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?

Thesis Defense – Anthony Federico

Congratulations to CBM PhD candidate Anthony Federico, who passed his thesis defense, "Development of Methods for Omics Network Inference and Analysis and Their Application to Disease Modeling," on Thursday, November 18. Anthony is a member of Monti lab and defended both virtually and in person on Evans 6.

Detection of dementia on voice recordings using deep learning: a Framingham Heart Study

(Source: BMC Alzheimer's Research and Therapy)

New publication from Chonghua Xue, Bioinformatics Analyst and 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.


Identification of reliable, affordable, and easy-to-use strategies for detection of dementia is sorely needed. Digital technologies, such as individual voice recordings, offer an attractive modality to assess cognition but methods that could automatically analyze such data are not readily available.

Methods and findings

We used 1264 voice recordings of neuropsychological examinations administered to participants from the Framingham Heart Study (FHS), a community-based longitudinal observational study. The recordings were 73 min in duration, on average, and contained at least two speakers (participant and examiner). Of the total voice recordings, 483 were of participants with normal cognition (NC), 451 recordings were of participants with mild cognitive impairment (MCI), and 330 were of participants with dementia (DE). We developed two deep learning models (a two-level long short-term memory (LSTM) network and a convolutional neural network (CNN)), which used the audio recordings to classify if the recording included a participant with only NC or only DE and to differentiate between recordings corresponding to those that had DE from those who did not have DE (i.e., NDE (NC+MCI)). Based on 5-fold cross-validation, the LSTM model achieved a mean (±std) area under the receiver operating characteristic curve (AUC) of 0.740 ± 0.017, mean balanced accuracy of 0.647 ± 0.027, and mean weighted F1 score of 0.596 ± 0.047 in classifying cases with DE from those with NC. The CNN model achieved a mean AUC of 0.805 ± 0.027, mean balanced accuracy of 0.743 ± 0.015, and mean weighted F1 score of 0.742 ± 0.033 in classifying cases with DE from those with NC. For the task related to the classification of participants with DE from NDE, the LSTM model achieved a mean AUC of 0.734 ± 0.014, mean balanced accuracy of 0.675 ± 0.013, and mean weighted F1 score of 0.671 ± 0.015. The CNN model achieved a mean AUC of 0.746 ± 0.021, mean balanced accuracy of 0.652 ± 0.020, and mean weighted F1 score of 0.635 ± 0.031 in classifying cases with DE from those who were NDE.


This proof-of-concept study demonstrates that automated deep learning-driven processing of audio recordings of neuropsychological testing performed on individuals recruited within a community cohort setting can facilitate dementia screening.


Click here to read the whole paper.

Researchers develop machine learning methods to accurately identify, characterize metabolism-disrupting chemicals

Source: EurekAlert!

Chemicals in your furniture, plastic housewares and pesticides used in your yard may be making  you fat, according to Boston University Schools of Medicine and Public Health researchers. A growing number of environmental pollutants (organotins in pesticides, phthalates in plastics, flame retardants in furniture) activate fat-forming pathways and enhance weight gain through white-fat accumulation. In a new study, researchers developed a novel experimental and computational framework for the identification of so-called metabolism-disrupting chemicals (MDCs), also known as obesogens, which are environmental chemicals that increase the risk of metabolic diseases (such as obesity, diabetes and cardiovascular disease) in subjects exposed to them. “Our study developed machine learning methods to accurately identify and characterize new metabolism-disrupting chemicals and applied these methods to the classification of a set of as-yet uncharacterized chemicals suspected to be obesogens,” explained corresponding author Stefano Monti, PhD, associate professor of medicine at Boston University School of Medicine (BUSM).

Click here to read more.

