Bina Bloggers

Free NGS Webinar: An Ensemble Approach with Machine Learning to Detect Cancer Variants

Posted by Jenny Hsu on May 12, 2016 10:00:00 AM

bio-it-webinar.jpg

Time & Date:

REGISTER TO JOIN US on Thursday June 16, 2016, 10 am PT // 1 pm ET.

SOMATICSEQ: AN ENSEMBLE APPROACH WITH MACHINE LEARNING TO DETECT SOMATIC MUTATION DETECTION

Accurate detection of somatic mutations has proven to be challenging in cancer NGS analysis, due to tumor heterogeneity and cross-contamination between tumor and matched normal samples. Oftentimes, a somatic caller that performs well for one tumor may not for another.

Read More

Topics: Somatic Mutation Detection, Bina Tools & Workflows, Webinar, Bina GMS, BioIT, SomaticSeq, NGS, VarScan, SomaticIndelDetector, VarDict, MuTect, SomaticSniper

VarDict: A Somatic Variant Caller Available in the Bina RAVE Software

Posted by Anoop Grewal on May 10, 2016 10:00:00 AM

somaticfinal.pngDetails on Vardict, a new variant caller, have been published recently in Nucleic Acids Research by authors, Zhongwu Lai and Jonathan Dry, among others from AstraZeneca [1]. The current version of the Bina Read Alignment Variant Calling and Expression software module for secondary analysis includes Vardict, along with five other tools, for calling SNVs or indels from tumor-normal pairs. As the article demonstrates, VarDict has multiple strengths that extend our capabilities in variant calling beyond what was available before its release. Notably, the algorithm is particularly good at detecting indels. It also handles ultra-deep sequenced samples, which have become more common of late, and supports variant calling in tumor-only samples (in addition to tumor-vs-normal calling).

Read More

Topics: DREAM Challenge Results, Somatic Mutation Detection, Tumor-Normal, Webinar, Bina RAVE, SomaticSeq, AstraZeneca, Sequencing, VarScan, JointSNVMix, SomaticIndelDetector, VarDict, MuTect, SomaticSniper

Assessing and Improving Accuracy of Next-Generation Sequencing Informatics. Watch Video!

Posted by Jenny Hsu on Apr 19, 2016 10:00:00 AM

Advancements in next-generation sequencing (NGS) technologies have produced massive number of short read sequences, making secondary analysis a challenging big data problem. In this seminar presented at Molecular Tri-Con 2016, Bina’s Senior Director of Bioinformatics, Hugo Lam, shared current approaches at Bina in assessing and improving the accuracy of NGS algorithms. Specifically, he touched on how Bina's research expanded the benchmarking toolset through the availability of a better gold set and a variant simulation and validation framework.

Read More

Topics: Bina Technologies, Events & Conferences, Videos, VarSim, MetaSV, SomaticSeq, Data Challenges, huref, Molecular Med, Mutation Detection, NGS, Tri-Con, Presentation

Check Out our New Science Section

Posted by Anoop Grewal on Jan 8, 2016 9:00:00 AM

With the new year, we’ve launched a new website with the goal of making it even easier for you to find relevant information. In addition to our product, company and careers pages, our top-level menu now highlights our Science section. We’re proud of the contributions that our dedicated Science team has made to advance genome analytics. We believe the tools and methods they have devised – and published – to more accurately detect and interpret variants in next-generation sequencing data are unique and vital.

Read More

Topics: VarSim, MetaSV, SomaticSeq, website

SomaticSeq Webinar Now Available on Demand

Posted by Jenny Hsu on Dec 10, 2015 10:30:00 AM


Did you miss last week’s webinar on SomaticSeq? It’s now available on demand. Watch it to learn how we used this newly published ensemble and machine learning approach to score first in indel calling and second in SNV calling in the recent ICGC-TCGA DREAM Somatic Mutation Calling Challenge.

Read More

Topics: DREAM Challenge Results, Somatic Mutation Detection, Bina Tools & Workflows, Cancer, Webinar, RAVE, SomaticSeq

SomaticSeq: An Ensemble Approach with Machine Learning to Accurately Detect Somatic Mutations

Posted by Li Tai Fang on Oct 22, 2015 10:00:00 AM

This is the third article in a series. The first post discussed challenges in somatic mutation detection with respect to false positives and false negatives. The second post reviewed how a concensus approach might increase the confidence of the call sets from multiple tumor-normal callers. 

We developed SomaticSeq, an integrative machine learning pipeline, to address the limitations of current approaches [1]. SomaticSeq currently incorporates five somatic mutation callers, and uses machine learning (Adaptive Boosting model) to distinguish true mutations from false positives based on over 70 genomic and sequencing features. Using SomaticSeq, we have recently placed #1 in INDEL (F1 score of 71.6%) and #2 in SNV (F1 score of 99.7%) in Stage 5 of the ICGC-TCGA DREAM Somatic Mutation Calling Challenge. SomaticSeq is released under BSD open-source license at http://bioinform.github.io/somaticseq/.    

Read More

Topics: DREAM Challenge Results, Cancer, Tumor-Normal, SomaticSeq

A Consensus Approach to Somatic Mutation Detection: When the Whole is Greater Than the Sum of Its Parts

Posted by Li Tai Fang on Oct 15, 2015 9:00:00 AM

In the previous post, we discussed challenges in somatic mutation detection with respect to false positives and false negatives. The research community probably is well aware of the aforementioned problems, and that is why the “naive subtract” method is rarely practiced. Instead, there is a plethora of specialized somatic mutation callers that analyze the tumor and normal genomes simultaneously to find somatic mutations. We benchmarked and selected  the best and most popular somatic mutation callers, namely MuTect [1], VarScan2 [2], JointSNVMix2 [3], SomaticSniper [4], and VarDict [5], for our ensemble calling approach.

Read More

Topics: Somatic Mutation Detection, Cancer, SomaticSeq

False positives and negatives in cancer sequencing: When naive subtraction is just not enough

Posted by Li Tai Fang on Oct 6, 2015 10:00:00 AM

In cancer research, it is common to search for somatic mutations that appear in the tumor but not in the healthy tissues. Thus, tumor-normal comparisons have become the norm in somatic mutation detection in DNA sequencing. In an ideal world the workflow sounds simple: compare the tumor sequencing data against the normal. If a variant was found in the tumor but not found in the normal, it’s a somatic mutation. 

Read More

Topics: DREAM Challenge Results, Cancer, Tumor-Normal, Bina RAVE, SomaticSeq

Subscribe to Email Updates

Recent Posts

Posts by Topic

see all