Trainee, Visitor and Volunteer Onboarding


Computer Resources: Please select the computer resource(s) this individual will use.
Will this person require access to Evans 6?
Will this person be on campus a minimum of 2 days per week?
If yes, will they need an assigned computational desk?

Deep learning-driven quantification of interstitial fibrosis in digitized kidney biopsies

(Source: The American Journal of Pathology)

New publication from Dr. Vijaya Kolachalama, Assistant Professor of Medicine in the Section of Computational Biomedicine. See below for a brief summary and click the link to read the whole article.

Interstitial fibrosis and tubular atrophy (IFTA) on a renal biopsy are strong indicators of disease chronicity and prognosis. Techniques that are typically used for IFTA grading remain manual, leading to variability among pathologists. Accurate IFTA estimation using computational techniques can reduce this variability and provide quantitative assessment. Using trichrome-stained whole slide images (WSIs) processed from human renal biopsies, we developed a deep learning framework that captured finer pathological structures at high resolution and overall context at the WSI-level to predict IFTA grade. WSIs (n=67) were obtained from The Ohio State University Wexner Medical Center (OSUWMC). Five nephropathologists independently reviewed them and provided fibrosis scores that were converted to IFTA grades: <=10% (None or minimal), 11-25% (Mild), 26-50% (Moderate), and >50% (Severe). The model was developed by associating the WSIs with the IFTA grade determined by majority voting (reference estimate). Model performance was evaluated on WSIs (n=28) obtained from the Kidney Precision Medicine Project (KPMP). There was good agreement on the IFTA grading between the pathologists and the reference estimate (Kappa=0.622±0.071). The accuracy of the DL model was 71.8±5.3% on OSUWMC and 65.0±4.2% on KPMP datasets, respectively. Our approach to analyzing microscopic- and WSI-level changes in renal biopsies attempts to mimic the pathologist and provides a regional and contextual estimation of IFTA. Such methods can assist clinicopathologic diagnosis.

Click here to read the full article.

Subchondral bone length in knee osteoarthritis: A deep learning derived imaging measure and its association with radiographic and clinical outcomes

(Source: Wiley Online Library)

New Publication from Dr. Vijaya Kochalama, Assistant Professor of Medicine in the Section of Computational Biomedicine. Please see below for a brief summary and click the link to read the full article.


Develop a bone shape measure that reflects the extent of cartilage loss and bone flattening in knee osteoarthritis (OA) and test it against estimates of disease severity.


A fast region‐based convolutional neural network was trained to crop the knee joints in sagittal dual‐echo steady state MRI sequences obtained from the Osteoarthritis Initiative (OAI). Publicly available annotations of the cartilage and menisci were used as references to annotate the tibia and the femur in 61 knees. Another deep neural network (U‐Net) was developed to learn these annotations. Model predictions were compared with radiologist‐driven annotations on an independent test set (27 knees). The U‐Net was applied to automatically extract the knee joint structures on the larger OAI dataset (9,434 knees). We defined subchondral bone length (SBL), a novel shape measure characterizing the extent of overlying cartilage and bone flattening, and examined its relationship with radiographic joint space narrowing (JSN), concurrent WOMAC pain and disability as well as subsequent partial or total knee replacement (KR). Odds ratios for each outcome were estimated using relative changes in SBL on the OAI dataset into quartiles.

Click here to read more.

Thesis Defenses – Zhe Wang and Ke Xu

Congratulations to CBM PhD candidates Zhe Wang and Ke Xu, who both passed their thesis defenses on Thursday, April 8. Zhe Wang, of the Campbell lab, defended his thesis entitled“Enhancing Preprocessing and Clustering of Single-Cell RNA Sequencing Data” and Ke Xu, of the Spira/Lenburg lab, defended his thesis entitled “Airway Gene Expression Alterations in Association with Radiographic Abnormalities of the Lung." Both candidates defended virtually.

Job Opportunity – Postdoctoral Associate

We are looking for a postdoctoral associate to develop methods to analyze NGS data including single-cell RNA sequencing and CITE-seq, whole exome/genome DNA sequencing, and bulk RNA sequencing in projects related to the genomic characterization of lung premalignant lesions in the “Pre-Cancer Genome Atlas” consortium funded by Human Tumor Atlas Network Therefore, data analysis and method development experience with single-cell RNA-seq, DNA-seq data, and/or RNA-seq data in the setting of cancer is preferred.

