(June 16, 2016)

Sponsored by
Bina logo



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.

In this webinar we will introduce SomaticSeq, a tool within the Bina Genomic Management Solution (Bina GMS) designed to boost the accuracy of somatic mutation detection with a machine learning approach. You will learn:

  • Benchmarking of leading somatic callers, namely MuTect, SomaticSniper, VarScan2, JointSNVMix2, and VarDict
  • Integration of such tools and how accuracy is achieved using a machine learning classifier that incorporates over 70 features with SomaticSeq
  • Accuracy validation including results from the ICGC-TCGA DREAM Somatic Mutation Calling Challenge, in which Bina placed 1st in indel calling and 2nd in SNV calling
  • Creation of a new SomaticSeq classifier utilizing your own dataset
  • Review of the somatic workflow within the Bina Genomic Management Solution


Li Tai FangLi Tai Fang

Sr. Bioinformatics Scientist

Bina Technologies, Part of Roche Sequencing

Li Tai Fang is a senior bioinformatics scientist at Bina. His work focuses on cancer informatics, and is a lead developer of SomaticSeq.

Anoop GrewalAnoop Grewal

Product Marketing Manager

Bina Technologies, Part of Roche Sequencing

Anoop Grewal leads product marketing efforts at Bina. She received her PhD from Columbia University in molecular and cell biology. Anoop has spent the last 15 years enabling scientists to extract insights from genomics data in capacities such as product marketing, product management, customer support and training.