About
Postdoctoral Fellow at Johns Hopkins Bloomberg School of Public Health (JHSPH) working…
Experience
Education
Licenses & Certifications
Publications
-
Book Review: The Indian Economy: A Macroeconomic Perspective
Asia-Pacific Research and Training Network on Trade, UNESCAP
-
An ensemble micro neural network approach for elucidating interactions between zinc finger proteins and their target DNA
BMC bioinformatics
The ability to engineer zinc finger proteins binding to a DNA sequence of choice is essential for targeted genome editing to be possible. Experimental techniques and molecular docking have been successful in predicting protein-DNA interactions, however, they are highly time and resource intensive. Here, we present a novel algorithm designed for high throughput prediction of optimal zinc finger protein for 9 bp DNA sequences of choice. Inaccordance with the principles of information theory, a…
The ability to engineer zinc finger proteins binding to a DNA sequence of choice is essential for targeted genome editing to be possible. Experimental techniques and molecular docking have been successful in predicting protein-DNA interactions, however, they are highly time and resource intensive. Here, we present a novel algorithm designed for high throughput prediction of optimal zinc finger protein for 9 bp DNA sequences of choice. Inaccordance with the principles of information theory, a subset identified by using K-means clustering was used as a representative for the space of all possible 9 bp DNA sequences. The modeling and simulation results assuming synergistic mode of binding obtained from this subset were used to train an ensemble micro neural network. Synergistic mode of binding is the closest to the DNA-protein binding seen in nature, and gives much higher quality predictions, while the time and resources increase exponentially in the trade off. Our algorithm is inspired from an ensemble machine learning approach, and incorporates the predictions made by 100 parallel neural networks, each with a different hidden layer architecture designed to pick up different features from the training dataset to predict optimal zinc finger proteins for any 9 bp target DNA
Other authorsSee publication -
Gargling affect on salivary electrochemical parameters to predict blood glucose
IEEE
The importance of saliva as a potent diagnostic biofluid was realized in the last decade, and since then a number of success stories have come up for diagnosing diseases using this body fluid. One of the crucial aspects of using saliva for any analysis is its collection since oral physiology varies not only between individuals but also during different times of the day. Hence, fixing a standard protocol for saliva collection is a matter of utter importance. In this paper, we have compared the…
The importance of saliva as a potent diagnostic biofluid was realized in the last decade, and since then a number of success stories have come up for diagnosing diseases using this body fluid. One of the crucial aspects of using saliva for any analysis is its collection since oral physiology varies not only between individuals but also during different times of the day. Hence, fixing a standard protocol for saliva collection is a matter of utter importance. In this paper, we have compared the implications of saliva collection on blood glucose prediction under two different conditions - (1) without gargling and (2) 15 min after gargling. 100 volunteers comprising half diabetic and rest healthy were recruited for this study and their salivary electrochemical parameters namely pH, conductivity, oxidation-reduction potential (ORP) and specific ion concentration (Na+, K+ and Ca2+) were analyzed. The variability in the data under both conditions was then determined using covariance matrix. Further, machine learning tools such as ordinary least square regression, support vector regression and kernel ridge regression were applied on the electrochemical data to predict the actual blood glucose level in both gargling and non-gargling conditions. Results obtained using non-gargled data showed higher variability but superior performance in predicting actual blood glucose levels.
-
Investigating the "Wisdom of Crowds" at Scale
Adjunct Proceedings of the 28th Annual ACM Symposium on User Interface Software & Technology
In a variety of problem domains, it has been observed that the aggregate opinions of groups are often more accurate than those of the constituent individuals, a phenomenon that has been termed the "wisdom of the crowd." Yet, perhaps surprisingly, there is still little consensus on how generally the phenomenon holds, how best to aggregate crowd judgements, and how social influence affects estimates. We investigate these questions by taking a meta wisdom of crowds approach. With a distributed…
In a variety of problem domains, it has been observed that the aggregate opinions of groups are often more accurate than those of the constituent individuals, a phenomenon that has been termed the "wisdom of the crowd." Yet, perhaps surprisingly, there is still little consensus on how generally the phenomenon holds, how best to aggregate crowd judgements, and how social influence affects estimates. We investigate these questions by taking a meta wisdom of crowds approach. With a distributed team of over 100 student researchers across 17 institutions in the United States and India, we develop a large-scale online experiment to systematically study the wisdom of crowds effect for 1,000 different tasks in 50 subject domains. These tasks involve various types of knowledge (e.g., explicit knowledge, tacit knowledge, and prediction), question formats (e.g., multiple choice and point estimation), and inputs (e.g., text, audio, and video). To examine the effect of social influence, participants are randomly assigned to one of three different experiment conditions in which they see varying degrees of information on the responses of others. In this ongoing project, we are now preparing to recruit participants via Amazon's Mechanical Turk.
-
Computational prediction of origin of replication in bacterial genomes using correlated entropy measure (CEM)
Elsevier
We have carried out an analysis on 500 bacterial genomes and found that the de-facto GC skew method could predict the replication origin site only for 376 genomes. We also found that the auto-correlation and cross-correlation based methods have a similar prediction performance. In this paper, we propose a new measure called correlated entropy measure (CEM) which is able to predict the replication origin of all these 500 bacterial genomes. The proposed measure is context sensitive and thus a…
We have carried out an analysis on 500 bacterial genomes and found that the de-facto GC skew method could predict the replication origin site only for 376 genomes. We also found that the auto-correlation and cross-correlation based methods have a similar prediction performance. In this paper, we propose a new measure called correlated entropy measure (CEM) which is able to predict the replication origin of all these 500 bacterial genomes. The proposed measure is context sensitive and thus a promising tool to identify functional sites. The process of identifying replication origins from the output of CEM and other methods has been automated to analyze a large number of genomes in a faster manner. We have also explored the applicability of SVM based classification of the workability of each of these methods on all the 500 bacterial genomes based on its length and GC content.
Other authorsSee publication
Honors & Awards
-
Duke Economics Master’s Scholar Award
Duke University
The Economics and Computer Science Departments are committed to providing funding to support your study up to four academic terms.
-
French Government Scholarship (Charpak Scholarship)
French Government
-Entitled by French embassy to receive Charpak Scholarship for my study in France
-Selected for Foreign Student Exchange Program 2013 by IIT Delhi for 5th semester
-Admission in University of Lorraine, France for a semester
Languages
-
English
-
-
Hindi
-
-
Gujarati
-
-
French
-
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore MoreOthers named Harsh Parikh in United States
-
Harsh Parikh
Master’s in Applied Data Science @ USC | Ex-AI Engineer Intern @ Delet | Specializing in AI, Machine Learning, & Data Science | Open to Fall 2024 Co-op & Full-Time Roles | GHC'24
-
Harsh Parikh
SQL | SSIS | SSRS | Power BI Developer
-
Harsh Parikh
-
Harsh Parikh
34 others named Harsh Parikh in United States are on LinkedIn
See others named Harsh Parikh