AI/ML/CS/QBio:

Arora R and Arnaout R. Repertoire-scale measures of antigen binding. PNAS 2023 HTML | PDF

Chinn E, Arora R, Arnaout R, Arnaout R. ENRICHing medical imaging training sets enables more efficient machine learning. JAMIA 2023 HTML | PDF

Arora R, Kaplinsky J, Li A, and Arnaout R. Repertoire-Based Diagnostics Using Statistical Biophysics. bioRxiv 2019 HTML | PDF

Madani A, Arnaout R, Mofrad M, and Arnaout R. Fast and accurate classification of echocardiograms using deep learning. NPJ Digital Med. 2018. 1(1): s41746-017-0013-1 HTML | PDF

Krishnan V, Stoppel DC, Nong Y, Johnson MA, Ozkaynak E, Nadler MJS, Peterson S, Teng BL, Silva M, Nagakura I, Kasper E, Mohammad F, Arnaout R, and Anderson MP. Ube3a and seizures impair sociability by down-regulating autism network gene Cbln1 in VTA. Nature. 2017. 543(7646):507-512 HTML | PDF

Kaplinsky J and Arnaout R. Robust Estimates of Overall Immune-Repertoire Diversity from High-Throughput Measurements on Samples. Nat Commun. 2016. 15(7):11881. HTML | PDF

Kaplinsky J, Li A, Sun A, Coffre M, Koralov SB, Arnaout R. Antibody Repertoire Deep-Sequencing Reveals Antigen-Independent Selection in Maturing B Cells. Proc Natl Acad Sci U S A 2014. 111(25):E2622-9. HTML | PDF

Lakhani KR, Boudreau KJ, Loh P-R, Backstrom L, Baldwin C, Lonstein E, Lydon M, MacCormack A, Arnaout RA†, Guinan EC†. Prize-Based Contests Can Provide Solutions to Computational Biology Problems. Nat. Biotechnol. 2013. 31(2):108-11. †Co-senior authors HTML | PDF

Tsibris AM, Korber B, Arnaout R, Russ C, Lo CC, Leitner T, et al. Quantitative deep sequencing reveals dynamic HIV-1 escape and large population shifts during CCR5 antagonist therapy in vivo. PLoS One. 2009. 4(5):e5683. PMCID: 2682648. HTML | PDF

Sallstrom B, Arnaout RA,* Davids W,* Bjelkmar P, Andersson SG. Protein evolutionary rates correlate with expression independently of synonymous substitutions in Helicobacter pylori. J Mol Evol. 2006. 62(5):600-14. *These authors contributed equally to this work PubMed

Dostie J, Richmond TA, Arnaout RA, Selzer RR, Lee WL, Honan TA, et al. Chromosome Conformation Capture Carbon Copy (5C): a massively parallel solution for mapping interactions between genomic elements. Genome Res. 2006. 16(10):1299-309. PMCID: 1581439. HTML | PDF

Arnaout RA. Specificity and overlap in gene segment-defined antibody repertoires. BMC Genomics. 2005. 6:148. PMCID: 1277825. HTML | PDF

Clinical/Microbiology/Policy:

Cheng A, Riedel S, Arnaout R, Kirby JE. Verification of the Abbott Alinity m Resp-4-Plex Assay for Detection of SARS-CoV-2, Influenza A/B, and Respiratory Syncytial Virus. Diagn Microbiol Infect Dis. In press. HTML | PDF

Callahan CJ, Lee RA, Lee GR, Zulauf K, Kirby JE, and Arnaout R. Nasal Swab Performance by Collection Timing, Procedure, and Method of Transport for Patients with SARS-CoV-2. J. Clin Microbiol. 59:e00569-21 2021 HTML | PDF

Callahan CJ, Ditelberg S, Dutta S, Littlehale N, Cheng A, Kupczewski K, McVay D, Riedel S, Kirby JE, Arnaout R. Saliva is Comparable to Nasopharyngeal Swabs for Molecular Detection of SARS-CoV-2. Microbiol Spectrum. 9:e0016221 2021 HTML | PDF

Arnaout R*, Lee R, Lee G, Callahan C, Yen C, Smith K, Arora R, and Kirby JE*. The Limit of Detection Matters: The Case for Benchmarking Severe Acute Respiratory Syndrome Coronavirus 2 Testing. Clin. Infect. Dis. ciaa1382 2021. *co-corresponding authors HTML | PDF