Multi-resolution characterization of molecular taxonomies in bulk and single-cell transcriptomics data

(Source: Oxford Academic)

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

As high-throughput genomics assays become more efficient and cost effective, their utilization has become standard in large-scale biomedical projects. These studies are often explorative, in that relationships between samples are not explicitly defined a priori, but rather emerge from data-driven discovery and annotation of molecular subtypes, thereby informing hypotheses and independent evaluation. Here, we present K2Taxonomer, a novel unsupervised recursive partitioning algorithm and associated R package that utilize ensemble learning to identify robust subgroups in a ‘taxonomy-like’ structure. K2Taxonomer was devised to accommodate different data paradigms, and is suitable for the analysis of both bulk and single-cell transcriptomics, and other ‘-omics’, data. For each of these data types, we demonstrate the power of K2Taxonomer to discover known relationships in both simulated and human tissue data. We conclude with a practical application on breast cancer tumor infiltrating lymphocyte (TIL) single-cell profiles, in which we identified co-expression of translational machinery genes as a dominant transcriptional program shared by T cells subtypes, associated with better prognosis in breast cancer tissue bulk expression data.

Click here to read more.

AAIC Travel Fellowship Awarded to Michael Romano

Michael Romano, MD/PhD student in the Kolachalama Lab, has been awarded a travel fellowship for the 2021 Alzheimer's Association International Conference (AAIC). AAIC is the largest international dementia conference where researchers and clinicians come together to share advances in treatment and prevention of Alzheimer’s Disease. The conference will take place in Denver, Colorado in the last week of July. Travel fellowships are competitive and reception is based on criteria including the reviewer’s score of the abstract, format of the presentation (oral or poster), and World Bank income level of the applicant’s country of origin. Michael received a partial travel fellowship for his upcoming poster presentation entitled, “Comparative analysis of cerebrospinal fluid markers and  multimodal imaging in predicting Alzheimer’s Disease progression”, written with his co-authors Akshara Balachandra*, Xiao Zhou*, Michalina Jadick, Shangran Qiu, Diya Nijhawan, Sang P. Chin, Rhoda Au, and  Vijaya B. Kolachalama. (*indicates equal contribution)

Thesis Defense – Xingyi Shi

Congratulations to CBM PhD candidate Xingyi Shi, who passed her thesis defense, "Bronchial Gene Expression Associated with Airway Premalignancy and Lung Cancer Subtypes," on Monday, June 21. Xingyi is a member of the Spira/Lenburg and Beane labs and defended virtually.

CBM Faculty Members Awarded CTSI 2021 Integrated Pilot Grants

Congratulations to Drs. Jennifer Beane, Joshua Campbell, Vijaya Kolachalama and Sarah Mazzilli for receiving Integrated Pilot Grants from BU Clinical & Translational Science Institute. Please see below for more information on their awards.

Identifying Coding and Non-Coding Genomic Alterations Associated with Aggressive Prostate Cancer in African American Men

Recipients: Christopher Heaphy, Joshua Campbell & Rachel Flynn

The overall goal of this pilot project is to identify coding and non-coding genomic alterations in the racially and socioeconomically diverse patient population surgically treated for prostate cancer at Boston Medical Cancer.

Highly Multiplexed Immunophenotyping of Aggressive Histologic Patterns of Early-Stage Lung Adenocarcinomas

Recipients: Sarah Mazzilli, Jennifer Beane & Eric Burks

The proposed study leverages a unique set of early-stage LUAD tumors with extensive pathologic characterization that may start to unravel aggressive LUAD immune changes, which has implications for lung cancer diagnosis and interception. The results of this work may suggest new lung cancer interception strategies for early-stage invasive LUAD as well as improve current clinical management and outcomes.

Prediction of Knee Pain Using Ultrasound Imaging and Machine Learning

Recipients: Vijaya Kolachalama & Eugene Kissin

This project (in collaboration with Dr. Juan-Pablo Lopez-Zertuche Ortiz, Dr. Eugene Kissin, and Dr. David Felson) proposes to develop advanced machine learning approaches that can process ultrasound images to predict knee pain.

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.