This position will be supervised by Drs. Jennifer Beane and Joshua Campbell and collaborate very closely with the Mazzilli and Spira/Lenburg Computational Biomedicine labs.  The position will involve working with several investigators and trainees with a wide range of expertise in areas such as clinical medicine, computational biology, functional genomics, and biostatistics. In addition, the postdoctoral associate will have access to and participate in multiple methods development and analysis working groups to increase knowledge and proficiency of genomic algorithms and approaches. Training in grant writing will be provided by supervising faculty and also available through university-sponsored workshops. Funding for this position is available through 2022 however independent fellowships will be encouraged and supported.

Required Skills
  • Ph.D. or equivalent degree in bioinformatics, computational biology, biostatistics, statistics, or a related field within the past 5 years.
  • Excellent communication skills in both spoken and written English are required.
  • Excellent critical thinking and problem-solving abilities are required.
  • Experience developing or applying algorithms for analyzing large-scale genomic datasets is preferred.
  • Experience with Unix/Linux is required and experience with R and Python is preferred.


Please email a cover letter and CV to Dr. Joshua Campbell (

Animalcules: interactive microbiome analytics and visualization in R

Source: BMC (Part of Springer Nature)

New publication from Dr. Evan Johnson, Dr. Stefano Monti, Anthony Federico and collaborators - see below for the abstract and to read more.


Microbial communities that live in and on the human body play a vital role in health and disease. Recent advances in sequencing technologies have enabled the study of microbial communities at unprecedented resolution. However, these advances in data generation have presented novel challenges to researchers attempting to analyze and visualize these data.


To address some of these challenges, we have developed animalcules, an easy-to-use interactive microbiome analysis toolkit for 16S rRNA sequencing data, shotgun DNA metagenomics data, and RNA-based metatranscriptomics profiling data. This toolkit combines novel and existing analytics, visualization methods, and machine learning models. For example, the toolkit features traditional microbiome analyses such as alpha/beta diversity and differential abundance analysis, combined with new methods for biomarker identification are. In addition, animalcules provides interactive and dynamic figures that enable users to understand their data and discover new insights. animalcules can be used as a standalone command-line R package or users can explore their data with the accompanying interactive R Shiny interface.


We present animalcules, an R package for interactive microbiome analysis through either an interactive interface facilitated by R Shiny or various command-line functions. It is the first microbiome analysis toolkit that supports the analysis of all 16S rRNA, DNA-based shotgun metagenomics, and RNA-sequencing based metatranscriptomics datasets. animalcules can be freely downloaded from GitHub at or installed through Bioconductor at

Click here to read the full article.

Enhancing magnetic resonance imaging-driven Alzheimer’s disease classification performance using generative adversarial learning

Source: BMC (Part of Springer Nature)

New publication from Dr. Vijaya Kolachalama and collaborators - see below for the abstract and to read more.

Generative adversarial networks (GAN) can produce images of improved quality but their ability to augment image-based classification is not fully explored. We evaluated if a modified GAN can learn from magnetic resonance imaging (MRI) scans of multiple magnetic field strengths to enhance Alzheimer’s disease (AD) classification performance.

T1-weighted brain MRI scans from 151 participants of the Alzheimer’s Disease Neuroimaging Initiative (ADNI), who underwent both 1.5-Tesla (1.5-T) and 3-Tesla imaging at the same time were selected to construct a GAN model. This model was trained along with a three-dimensional fully convolutional network (FCN) using the generated images (3T*) as inputs to predict AD status. Quality of the generated images was evaluated using signal to noise ratio (SNR), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Natural Image Quality Evaluator (NIQE). Cases from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL, n = 107) and the National Alzheimer’s Coordinating Center (NACC, n = 565) were used for model validation.

The 3T*-based FCN classifier performed better than the FCN model trained using the 1.5-T scans. Specifically, the mean area under curve increased from 0.907 to 0.932, from 0.934 to 0.940, and from 0.870 to 0.907 on the ADNI test, AIBL, and NACC datasets, respectively. Additionally, we found that the mean quality of the generated (3T*) images was consistently higher than the 1.5-T images, as measured using SNR, BRISQUE, and NIQE on the validation datasets.

This study demonstrates a proof of principle that GAN frameworks can be constructed to augment AD classification performance and improve image quality.