Callahan CJ, Lee R, Zulauf K, Tamburello L, Smith KP, Previtera J, Cheng A, Green A, Abdul Azim A, Yano A, Kirby JE, Arnaout R. Rapid Open Development and Clinical Validation of Multiple New 3D-Printed Nasopharyngeal Swabs in Response to the COVID-19 Pandemic. J. Clin. Microbiol. 58:e00876-20 2020 HTML | PDF

Callahan C, Lee R, Lee G, Zulauf KE, Kirby JE, Arnaout R. Nasal-Swab Testing Misses Patients with Low SARS-CoV-2 Viral Loads. medRxiv 2020 HTML | PDF

Kaushik N, Khangulov VS, O’Hara M, and Arnaout R. Evaluation of the reduction in Laboratory turnaround time as a potential driver to the decrease in ED length of stay: A retrospective analysis. Open Access Emerg Med. 2018. 10:37 HTML | PDF

Arnaout R. Seeing the Forest for the Trees: Machine Learning in Clinical Pathology. Clin Chem. 64(11):1553-1554. 2018 HTML | PDF

Theisen-Toupal J, Breu AC, Mattison MLP, Arnaout R. Diagnostic yield of head computed tomography for the hospitalized medical patient with delirium. Journal of Hospital Medicine 2014. 9(8):497-501. HTML | PDF

Mohammad, F, Theisen-Toupal J, Arnaout R. Advantages and Limitations of Anticipating Laboratory Test Results from Regression- and Tree-Based Rules Derived from Electronic Health-Record Data. PLoS One 2014; 9(4): e92199. HTML | PDF

Zhi M, Ding, EL, Toupal-Thiessen J, Whelan J, Arnaout R. The landscape of inappropriate laboratory testing: a 15-year systematic review and meta-analysis. PLoS One 2013; 8(11): e78962. HTML | PDF

Arnaout R, Buck TP, Roulette P, Sukhatme, VP. Economic modeling could aid brain map. Nature. 2013; 497(7450):439. HTML | PDF

Arnaout R, Buck TP, Roulette P, Sukhatme VP. Predicting the Cost and Pace of Pharmacogenomic Advances: An Evidence-Based Study. Clin Chem. 2013. 59(4):649-57. HTML | PDF

Buck TP, Connor IM, Horowitz GL, Arnaout RA. CallWall: tracking resident calls to improve clinical utilization of pathology laboratories. Arch Pathol Lab Med. 2011. 135(7):920-4. HTML | PDF

Ramy Arnaout, MD, DPhil, director of the lab, is Associate Professor of Pathology at Beth Israel Deaconness Medical Center and Harvard Medical School, and Associate Director of the Clinical Microbiology Laboratories at BIDMC. He is president-elect of the American Society of Microbiology Northeast Branch and past Chairman of the FDA/CMS/CDC CLIA Committee. He received his SB from MIT, DPhil from Oxford University (Marshall Scholarship), and MD from Harvard Medical School (Soros Fellow). He completed residency in pathology at Brigham and Women's Hospital and postdoctoral work at the Broad Institute.

Jasper Braun, PhD is a postdoctoral fellow working on immunomics in the lab. He received his doctorate in Mathematics from the University of South Florida, where he refined computational annotation and analysis techniques for DNA rearrangements in ciliates. He enjoys working wherever math and computer science meet real world data.

Elisa Contreras is a research assistant in our immunomics lab. She received her bachelor's in Biotechnology from the Institute of Technology of Santo Domingo, after graduating she worked in clinical diagnostics amid the Covid-19 pandemic, later on focusing on research of SARS-CoV-2. She is interested in molecular biology, sequencing and good food.

Josiah Couch, PhD (ORCID) is a postdoctoral fellow working on applications of information theory and machine learning to biology. He received his PhD in physics from the University of Texas at Austin, where he worked at the intersection of information theory, gravity, and field theory. Afterward, he spent time in the computer science department at Boston College, studying problems related to random graphs. His interests include physics, information theory, and machine learning.

Michie Yasuda, PhD is a research laboratory technician in our immunomics lab. She has 30 years of experience in biological laboratories mostly focusing on bacteriology and microbial analysis. A veteran of the University of Massachusetts, she is interested in mushroom hunting and sake brewing.

Tarini Shankar is a student research assistant completing her co-op in our immunomics laboratory. She is a second year student at Northeastern University and is majoring in Cell and Molecular Biology with a minor in Data Science. She is interested in microbiology and computational biology. She is also an avid painter and spicy food enthusiast.

