9/9/19	Fri 9/13/19	21
Literature review	57 days	Mon 9/16/19	Tue 12/3/19
Developing rough draft based on the conducted literature review	12 days	Mon 9/16/19	Tue 10/1/19	22
Findings from the literature	15 days	Wed 10/2/19	Tue 10/22/19	24
Result analysis from the literature	30 days	Wed 10/23/19	Tue 12/3/19	25
Closure	32 days	Wed 12/4/19	Thu 1/16/20
Risk management program planning	20 days	Wed 12/4/19	Tue 12/31/19	26
Final paper submission	12 days	Wed 1/1/20	Thu 1/16/20	28

References

Becker, N., Chang, C., Raschid, L., Srinivasan, P., Van de Poel, B., Zhang, X.N. and Zotkina, E., 2015, July. Mining Sentence and Annotation Evidence for a Cross Genome Study of the Plant Hormone Ethylene. In International Conference on Data Integration in the Life Sciences (pp. 251-255). Springer, Cham.

Burghardt, M., 2014. Engineering annotation usability-Toward usability patterns for linguistic annotation tools (Doctoral dissertation).

Chicco, D., Sadowski, P. and Baldi, P., 2014, September. Deep autoencoder neural networks for gene ontology annotation predictions. In Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 533-540). ACM.

Gu, Z., Eils, R. and Schlesner, M., 2016. Complex heatmaps reveal patterns and correlations in multidimensional genomic data. Bioinformatics, 32(18), pp.2847-2849.

Guo, Y., 2016. Characterization, annotation and expression patterns of bovine X-degenerate Y-chromosome genes UTY, ZFY, USP9Y, PRKY, RPS4Y, TBL1Y and their isoforms.

Hoff, K. and Preminger, M., 2015, September. Usability testing of an annotation tool in a cultural heritage context. In Research Conference on Metadata and Semantics Research(pp. 237-248). Springer, Cham.

Jaouachi, R.T., Khemakhem, M.T., Hernandez, N., Haemmerle, O. and Jemaa, M.B., 2015, April. Semantic Annotation of Images Extracted from the Web using RDF Patterns and a Domain Ontology. In ICEIS (2) (pp. 137-144).

Kächele, M., Rukavina, S., Palm, G., Schwenker, F. and Schels, M., 2015, January. Paradigms for the Construction and Annotation of Emotional Corpora for Real-world Human-Computer-Interaction. In ICPRAM (1) (pp. 367-373).

Kairam, S. and Heer, J., 2016, February. Parting crowds: Characterizing divergent interpretations in crowdsourced annotation tasks. In Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing (pp. 1637-1648). ACM.

Kanehisa, M., Sato, Y., Kawashima, M., Furumichi, M. and Tanabe, M., 2015. KEGG as a reference resource for gene and protein annotation. Nucleic acids research, 44(D1), pp.D457-D462.

Kolesnikov, A. and Lampert, C.H., 2016. Improving weakly-supervised object localization by micro-annotation. arXiv preprint arXiv:1605.05538.

Letunic, I. and Bork, P., 2017. 20 years of the SMART protein domain annotation resource. Nucleic acids research, 46(D1), pp.D493-D496.

Mi, H., Huang, X., Muruganujan, A., Tang, H., Mills, C., Kang, D. and Thomas, P.D., 2016. PANTHER version 11: expanded annotation data from Gene Ontology and Reactome pathways, and data analysis tool enhancements. Nucleic acids research, 45(D1), pp.D183-D189.

Miñarro-Giménez, J.A., Martínez-Costa, C., López-García, P. and Schulz, S., 2017. Building SNOMED CT Post-Coordinated Expressions from Annotation Groups. Studies in health technology and informatics, 235, pp.446-450.

Shin, H.C., Roberts, K., Lu, L., Demner-Fushman, D., Yao, J. and Summers, R.M., 2016. Learning to read chest x-rays: Recurrent neural cascade model for automated image annotation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2497-2506).

Suzuki, K., Kato, Y. and Matsubara, S., 2017. Correcting Syntactic Annotation Errors Based on Tree Mining. IEICE TRANSACTIONS on Information and Systems, 100(5), pp.1106-1113.

Zhang, J., Mu, Y., Feng, S., Li, K., Yuan, Y. and Lee, C.H., 2018. Image region annotation based on segmentation and semantic correlation analysis. IET Image Processing.