Cancer genome sequencing enables accurate classification of tumours and tumour subtypes. However, prediction performance is still limited using exome-only sequencing and for tumor types with low somatic mutation burden such as many pediatric tumours. Moreover, the ability to leverage deep representation learning in discovery of tumour entities remains unknown. We introduce here Mutation-Attention (MuAt), a deep neural network to learn representations of simple and complex somatic alterations for prediction of tumour types and subtypes. MuAt achieved prediction accuracy of 89% for whole genomes (24 tumour types) and 64% for whole exomes (20 types), and a top-5 accuracy of 97% and 90%, respectively. Tumour representations learnt by MuAt included tumour entitites such as acral melanoma, SHH-activated medulloblastoma, SPOP-associated prostate cancer, microsatellite instability, and MUTYH-associated pancreatic endocrine tumours although these tumour subtypes and subgroups were not used as training labels. Integrated representations of somatic alterations hold significant potential to drive discovery of novel tumour entities and clinical application.

No abstract

In recent years, one of deep learning models called Deep Belief Network (DBN) which formed by stacking restricted Boltzman machine in a greedy fashion has beed widely used for classification and recognition. With an ability to extracting features of high-level abstraction and deal with higher dimensional data structure, this model has ouperformed outstanding result on image and speech recognition. In this research, we assess the applicability of deep learning in dna classification level. Since the training phase of DBN is costly expensive, specially if deals with DNA sequence with thousand of variables, we introduce a new encoding method, using decimal-binary vector to represent the sequence as input to the model, thereafter compare with one-hot-vector encoding in two datasets. We evaluated our proposed model with different contrastive algorithms which achieved significant improvement for the training speed with comparable classification result. This result has shown a potential of using decimal-binary vector on DBN for DNA sequence to solve other sequence problem in bioinformatics.

ABSTRAKkajian ini bertujuan untuk memberikan pengetahuan serta pemahaman terhadap pelaku umkm khususnya di Desa Sriharjo yang akan mencari tambahan modal usaha dengan pengembalian yang ringan melalui program dana KUR (Kredit Usaha Rakyat). Metode yang digunakan adalah metode kaji tindak (Action Research) melalui pendekatan program tindak partisipatif (Partisipatory Action Program), dan studi pustaka (library research). Sasaran pada kegiatan ini adalah pelaku UMKM yang ada di Desa Sriharjo. Wawancara dan observasi langsung dilakukan ke Desa Sriharjo, Imogiri, Bantul. Tahapan pelaksanaan dilakukan dengan metode ceramah yakni penyampaian materi penyuluhan berupa sosialisasi, pendampingan dan bimbingan. Tahapan FGD dilaksanakan dengan cara penyampaian materi secara langsung pada pelaku UMKM oleh narasumber yang kompeten, cara ini disesuaikan dengan kondisi lingkungan dengan tanya jawab interaktif. Kegiatan ini diharapkan untuk menjembatani kebutuhan pembiayaan atau permodalan bagi UMKM di Sriharjo, Imogiri, Bantul. Berdasarkan hasil observasi dan survei yang dilakukan, mayoritas masyarakat masih bergantung terhadap peminjaman kepada rentenir. Untuk menanggulangi hal tersebut perlu di adakan penyuluhan khusus terkait dampak peminjaman modal usaha kepada rentenir, dengan demikian masyarakat akan sadar bahwa peminjaman melalui rentenir sangat tidak manusiawi. Sebagai gantinya, masyarakat dapat mengajukan pinjaman KUR melalui bank pelaksana yang telah di tunjuk oleh pemerintah. Kata kunci: rentenir; pelaku UMKM; pembiayaan KUR (Kredit Usaha Rakyat). ABSTRACTThis study aims to provide knowledge and understanding to MSME actors, especially in Sriharjo Village, who will seek additional business capital with a light return through the KUR (Kredit Usaha Rakyat) fund program. The method used is the action research method through a participatory action program approach, and library research. The targets of this activity are MSME actors in Sriharjo Village. Interviews and direct observations were conducted in Sriharjo Village, Imogiri, Bantul. The implementation stage was carried out using the lecture method, namely the delivery of extension material in the form of socialization, assistance and guidance. The FGD stage is carried out by delivering material directly to MSME actors by competent resource persons, this method is adjusted to environmental conditions with interactive questions and answers. This activity is expected to bridge the financing or capital needs of MSMEs in Sriharjo, Imogiri, Bantul. Based on the results of observations and surveys conducted, the majority of people still depend on loans to loan sharks. To overcome this, it is necessary to hold special counseling related to the impact of borrowing business capital from loan sharks, so that people will realize that lending through loan sharks is very inhumane. Instead, the community can apply for KUR loans through implementing banks that have been appointed by the government. Keywords: loan sharks; MSME actors; KUR (Kredit Usaha Rakyat) financing.