Diane Balallo is a student research assistant in our immunomics lab. She is a second-year student at Boston College where she is completing her Bachelor of Science in Neuroscience. Her interests include pain neuroscience, learning theory, and autoimmune disorders. She enjoys volunteering, running, and playing the piano.

Alex Morgan is a software developer working on analysis and visualization of COVID-19 clinical data in the lab. Alex has extensive experience working in scientific research and the healthcare sector, using C, Java, Python, and many other languages. Since receiving her bachelor's degree in Geophysics from Brown University, she has piled on additional coursework in biology and computer science. She is interested in evolution, software quality, and many other subjects.

Alumni

Rohit Arora, PhD is a research scientist at Iktos, Inc. He worked on immunomics as a postdoc in the lab. He received his doctorate in computational biology with highest honors from the Ecole Normale Superieure where he studied the origin and mechanism of resistance to the inhibitors of HIV-1 integrase. Previously he received his MS summa cum laude as an Erasmus Mundus scholar.

Thomas Buck, MD is a hematopathologist in Connecticut. He completed his pathology training at the Beth Israel Deaconess Medical Center. He is interested in promoting an empirical approach to the practice of laboratory medicine and in finding ways to apply this directly to patient care. In the lab he helped build models and analyzed data on the pace of pharmacogenomic advances to forecast when they will affect patients in the clinic, and how much this is likely to cost.

Ashley Burke was a summer research student for the Arnaout Lab. She is currently finishing her bachelor’s degree in Computer Science at Worcester Polytechnic Institute. During her studies at WPI, she has developed a passion for Software Engineering and hopes to use her skills to develop applications to improve people's lives.

Cody Callahan is a biochemist from the University of Vermont, with an emphasis on cancer biology and microRNAs in prostate cancer. In the wake of the COVID-19 pandemic, he has devoted himself to clinical diagnostics, developing 3D-printed swabs and assessing various specimen types as clinical diagnostics for SARS-CoV-2. At present, his work has ranged from studying perfusion with hyperpolarized ¹³C, clinical diagnostics, next-gen sequencing, and robotics.

Eric L. Ding, ScD is an epidemiologist, nutritionist. His research focuses on obesity and nutritional risk factors for chronic diseases, social networks on health, and social media technology for health. In 2006, he was noted for his key role in leading a two-year-long investigation into the controversial drug safety and adverse metabolic risks of Vioxx®.

Sarah Ditelberg is a former research assistant in the lab where she helped uncover and sequence novel B and T cell receptors for SARS-CoV-2. She received her Bachelors in Biology from UMass Amherst in 2020, and throughout worked in Dr. James Kirby's lab studying synergistic treatments for Candida auris, later collaborating in Dr. Stefan Riedel lab on SARS-CoV-2 diagnostics. She is currently applying to medical school and working as a medical assistant in Brigham and Women's Orthopaedics Department.

Elliot Hill, MsC is a computational scientist who developed software and machine learning models for immunome-based diagnostic tools in the Arnaout Lab. He received his MS in computational science from Tulane University, where he completed his thesis on numerical optimization. His research interests lie at the intersection of statistics, machine learning, mathematics, and computer science. He is currently a fellow at Duke’s AI Health program where he is working on predicting neurodevelopment disorders in adolescents.

Joseph Kaplinsky, PhD is former a postdoctoral fellow studying immunomics in the lab. He received his doctorate from Imperial College, where he built microfluidic systems for single-cell analysis. Trained in theoretical and experimental physics as well as biology, he is interested in applying physical and quantitative systems approaches to biological problems.

Anthony Li, MS is a former research assistant in the lab. He received his MS in Pharmaceutical Sciences from the Massachusetts College of Pharmacy and Health Sciences where he helped develop of liposomal techniques to specifically target mitochondria in malignant murine glial cells. He moonlights at the circus.

Gaby Mazzoni is a former summer research assistant in the lab. She is currently finishing her bachelor's in Chemical Engineering at Worcester Polytechnic Institute. She is currently working on her senior project engineering different metabolic pathways into probiotic yeast.

Fahim Mohammad, PhD is a former postdoctoral fellow studying the bioinformatics of complex diseases, computational biology, and systems medicine in the lab. He received his doctorate from the University of Louisville, where he devised a systems-based approach for detecting and predicting molecular interactions across tissues.

