The development of large language models (LLMs) has grown exponentially since the release of ChatGPT. Large language models have gained attention for their robust performance across various tasks. The ability of LLMs to understand and produce general-purpose language is achieved by training billions of parameters. These models have emerged as a transformative force in increasing natural language understanding, representing an important step toward general artificial intelligence(AI). LLMs have become powerful tools for various tasks, including natural language processing (NLP), machine translation(MT), vision applications, and question-answering(QA). The expanded reach of LLMs goes beyond the conventional linguistic bounds and includes specialized languages created in different scientific disciplines. The intensification of interest in this new subclass of scientifically oriented LLMs has led to the birth of the scientific LLMs. These scientific LLMs are gradually gaining a foothold as an exciting research area for science study. Theoretically, they share a structure in common with general LLMs. In practice, however, they differ regarding input and usage. This paper undertakes an exhaustive effort to study all the scientific LLMs, the types of structures offered, the datasets, the parameters, and the context of use. Our analysis uses a focused lens that focuses on the biological and chemical domains, which enables an in-depth examination of LLMs for textual knowledge, small molecules, macromolecules, proteins, genomic sequences, and combinations. By providing an overview of the technical advances in the field, this survey is a valuable resource for researchers navigating the complex landscape of scientific LLMs.

Digital currencies have become popular in the last decade due to their non-dependency and decentralized nature. The price of these currencies has seen a lot of fluctuations at times, which has increased the need for prediction. As their most popular, Bitcoin(BTC) has become a research hotspot. The main challenge and trend of digital currencies, especially BTC, is price fluctuations, which require studying the basic price prediction model. This research presents a classification and regression model based on stack deep learning that uses a wavelet to remove noise to predict movements and prices of BTC at different time intervals. The proposed model based on the stacking technique uses models based on deep learning, especially neural networks and transformers, for one, seven, thirty and ninety-day forecasting. Three feature selection models, Chi2, RFE and Embedded, were also applied to the data in the pre-processing stage. The classification model achieved 63\% accuracy for predicting the next day and 64\%, 67\% and 82\% for predicting the seventh, thirty and ninety days, respectively. For daily price forecasting, the percentage error was reduced to 0.58, while the error ranged from 2.72\% to 2.85\% for seven- to ninety-day horizons. These results show that the proposed model performed better than other models in the literature.

Large language models (LLMs) have recently gained attention in the life sciences due to their capacity to model, extract, and apply complex biological information. Beyond their classical use as chatbots, these systems are increasingly used for complex analysis and problem-solving in specialized fields, including bioinformatics. First, we introduce BIOPARS-BENCH, a dataset from over 10,000 scientific articles, textbooks, and medical websites. BioParsQA was also introduced to evaluate the proposed model, which consists of 5231 Persian medical questions and answers. This study then introduces BioPars, a simple but accurate measure designed to assess LLMs for three main abilities: acquiring subject-specific knowledge, interpreting and synthesizing such knowledge, and demonstrating proper evidence. Comparing ChatGPT, Llama, and Galactica, our study highlights their ability to remember and retrieve learned knowledge but also reveals shortcomings in addressing higher-level, real-world questions and fine-grained inferences. These findings indicate the need for further fine-tuning to address the capabilities of LLM in bioinformatics tasks. To our knowledge, BioPars is the first application of LLM in Persian medical QA, especially for generating long answers. Evaluation of four selected medical QA datasets shows that BioPars has achieved remarkable results compared to comparative approaches. The model on BioParsQA achieved a ROUGE-L score of 29.99, which is an improvement over GPT-4 1.0. The model achieved a BERTScore of 90.87 with the MMR method. The MoverScore and BLEURT values were also higher in this model than the other three models. In addition, the reported scores for the model are MoverScore = 60.43 and BLEURT = 50.78.

Large Language Models (LLMs) have recently gained attention in the life sciences due to their capacity to model, extract, and apply complex biological information. Beyond their classical use as chatbots, these systems are increasingly used for complex analysis and problem-solving in specialized fields, including bioinformatics. First, we introduce BIOPARS-BENCH, a dataset from over 10,000 scientific articles, textbooks, and medical websites. BioParsQA was also introduced to evaluate the proposed model, which consists of 5,231 Persian medical questions and answers. This study then introduces BioPars, a simple but accurate measure designed to assess LLMs for three main abilities: acquiring subject-specific knowledge, interpreting and synthesizing such knowledge, and demonstrating proper evidence. Comparing ChatGPT, Llama, and Galactica, our study highlights their ability to remember and retrieve learned knowledge but also reveals shortcomings in addressing higher-level, real-world questions and fine-grained inferences. These findings indicate the need for further fine-tuning to address the capabilities of LLM in bioinformatics tasks. To our knowledge, BioPars is the first application of LLM in Persian medical QA, especially for generating long answers. Evaluation of four selected medical QA datasets shows that BioPars has achieved remarkable results compared to comparative approaches. The model on BioParsQA achieved a ROUGE-L score of 29.99, which is an improvement over GPT-4 1.0. The model achieved a BERTScore of 90.87 with the MMR method. The MoverScore and BLEURT values were also higher in this model than the other three models. In addition, the reported scores for the model are MoverScore=60.43 and BLEURT=50.78. It should be noted that BioPars is an ongoing project, and all resources related to continued development will be made available and can be accessed via the following GitHub repository: \url{https://github.com/amirap80/BioPars}.

Cryptocurrencies are alternative payment methods that are created using encrypted algorithms. Encryption technologies mean that cryptocurrencies act as both a currency and a virtual accounting system. The global crypto market value is \$2.9 trillion. Hence, it requires high investment requirements. One of the challenging issues in cryptocurrencies is illiquidity. Due to behavioural chaos in the market, some currencies have severe dumps and pumps, which cause concerns for investors. This paper deals with price prediction and illiquidity prediction (converting one asset to another while maintaining its value). The proposed Wavelet Deep average model uses a combination of Wavelet transform and average deep learning models for the final prediction. This model uses the hash rate information of currencies as the main inputs. Then, it achieves the selection of a subset of features using a Random Forest(RF). The selected features are designed by a Wavelet and are considered as the input to the deep network. Four currencies, BTC, Dogecoin, Ethereum(ETH), and Bitcoin Cash(BCH), were considered for model evaluation. In Bitcoin prediction, the lowest MAE for price prediction and illiquidity was achieved, which was 1.19 and 1.49, respectively. Also, the proposed model achieved MAE of 1.99, 3.69, and 2.99 for the illiquidity of three currencies Dogecoin, ETH, and BCH. The implementation codes are available in

One of the most dangerous types of cancer is skin cancer (SC), which is seen in the form of skin lesions in the patient and can threaten the patient's life if not treated on time. With early diagnosis of this disease, more effective treatment methods can be used and the progression of the disease can be prevented. Various machine learning and deep learning methods have been developed for early skin cancer diagnosis. However, one of the benefits of deep learning is the ability to learn enormous volumes of data which abundances the trend towards deep learning methods. In this article, a method based on the combination of EfficientNet and Wavelet is presented to classify skin cancer images. Various combinations of the EfficientNet approach, including B0, B1, B2 and B3, are considered for this purpose. Also, Gray Wolf Optimization (WGO) is used to find the optimal values of the features. Two datasets of ISIC-2016 and ISIC-2017 are considered for model evaluation. Based on the obtain results, the EfficientNetB3+Wavelet+GWO model obtained the best result on the ISIC-2016 data and is able to achieve an accuracy of 0.9814 and an F-measure of 0.9827. Furthermore, in the ISIC-2017 data set, the EfficientNetB1+Wavelet+GWO model achieves the best performance with an accuracy of 0.9795 and an F-measure of 0.9797 in ISIC-2017 data.