Bioinformaticist I

Harvard Medical School

Boston, MA

ID: 7089376
Posted: November 17, 2021
Application Deadline: Open Until Filled

Job Description

Job-Specific Responsibilities

We are seeking a computational expert to join the laboratory of Ting Wu (Harvard Medical School) in their CEGS (NIH/NHGRI) journey to image, analyze, and model the human genome, in its entirety, at super-resolution. Beyond an introductory acclimation to the research program, the successful candidate should very quickly be able to independently carry out, as well as lead, computational studies within the context of the program. A strong sense of collaboration and high levels of self-motivation, creativity, and open-mindedness will be appreciated. Candidates can anticipate working as part of an interdisciplinary team of geneticists, microscopists, chemists, engineers, physicists, and computational experts.

General: The selected individual will be expected to have had extensive computational experience, equivalent to, or exceeding, that of senior postdoctoral fellows in the field of genetics, epigenetics, and 3D genome organization or someone who has had significant experience working independently in an industrial setting. The successful candidate will have had experience in both supervised and unsupervised machine/deep learning, Bayesian theory, wave theory, image segmentation and analysis, signal processing, transfer learning, etc., and be able to apply these tools to images acquired by diffraction-limited microscopy or single-molecule localization.

Specific: The successful candidate will be addressing long-standing challenges in the field of in situ genome imaging, which falls within the larger field of 3D genome organization. These challenges include: detection of signal over noise (S:N), drift correction, cluster analysis, pattern recognition within a structurally variable genome, and integrative genome modelling, to mention just a few. The challenges also include bottlenecks in terms of data curation, transfer, and storage, the latter potentially involving tens of Tbs of data being generated per day.

The successful applicant will, therefore, be:

a) providing solutions that improve S:N via the development of new imaging strategies and computational pipelines,

b) developing de novo strategies for data validation,

c) developing de novo tools for data analysis (e.g., PCA analysis, signal resizing/resampling, alignment, filtering)

d) developing de novo tools for image processing (e.g., via denoising, mathematic transformation, automated tracking)

e) developing new tools for pattern recognition via unsupervised machine learning (e.g., via VAEs, GANs, K-means), including image segmentation, edge detection, and automated tracking.

f) developing new pipelines for integrated as well as polymer/biophysics-based modelling,

g) developing new tools for predictive modelling (via, e.g., machine/deep learning).

Basic Qualifications

Bachelor's degree in biological science or related field. 3+ years relevant experience

Additional Qualifications and Skills

• Applicants should have had extensive training and experience in computational biology, data science, statistics, and/or related fields, including hands-on expertise with machine learning, neural networks, and/or artificial intelligence for building, testing, and evaluating predictive and classification models.
• Applicants must have demonstrated or exceeded the capacity of a senior level postdoctoral fellow in genetics, epigenetics, and 3D genome organization or have had several years’ experience working independently in an industrial setting.
• Applicants should be proficient in Python, R, C/C++,
SQL, Fortran, MATLAB, Julia, etc. and cloud/cluster computing.
• Applicants must have robust experience in supervised (e.g., SVM, RF, XGBoost, LASSO, MLP, U-NET, ResNet, LSTM, and GRUs) and unsupervised (e.g., PCA, K-means, VAEs, GANs) machine/deep learning, Bayesian theory, wave theory, image segmentation and analysis, signal processing (e.g., Convolution, Complex analysis, STFT, CWT, ST, and filtering), transfer learning, etc.
• Applicants should have strong presentation and communication skills both verbal and written.

Additional Information

This is a one-year funded term position with possibility of extension, contingent on work performance and continued funding to support the position.

Harvard requires COVID vaccination for all Harvard community members. Individuals may claim exemption from the vaccine requirement for medical or religious reasons. More information regarding the University’s COVID vaccination requirement, exemptions, and verification of vaccination status may be found at the University’s “COVID-19 Vaccine Information” webpage: http://www.harvard.edu/coronavirus/covid-19-vaccine-information/.

Please note that we are currently conducting a majority of interviews and onboarding remotely and virtually. We appreciate your understanding.

Harvard University offers an outstanding benefits package including:
Time Off: 3 - 4 weeks paid vacation, paid holiday break, 12 paid sick days, 12.5 paid holidays, and 3 paid personal days per year.
Medical/Dental/Vision: We offer a variety of excellent medical plans, dental & vision plans, all coverage begins as of your start date.
Retirement: University-funded retirement plan with full vesting after 3 years of service.
Tuition Assistance Program: Competitive tuition assistance program, incredibly affordable classes directly at the Harvard Extension School, and discounted options through participating Harvard grad schools.
Transportation: Harvard offers a 50% discounted MBTA pass as well as additional options to assist employees in their daily commute.
Wellness options: Harvard offers programs and classes at little or no cost, including stress management, massages, nutrition, meditation, and complementary health services.
Harvard access to athletic facilities, libraries, campus events, and many discounts throughout metro Boston.
The Harvard Medical School is not able to provide visa sponsorship for this position.

Harvard Medical School strives to cultivate an environment that promotes inclusiveness and collaboration among students, faculty and staff and to create new avenues for discussion that will advance our shared mission to improve the health of people throughout the world.