Paulvalery Roulette, MD is an orthopedic hand surgeon at Carolinas Medical Center and an alumnus of Harvard Medical School and Cornell University. In the lab he compiled and analyzed data on the pace of pharmacogenomic advances to forecast when they will affect patients in the clinic, and how much this is likely to cost.

Ethan Winter is a medical student at Case Western Reserve University. He graduated with his B.S. in Biology from UMass Amherst in 2020 and worked with the Arnaout Lab during his gap year before medical school. His work in the lab pertained to immune repertoire sequencing for natural and vaccine-mediated COVID-19 immunity during the height of the pandemic.

Fazilet Yilmaz is a pathology resident at the Warren Alpert Medical School of Brown University who was a visiting research rotator with the lab, working on COVID-19.

Ming Zhi, MD is a radiation oncologist in California. He is an alumnus of Harvard Medical School and of Stanford University, where he majored in biology. His interests lie at the intersection of medicine, design, and technology. In the Arnaout Lab he studied the utilization of laboratory diagnostics across medicine. He has been known to school Dr. Arnaout on the basketball court and prefers to be paid in Gatorade.

We're hiring machine-learning postdocs and wet-lab techs! If you'd like to apply to one of the open positions below, send a CV or resume to rarnaout at bidmc dot harvard dot edu together with a brief (~200-word) statement about why you'd like to join the lab and what you'd like to accomplish while here.

05.23 | Postdoctoral Fellow / Computational Immunology Data Scientist

We are looking for a postdoc-level computational/systems biologist to help design and operate the AI/ML infrastructure required to detect signals of infection and cancer in large immune-repertoire sequencing datasets.

Responsibilities

Devise, test, and implement novel learning algorithms for high-throughput data

Contribute to the generation of standard protocols and intellectual property

Core Qualifications

PhD degree in physics, engineering, mathematics, computational/systems biology, machine learning, artificial intelligence, immunology, bioinformatics, or related field, or equivalent practical experience

Hands-on experience designing and implementing computer algorithms, including supervised and unsupervised machine learning methods like Regression analysis, SVM, deep learning (autoencoders, transformers, geometric deep learning, dynamical systems, model decomposition), etc.

Hands-on expertise with statistical descriptions of complex systems (e.g. energy, entropy, moments, etc. and see under 2 above) and their theoretical underpinnings

Fluency in Unix/Linux environments, Python and ideally other standard bioinformatics tools (e.g. R, Perl, C, bash/csh/zsh, CUDA, OpenGL), ideally including hands-on experience with parallel processing.

Demonstrated expertise in computational analysis of large data sets, ideally biological sequence- based data sets, and 3D protein structures

Excellent creativity, decision-making, troubleshooting, and English-language communication skills

Comfort with and excitement about working in a startup-type atmosphere

Preferred Qualifications

Prior experience with implementing deep learning methods

Prior experience with high-performance computing clusters (SLURM, LSF or PBS schedulers), and AWS

Expertise with using Python libraries like Numpy, Scipy, Pandas, Matplotlib, Seaborn, and Tensorflow

Prior experience with/training in structural biology, immunology, cancer, and/or infectious disease

Experience with web applications/portals (e.g. Shiny Server or Python analogs)

Start date

As soon as possible

How to apply

Please send an email to Dr. Arnaout at rarnaout [at] bidmc [dot] org with your CV explaining why you would be good for the job.

05.23 | Deep-Learning Engineer / Postdoctoral Fellow / Research Scientist

We are looking for postdoc-level scientists/engineers with both conceptual/theoretical and practical/hands-on expertise in deep learning/computer vision to help make machine learning more efficient.

Location

The Beth Israel Deaconess Medical Center is a teaching affiliate of Harvard Medical School located in the heart of Boston’s Longwood Medical Area, a world-renowned center for biomedical research.

Responsibilities

Devise, test, and implement algorithms for high-throughput data

Contribute to the generation of standard protocols and intellectual property

Core Qualifications

PhD degree in physics, engineering, mathematics, machine learning, artificial intelligence, or related field, or equivalent practical experience

Hands-on experience designing and implementing computer algorithms, including supervised and unsupervised machine learning methods, deep learning (autoencoders, transformers, geometric deep learning, dynamical systems, model decomposition), etc.

Hands-on expertise with statistical descriptions of complex systems (e.g. energy, entropy, moments, etc. and see under 2 above) and their theoretical underpinnings

Fluency in Unix/Linux environments, Python and ideally other standard bioinformatics tools (e.g. R, Perl, C, bash/csh/zsh, CUDA, OpenGL), ideally including hands-on experience with parallel processing

Demonstrated expertise in computational analysis of large data sets, ideally in imaging

Excellent creativity, decision-making, troubleshooting, and English-language communication skills

Comfort with and excitement about working in a startup-type atmosphere

Preferred Qualifications

Prior experience with implementing deep learning methods

Prior experience with high-performance computing clusters (SLURM, LSF or PBS schedulers), and AWS

Expertise with using Python libraries like Tensorflow/Theano/Keras, Numpy, Scipy, Pandas, Matplotlib, and Seaborn

Prior experience with/training in medical imaging

Experience with web applications/portals (e.g. Shiny Server or Python analogs)

Start date

As soon as possible

How to apply

Please send an email to Dr. Arnaout at rarnaout [at] bidmc [dot] org with your CV explaining why you would be good for the job.

10.21 | Technologist / Research Assistant II

We are looking for a technologist/research assistant to conduct a variety of routine and specialized laboratory tests using molecular, cell biology and/or biochemistry techniques.

Responsibilities

Perform routine and non-routine laboratory tests (e.g.: next-generation sequencing library prep, DNA sequencing) and synthesize and interpret results

Operate and maintain moderate-to-complex lab equipment

Make decisions regarding the reliability and accuracy of results, repeating experiments when necessary

Assist with planning specific research procedures and coordinate scheduling of experiments

Prepare written and/or verbal reports on status of research and the technical procedures used, including statistical and graphical summaries of findings and possible conclusions

Demonstrate routine to complex lab techniques to others in the lab

Qualifications

Bachelor's or Master's degree in a life-sciences or related scientific field with 1-3 years' relevant work experience

Experience with productivity software (Microsoft Office or LibreOffice)

Excellent creativity, decision-making, troubleshooting, and English-language communication skills

Comfort with and excitement about working in a startup-type atmosphere

Start date

As soon as possible

How to apply

Please send an email to Dr. Arnaout at rarnaout [at] bidmc [dot] org with your CV explaining why you would be good for the job.

10.21 | Deep-Learning Engineer / Research Scientist

We are looking for postdoc-level scientists/engineers with both conceptual/theoretical and practical/hands-on expertise in deep learning/computer vision to help make machine learning more efficient.

Responsibilities

Devise, test, and implement algorithms for high-throughput data

Contribute to the generation of standard protocols and intellectual property

Core Qualifications

PhD degree or equivalent practical experience in physics, engineering, mathematics, computer science, machine learning, artificial intelligence

Hands-on experience designing and implementing computer algorithms, including supervised and unsupervised machine learning methods, deep learning (autoencoders, transformers, geometric deep learning, dynamical systems, model decomposition), etc.

Hands-on expertise with statistical descriptions of complex systems (e.g. energy, entropy, moments, etc.) and their theoretical underpinnings

Fluency in Unix/Linux environments, Python and ideally other standard bioinformatics tools (e.g. R, Perl, C, bash/csh/zsh, CUDA, OpenGL), ideally including hands-on experience with parallel processing.

Demonstrated expertise in computational analysis of large data sets, ideally in imaging

Excellent creativity, decision-making, troubleshooting, and English-language communication skills

Comfort with and excitement about working in a startup-type atmosphere

Preferred Qualifications

Prior experience with implementing deep learning methods

Prior experience with high-performance computing clusters (SLURM, LSF or PBS schedulers), and AWS

Expertise with using Python libraries like Tensorflow/Theano/Keras, Numpy, Scipy, Pandas, Matplotlib, and Seaborn

Prior experience with/training in medical imaging

Experience with web applications/portals (e.g. Shiny Server or Python analogs)

Start date

As soon as possible

How to apply

Please send an email to Dr. Arnaout at rarnaout [at] bidmc [dot] org with your CV explaining why you would be good for the job.

One way is to make a gift to the lab through a donation to our parent institution. Other options may be available. Please direct inquiries to us at rarnaout at bidmc dot harvard dot edu.

Immunomics today is where genomics was a decade ago: we have lots to learn. One of the best ways to help is by letting us sequence your immunome, following the precedent set by the the Personal Genomes Project, the Million Veterans Program, and other citizen science projects. Speaking with or involving other people, from students to policymakers, are also helpful things to do. If you are interested, or can think of other ways to help, please write us at rarnaout at bidmc dot harvard dot edu.