Click here to read more.

Protein signatures of centenarians and their offspring suggest centenarians age slower than other humans

Source: Aging Cell

New publication from Dr. Stefano Monti, Associate Professor of Medicine, in collaboration with Dr. Thomas Perls and Dr. Paola Sebastiani of the New England Centenarian Study. See below for a brief summary and click the link to read more.

Using samples from the New England Centenarian Study (NECS), we sought to characterize the serum proteome of 77 centenarians, 82 centenarians' offspring, and 65 age‐matched controls of the offspring (mean ages: 105, 80, and 79 years). We identified 1312 proteins that significantly differ between centenarians and their offspring and controls (FDR < 1%), and two different protein signatures that predict longer survival in centenarians and in younger people. By comparing the centenarian signature with 2 independent proteomic studies of aging, we replicated the association of 484 proteins of aging and we identified two serum protein signatures that are specific of extreme old age. The data suggest that centenarians acquire similar aging signatures as seen in younger cohorts that have short survival periods, suggesting that they do not escape normal aging markers, but rather acquire them much later than usual. For example, centenarian signatures are significantly enriched for senescence‐associated secretory phenotypes, consistent with those seen with younger aged individuals, and from this finding, we provide a new list of serum proteins that can be used to measure cellular senescence. Protein co‐expression network analysis suggests that a small number of biological drivers may regulate aging and extreme longevity, and that changes in gene regulation may be important to reach extreme old age. This centenarian study thus provides additional signatures that can be used to measure aging and provides specific circulating biomarkers of healthy aging and longevity, suggesting potential mechanisms that could help prolong health and support longevity.

(Click here to read more)

2021 Toffler Scholars in Neuroscience

Source: Boston University School of Medicine Office of the Dean

Vijaya  Kolachalama, PhD, Assistant Professor of Medicine (Computational Biomedicine) and Computer Science, and founding member of the faculty of BU Computing & Data Sciences; Shangran Qiu, BA, BU CAS; Prajakta Joshi, BDS, MPH, GSDM; Chonghua Xue, BA, Medicine (Computational Biomedicine); and Matthew Miller, BUSM’22, are the 2021 Toffler Scholars in Neuroscience grant recipients for their project Alzheimer’s Disease Classification Using Deep Learning.

The Toffler Scholar Program was established by the Karen Toffler Charitable Trust to support promising young medical researchers, physicians and scientists working on early-stage, future-focused brain science with funding and a vital, relevant network through an internal competition at BUSM.

Their research is focused on building artificial intelligence models to identify brain regions that suggest Alzheimer’s disease risk and seek ways to differentiate these patterns from other forms of dementia. They use MRI and PET scans, neuropathology scores, digital voice recordings, and various other forms of data that can be easily collected in memory clinics to build their models. They work closely with neuropsychologists, neurologists, neuroradiologists and neuropathologists to validate their findings. Their long-term goal is to accurately detect memory disorders by providing these models as diagnostic aids to assist primary care providers and general neurologists.

Lung Cancer Research Foundation Research Grant on Disparities in Lung Cancer Awarded to Dr. Joshua Campbell

Dr. Joshua Campbell, Assistant Professor of Medicine in the Section of Computational Biomedicine, received a Lung Cancer Research Foundation (LCRF) Disparities Award in collaboration with Dr. Umit Tapan, Assistant Professor of Medicine in the Section of Hematology & Medical Oncology. Click here to read more about their research project. 

Boston University researchers to develop new breast tumor models

Source: Eurekalert

Breast cancer is the second most common cancer diagnosed in women in the United States after skin cancer, and women with comorbidities (the presence of more than one condition/disease) often fare worse in terms of their breast cancer. Researchers believe that comorbid conditions such as diabetes, obesity and metabolic disease may alter the biology of the non-malignant cells of the tumor microenvironment and may promote progression.

Boston University School of Medicine (BUSM) researchers Gerald Denis, PhD, Andrew Emili, PhD, and Stefano Monti, PhD, together with Beth Israel Deaconess/Harvard Medical School researcher Senthil Muthuswamy, PhD, have been awarded a five-year, $2.5 million National Cancer Institute UO1 grant to develop and analyze breast tumor organoids (models). Specifically, the award will support their project: Multiscale analysis of metabolic inflammation as a driver of breast cancer.

Read more