Lack of Response to Vemurafenib in Melanoma Carrying BRAF K601E Mutation.

Vemurafenib has been developed to target common BRAF mutation V600E. It also exerts activity towards some but not all rare BRAF substitutions. Proper cataloguing of drug-sensitive and -insensitive rare mutations remains a challenge, due to low occurrence of these events and inability of commercial PCR-based diagnostic kits to detect the full spectrum of BRAF gene lesions. We considered the results of BRAF exon 15 testing in 1872 consecutive melanoma patients. BRAF mutation was identified in 1,090 (58.2%) cases. While drug-sensitive codon 600 substitutions constituted the majority of BRAF gene lesions (V600E: 962 [51.4%]; V600K: 86 [4.6%]; V600R: 17 [0.9%]), the fourth common BRAF allele was K601E accounting for 9 (0.5%) melanoma cases. The data on BRAF inhibitor sensitivity of tumors with K601E substitution are scarce. We administered single-agent vemurafenib to a melanoma patient carrying BRAF K601E mutation as the first-line treatment. Unfortunately, this therapy did not result in a tumor response. Taken together with already published data, this report indicates lack of benefit from conventional BRAF inhibitors in patients with BRAF K601E mutated melanoma.

Exome-based search for recurrent disease-causing alleles in Russian population.

Exomes of 27 Russian subjects were analyzed for the presence of medically relevant alleles, such as protein-truncating variants (PTVs) in known recessive disease-associated genes and pathogenic missense mutations included in the ClinVar database. 36 variants (24 PTVs and 12 amino acid substitutions) were identified and then subjected to the analysis in 897 population controls. 9/36 mutations were novel, however only two of them (POLH c.490delG associated with xeroderma pigmentosum variant (XPV) and CATSPER1 c.859_860delCA responsible for spermatogenic failure) were shown to be recurrent. 27 out of 36 pathogenic alleles were already described in prior genetic studies; seven of them occurred only in the index cases, while 20 demonstrated evidence for persistence in Russian population. In particular, non-random occurrence was revealed for SERPINA1 c.1096G > A (alpha-1 antitrypsin deficiency), C8B c.1282C > T and c.1653G > A (complement component 8B deficiency), ATP7B c.3207C > A (Wilson disease), PROP1 c.301_302delAG (combined pituitary hormone deficiency), CYP21A2 c.844G > T (non-classical form of adrenogenital syndrome), EYS c.1155T > A (retinitis pigmentosa), HADHA c.1528G > C (LCHAD deficiency), SCO2 c.418G > A (cytochrome c oxidase deficiency), OTOA c.2359G > T (sensorineural deafness), C2 c.839_866del (complement component 2 deficiency), ACADVL c.848T > C (VLCAD deficiency), TGM5 c.337G > T (acral peeling skin syndrome) and VWF c.2561 G > A (von Willebrand disease, type 2N). These data deserve to be considered in future medical genetic activities.

Putting hands to rest: efficient deep CNN-RNN architecture for chemical named entity recognition with no hand-crafted rules.

Chemical named entity recognition (NER) is an active field of research in biomedical natural language processing. To facilitate the development of new and superior chemical NER systems, BioCreative released the CHEMDNER corpus, an extensive dataset of diverse manually annotated chemical entities. Most of the systems trained on the corpus rely on complicated hand-crafted rules or curated databases for data preprocessing, feature extraction and output post-processing, though modern machine learning algorithms, such as deep neural networks, can automatically design the rules with little to none human intervention. Here we explored this approach by experimenting with various deep learning architectures for targeted tokenisation and named entity recognition. Our final model, based on a combination of convolutional and stateful recurrent neural networks with attention-like loops and hybrid word- and character-level embeddings, reaches near human-level performance on the testing dataset with no manually asserted rules. To make our model easily accessible for standalone use and integration in third-party software, we've developed a Python package with a minimalistic user interface.