From games at imap.dim.uchile.cl Fri Jan 22 07:52:03 2016 From: games at imap.dim.uchile.cl (games) Date: Fri, 22 Jan 2016 07:52:03 -0300 Subject: [Games-news] =?utf-8?q?=5BBolet=C3=ADn_=232_Grupo_Aprendizaje_de_?= =?utf-8?b?TcOhcXVpbmFzLCBpbmZFcmVuY2lhIHkgU2XDsWFsZXNd?= In-Reply-To: <75f0b85606fcebcf091855f98c6a4a0d@imap.dim.uchile.cl> References: <75f0b85606fcebcf091855f98c6a4a0d@imap.dim.uchile.cl> Message-ID: Este es el Bolet?n #2 de GAMES - para suscribirse o de-suscribirse de esta lista, escribir a games at dim.uchile.cl. Los temas de hoy son: 1) [RECUERDO] Seminario hoy a las 15.00 Hrs: Aprendizaje de M?quinas y Redes de Regulaci?n G?nica 2) P?gina web est? activa: http://games.cmm.uchile.cl/ 3) Charlas pasadas: videos y slides disponibles en la p?gina 4) Nuevo curso para Oto?o 2016: Aprendizaje de M?quinas Probabil?stico ------------------------- 1) Seminario: Hoy a las 15:00 hrs tenemos el tercer seminario de GAMES: T?tulo: Inference of Gene Regulatory Networks from Gene Expression Data using Artificial Neural Networks Expositor: Dr Alberto J. M. Mart?n (postdoc, DLab, Fundaci?n Ciencia & Vida) Fecha y hora: 22/1/2016 15:00 Lugar: Sala John von Neumann, CMM. Abstract: Gene Regulatory Networks (GRNs) are directed networks where nodes represent genes, and edges exist solely if the Transcription Factor (TF) encoded by a source gene directly regulates the expression of another target gene. Two main approaches exist for the inference of GRNs, high-throughput experiments and computational methods that solely make use of gene expression data. While the first ones are expensive and time consuming, the second ones are faster and require fewer resources. Computational methods for the inference of GRNs can be broadly classified into supervised, where examples with known labels are needed, and unsupervised, e.g., correlation coefficients, where no known examples are required. Whereas the majority of computational methods benefit from the use of as many expression experiments in as diverse conditions as possible, approaches that use a single experiment are few or almost nonexistent. This work presents advances in the development of a supervised method for the inference of GRNs based on Artificial Neural Networks (ANNs). Our method only uses gene expression levels from a single time series expression experiment and several correlations computed between TF coding genes and their possible targets expression. Notably, known reference GRNs are noisy, static and highly unbalanced so we created new procedures to properly deal with these characteristics. 2) Sitio Web: La primera versi?n de la p?gina ya se encuentra disponible en http://games.cmm.uchile.cl/ - ?gracias Gonzalo y Mat?as! Por ahora, la p?gina incluye informaci?n sobre los seminarios y el anuncio del curso MA5203, pero en el futuro pr?ximo se incorporar?n los invitados para marzo, grupos de lectura y reuniones de investigaci?n. El logo y layout es tentativo, as? que se reciben recomendaciones. 3) Seminarios pasados: Los videos y presentaciones de los primeros dos seminarios ya se encuentran disponibles en la p?gina web o directamente en el canal YouTube del grupo: https://www.youtube.com/channel/UCqtRBEV1r7X4ZbO3089CaaA (?gracias Ernesto!) 4) Nuevo Curso: El semestre Oto?o 2016 se dictar? el curso MA5203: Aprendizaje de M?quinas Probabil?stico, condicional a que al menos siete alumnos lo inscriba. Por esta raz?n, agradecer?amos que nos ayudaran a difundirlo en la facultad, usando: (a) este llamado: http://games.cmm.uchile.cl/files/2016/01/llamado-curso.pdf (Es necesario abrirlo en Acrobat Reader para ver la animaci?n) (b) o bien el programa: http://games.cmm.uchile.cl/files/2016/01/MA5203_161.pdf ------------------------- Fin del bolet?n. -------------- next part -------------- An HTML attachment was scrubbed... URL: