MOTIVATION: Predictions of protein local structure, derived from sequence alignment information alone, provide visualization tools for biologists to evaluate the importance of amino acid residue positions of interest in the absence of X-ray crystal/NMR structures or homology models. They are also useful as inputs to sequence analysis and modeling tools, such as hidden Markov models (HMMs), which can be used to search for homology in databases of known protein structure. In addition, local structure predictions can be used as a component of cost functions in genetic algorithms that predict protein tertiary structure. We have developed a program (predict-2nd) that trains multilayer neural networks and have applied it to numerous local structure alphabets, tuning network parameters such as the number of layers, the number of units in each layer and the window sizes of each layer. We have had the most success with four-layer networks, with gradually increasing window sizes at each layer. RESULTS: Because the four-layer neural nets occasionally get trapped in poor local optima, our training protocol now uses many different random starts, with short training runs, followed by more training on the best performing networks from the short runs. One recent addition to the program is the option to add a guide sequence to the profile inputs, increasing the number of inputs per position by 20. We find that use of a guide sequence provides a small but consistent improvement in the predictions for several different local-structure alphabets. AVAILABILITY: Local structure prediction with the methods described here is available for use online at http://www.soe.ucsc.edu/compbio/SAM_T08/T08-query.html. The source code and example networks for PREDICT-2ND are available at http://www.soe.ucsc.edu/~karplus/predict-2nd/ A required C++ library is available at http://www.soe.ucsc.edu/~karplus/ultimate/

MOTIVATION: A new hidden Markov model method (SAM-T98) for finding remote homologs of protein sequences is described and evaluated. The method begins with a single target sequence and iteratively builds a hidden Markov model (HMM) from the sequence and homologs found using the HMM for database search. SAM-T98 is also used to construct model libraries automatically from sequences in structural databases. METHODS: We evaluate the SAM-T98 method with four datasets. Three of the test sets are fold-recognition tests, where the correct answers are determined by structural similarity. The fourth uses a curated database. The method is compared against WU-BLASTP and against DOUBLE-BLAST, a two-step method similar to ISS, but using BLAST instead of FASTA. RESULTS: SAM-T98 had the fewest errors in all tests-dramatically so for the fold-recognition tests. At the minimum-error point on the SCOP (Structural Classification of Proteins)-domains test, SAM-T98 got 880 true positives and 68 false positives, DOUBLE-BLAST got 533 true positives with 71 false positives, and WU-BLASTP got 353 true positives with 24 false positives. The method is optimized to recognize superfamilies, and would require parameter adjustment to be used to find family or fold relationships. One key to the performance of the HMM method is a new score-normalization technique that compares the score to the score with a reversed model rather than to a uniform null model. AVAILABILITY: A World Wide Web server, as well as information on obtaining the Sequence Alignment and Modeling (SAM) software suite, can be found at http://www.cse.ucsc.edu/research/compbi o/ CONTACT: [email protected]; http://www.cse.ucsc.edu/karplus

Statistical sequence comparison techniques, such as hidden Markov models and generalized profiles, calculate the probability that a sequence was generated by a given model. Log-odds scoring is a means of evaluating this probability by comparing it to a null hypothesis, usually a simpler statistical model intended to represent the universe of sequences as a whole, rather than the group of interest. Such scoring leads to two immediate questions: what should the null model be, and what threshold of log-odds score should be deemed a match to the model. This paper analyses these two issues experimentally. Within the context of the Sequence Alignment and Modeling software suite (SAM), we consider a variety of null models and suitable thresholds. Additionally, we consider HMMer's log-odds scoring and SAM's original Z-scoring method. Among the null model choices, a simple looping null model that emits characters according to the geometric mean of the character probabilities in the columns modeled by the hidden Markov model (HMM) performs well or best across all four discrimination experiments. Information on obtaining the SAM program suite (free for academic use), as well as a server interface, is available from http://www.cse.ucsc.edu/research/compbio/sam.html. HMMer is freely available from http://genome.wustl.edu/eddy/hmm.html. E-mail: [email protected]